diff options
Diffstat (limited to 'net')
257 files changed, 3387 insertions, 2767 deletions
diff --git a/net/802/mrp.c b/net/802/mrp.c index a4cc3229952a..e085bcc754f6 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -870,8 +870,12 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) * all pending messages before the applicant is gone. */ del_timer_sync(&app->join_timer); + + spin_lock(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); mrp_pdu_queue(app); + spin_unlock(&app->lock); + mrp_queue_xmit(app); dev_mc_del(dev, appl->group_address); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a18714469bf7..85addcd9372b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -86,13 +86,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp = &vlan_info->grp; - /* Take it out of our own structures, but be sure to interlock with - * HW accelerating devices or SW vlan input packet processing if - * VLAN is not 0 (leave it there for 802.1p). - */ - if (vlan_id) - vlan_vid_del(real_dev, vlan_id); - grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_MVRP) @@ -114,6 +107,13 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) vlan_gvrp_uninit_applicant(real_dev); } + /* Take it out of our own structures, but be sure to interlock with + * HW accelerating devices or SW vlan input packet processing if + * VLAN is not 0 (leave it there for 802.1p). + */ + if (vlan_id) + vlan_vid_del(real_dev, vlan_id); + /* Get rid of the vlan's reference to real_dev */ dev_put(real_dev); } diff --git a/net/9p/client.c b/net/9p/client.c index 34d417670935..8eb75425e6e6 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1100,7 +1100,7 @@ void p9_client_begin_disconnect(struct p9_client *clnt) EXPORT_SYMBOL(p9_client_begin_disconnect); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, - char *uname, u32 n_uname, char *aname) + char *uname, kuid_t n_uname, char *aname) { int err = 0; struct p9_req_t *req; @@ -1117,7 +1117,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, goto error; } - req = p9_client_rpc(clnt, P9_TATTACH, "ddss?d", fid->fid, + req = p9_client_rpc(clnt, P9_TATTACH, "ddss?u", fid->fid, afid ? afid->fid : P9_NOFID, uname, aname, n_uname); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -1270,7 +1270,7 @@ error: EXPORT_SYMBOL(p9_client_open); int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode, - gid_t gid, struct p9_qid *qid) + kgid_t gid, struct p9_qid *qid) { int err = 0; struct p9_client *clnt; @@ -1279,13 +1279,14 @@ int p9_client_create_dotl(struct p9_fid *ofid, char *name, u32 flags, u32 mode, p9_debug(P9_DEBUG_9P, ">>> TLCREATE fid %d name %s flags %d mode %d gid %d\n", - ofid->fid, name, flags, mode, gid); + ofid->fid, name, flags, mode, + from_kgid(&init_user_ns, gid)); clnt = ofid->clnt; if (ofid->mode != -1) return -EINVAL; - req = p9_client_rpc(clnt, P9_TLCREATE, "dsddd", ofid->fid, name, flags, + req = p9_client_rpc(clnt, P9_TLCREATE, "dsddg", ofid->fid, name, flags, mode, gid); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -1358,7 +1359,7 @@ error: } EXPORT_SYMBOL(p9_client_fcreate); -int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, gid_t gid, +int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, kgid_t gid, struct p9_qid *qid) { int err = 0; @@ -1369,7 +1370,7 @@ int p9_client_symlink(struct p9_fid *dfid, char *name, char *symtgt, gid_t gid, dfid->fid, name, symtgt); clnt = dfid->clnt; - req = p9_client_rpc(clnt, P9_TSYMLINK, "dssd", dfid->fid, name, symtgt, + req = p9_client_rpc(clnt, P9_TSYMLINK, "dssg", dfid->fid, name, symtgt, gid); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -1710,7 +1711,9 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid) (unsigned long long)ret->qid.path, ret->qid.version, ret->mode, ret->atime, ret->mtime, (unsigned long long)ret->length, ret->name, ret->uid, ret->gid, ret->muid, ret->extension, - ret->n_uid, ret->n_gid, ret->n_muid); + from_kuid(&init_user_ns, ret->n_uid), + from_kgid(&init_user_ns, ret->n_gid), + from_kuid(&init_user_ns, ret->n_muid)); p9_free_req(clnt, req); return ret; @@ -1764,8 +1767,10 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, "<<< st_btime_sec=%lld st_btime_nsec=%lld\n" "<<< st_gen=%lld st_data_version=%lld", ret->st_result_mask, ret->qid.type, ret->qid.path, - ret->qid.version, ret->st_mode, ret->st_nlink, ret->st_uid, - ret->st_gid, ret->st_rdev, ret->st_size, ret->st_blksize, + ret->qid.version, ret->st_mode, ret->st_nlink, + from_kuid(&init_user_ns, ret->st_uid), + from_kgid(&init_user_ns, ret->st_gid), + ret->st_rdev, ret->st_size, ret->st_blksize, ret->st_blocks, ret->st_atime_sec, ret->st_atime_nsec, ret->st_mtime_sec, ret->st_mtime_nsec, ret->st_ctime_sec, ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec, @@ -1828,7 +1833,9 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) (unsigned long long)wst->qid.path, wst->qid.version, wst->mode, wst->atime, wst->mtime, (unsigned long long)wst->length, wst->name, wst->uid, wst->gid, wst->muid, wst->extension, - wst->n_uid, wst->n_gid, wst->n_muid); + from_kuid(&init_user_ns, wst->n_uid), + from_kgid(&init_user_ns, wst->n_gid), + from_kuid(&init_user_ns, wst->n_muid)); req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size+2, wst); if (IS_ERR(req)) { @@ -1857,7 +1864,9 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr) " valid=%x mode=%x uid=%d gid=%d size=%lld\n" " atime_sec=%lld atime_nsec=%lld\n" " mtime_sec=%lld mtime_nsec=%lld\n", - p9attr->valid, p9attr->mode, p9attr->uid, p9attr->gid, + p9attr->valid, p9attr->mode, + from_kuid(&init_user_ns, p9attr->uid), + from_kgid(&init_user_ns, p9attr->gid), p9attr->size, p9attr->atime_sec, p9attr->atime_nsec, p9attr->mtime_sec, p9attr->mtime_nsec); @@ -2106,7 +2115,7 @@ error: EXPORT_SYMBOL(p9_client_readdir); int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode, - dev_t rdev, gid_t gid, struct p9_qid *qid) + dev_t rdev, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; @@ -2116,7 +2125,7 @@ int p9_client_mknod_dotl(struct p9_fid *fid, char *name, int mode, clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d " "minor %d\n", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev)); - req = p9_client_rpc(clnt, P9_TMKNOD, "dsdddd", fid->fid, name, mode, + req = p9_client_rpc(clnt, P9_TMKNOD, "dsdddg", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev), gid); if (IS_ERR(req)) return PTR_ERR(req); @@ -2137,7 +2146,7 @@ error: EXPORT_SYMBOL(p9_client_mknod_dotl); int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode, - gid_t gid, struct p9_qid *qid) + kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; @@ -2146,8 +2155,8 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, char *name, int mode, err = 0; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n", - fid->fid, name, mode, gid); - req = p9_client_rpc(clnt, P9_TMKDIR, "dsdd", fid->fid, name, mode, + fid->fid, name, mode, from_kgid(&init_user_ns, gid)); + req = p9_client_rpc(clnt, P9_TMKDIR, "dsdg", fid->fid, name, mode, gid); if (IS_ERR(req)) return PTR_ERR(req); diff --git a/net/9p/error.c b/net/9p/error.c index 2ab2de76010f..126fd0dceea2 100644 --- a/net/9p/error.c +++ b/net/9p/error.c @@ -221,15 +221,13 @@ EXPORT_SYMBOL(p9_error_init); int p9_errstr2errno(char *errstr, int len) { int errno; - struct hlist_node *p; struct errormap *c; int bucket; errno = 0; - p = NULL; c = NULL; bucket = jhash(errstr, len, 0) % ERRHASHSZ; - hlist_for_each_entry(c, p, &hash_errmap[bucket], list) { + hlist_for_each_entry(c, &hash_errmap[bucket], list) { if (c->namelen == len && !memcmp(c->name, errstr, len)) { errno = c->val; break; diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 3d33ecf13327..ab9127ec5b7a 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -85,6 +85,8 @@ pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size) d - int32_t q - int64_t s - string + u - numeric uid + g - numeric gid S - stat Q - qid D - data blob (int32_t size followed by void *, results are not freed) @@ -163,6 +165,26 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, (*sptr)[len] = 0; } break; + case 'u': { + kuid_t *uid = va_arg(ap, kuid_t *); + __le32 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { + errcode = -EFAULT; + break; + } + *uid = make_kuid(&init_user_ns, + le32_to_cpu(le_val)); + } break; + case 'g': { + kgid_t *gid = va_arg(ap, kgid_t *); + __le32 le_val; + if (pdu_read(pdu, &le_val, sizeof(le_val))) { + errcode = -EFAULT; + break; + } + *gid = make_kgid(&init_user_ns, + le32_to_cpu(le_val)); + } break; case 'Q':{ struct p9_qid *qid = va_arg(ap, struct p9_qid *); @@ -177,11 +199,12 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, va_arg(ap, struct p9_wstat *); memset(stbuf, 0, sizeof(struct p9_wstat)); - stbuf->n_uid = stbuf->n_gid = stbuf->n_muid = - -1; + stbuf->n_uid = stbuf->n_muid = INVALID_UID; + stbuf->n_gid = INVALID_GID; + errcode = p9pdu_readf(pdu, proto_version, - "wwdQdddqssss?sddd", + "wwdQdddqssss?sugu", &stbuf->size, &stbuf->type, &stbuf->dev, &stbuf->qid, &stbuf->mode, &stbuf->atime, @@ -294,7 +317,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, memset(stbuf, 0, sizeof(struct p9_stat_dotl)); errcode = p9pdu_readf(pdu, proto_version, - "qQdddqqqqqqqqqqqqqqq", + "qQdugqqqqqqqqqqqqqqq", &stbuf->st_result_mask, &stbuf->qid, &stbuf->st_mode, @@ -377,6 +400,20 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, errcode = -EFAULT; } break; + case 'u': { + kuid_t uid = va_arg(ap, kuid_t); + __le32 val = cpu_to_le32( + from_kuid(&init_user_ns, uid)); + if (pdu_write(pdu, &val, sizeof(val))) + errcode = -EFAULT; + } break; + case 'g': { + kgid_t gid = va_arg(ap, kgid_t); + __le32 val = cpu_to_le32( + from_kgid(&init_user_ns, gid)); + if (pdu_write(pdu, &val, sizeof(val))) + errcode = -EFAULT; + } break; case 'Q':{ const struct p9_qid *qid = va_arg(ap, const struct p9_qid *); @@ -390,7 +427,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, va_arg(ap, const struct p9_wstat *); errcode = p9pdu_writef(pdu, proto_version, - "wwdQdddqssss?sddd", + "wwdQdddqssss?sugu", stbuf->size, stbuf->type, stbuf->dev, &stbuf->qid, stbuf->mode, stbuf->atime, @@ -468,7 +505,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt, struct p9_iattr_dotl *); errcode = p9pdu_writef(pdu, proto_version, - "ddddqqqqq", + "ddugqqqqq", p9attr->valid, p9attr->mode, p9attr->uid, diff --git a/net/9p/util.c b/net/9p/util.c index 6ceeeb384de7..59f278e64f58 100644 --- a/net/9p/util.c +++ b/net/9p/util.c @@ -87,23 +87,18 @@ EXPORT_SYMBOL(p9_idpool_destroy); int p9_idpool_get(struct p9_idpool *p) { - int i = 0; - int error; + int i; unsigned long flags; -retry: - if (idr_pre_get(&p->pool, GFP_NOFS) == 0) - return -1; - + idr_preload(GFP_NOFS); spin_lock_irqsave(&p->lock, flags); /* no need to store exactly p, we just need something non-null */ - error = idr_get_new(&p->pool, p, &i); - spin_unlock_irqrestore(&p->lock, flags); + i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT); - if (error == -EAGAIN) - goto retry; - else if (error) + spin_unlock_irqrestore(&p->lock, flags); + idr_preload_end(); + if (i < 0) return -1; p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p); diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 33475291c9c1..4a141e3cf076 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -93,10 +93,9 @@ static struct sock *atalk_search_socket(struct sockaddr_at *to, struct atalk_iface *atif) { struct sock *s; - struct hlist_node *node; read_lock_bh(&atalk_sockets_lock); - sk_for_each(s, node, &atalk_sockets) { + sk_for_each(s, &atalk_sockets) { struct atalk_sock *at = at_sk(s); if (to->sat_port != at->src_port) @@ -141,11 +140,10 @@ static struct sock *atalk_find_or_insert_socket(struct sock *sk, struct sockaddr_at *sat) { struct sock *s; - struct hlist_node *node; struct atalk_sock *at; write_lock_bh(&atalk_sockets_lock); - sk_for_each(s, node, &atalk_sockets) { + sk_for_each(s, &atalk_sockets) { at = at_sk(s); if (at->src_net == sat->sat_addr.s_net && @@ -1084,9 +1082,8 @@ static int atalk_pick_and_bind_port(struct sock *sk, struct sockaddr_at *sat) sat->sat_port < ATPORT_LAST; sat->sat_port++) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &atalk_sockets) { + sk_for_each(s, &atalk_sockets) { struct atalk_sock *at = at_sk(s); if (at->src_net == sat->sat_addr.s_net && diff --git a/net/atm/common.c b/net/atm/common.c index 806fc0a40051..737bef59ce89 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -270,11 +270,11 @@ void atm_dev_release_vccs(struct atm_dev *dev) write_lock_irq(&vcc_sklist_lock); for (i = 0; i < VCC_HTABLE_SIZE; i++) { struct hlist_head *head = &vcc_hash[i]; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct sock *s; struct atm_vcc *vcc; - sk_for_each_safe(s, node, tmp, head) { + sk_for_each_safe(s, tmp, head) { vcc = atm_sk(s); if (vcc->dev == dev) { vcc_release_async(vcc, -EPIPE); @@ -317,11 +317,10 @@ static int adjust_tp(struct atm_trafprm *tp, unsigned char aal) static int check_ci(const struct atm_vcc *vcc, short vpi, int vci) { struct hlist_head *head = &vcc_hash[vci & (VCC_HTABLE_SIZE - 1)]; - struct hlist_node *node; struct sock *s; struct atm_vcc *walk; - sk_for_each(s, node, head) { + sk_for_each(s, head) { walk = atm_sk(s); if (walk->dev != vcc->dev) continue; @@ -532,6 +531,8 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sk_buff *skb; int copied, error = -EINVAL; + msg->msg_namelen = 0; + if (sock->state != SS_CONNECTED) return -ENOTCONN; diff --git a/net/atm/lec.c b/net/atm/lec.c index 2e3d942e77f1..f23916be18fb 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -842,7 +842,9 @@ static void *lec_tbl_walk(struct lec_state *state, struct hlist_head *tbl, --*l; } - hlist_for_each_entry_from(tmp, e, next) { + tmp = container_of(e, struct lec_arp_table, next); + + hlist_for_each_entry_from(tmp, next) { if (--*l < 0) break; } @@ -1307,7 +1309,6 @@ lec_arp_add(struct lec_priv *priv, struct lec_arp_table *entry) static int lec_arp_remove(struct lec_priv *priv, struct lec_arp_table *to_remove) { - struct hlist_node *node; struct lec_arp_table *entry; int i, remove_vcc = 1; @@ -1326,7 +1327,7 @@ lec_arp_remove(struct lec_priv *priv, struct lec_arp_table *to_remove) * ESI_FLUSH_PENDING, ESI_FORWARD_DIRECT */ for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (memcmp(to_remove->atm_addr, entry->atm_addr, ATM_ESA_LEN) == 0) { @@ -1364,14 +1365,13 @@ static const char *get_status_string(unsigned char st) static void dump_arp_table(struct lec_priv *priv) { - struct hlist_node *node; struct lec_arp_table *rulla; char buf[256]; int i, j, offset; pr_info("Dump %p:\n", priv); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(rulla, node, + hlist_for_each_entry(rulla, &priv->lec_arp_tables[i], next) { offset = 0; offset += sprintf(buf, "%d: %p\n", i, rulla); @@ -1403,7 +1403,7 @@ static void dump_arp_table(struct lec_priv *priv) if (!hlist_empty(&priv->lec_no_forward)) pr_info("No forward\n"); - hlist_for_each_entry(rulla, node, &priv->lec_no_forward, next) { + hlist_for_each_entry(rulla, &priv->lec_no_forward, next) { offset = 0; offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); offset += sprintf(buf + offset, " Atm:"); @@ -1428,7 +1428,7 @@ static void dump_arp_table(struct lec_priv *priv) if (!hlist_empty(&priv->lec_arp_empty_ones)) pr_info("Empty ones\n"); - hlist_for_each_entry(rulla, node, &priv->lec_arp_empty_ones, next) { + hlist_for_each_entry(rulla, &priv->lec_arp_empty_ones, next) { offset = 0; offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); offset += sprintf(buf + offset, " Atm:"); @@ -1453,7 +1453,7 @@ static void dump_arp_table(struct lec_priv *priv) if (!hlist_empty(&priv->mcast_fwds)) pr_info("Multicast Forward VCCs\n"); - hlist_for_each_entry(rulla, node, &priv->mcast_fwds, next) { + hlist_for_each_entry(rulla, &priv->mcast_fwds, next) { offset = 0; offset += sprintf(buf + offset, "Mac: %pM", rulla->mac_addr); offset += sprintf(buf + offset, " Atm:"); @@ -1487,7 +1487,7 @@ static void dump_arp_table(struct lec_priv *priv) static void lec_arp_destroy(struct lec_priv *priv) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; int i; @@ -1499,7 +1499,7 @@ static void lec_arp_destroy(struct lec_priv *priv) spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { lec_arp_remove(priv, entry); lec_arp_put(entry); @@ -1507,7 +1507,7 @@ static void lec_arp_destroy(struct lec_priv *priv) INIT_HLIST_HEAD(&priv->lec_arp_tables[i]); } - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { del_timer_sync(&entry->timer); lec_arp_clear_vccs(entry); @@ -1516,7 +1516,7 @@ static void lec_arp_destroy(struct lec_priv *priv) } INIT_HLIST_HEAD(&priv->lec_arp_empty_ones); - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_no_forward, next) { del_timer_sync(&entry->timer); lec_arp_clear_vccs(entry); @@ -1525,7 +1525,7 @@ static void lec_arp_destroy(struct lec_priv *priv) } INIT_HLIST_HEAD(&priv->lec_no_forward); - hlist_for_each_entry_safe(entry, node, next, &priv->mcast_fwds, next) { + hlist_for_each_entry_safe(entry, next, &priv->mcast_fwds, next) { /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ lec_arp_clear_vccs(entry); hlist_del(&entry->next); @@ -1542,14 +1542,13 @@ static void lec_arp_destroy(struct lec_priv *priv) static struct lec_arp_table *lec_arp_find(struct lec_priv *priv, const unsigned char *mac_addr) { - struct hlist_node *node; struct hlist_head *head; struct lec_arp_table *entry; pr_debug("%pM\n", mac_addr); head = &priv->lec_arp_tables[HASH(mac_addr[ETH_ALEN - 1])]; - hlist_for_each_entry(entry, node, head, next) { + hlist_for_each_entry(entry, head, next) { if (ether_addr_equal(mac_addr, entry->mac_addr)) return entry; } @@ -1686,7 +1685,7 @@ static void lec_arp_check_expire(struct work_struct *work) unsigned long flags; struct lec_priv *priv = container_of(work, struct lec_priv, lec_arp_work.work); - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; unsigned long now; int i; @@ -1696,7 +1695,7 @@ static void lec_arp_check_expire(struct work_struct *work) restart: spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { if (__lec_arp_check_expire(entry, now, priv)) { struct sk_buff *skb; @@ -1823,14 +1822,14 @@ lec_addr_delete(struct lec_priv *priv, const unsigned char *atm_addr, unsigned long permanent) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; int i; pr_debug("\n"); spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN) && (permanent || @@ -1855,7 +1854,7 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr, unsigned int targetless_le_arp) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry, *tmp; int i; @@ -1870,7 +1869,7 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr, * we have no entry in the cache. 7.1.30 */ if (!hlist_empty(&priv->lec_arp_empty_ones)) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { if (memcmp(entry->atm_addr, atm_addr, ATM_ESA_LEN) == 0) { hlist_del(&entry->next); @@ -1915,7 +1914,7 @@ lec_arp_update(struct lec_priv *priv, const unsigned char *mac_addr, memcpy(entry->atm_addr, atm_addr, ATM_ESA_LEN); del_timer(&entry->timer); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(tmp, node, + hlist_for_each_entry(tmp, &priv->lec_arp_tables[i], next) { if (entry != tmp && !memcmp(tmp->atm_addr, atm_addr, ATM_ESA_LEN)) { @@ -1956,7 +1955,6 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, void (*old_push) (struct atm_vcc *vcc, struct sk_buff *skb)) { unsigned long flags; - struct hlist_node *node; struct lec_arp_table *entry; int i, found_entry = 0; @@ -2026,7 +2024,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data, ioc_data->atm_addr[16], ioc_data->atm_addr[17], ioc_data->atm_addr[18], ioc_data->atm_addr[19]); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (memcmp (ioc_data->atm_addr, entry->atm_addr, @@ -2103,7 +2101,6 @@ out: static void lec_flush_complete(struct lec_priv *priv, unsigned long tran_id) { unsigned long flags; - struct hlist_node *node; struct lec_arp_table *entry; int i; @@ -2111,7 +2108,7 @@ static void lec_flush_complete(struct lec_priv *priv, unsigned long tran_id) restart: spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (entry->flush_tran_id == tran_id && entry->status == ESI_FLUSH_PENDING) { @@ -2140,13 +2137,12 @@ lec_set_flush_tran_id(struct lec_priv *priv, const unsigned char *atm_addr, unsigned long tran_id) { unsigned long flags; - struct hlist_node *node; struct lec_arp_table *entry; int i; spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) - hlist_for_each_entry(entry, node, + hlist_for_each_entry(entry, &priv->lec_arp_tables[i], next) { if (!memcmp(atm_addr, entry->atm_addr, ATM_ESA_LEN)) { entry->flush_tran_id = tran_id; @@ -2198,7 +2194,7 @@ out: static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry; int i; @@ -2208,7 +2204,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) spin_lock_irqsave(&priv->lec_arp_lock, flags); for (i = 0; i < LEC_ARP_TABLE_SIZE; i++) { - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_tables[i], next) { if (vcc == entry->vcc) { lec_arp_remove(priv, entry); @@ -2219,7 +2215,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) } } - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { if (entry->vcc == vcc) { lec_arp_clear_vccs(entry); @@ -2229,7 +2225,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) } } - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_no_forward, next) { if (entry->recv_vcc == vcc) { lec_arp_clear_vccs(entry); @@ -2239,7 +2235,7 @@ static void lec_vcc_close(struct lec_priv *priv, struct atm_vcc *vcc) } } - hlist_for_each_entry_safe(entry, node, next, &priv->mcast_fwds, next) { + hlist_for_each_entry_safe(entry, next, &priv->mcast_fwds, next) { if (entry->recv_vcc == vcc) { lec_arp_clear_vccs(entry); /* No timer, LANEv2 7.1.20 and 2.3.5.3 */ @@ -2257,13 +2253,13 @@ lec_arp_check_empties(struct lec_priv *priv, struct atm_vcc *vcc, struct sk_buff *skb) { unsigned long flags; - struct hlist_node *node, *next; + struct hlist_node *next; struct lec_arp_table *entry, *tmp; struct lecdatahdr_8023 *hdr = (struct lecdatahdr_8023 *)skb->data; unsigned char *src = hdr->h_source; spin_lock_irqsave(&priv->lec_arp_lock, flags); - hlist_for_each_entry_safe(entry, node, next, + hlist_for_each_entry_safe(entry, next, &priv->lec_arp_empty_ones, next) { if (vcc == entry->vcc) { del_timer(&entry->timer); diff --git a/net/atm/proc.c b/net/atm/proc.c index b4e75340b162..6ac35ff0d6b9 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -385,7 +385,7 @@ static ssize_t proc_dev_atm_read(struct file *file, char __user *buf, page = get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; - dev = PDE(file->f_path.dentry->d_inode)->data; + dev = PDE(file_inode(file))->data; if (!dev->ops->proc_read) length = -EINVAL; else { diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 86767ca908a3..4176887e72eb 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -217,7 +217,6 @@ static void purge_vcc(struct atm_vcc *vcc) static void sigd_close(struct atm_vcc *vcc) { - struct hlist_node *node; struct sock *s; int i; @@ -231,7 +230,7 @@ static void sigd_close(struct atm_vcc *vcc) for (i = 0; i < VCC_HTABLE_SIZE; ++i) { struct hlist_head *head = &vcc_hash[i]; - sk_for_each(s, node, head) { + sk_for_each(s, head) { vcc = atm_sk(s); purge_vcc(vcc); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 69a06c47b648..e277e38f736b 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -81,14 +81,13 @@ static void ax25_kill_by_device(struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *s; - struct hlist_node *node; if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; spin_lock_bh(&ax25_list_lock); again: - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { s->ax25_dev = NULL; spin_unlock_bh(&ax25_list_lock); @@ -158,10 +157,9 @@ struct sock *ax25_find_listener(ax25_address *addr, int digi, struct net_device *dev, int type) { ax25_cb *s; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if ((s->iamdigi && !digi) || (!s->iamdigi && digi)) continue; if (s->sk && !ax25cmp(&s->source_addr, addr) && @@ -187,10 +185,9 @@ struct sock *ax25_get_socket(ax25_address *my_addr, ax25_address *dest_addr, { struct sock *sk = NULL; ax25_cb *s; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->sk && !ax25cmp(&s->source_addr, my_addr) && !ax25cmp(&s->dest_addr, dest_addr) && s->sk->sk_type == type) { @@ -213,10 +210,9 @@ ax25_cb *ax25_find_cb(ax25_address *src_addr, ax25_address *dest_addr, ax25_digi *digi, struct net_device *dev) { ax25_cb *s; - struct hlist_node *node; spin_lock_bh(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->sk && s->sk->sk_type != SOCK_SEQPACKET) continue; if (s->ax25_dev == NULL) @@ -248,10 +244,9 @@ void ax25_send_to_raw(ax25_address *addr, struct sk_buff *skb, int proto) { ax25_cb *s; struct sk_buff *copy; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(s, node, &ax25_list) { + ax25_for_each(s, &ax25_list) { if (s->sk != NULL && ax25cmp(&s->source_addr, addr) == 0 && s->sk->sk_type == SOCK_RAW && s->sk->sk_protocol == proto && @@ -1647,6 +1642,7 @@ static int ax25_recvmsg(struct kiocb *iocb, struct socket *sock, ax25_address src; const unsigned char *mac = skb_mac_header(skb); + memset(sax, 0, sizeof(struct full_sockaddr_ax25)); ax25_addr_parse(mac + 1, skb->data - mac - 1, &src, NULL, &digi, NULL, NULL); sax->sax25_family = AF_AX25; diff --git a/net/ax25/ax25_ds_subr.c b/net/ax25/ax25_ds_subr.c index 5ea7fd3e2af9..e05bd57b5afd 100644 --- a/net/ax25/ax25_ds_subr.c +++ b/net/ax25/ax25_ds_subr.c @@ -39,7 +39,6 @@ void ax25_ds_nr_error_recovery(ax25_cb *ax25) void ax25_ds_enquiry_response(ax25_cb *ax25) { ax25_cb *ax25o; - struct hlist_node *node; /* Please note that neither DK4EG's nor DG2FEF's * DAMA spec mention the following behaviour as seen @@ -80,7 +79,7 @@ void ax25_ds_enquiry_response(ax25_cb *ax25) ax25_ds_set_timer(ax25->ax25_dev); spin_lock(&ax25_list_lock); - ax25_for_each(ax25o, node, &ax25_list) { + ax25_for_each(ax25o, &ax25_list) { if (ax25o == ax25) continue; @@ -159,10 +158,9 @@ static int ax25_check_dama_slave(ax25_dev *ax25_dev) { ax25_cb *ax25; int res = 0; - struct hlist_node *node; spin_lock(&ax25_list_lock); - ax25_for_each(ax25, node, &ax25_list) + ax25_for_each(ax25, &ax25_list) if (ax25->ax25_dev == ax25_dev && (ax25->condition & AX25_COND_DAMA_MODE) && ax25->state > AX25_STATE_1) { res = 1; break; diff --git a/net/ax25/ax25_ds_timer.c b/net/ax25/ax25_ds_timer.c index 993c439b4f71..951cd57bb07d 100644 --- a/net/ax25/ax25_ds_timer.c +++ b/net/ax25/ax25_ds_timer.c @@ -70,7 +70,6 @@ static void ax25_ds_timeout(unsigned long arg) { ax25_dev *ax25_dev = (struct ax25_dev *) arg; ax25_cb *ax25; - struct hlist_node *node; if (ax25_dev == NULL || !ax25_dev->dama.slave) return; /* Yikes! */ @@ -81,7 +80,7 @@ static void ax25_ds_timeout(unsigned long arg) } spin_lock(&ax25_list_lock); - ax25_for_each(ax25, node, &ax25_list) { + ax25_for_each(ax25, &ax25_list) { if (ax25->ax25_dev != ax25_dev || !(ax25->condition & AX25_COND_DAMA_MODE)) continue; diff --git a/net/ax25/ax25_iface.c b/net/ax25/ax25_iface.c index 7d5f24b82cc8..7f16e8a931b2 100644 --- a/net/ax25/ax25_iface.c +++ b/net/ax25/ax25_iface.c @@ -193,10 +193,9 @@ int ax25_listen_mine(ax25_address *callsign, struct net_device *dev) void ax25_link_failed(ax25_cb *ax25, int reason) { struct ax25_linkfail *lf; - struct hlist_node *node; spin_lock_bh(&linkfail_lock); - hlist_for_each_entry(lf, node, &ax25_linkfail_list, lf_node) + hlist_for_each_entry(lf, &ax25_linkfail_list, lf_node) lf->func(ax25, reason); spin_unlock_bh(&linkfail_lock); } diff --git a/net/ax25/ax25_uid.c b/net/ax25/ax25_uid.c index 957999e43ff7..71c4badbc807 100644 --- a/net/ax25/ax25_uid.c +++ b/net/ax25/ax25_uid.c @@ -54,10 +54,9 @@ EXPORT_SYMBOL(ax25_uid_policy); ax25_uid_assoc *ax25_findbyuid(kuid_t uid) { ax25_uid_assoc *ax25_uid, *res = NULL; - struct hlist_node *node; read_lock(&ax25_uid_lock); - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { if (uid_eq(ax25_uid->uid, uid)) { ax25_uid_hold(ax25_uid); res = ax25_uid; @@ -74,7 +73,6 @@ EXPORT_SYMBOL(ax25_findbyuid); int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) { ax25_uid_assoc *ax25_uid; - struct hlist_node *node; ax25_uid_assoc *user; unsigned long res; @@ -82,7 +80,7 @@ int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) case SIOCAX25GETUID: res = -ENOENT; read_lock(&ax25_uid_lock); - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { if (ax25cmp(&sax->sax25_call, &ax25_uid->call) == 0) { res = from_kuid_munged(current_user_ns(), ax25_uid->uid); break; @@ -126,7 +124,7 @@ int ax25_uid_ioctl(int cmd, struct sockaddr_ax25 *sax) ax25_uid = NULL; write_lock(&ax25_uid_lock); - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { if (ax25cmp(&sax->sax25_call, &ax25_uid->call) == 0) break; } @@ -212,11 +210,10 @@ const struct file_operations ax25_uid_fops = { void __exit ax25_uid_free(void) { ax25_uid_assoc *ax25_uid; - struct hlist_node *node; write_lock(&ax25_uid_lock); again: - ax25_uid_for_each(ax25_uid, node, &ax25_uid_list) { + ax25_uid_for_each(ax25_uid, &ax25_uid_list) { hlist_del_init(&ax25_uid->uid_node); ax25_uid_put(ax25_uid); goto again; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 72fe1bbf7721..a5bb0a769eb9 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -487,7 +487,6 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, */ struct batadv_forw_packet *forw_packet_aggr = NULL; struct batadv_forw_packet *forw_packet_pos = NULL; - struct hlist_node *tmp_node; struct batadv_ogm_packet *batadv_ogm_packet; bool direct_link; unsigned long max_aggregation_jiffies; @@ -500,7 +499,7 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->forw_bat_list_lock); /* own packets are not to be aggregated */ if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { - hlist_for_each_entry(forw_packet_pos, tmp_node, + hlist_for_each_entry(forw_packet_pos, &bat_priv->forw_bat_list, list) { if (batadv_iv_ogm_can_aggregate(batadv_ogm_packet, bat_priv, packet_len, @@ -655,7 +654,6 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; struct batadv_neigh_node *router = NULL; struct batadv_orig_node *orig_node_tmp; - struct hlist_node *node; int if_num; uint8_t sum_orig, sum_neigh; uint8_t *neigh_addr; @@ -665,7 +663,7 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv, "update_originator(): Searching and updating originator entry of received packet\n"); rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { neigh_addr = tmp_neigh_node->addr; if (batadv_compare_eth(neigh_addr, ethhdr->h_source) && @@ -801,7 +799,6 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node; - struct hlist_node *node; uint8_t total_count; uint8_t orig_eq_count, neigh_rq_count, neigh_rq_inv, tq_own; unsigned int neigh_rq_inv_cube, neigh_rq_max_cube; @@ -810,7 +807,7 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, /* find corresponding one hop neighbor */ rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_neigh_node->neigh_list, list) { if (!batadv_compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) @@ -920,7 +917,6 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_orig_node *orig_node; struct batadv_neigh_node *tmp_neigh_node; - struct hlist_node *node; int is_duplicate = 0; int32_t seq_diff; int need_update = 0; @@ -943,7 +939,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, goto out; rcu_read_lock(); - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { is_duplicate |= batadv_test_bit(tmp_neigh_node->real_bits, orig_node->last_real_seqno, @@ -1292,7 +1288,8 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, batadv_ogm_packet = (struct batadv_ogm_packet *)packet_buff; /* unpack the aggregated packets and process them one by one */ - do { + while (batadv_iv_ogm_aggr_packet(buff_pos, packet_len, + batadv_ogm_packet->tt_num_changes)) { tt_buff = packet_buff + buff_pos + BATADV_OGM_HLEN; batadv_iv_ogm_process(ethhdr, batadv_ogm_packet, tt_buff, @@ -1303,8 +1300,7 @@ static int batadv_iv_ogm_receive(struct sk_buff *skb, packet_pos = packet_buff + buff_pos; batadv_ogm_packet = (struct batadv_ogm_packet *)packet_pos; - } while (batadv_iv_ogm_aggr_packet(buff_pos, packet_len, - batadv_ogm_packet->tt_num_changes)); + } kfree_skb(skb); return NET_RX_SUCCESS; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 30f46526cbbd..6a4f728680ae 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -144,7 +144,6 @@ static struct batadv_bla_claim { struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_bla_claim *claim; struct batadv_bla_claim *claim_tmp = NULL; int index; @@ -156,7 +155,7 @@ static struct batadv_bla_claim head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { if (!batadv_compare_claim(&claim->hash_entry, data)) continue; @@ -185,7 +184,6 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv, { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_bla_backbone_gw search_entry, *backbone_gw; struct batadv_bla_backbone_gw *backbone_gw_tmp = NULL; int index; @@ -200,7 +198,7 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv, head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_backbone_gw(&backbone_gw->hash_entry, &search_entry)) continue; @@ -221,7 +219,7 @@ static void batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_hashtable *hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_bla_claim *claim; int i; @@ -236,13 +234,13 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(claim, node, node_tmp, + hlist_for_each_entry_safe(claim, node_tmp, head, hash_entry) { if (claim->backbone_gw != backbone_gw) continue; batadv_claim_free_ref(claim); - hlist_del_rcu(node); + hlist_del_rcu(&claim->hash_entry); } spin_unlock_bh(list_lock); } @@ -460,7 +458,6 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, short vid) { - struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; struct batadv_bla_claim *claim; @@ -481,7 +478,7 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { /* only own claims are interesting */ if (claim->backbone_gw != backbone_gw) continue; @@ -958,7 +955,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) { struct batadv_bla_backbone_gw *backbone_gw; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -973,7 +970,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(backbone_gw, node, node_tmp, + hlist_for_each_entry_safe(backbone_gw, node_tmp, head, hash_entry) { if (now) goto purge_now; @@ -992,7 +989,7 @@ purge_now: batadv_bla_del_backbone_claims(backbone_gw); - hlist_del_rcu(node); + hlist_del_rcu(&backbone_gw->hash_entry); batadv_backbone_gw_free_ref(backbone_gw); } spin_unlock_bh(list_lock); @@ -1013,7 +1010,6 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, int now) { struct batadv_bla_claim *claim; - struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; int i; @@ -1026,7 +1022,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { if (now) goto purge_now; if (!batadv_compare_eth(claim->backbone_gw->orig, @@ -1062,7 +1058,6 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, struct batadv_hard_iface *oldif) { struct batadv_bla_backbone_gw *backbone_gw; - struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; __be16 group; @@ -1086,7 +1081,7 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { /* own orig still holds the old value. */ if (!batadv_compare_eth(backbone_gw->orig, oldif->net_dev->dev_addr)) @@ -1112,7 +1107,6 @@ static void batadv_bla_periodic_work(struct work_struct *work) struct delayed_work *delayed_work; struct batadv_priv *bat_priv; struct batadv_priv_bla *priv_bla; - struct hlist_node *node; struct hlist_head *head; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hashtable *hash; @@ -1140,7 +1134,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (!batadv_compare_eth(backbone_gw->orig, primary_if->net_dev->dev_addr)) continue; @@ -1322,7 +1316,6 @@ int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_bla_backbone_gw *backbone_gw; int i; @@ -1336,7 +1329,7 @@ int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { if (batadv_compare_eth(backbone_gw->orig, orig)) { rcu_read_unlock(); return 1; @@ -1607,7 +1600,6 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; uint32_t i; bool is_own; @@ -1628,7 +1620,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(claim, node, head, hash_entry) { + hlist_for_each_entry_rcu(claim, head, hash_entry) { is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); seq_printf(seq, " * %pM on % 5d by %pM [%c] (%#.4x)\n", @@ -1652,7 +1644,6 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; int secs, msecs; uint32_t i; @@ -1674,7 +1665,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(backbone_gw, node, head, hash_entry) { + hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) { msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime); secs = msecs / 1000; diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 761a59002e34..d54188a112ea 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -83,7 +83,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, { spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_dat_entry *dat_entry; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; uint32_t i; @@ -95,7 +95,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, list_lock = &bat_priv->dat.hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(dat_entry, node, node_tmp, head, + hlist_for_each_entry_safe(dat_entry, node_tmp, head, hash_entry) { /* if an helper function has been passed as parameter, * ask it if the entry has to be purged or not @@ -103,7 +103,7 @@ static void __batadv_dat_purge(struct batadv_priv *bat_priv, if (to_purge && !to_purge(dat_entry)) continue; - hlist_del_rcu(node); + hlist_del_rcu(&dat_entry->hash_entry); batadv_dat_entry_free_ref(dat_entry); } spin_unlock_bh(list_lock); @@ -235,7 +235,6 @@ static struct batadv_dat_entry * batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip) { struct hlist_head *head; - struct hlist_node *node; struct batadv_dat_entry *dat_entry, *dat_entry_tmp = NULL; struct batadv_hashtable *hash = bat_priv->dat.hash; uint32_t index; @@ -247,7 +246,7 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(dat_entry, node, head, hash_entry) { + hlist_for_each_entry_rcu(dat_entry, head, hash_entry) { if (dat_entry->ip != ip) continue; @@ -465,7 +464,6 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, batadv_dat_addr_t max = 0, tmp_max = 0; struct batadv_orig_node *orig_node, *max_orig_node = NULL; struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; int i; @@ -481,7 +479,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { /* the dht space is a ring and addresses are unsigned */ tmp_max = BATADV_DAT_ADDR_MAX - orig_node->dat_addr + ip_key; @@ -686,7 +684,6 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset) struct batadv_hashtable *hash = bat_priv->dat.hash; struct batadv_dat_entry *dat_entry; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; unsigned long last_seen_jiffies; int last_seen_msecs, last_seen_secs, last_seen_mins; @@ -704,7 +701,7 @@ int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(dat_entry, node, head, hash_entry) { + hlist_for_each_entry_rcu(dat_entry, head, hash_entry) { last_seen_jiffies = jiffies - dat_entry->last_update; last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); last_seen_mins = last_seen_msecs / 60000; diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 074107f2cfaa..34f99a46ec1d 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -114,7 +114,6 @@ static struct batadv_gw_node * batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) { struct batadv_neigh_node *router; - struct hlist_node *node; struct batadv_gw_node *gw_node, *curr_gw = NULL; uint32_t max_gw_factor = 0, tmp_gw_factor = 0; uint32_t gw_divisor; @@ -127,7 +126,7 @@ batadv_gw_get_best_gw_node(struct batadv_priv *bat_priv) gw_divisor *= 64; rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw.list, list) { + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { if (gw_node->deleted) continue; @@ -344,7 +343,6 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, uint8_t new_gwflags) { - struct hlist_node *node; struct batadv_gw_node *gw_node, *curr_gw; /* Note: We don't need a NULL check here, since curr_gw never gets @@ -355,7 +353,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, curr_gw = batadv_gw_get_selected_gw_node(bat_priv); rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw.list, list) { + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { if (gw_node->orig_node != orig_node) continue; @@ -403,7 +401,7 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, void batadv_gw_node_purge(struct batadv_priv *bat_priv) { struct batadv_gw_node *gw_node, *curr_gw; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; unsigned long timeout = msecs_to_jiffies(2 * BATADV_PURGE_TIMEOUT); int do_deselect = 0; @@ -411,7 +409,7 @@ void batadv_gw_node_purge(struct batadv_priv *bat_priv) spin_lock_bh(&bat_priv->gw.list_lock); - hlist_for_each_entry_safe(gw_node, node, node_tmp, + hlist_for_each_entry_safe(gw_node, node_tmp, &bat_priv->gw.list, list) { if (((!gw_node->deleted) || (time_before(jiffies, gw_node->deleted + timeout))) && @@ -476,7 +474,6 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hard_iface *primary_if; struct batadv_gw_node *gw_node; - struct hlist_node *node; int gw_count = 0; primary_if = batadv_seq_print_text_primary_if_get(seq); @@ -490,7 +487,7 @@ int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset) primary_if->net_dev->dev_addr, net_dev->name); rcu_read_lock(); - hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw.list, list) { + hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.list, list) { if (gw_node->deleted) continue; diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 21fe6987733b..fa563e497c48 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -169,7 +169,7 @@ void batadv_mesh_free(struct net_device *soft_iface) atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); } -int batadv_is_my_mac(const uint8_t *addr) +int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr) { const struct batadv_hard_iface *hard_iface; @@ -178,6 +178,9 @@ int batadv_is_my_mac(const uint8_t *addr) if (hard_iface->if_status != BATADV_IF_ACTIVE) continue; + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) { rcu_read_unlock(); return 1; @@ -345,9 +348,8 @@ void batadv_recv_handler_unregister(uint8_t packet_type) static struct batadv_algo_ops *batadv_algo_get(char *name) { struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; - struct hlist_node *node; - hlist_for_each_entry(bat_algo_ops_tmp, node, &batadv_algo_list, list) { + hlist_for_each_entry(bat_algo_ops_tmp, &batadv_algo_list, list) { if (strcmp(bat_algo_ops_tmp->name, name) != 0) continue; @@ -411,11 +413,10 @@ out: int batadv_algo_seq_print_text(struct seq_file *seq, void *offset) { struct batadv_algo_ops *bat_algo_ops; - struct hlist_node *node; seq_printf(seq, "Available routing algorithms:\n"); - hlist_for_each_entry(bat_algo_ops, node, &batadv_algo_list, list) { + hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) { seq_printf(seq, "%s\n", bat_algo_ops->name); } diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index ced08b936a96..d40910dfc8ea 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -162,7 +162,7 @@ extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *soft_iface); void batadv_mesh_free(struct net_device *soft_iface); -int batadv_is_my_mac(const uint8_t *addr); +int batadv_is_my_mac(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_hard_iface * batadv_seq_print_text_primary_if_get(struct seq_file *seq); int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 457ea445217c..96fb80b724dc 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -118,7 +118,7 @@ out: static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node, *tmp_neigh_node; struct batadv_orig_node *orig_node; @@ -134,7 +134,7 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) } /* for all neighbors towards this originator ... */ - hlist_for_each_entry_safe(neigh_node, node, node_tmp, + hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); batadv_neigh_node_free_ref(neigh_node); @@ -161,7 +161,7 @@ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) void batadv_originator_free(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; @@ -179,9 +179,9 @@ void batadv_originator_free(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(orig_node, node, node_tmp, + hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { - hlist_del_rcu(node); + hlist_del_rcu(&orig_node->hash_entry); batadv_orig_node_free_ref(orig_node); } spin_unlock_bh(list_lock); @@ -274,7 +274,7 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, struct batadv_neigh_node **best_neigh_node) { - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; bool neigh_purged = false; unsigned long last_seen; @@ -285,7 +285,7 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ - hlist_for_each_entry_safe(neigh_node, node, node_tmp, + hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; @@ -348,7 +348,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv, static void _batadv_purge_orig(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct batadv_orig_node *orig_node; @@ -363,13 +363,13 @@ static void _batadv_purge_orig(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(orig_node, node, node_tmp, + hlist_for_each_entry_safe(orig_node, node_tmp, head, hash_entry) { if (batadv_purge_orig_node(bat_priv, orig_node)) { if (orig_node->gw_flags) batadv_gw_node_delete(bat_priv, orig_node); - hlist_del_rcu(node); + hlist_del_rcu(&orig_node->hash_entry); batadv_orig_node_free_ref(orig_node); continue; } @@ -408,7 +408,6 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node, *node_tmp; struct hlist_head *head; struct batadv_hard_iface *primary_if; struct batadv_orig_node *orig_node; @@ -434,7 +433,7 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { neigh_node = batadv_orig_node_get_router(orig_node); if (!neigh_node) continue; @@ -453,7 +452,7 @@ int batadv_orig_seq_print_text(struct seq_file *seq, void *offset) neigh_node->addr, neigh_node->if_incoming->net_dev->name); - hlist_for_each_entry_rcu(neigh_node_tmp, node_tmp, + hlist_for_each_entry_rcu(neigh_node_tmp, &orig_node->neigh_list, list) { seq_printf(seq, " %pM (%3i)", neigh_node_tmp->addr, @@ -511,7 +510,6 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; uint32_t i; @@ -524,7 +522,7 @@ int batadv_orig_hash_add_if(struct batadv_hard_iface *hard_iface, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); ret = batadv_orig_node_add_if(orig_node, max_if_num); spin_unlock_bh(&orig_node->ogm_cnt_lock); @@ -595,7 +593,6 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_hard_iface *hard_iface_tmp; struct batadv_orig_node *orig_node; @@ -609,7 +606,7 @@ int batadv_orig_hash_del_if(struct batadv_hard_iface *hard_iface, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); ret = batadv_orig_node_del_if(orig_node, max_if_num, hard_iface->if_num); diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 286bf743e76a..7df48fa7669d 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -68,7 +68,6 @@ batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data) { struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_orig_node *orig_node, *orig_node_tmp = NULL; int index; @@ -79,7 +78,7 @@ batadv_orig_hash_find(struct batadv_priv *bat_priv, const void *data) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { if (!batadv_compare_eth(orig_node, data)) continue; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 60ba03fc8390..319f2906c71a 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -37,7 +37,6 @@ void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; unsigned long *word; @@ -49,7 +48,7 @@ void batadv_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { spin_lock_bh(&orig_node->ogm_cnt_lock); word_index = hard_iface->if_num * BATADV_NUM_WORDS; word = &(orig_node->bcast_own[word_index]); @@ -146,7 +145,6 @@ out: void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) { - struct hlist_node *node; struct batadv_neigh_node *tmp_neigh_node, *router = NULL; uint8_t interference_candidate = 0; @@ -169,7 +167,7 @@ void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, * interface. If we do, we won't select this candidate because of * possible interference. */ - hlist_for_each_entry_rcu(tmp_neigh_node, node, + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { if (tmp_neigh_node == neigh_node) continue; @@ -404,7 +402,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, goto out; /* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) goto out; icmp_packet = (struct batadv_icmp_packet_rr *)skb->data; @@ -418,7 +416,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb, } /* packet for me */ - if (batadv_is_my_mac(icmp_packet->dst)) + if (batadv_is_my_mac(bat_priv, icmp_packet->dst)) return batadv_recv_my_icmp_packet(bat_priv, skb, hdr_size); /* TTL exceeded */ @@ -550,7 +548,8 @@ batadv_find_ifalter_router(struct batadv_orig_node *primary_orig, return router; } -static int batadv_check_unicast_packet(struct sk_buff *skb, int hdr_size) +static int batadv_check_unicast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) { struct ethhdr *ethhdr; @@ -569,7 +568,7 @@ static int batadv_check_unicast_packet(struct sk_buff *skb, int hdr_size) return -1; /* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return -1; return 0; @@ -584,7 +583,7 @@ int batadv_recv_tt_query(struct sk_buff *skb, struct batadv_hard_iface *recv_if) char tt_flag; size_t packet_size; - if (batadv_check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) return NET_RX_DROP; /* I could need to modify it */ @@ -616,7 +615,7 @@ int batadv_recv_tt_query(struct sk_buff *skb, struct batadv_hard_iface *recv_if) case BATADV_TT_RESPONSE: batadv_inc_counter(bat_priv, BATADV_CNT_TT_RESPONSE_RX); - if (batadv_is_my_mac(tt_query->dst)) { + if (batadv_is_my_mac(bat_priv, tt_query->dst)) { /* packet needs to be linearized to access the TT * changes */ @@ -659,14 +658,15 @@ int batadv_recv_roam_adv(struct sk_buff *skb, struct batadv_hard_iface *recv_if) struct batadv_roam_adv_packet *roam_adv_packet; struct batadv_orig_node *orig_node; - if (batadv_check_unicast_packet(skb, sizeof(*roam_adv_packet)) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, + sizeof(*roam_adv_packet)) < 0) goto out; batadv_inc_counter(bat_priv, BATADV_CNT_TT_ROAM_ADV_RX); roam_adv_packet = (struct batadv_roam_adv_packet *)skb->data; - if (!batadv_is_my_mac(roam_adv_packet->dst)) + if (!batadv_is_my_mac(bat_priv, roam_adv_packet->dst)) return batadv_route_unicast_packet(skb, recv_if); /* check if it is a backbone gateway. we don't accept @@ -969,7 +969,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, * last time) the packet had an updated information or not */ curr_ttvn = (uint8_t)atomic_read(&bat_priv->tt.vn); - if (!batadv_is_my_mac(unicast_packet->dest)) { + if (!batadv_is_my_mac(bat_priv, unicast_packet->dest)) { orig_node = batadv_orig_hash_find(bat_priv, unicast_packet->dest); /* if it is not possible to find the orig_node representing the @@ -1046,14 +1046,14 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, if (is4addr) hdr_size = sizeof(*unicast_4addr_packet); - if (batadv_check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) return NET_RX_DROP; if (!batadv_check_unicast_ttvn(bat_priv, skb)) return NET_RX_DROP; /* packet for me */ - if (batadv_is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { if (is4addr) { batadv_dat_inc_counter(bat_priv, unicast_4addr_packet->subtype); @@ -1090,7 +1090,7 @@ int batadv_recv_ucast_frag_packet(struct sk_buff *skb, struct sk_buff *new_skb = NULL; int ret; - if (batadv_check_unicast_packet(skb, hdr_size) < 0) + if (batadv_check_unicast_packet(bat_priv, skb, hdr_size) < 0) return NET_RX_DROP; if (!batadv_check_unicast_ttvn(bat_priv, skb)) @@ -1099,7 +1099,7 @@ int batadv_recv_ucast_frag_packet(struct sk_buff *skb, unicast_packet = (struct batadv_unicast_frag_packet *)skb->data; /* packet for me */ - if (batadv_is_my_mac(unicast_packet->dest)) { + if (batadv_is_my_mac(bat_priv, unicast_packet->dest)) { ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) @@ -1153,13 +1153,13 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, goto out; /* ignore broadcasts sent by myself */ - if (batadv_is_my_mac(ethhdr->h_source)) + if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto out; bcast_packet = (struct batadv_bcast_packet *)skb->data; /* ignore broadcasts originated by myself */ - if (batadv_is_my_mac(bcast_packet->orig)) + if (batadv_is_my_mac(bat_priv, bcast_packet->orig)) goto out; if (bcast_packet->header.ttl < 2) @@ -1245,14 +1245,14 @@ int batadv_recv_vis_packet(struct sk_buff *skb, ethhdr = (struct ethhdr *)skb_mac_header(skb); /* not for me */ - if (!batadv_is_my_mac(ethhdr->h_dest)) + if (!batadv_is_my_mac(bat_priv, ethhdr->h_dest)) return NET_RX_DROP; /* ignore own packets */ - if (batadv_is_my_mac(vis_packet->vis_orig)) + if (batadv_is_my_mac(bat_priv, vis_packet->vis_orig)) return NET_RX_DROP; - if (batadv_is_my_mac(vis_packet->sender_orig)) + if (batadv_is_my_mac(bat_priv, vis_packet->sender_orig)) return NET_RX_DROP; switch (vis_packet->vis_type) { diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 80ca65fc89a1..a67cffde37ae 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -316,7 +316,7 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface) { struct batadv_forw_packet *forw_packet; - struct hlist_node *tmp_node, *safe_tmp_node; + struct hlist_node *safe_tmp_node; bool pending; if (hard_iface) @@ -329,7 +329,7 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, /* free bcast list */ spin_lock_bh(&bat_priv->forw_bcast_list_lock); - hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, + hlist_for_each_entry_safe(forw_packet, safe_tmp_node, &bat_priv->forw_bcast_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface @@ -355,7 +355,7 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, /* free batman packet list */ spin_lock_bh(&bat_priv->forw_bat_list_lock); - hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, + hlist_for_each_entry_safe(forw_packet, safe_tmp_node, &bat_priv->forw_bat_list, list) { /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index d44672f4a349..7abee19567e9 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -56,7 +56,6 @@ static struct batadv_tt_common_entry * batadv_tt_hash_find(struct batadv_hashtable *hash, const void *data) { struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_common_entry *tt_common_entry_tmp = NULL; uint32_t index; @@ -68,7 +67,7 @@ batadv_tt_hash_find(struct batadv_hashtable *hash, const void *data) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (!batadv_compare_eth(tt_common_entry, data)) continue; @@ -257,7 +256,6 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, struct batadv_tt_local_entry *tt_local; struct batadv_tt_global_entry *tt_global; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry; int hash_added; bool roamed_back = false; @@ -339,7 +337,7 @@ check_roaming: /* These node are probably going to update their tt table */ head = &tt_global->orig_list; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { batadv_send_roam_adv(bat_priv, tt_global->common.addr, orig_entry->orig_node); } @@ -470,7 +468,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; uint32_t i; int last_seen_secs; @@ -494,7 +491,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { tt_local = container_of(tt_common_entry, struct batadv_tt_local_entry, @@ -605,9 +602,9 @@ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv, { struct batadv_tt_local_entry *tt_local_entry; struct batadv_tt_common_entry *tt_common_entry; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, head, + hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { tt_local_entry = container_of(tt_common_entry, struct batadv_tt_local_entry, @@ -651,7 +648,7 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; uint32_t i; @@ -665,9 +662,9 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, + hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { - hlist_del_rcu(node); + hlist_del_rcu(&tt_common_entry->hash_entry); tt_local = container_of(tt_common_entry, struct batadv_tt_local_entry, common); @@ -724,11 +721,10 @@ batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry, { struct batadv_tt_orig_list_entry *tmp_orig_entry, *orig_entry = NULL; const struct hlist_head *head; - struct hlist_node *node; rcu_read_lock(); head = &entry->orig_list; - hlist_for_each_entry_rcu(tmp_orig_entry, node, head, list) { + hlist_for_each_entry_rcu(tmp_orig_entry, head, list) { if (tmp_orig_entry->orig_node != orig_node) continue; if (!atomic_inc_not_zero(&tmp_orig_entry->refcount)) @@ -940,12 +936,11 @@ batadv_transtable_best_orig(struct batadv_tt_global_entry *tt_global_entry) { struct batadv_neigh_node *router = NULL; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry, *best_entry = NULL; int best_tq = 0; head = &tt_global_entry->orig_list; - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { router = batadv_orig_node_get_router(orig_entry->orig_node); if (!router) continue; @@ -973,7 +968,6 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, struct seq_file *seq) { struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry, *best_entry; struct batadv_tt_common_entry *tt_common_entry; uint16_t flags; @@ -997,7 +991,7 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, head = &tt_global_entry->orig_list; - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { if (best_entry == orig_entry) continue; @@ -1020,7 +1014,6 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_global_entry *tt_global; struct batadv_hard_iface *primary_if; - struct hlist_node *node; struct hlist_head *head; uint32_t i; @@ -1039,7 +1032,7 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, @@ -1059,13 +1052,13 @@ static void batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) { struct hlist_head *head; - struct hlist_node *node, *safe; + struct hlist_node *safe; struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; - hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { - hlist_del_rcu(node); + hlist_for_each_entry_safe(orig_entry, safe, head, list) { + hlist_del_rcu(&orig_entry->list); batadv_tt_orig_list_entry_free_ref(orig_entry); } spin_unlock_bh(&tt_global_entry->list_lock); @@ -1078,18 +1071,18 @@ batadv_tt_global_del_orig_entry(struct batadv_priv *bat_priv, const char *message) { struct hlist_head *head; - struct hlist_node *node, *safe; + struct hlist_node *safe; struct batadv_tt_orig_list_entry *orig_entry; spin_lock_bh(&tt_global_entry->list_lock); head = &tt_global_entry->orig_list; - hlist_for_each_entry_safe(orig_entry, node, safe, head, list) { + hlist_for_each_entry_safe(orig_entry, safe, head, list) { if (orig_entry->orig_node == orig_node) { batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting %pM from global tt entry %pM: %s\n", orig_node->orig, tt_global_entry->common.addr, message); - hlist_del_rcu(node); + hlist_del_rcu(&orig_entry->list); batadv_tt_orig_list_entry_free_ref(orig_entry); } } @@ -1108,7 +1101,6 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv, { bool last_entry = true; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_orig_list_entry *orig_entry; /* no local entry exists, case 1: @@ -1117,7 +1109,7 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv, rcu_read_lock(); head = &tt_global_entry->orig_list; - hlist_for_each_entry_rcu(orig_entry, node, head, list) { + hlist_for_each_entry_rcu(orig_entry, head, list) { if (orig_entry->orig_node != orig_node) { last_entry = false; break; @@ -1202,7 +1194,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, struct batadv_tt_common_entry *tt_common_entry; uint32_t i; struct batadv_hashtable *hash = bat_priv->tt.global_hash; - struct hlist_node *node, *safe; + struct hlist_node *safe; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -1214,7 +1206,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, safe, + hlist_for_each_entry_safe(tt_common_entry, safe, head, hash_entry) { tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, @@ -1227,7 +1219,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv, batadv_dbg(BATADV_DBG_TT, bat_priv, "Deleting global tt entry %pM: %s\n", tt_global->common.addr, message); - hlist_del_rcu(node); + hlist_del_rcu(&tt_common_entry->hash_entry); batadv_tt_global_entry_free_ref(tt_global); } } @@ -1262,7 +1254,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct hlist_head *head; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; spinlock_t *list_lock; /* protects write access to the hash lists */ uint32_t i; char *msg = NULL; @@ -1274,7 +1266,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common, node, node_tmp, head, + hlist_for_each_entry_safe(tt_common, node_tmp, head, hash_entry) { tt_global = container_of(tt_common, struct batadv_tt_global_entry, @@ -1287,7 +1279,7 @@ static void batadv_tt_global_purge(struct batadv_priv *bat_priv) "Deleting global tt entry (%pM): %s\n", tt_global->common.addr, msg); - hlist_del_rcu(node); + hlist_del_rcu(&tt_common->hash_entry); batadv_tt_global_entry_free_ref(tt_global); } @@ -1301,7 +1293,7 @@ static void batadv_tt_global_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_global_entry *tt_global; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; uint32_t i; @@ -1315,9 +1307,9 @@ static void batadv_tt_global_table_free(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common_entry, node, node_tmp, + hlist_for_each_entry_safe(tt_common_entry, node_tmp, head, hash_entry) { - hlist_del_rcu(node); + hlist_del_rcu(&tt_common_entry->hash_entry); tt_global = container_of(tt_common_entry, struct batadv_tt_global_entry, common); @@ -1397,7 +1389,6 @@ static uint16_t batadv_tt_global_crc(struct batadv_priv *bat_priv, struct batadv_hashtable *hash = bat_priv->tt.global_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_global_entry *tt_global; - struct hlist_node *node; struct hlist_head *head; uint32_t i; int j; @@ -1406,7 +1397,7 @@ static uint16_t batadv_tt_global_crc(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common, node, head, hash_entry) { + hlist_for_each_entry_rcu(tt_common, head, hash_entry) { tt_global = container_of(tt_common, struct batadv_tt_global_entry, common); @@ -1449,7 +1440,6 @@ static uint16_t batadv_tt_local_crc(struct batadv_priv *bat_priv) uint16_t total = 0, total_one; struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; - struct hlist_node *node; struct hlist_head *head; uint32_t i; int j; @@ -1458,7 +1448,7 @@ static uint16_t batadv_tt_local_crc(struct batadv_priv *bat_priv) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common, node, head, hash_entry) { + hlist_for_each_entry_rcu(tt_common, head, hash_entry) { /* not yet committed clients have not to be taken into * account while computing the CRC */ @@ -1597,7 +1587,6 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_query_packet *tt_response; struct batadv_tt_change *tt_change; - struct hlist_node *node; struct hlist_head *head; struct sk_buff *skb = NULL; uint16_t tt_tot, tt_count; @@ -1627,7 +1616,7 @@ batadv_tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (tt_count == tt_tot) break; @@ -1964,7 +1953,7 @@ out: bool batadv_send_tt_response(struct batadv_priv *bat_priv, struct batadv_tt_query_packet *tt_request) { - if (batadv_is_my_mac(tt_request->dst)) { + if (batadv_is_my_mac(bat_priv, tt_request->dst)) { /* don't answer backbone gws! */ if (batadv_bla_is_backbone_gw_orig(bat_priv, tt_request->src)) return true; @@ -2307,7 +2296,6 @@ static uint16_t batadv_tt_set_flags(struct batadv_hashtable *hash, uint32_t i; uint16_t changed_num = 0; struct hlist_head *head; - struct hlist_node *node; struct batadv_tt_common_entry *tt_common_entry; if (!hash) @@ -2317,7 +2305,7 @@ static uint16_t batadv_tt_set_flags(struct batadv_hashtable *hash, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { if (enable) { if ((tt_common_entry->flags & flags) == flags) @@ -2342,7 +2330,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_local_entry *tt_local; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ uint32_t i; @@ -2355,7 +2343,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) list_lock = &hash->list_locks[i]; spin_lock_bh(list_lock); - hlist_for_each_entry_safe(tt_common, node, node_tmp, head, + hlist_for_each_entry_safe(tt_common, node_tmp, head, hash_entry) { if (!(tt_common->flags & BATADV_TT_CLIENT_PENDING)) continue; @@ -2365,7 +2353,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) tt_common->addr); atomic_dec(&bat_priv->tt.local_entry_num); - hlist_del_rcu(node); + hlist_del_rcu(&tt_common->hash_entry); tt_local = container_of(tt_common, struct batadv_tt_local_entry, common); diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 22d2785177d1..6a1e646be96d 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -97,7 +97,6 @@ batadv_vis_hash_find(struct batadv_priv *bat_priv, const void *data) { struct batadv_hashtable *hash = bat_priv->vis.hash; struct hlist_head *head; - struct hlist_node *node; struct batadv_vis_info *vis_info, *vis_info_tmp = NULL; uint32_t index; @@ -108,8 +107,8 @@ batadv_vis_hash_find(struct batadv_priv *bat_priv, const void *data) head = &hash->table[index]; rcu_read_lock(); - hlist_for_each_entry_rcu(vis_info, node, head, hash_entry) { - if (!batadv_vis_info_cmp(node, data)) + hlist_for_each_entry_rcu(vis_info, head, hash_entry) { + if (!batadv_vis_info_cmp(&vis_info->hash_entry, data)) continue; vis_info_tmp = vis_info; @@ -128,9 +127,8 @@ static void batadv_vis_data_insert_interface(const uint8_t *interface, bool primary) { struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos; - hlist_for_each_entry(entry, pos, if_list, list) { + hlist_for_each_entry(entry, if_list, list) { if (batadv_compare_eth(entry->addr, interface)) return; } @@ -148,9 +146,8 @@ static void batadv_vis_data_read_prim_sec(struct seq_file *seq, const struct hlist_head *if_list) { struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos; - hlist_for_each_entry(entry, pos, if_list, list) { + hlist_for_each_entry(entry, if_list, list) { if (entry->primary) seq_printf(seq, "PRIMARY, "); else @@ -198,9 +195,8 @@ static void batadv_vis_data_read_entries(struct seq_file *seq, { int i; struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos; - hlist_for_each_entry(entry, pos, list, list) { + hlist_for_each_entry(entry, list, list) { seq_printf(seq, "%pM,", entry->addr); for (i = 0; i < packet->entries; i++) @@ -218,17 +214,16 @@ static void batadv_vis_data_read_entries(struct seq_file *seq, static void batadv_vis_seq_print_text_bucket(struct seq_file *seq, const struct hlist_head *head) { - struct hlist_node *node; struct batadv_vis_info *info; struct batadv_vis_packet *packet; uint8_t *entries_pos; struct batadv_vis_info_entry *entries; struct batadv_vis_if_list_entry *entry; - struct hlist_node *pos, *n; + struct hlist_node *n; HLIST_HEAD(vis_if_list); - hlist_for_each_entry_rcu(info, node, head, hash_entry) { + hlist_for_each_entry_rcu(info, head, hash_entry) { packet = (struct batadv_vis_packet *)info->skb_packet->data; entries_pos = (uint8_t *)packet + sizeof(*packet); entries = (struct batadv_vis_info_entry *)entries_pos; @@ -240,7 +235,7 @@ static void batadv_vis_seq_print_text_bucket(struct seq_file *seq, batadv_vis_data_read_entries(seq, &vis_if_list, packet, entries); - hlist_for_each_entry_safe(entry, pos, n, &vis_if_list, list) { + hlist_for_each_entry_safe(entry, n, &vis_if_list, list) { hlist_del(&entry->list); kfree(entry); } @@ -482,7 +477,7 @@ void batadv_receive_client_update_packet(struct batadv_priv *bat_priv, /* Are we the target for this VIS packet? */ if (vis_server == BATADV_VIS_TYPE_SERVER_SYNC && - batadv_is_my_mac(vis_packet->target_orig)) + batadv_is_my_mac(bat_priv, vis_packet->target_orig)) are_target = 1; spin_lock_bh(&bat_priv->vis.hash_lock); @@ -501,7 +496,7 @@ void batadv_receive_client_update_packet(struct batadv_priv *bat_priv, batadv_send_list_add(bat_priv, info); /* ... we're not the recipient (and thus need to forward). */ - } else if (!batadv_is_my_mac(packet->target_orig)) { + } else if (!batadv_is_my_mac(bat_priv, packet->target_orig)) { batadv_send_list_add(bat_priv, info); } @@ -519,7 +514,6 @@ static int batadv_find_best_vis_server(struct batadv_priv *bat_priv, { struct batadv_hashtable *hash = bat_priv->orig_hash; struct batadv_neigh_node *router; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; struct batadv_vis_packet *packet; @@ -532,7 +526,7 @@ static int batadv_find_best_vis_server(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { router = batadv_orig_node_get_router(orig_node); if (!router) continue; @@ -571,7 +565,6 @@ static bool batadv_vis_packet_full(const struct batadv_vis_info *info) static int batadv_generate_vis_packet(struct batadv_priv *bat_priv) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; struct batadv_neigh_node *router; @@ -605,7 +598,7 @@ static int batadv_generate_vis_packet(struct batadv_priv *bat_priv) head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { router = batadv_orig_node_get_router(orig_node); if (!router) continue; @@ -644,7 +637,7 @@ next: head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(tt_common_entry, node, head, + hlist_for_each_entry_rcu(tt_common_entry, head, hash_entry) { packet_pos = skb_put(info->skb_packet, sizeof(*entry)); entry = (struct batadv_vis_info_entry *)packet_pos; @@ -673,14 +666,14 @@ static void batadv_purge_vis_packets(struct batadv_priv *bat_priv) { uint32_t i; struct batadv_hashtable *hash = bat_priv->vis.hash; - struct hlist_node *node, *node_tmp; + struct hlist_node *node_tmp; struct hlist_head *head; struct batadv_vis_info *info; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - hlist_for_each_entry_safe(info, node, node_tmp, + hlist_for_each_entry_safe(info, node_tmp, head, hash_entry) { /* never purge own data. */ if (info == bat_priv->vis.my_info) @@ -688,7 +681,7 @@ static void batadv_purge_vis_packets(struct batadv_priv *bat_priv) if (batadv_has_timed_out(info->first_seen, BATADV_VIS_TIMEOUT)) { - hlist_del(node); + hlist_del(&info->hash_entry); batadv_send_list_del(info); kref_put(&info->refcount, batadv_free_info); } @@ -700,7 +693,6 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, struct batadv_vis_info *info) { struct batadv_hashtable *hash = bat_priv->orig_hash; - struct hlist_node *node; struct hlist_head *head; struct batadv_orig_node *orig_node; struct batadv_vis_packet *packet; @@ -715,7 +707,7 @@ static void batadv_broadcast_vis_packet(struct batadv_priv *bat_priv, head = &hash->table[i]; rcu_read_lock(); - hlist_for_each_entry_rcu(orig_node, node, head, hash_entry) { + hlist_for_each_entry_rcu(orig_node, head, hash_entry) { /* if it's a vis server and reachable, send it. */ if (!(orig_node->flags & BATADV_VIS_SERVER)) continue; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index d3ee69b35a78..0d1b08cc76e1 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -230,6 +230,8 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (flags & (MSG_OOB)) return -EOPNOTSUPP; + msg->msg_namelen = 0; + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -237,8 +239,6 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - msg->msg_namelen = 0; - copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 07f073935811..6a93614f2c49 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -70,14 +70,13 @@ static struct bt_sock_list hci_sk_list = { void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; struct sk_buff *skb_copy = NULL; BT_DBG("hdev %p len %d", hdev, skb->len); read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct hci_filter *flt; struct sk_buff *nskb; @@ -142,13 +141,12 @@ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb) void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk) { struct sock *sk; - struct hlist_node *node; BT_DBG("len %d", skb->len); read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; /* Skip the original socket */ @@ -176,7 +174,6 @@ void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk) void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; struct sk_buff *skb_copy = NULL; __le16 opcode; @@ -210,7 +207,7 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; if (sk->sk_state != BT_BOUND) @@ -251,13 +248,12 @@ void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb) static void send_monitor_event(struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; BT_DBG("len %d", skb->len); read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { struct sk_buff *nskb; if (sk->sk_state != BT_BOUND) @@ -393,11 +389,10 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) if (event == HCI_DEV_UNREG) { struct sock *sk; - struct hlist_node *node; /* Detach sockets from device */ read_lock(&hci_sk_list.lock); - sk_for_each(sk, node, &hci_sk_list.head) { + sk_for_each(sk, &hci_sk_list.head) { bh_lock_sock_nested(sk); if (hci_pi(sk)->hdev == hdev) { hci_pi(sk)->hdev = NULL; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index ce3f6658f4b2..7c9224bcce17 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -107,15 +107,14 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err) static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src) { struct sock *sk = NULL; - struct hlist_node *node; - sk_for_each(sk, node, &rfcomm_sk_list.head) { + sk_for_each(sk, &rfcomm_sk_list.head) { if (rfcomm_pi(sk)->channel == channel && !bacmp(&bt_sk(sk)->src, src)) break; } - return node ? sk : NULL; + return sk ? sk : NULL; } /* Find socket with channel and source bdaddr. @@ -124,11 +123,10 @@ static struct sock *__rfcomm_get_sock_by_addr(u8 channel, bdaddr_t *src) static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; - struct hlist_node *node; read_lock(&rfcomm_sk_list.lock); - sk_for_each(sk, node, &rfcomm_sk_list.head) { + sk_for_each(sk, &rfcomm_sk_list.head) { if (state && sk->sk_state != state) continue; @@ -145,7 +143,7 @@ static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t * read_unlock(&rfcomm_sk_list.lock); - return node ? sk : sk1; + return sk ? sk : sk1; } static void rfcomm_sock_destruct(struct sock *sk) @@ -610,6 +608,7 @@ static int rfcomm_sock_recvmsg(struct kiocb *iocb, struct socket *sock, if (test_and_clear_bit(RFCOMM_DEFER_SETUP, &d->flags)) { rfcomm_dlc_accept(d); + msg->msg_namelen = 0; return 0; } @@ -970,11 +969,10 @@ done: static int rfcomm_sock_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; - struct hlist_node *node; read_lock(&rfcomm_sk_list.lock); - sk_for_each(sk, node, &rfcomm_sk_list.head) { + sk_for_each(sk, &rfcomm_sk_list.head) { seq_printf(f, "%pMR %pMR %d %d\n", &bt_sk(sk)->src, &bt_sk(sk)->dst, sk->sk_state, rfcomm_pi(sk)->channel); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index b5178d62064e..fb6192c9812e 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -259,10 +259,9 @@ drop: /* -------- Socket interface ---------- */ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) { - struct hlist_node *node; struct sock *sk; - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; @@ -279,11 +278,10 @@ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) static struct sock *sco_get_sock_listen(bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; - struct hlist_node *node; read_lock(&sco_sk_list.lock); - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; @@ -298,7 +296,7 @@ static struct sock *sco_get_sock_listen(bdaddr_t *src) read_unlock(&sco_sk_list.lock); - return node ? sk : sk1; + return sk ? sk : sk1; } static void sco_sock_destruct(struct sock *sk) @@ -361,6 +359,7 @@ static void __sco_sock_close(struct sock *sk) sco_chan_del(sk, ECONNRESET); break; + case BT_CONNECT2: case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); @@ -666,6 +665,7 @@ static int sco_sock_recvmsg(struct kiocb *iocb, struct socket *sock, test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { hci_conn_accept(pi->conn->hcon, 0); sk->sk_state = BT_CONFIG; + msg->msg_namelen = 0; release_sock(sk); return 0; @@ -951,14 +951,13 @@ static void sco_conn_ready(struct sco_conn *conn) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct sock *sk; - struct hlist_node *node; int lm = 0; BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets */ read_lock(&sco_sk_list.lock); - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; @@ -1018,11 +1017,10 @@ drop: static int sco_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; - struct hlist_node *node; read_lock(&sco_sk_list.lock); - sk_for_each(sk, node, &sco_sk_list.head) { + sk_for_each(sk, &sco_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &bt_sk(sk)->src, &bt_sk(sk)->dst, sk->sk_state); } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index d5f1d3fd4b28..314c73ed418f 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -66,7 +66,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } - mdst = br_mdb_get(br, skb); + mdst = br_mdb_get(br, skb, vid); if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) br_multicast_deliver(mdst, skb); else diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 8117900af4de..bab338e6270d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -181,9 +181,9 @@ void br_fdb_cleanup(unsigned long _data) spin_lock(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; - struct hlist_node *h, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) { + hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) { unsigned long this_timer; if (f->is_static) continue; @@ -207,8 +207,8 @@ void br_fdb_flush(struct net_bridge *br) spin_lock_bh(&br->hash_lock); for (i = 0; i < BR_HASH_SIZE; i++) { struct net_bridge_fdb_entry *f; - struct hlist_node *h, *n; - hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) { + struct hlist_node *n; + hlist_for_each_entry_safe(f, n, &br->hash[i], hlist) { if (!f->is_static) fdb_delete(br, f); } @@ -266,10 +266,9 @@ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, const unsigned char *addr, __u16 vid) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry_rcu(fdb, h, + hlist_for_each_entry_rcu(fdb, &br->hash[br_mac_hash(addr, vid)], hlist) { if (ether_addr_equal(fdb->addr.addr, addr) && fdb->vlan_id == vid) { @@ -315,14 +314,13 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, { struct __fdb_entry *fe = buf; int i, num = 0; - struct hlist_node *h; struct net_bridge_fdb_entry *f; memset(buf, 0, maxnum*sizeof(struct __fdb_entry)); rcu_read_lock(); for (i = 0; i < BR_HASH_SIZE; i++) { - hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { + hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { if (num >= maxnum) goto out; @@ -363,10 +361,9 @@ static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, const unsigned char *addr, __u16 vid) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry(fdb, h, head, hlist) { + hlist_for_each_entry(fdb, head, hlist) { if (ether_addr_equal(fdb->addr.addr, addr) && fdb->vlan_id == vid) return fdb; @@ -378,10 +375,9 @@ static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head, const unsigned char *addr, __u16 vid) { - struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry_rcu(fdb, h, head, hlist) { + hlist_for_each_entry_rcu(fdb, head, hlist) { if (ether_addr_equal(fdb->addr.addr, addr) && fdb->vlan_id == vid) return fdb; @@ -427,7 +423,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, return 0; br_warn(br, "adding interface %s with same address " "as a received packet\n", - source->dev->name); + source ? source->dev->name : br->dev->name); fdb_delete(br, fdb); } @@ -593,10 +589,9 @@ int br_fdb_dump(struct sk_buff *skb, goto out; for (i = 0; i < BR_HASH_SIZE; i++) { - struct hlist_node *h; struct net_bridge_fdb_entry *f; - hlist_for_each_entry_rcu(f, h, &br->hash[i], hlist) { + hlist_for_each_entry_rcu(f, &br->hash[i], hlist) { if (idx < cb->args[0]) goto skip; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index ef1b91431c6b..459dab22b3f6 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -67,7 +67,8 @@ void br_port_carrier_check(struct net_bridge_port *p) struct net_device *dev = p->dev; struct net_bridge *br = p->br; - if (netif_running(dev) && netif_oper_up(dev)) + if (!(p->flags & BR_ADMIN_COST) && + netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); if (!netif_running(br->dev)) diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 480330151898..828e2bcc1f52 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -97,7 +97,7 @@ int br_handle_frame_finish(struct sk_buff *skb) if (is_broadcast_ether_addr(dest)) skb2 = skb; else if (is_multicast_ether_addr(dest)) { - mdst = br_mdb_get(br, skb); + mdst = br_mdb_get(br, skb, vid); if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) { if ((mdst && mdst->mglist) || br_multicast_is_router(br)) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 38991e03646d..ee79f3f20383 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -18,7 +18,6 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, { struct net_bridge *br = netdev_priv(dev); struct net_bridge_port *p; - struct hlist_node *n; struct nlattr *nest; if (!br->multicast_router || hlist_empty(&br->router_list)) @@ -28,7 +27,7 @@ static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, if (nest == NULL) return -EMSGSIZE; - hlist_for_each_entry_rcu(p, n, &br->router_list, rlist) { + hlist_for_each_entry_rcu(p, &br->router_list, rlist) { if (p && nla_put_u32(skb, MDBA_ROUTER_PORT, p->dev->ifindex)) goto fail; } @@ -61,12 +60,11 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, return -EMSGSIZE; for (i = 0; i < mdb->max; i++) { - struct hlist_node *h; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p, **pp; struct net_bridge_port *port; - hlist_for_each_entry_rcu(mp, h, &mdb->mhash[i], hlist[mdb->ver]) { + hlist_for_each_entry_rcu(mp, &mdb->mhash[i], hlist[mdb->ver]) { if (idx < s_idx) goto skip; @@ -82,6 +80,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, port = p->port; if (port) { struct br_mdb_entry e; + memset(&e, 0, sizeof(e)); e.ifindex = port->dev->ifindex; e.state = p->state; if (p->addr.proto == htons(ETH_P_IP)) @@ -138,6 +137,7 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) break; bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); bpm->ifindex = dev->ifindex; if (br_mdb_fill_info(skb, cb, dev) < 0) goto out; @@ -173,6 +173,7 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, return -EMSGSIZE; bpm = nlmsg_data(nlh); + memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; nest = nla_nest_start(skb, MDBA_MDB); @@ -230,6 +231,7 @@ void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, { struct br_mdb_entry entry; + memset(&entry, 0, sizeof(entry)); entry.ifindex = port->dev->ifindex; entry.addr.proto = group->proto; entry.addr.u.ip4 = group->u.ip4; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 7d886b0a8b7b..923fbeaf7afd 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -86,9 +86,8 @@ static struct net_bridge_mdb_entry *__br_mdb_ip_get( struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash) { struct net_bridge_mdb_entry *mp; - struct hlist_node *p; - hlist_for_each_entry_rcu(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) { + hlist_for_each_entry_rcu(mp, &mdb->mhash[hash], hlist[mdb->ver]) { if (br_ip_equal(&mp->addr, dst)) return mp; } @@ -133,7 +132,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get( #endif struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, - struct sk_buff *skb) + struct sk_buff *skb, u16 vid) { struct net_bridge_mdb_htable *mdb = rcu_dereference(br->mdb); struct br_ip ip; @@ -145,6 +144,7 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, return NULL; ip.proto = skb->protocol; + ip.vid = vid; switch (skb->protocol) { case htons(ETH_P_IP): @@ -178,13 +178,12 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, int elasticity) { struct net_bridge_mdb_entry *mp; - struct hlist_node *p; int maxlen; int len; int i; for (i = 0; i < old->max; i++) - hlist_for_each_entry(mp, p, &old->mhash[i], hlist[old->ver]) + hlist_for_each_entry(mp, &old->mhash[i], hlist[old->ver]) hlist_add_head(&mp->hlist[new->ver], &new->mhash[br_ip_hash(new, &mp->addr)]); @@ -194,7 +193,7 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new, maxlen = 0; for (i = 0; i < new->max; i++) { len = 0; - hlist_for_each_entry(mp, p, &new->mhash[i], hlist[new->ver]) + hlist_for_each_entry(mp, &new->mhash[i], hlist[new->ver]) len++; if (len > maxlen) maxlen = len; @@ -510,14 +509,13 @@ static struct net_bridge_mdb_entry *br_multicast_get_group( { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; - struct hlist_node *p; unsigned int count = 0; unsigned int max; int elasticity; int err; mdb = rcu_dereference_protected(br->mdb, 1); - hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) { + hlist_for_each_entry(mp, &mdb->mhash[hash], hlist[mdb->ver]) { count++; if (unlikely(br_ip_equal(group, &mp->addr))) return mp; @@ -882,10 +880,10 @@ void br_multicast_disable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; - struct hlist_node *p, *n; + struct hlist_node *n; spin_lock(&br->multicast_lock); - hlist_for_each_entry_safe(pg, p, n, &port->mglist, mglist) + hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_del_pg(br, pg); if (!hlist_unhashed(&port->rlist)) @@ -1025,12 +1023,12 @@ static void br_multicast_add_router(struct net_bridge *br, struct net_bridge_port *port) { struct net_bridge_port *p; - struct hlist_node *n, *slot = NULL; + struct hlist_node *slot = NULL; - hlist_for_each_entry(p, n, &br->router_list, rlist) { + hlist_for_each_entry(p, &br->router_list, rlist) { if ((unsigned long) port >= (unsigned long) p) break; - slot = n; + slot = &p->rlist; } if (slot) @@ -1653,7 +1651,7 @@ void br_multicast_stop(struct net_bridge *br) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; - struct hlist_node *p, *n; + struct hlist_node *n; u32 ver; int i; @@ -1670,7 +1668,7 @@ void br_multicast_stop(struct net_bridge *br) ver = mdb->ver; for (i = 0; i < mdb->max; i++) { - hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i], + hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 27aa3ee517ce..299fc5f40a26 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -29,6 +29,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_MODE */ + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + 0; } @@ -329,6 +330,7 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); + br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 6d314c4e6bcb..d2c043a857b6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -156,6 +156,7 @@ struct net_bridge_port #define BR_BPDU_GUARD 0x00000002 #define BR_ROOT_BLOCK 0x00000004 #define BR_MULTICAST_FAST_LEAVE 0x00000008 +#define BR_ADMIN_COST 0x00000010 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING u32 multicast_startup_queries_sent; @@ -442,7 +443,7 @@ extern int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb); extern struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, - struct sk_buff *skb); + struct sk_buff *skb, u16 vid); extern void br_multicast_add_port(struct net_bridge_port *port); extern void br_multicast_del_port(struct net_bridge_port *port); extern void br_multicast_enable_port(struct net_bridge_port *port); @@ -504,7 +505,7 @@ static inline int br_multicast_rcv(struct net_bridge *br, } static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, - struct sk_buff *skb) + struct sk_buff *skb, u16 vid) { return NULL; } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 0bdb4ebd362b..d45e760141bb 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -288,6 +288,7 @@ int br_stp_set_path_cost(struct net_bridge_port *p, unsigned long path_cost) path_cost > BR_MAX_PATH_COST) return -ERANGE; + p->flags |= BR_ADMIN_COST; p->path_cost = path_cost; br_configuration_update(p->br); br_port_state_selection(p->br); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 1ae1d9cb278d..21760f008974 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -118,7 +118,7 @@ static struct caif_device_entry *caif_get(struct net_device *dev) return NULL; } -void caif_flow_cb(struct sk_buff *skb) +static void caif_flow_cb(struct sk_buff *skb) { struct caif_device_entry *caifd; void (*dtor)(struct sk_buff *skb) = NULL; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 095259f83902..ff2ff3ce6965 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -286,6 +286,8 @@ static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock, if (m->msg_flags&MSG_OOB) goto read_error; + m->msg_namelen = 0; + skb = skb_recv_datagram(sk, flags, 0 , &ret); if (!skb) goto read_error; diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 3ebc8cbc91ff..ef8ebaa993cf 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -81,8 +81,8 @@ static void cfusbl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, layr->up->ctrlcmd(layr->up, ctrl, layr->id); } -struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN], - u8 braddr[ETH_ALEN]) +static struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN], + u8 braddr[ETH_ALEN]) { struct cfusbl *this = kmalloc(sizeof(struct cfusbl), GFP_ATOMIC); diff --git a/net/can/af_can.c b/net/can/af_can.c index ddac1ee2ed20..c48e5220bbac 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -516,7 +516,6 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, { struct receiver *r = NULL; struct hlist_head *rl; - struct hlist_node *next; struct dev_rcv_lists *d; if (dev && dev->type != ARPHRD_CAN) @@ -540,7 +539,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, * been registered before. */ - hlist_for_each_entry_rcu(r, next, rl, list) { + hlist_for_each_entry_rcu(r, rl, list) { if (r->can_id == can_id && r->mask == mask && r->func == func && r->data == data) break; @@ -552,7 +551,7 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask, * will be NULL, while r will point to the last item of the list. */ - if (!next) { + if (!r) { printk(KERN_ERR "BUG: receive list entry not found for " "dev %s, id %03X, mask %03X\n", DNAME(dev), can_id, mask); @@ -590,7 +589,6 @@ static inline void deliver(struct sk_buff *skb, struct receiver *r) static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) { struct receiver *r; - struct hlist_node *n; int matches = 0; struct can_frame *cf = (struct can_frame *)skb->data; canid_t can_id = cf->can_id; @@ -600,7 +598,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) if (can_id & CAN_ERR_FLAG) { /* check for error message frame entries only */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_ERR], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_ERR], list) { if (can_id & r->mask) { deliver(skb, r); matches++; @@ -610,13 +608,13 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) } /* check for unfiltered entries */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_ALL], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_ALL], list) { deliver(skb, r); matches++; } /* check for can_id/mask entries */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_FIL], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_FIL], list) { if ((can_id & r->mask) == r->can_id) { deliver(skb, r); matches++; @@ -624,7 +622,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) } /* check for inverted can_id/mask entries */ - hlist_for_each_entry_rcu(r, n, &d->rx[RX_INV], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_INV], list) { if ((can_id & r->mask) != r->can_id) { deliver(skb, r); matches++; @@ -636,7 +634,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) return matches; if (can_id & CAN_EFF_FLAG) { - hlist_for_each_entry_rcu(r, n, &d->rx[RX_EFF], list) { + hlist_for_each_entry_rcu(r, &d->rx[RX_EFF], list) { if (r->can_id == can_id) { deliver(skb, r); matches++; @@ -644,7 +642,7 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb) } } else { can_id &= CAN_SFF_MASK; - hlist_for_each_entry_rcu(r, n, &d->rx_sff[can_id], list) { + hlist_for_each_entry_rcu(r, &d->rx_sff[can_id], list) { deliver(skb, r); matches++; } diff --git a/net/can/gw.c b/net/can/gw.c index c185fcd5e828..117814a7e73c 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -457,16 +457,16 @@ static int cgw_notifier(struct notifier_block *nb, if (msg == NETDEV_UNREGISTER) { struct cgw_job *gwj = NULL; - struct hlist_node *n, *nx; + struct hlist_node *nx; ASSERT_RTNL(); - hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } } } @@ -575,12 +575,11 @@ cancel: static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) { struct cgw_job *gwj = NULL; - struct hlist_node *n; int idx = 0; int s_idx = cb->args[0]; rcu_read_lock(); - hlist_for_each_entry_rcu(gwj, n, &cgw_list, list) { + hlist_for_each_entry_rcu(gwj, &cgw_list, list) { if (idx < s_idx) goto cont; @@ -858,21 +857,21 @@ out: static void cgw_remove_all_jobs(void) { struct cgw_job *gwj = NULL; - struct hlist_node *n, *nx; + struct hlist_node *nx; ASSERT_RTNL(); - hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); } } static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct cgw_job *gwj = NULL; - struct hlist_node *n, *nx; + struct hlist_node *nx; struct rtcanmsg *r; struct cf_mod mod; struct can_can_gw ccgw; @@ -907,7 +906,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ASSERT_RTNL(); /* remove only the first matching entry */ - hlist_for_each_entry_safe(gwj, n, nx, &cgw_list, list) { + hlist_for_each_entry_safe(gwj, nx, &cgw_list, list) { if (gwj->flags != r->flags) continue; @@ -921,7 +920,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) hlist_del(&gwj->list); cgw_unregister_filter(gwj); - kfree(gwj); + kmem_cache_free(cgw_cache, gwj); err = 0; break; } diff --git a/net/can/proc.c b/net/can/proc.c index 497335892146..1ab8c888f102 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -195,9 +195,8 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, struct net_device *dev) { struct receiver *r; - struct hlist_node *n; - hlist_for_each_entry_rcu(r, n, rx_list, list) { + hlist_for_each_entry_rcu(r, rx_list, list) { char *fmt = (r->can_id & CAN_EFF_FLAG)? " %-5s %08x %08x %pK %pK %8ld %s\n" : " %-5s %03x %08x %pK %pK %8ld %s\n"; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index ee71ea26777a..e65e6e4be38b 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -15,6 +15,8 @@ #include <linux/slab.h> #include <linux/statfs.h> #include <linux/string.h> +#include <linux/nsproxy.h> +#include <net/net_namespace.h> #include <linux/ceph/ceph_features.h> @@ -26,6 +28,22 @@ #include "crypto.h" +/* + * Module compatibility interface. For now it doesn't do anything, + * but its existence signals a certain level of functionality. + * + * The data buffer is used to pass information both to and from + * libceph. The return value indicates whether libceph determines + * it is compatible with the caller (from another kernel module), + * given the provided data. + * + * The data pointer can be null. + */ +bool libceph_compatible(void *data) +{ + return true; +} +EXPORT_SYMBOL(libceph_compatible); /* * find filename portion of a path (/foo/bar/baz -> baz) @@ -292,6 +310,9 @@ ceph_parse_options(char *options, const char *dev_name, int err = -ENOMEM; substring_t argstr[MAX_OPT_ARGS]; + if (current->nsproxy->net_ns != &init_net) + return ERR_PTR(-EINVAL); + opt = kzalloc(sizeof(*opt), GFP_KERNEL); if (!opt) return ERR_PTR(-ENOMEM); @@ -585,10 +606,8 @@ static int __init init_ceph_lib(void) if (ret < 0) goto out_crypto; - pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n", - CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL, - CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT, - CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT); + pr_info("loaded (mon/osd proto %d/%d)\n", + CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL); return 0; diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c index 3fbda04de29c..1348df96fe15 100644 --- a/net/ceph/ceph_strings.c +++ b/net/ceph/ceph_strings.c @@ -21,9 +21,15 @@ const char *ceph_osd_op_name(int op) switch (op) { case CEPH_OSD_OP_READ: return "read"; case CEPH_OSD_OP_STAT: return "stat"; + case CEPH_OSD_OP_MAPEXT: return "mapext"; + case CEPH_OSD_OP_SPARSE_READ: return "sparse-read"; + case CEPH_OSD_OP_NOTIFY: return "notify"; + case CEPH_OSD_OP_NOTIFY_ACK: return "notify-ack"; + case CEPH_OSD_OP_ASSERT_VER: return "assert-version"; case CEPH_OSD_OP_MASKTRUNC: return "masktrunc"; + case CEPH_OSD_OP_CREATE: return "create"; case CEPH_OSD_OP_WRITE: return "write"; case CEPH_OSD_OP_DELETE: return "delete"; case CEPH_OSD_OP_TRUNCATE: return "truncate"; @@ -39,6 +45,11 @@ const char *ceph_osd_op_name(int op) case CEPH_OSD_OP_TMAPUP: return "tmapup"; case CEPH_OSD_OP_TMAPGET: return "tmapget"; case CEPH_OSD_OP_TMAPPUT: return "tmapput"; + case CEPH_OSD_OP_WATCH: return "watch"; + + case CEPH_OSD_OP_CLONERANGE: return "clonerange"; + case CEPH_OSD_OP_ASSERT_SRC_VERSION: return "assert-src-version"; + case CEPH_OSD_OP_SRC_CMPXATTR: return "src-cmpxattr"; case CEPH_OSD_OP_GETXATTR: return "getxattr"; case CEPH_OSD_OP_GETXATTRS: return "getxattrs"; @@ -53,6 +64,10 @@ const char *ceph_osd_op_name(int op) case CEPH_OSD_OP_BALANCEREADS: return "balance-reads"; case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads"; case CEPH_OSD_OP_SCRUB: return "scrub"; + case CEPH_OSD_OP_SCRUB_RESERVE: return "scrub-reserve"; + case CEPH_OSD_OP_SCRUB_UNRESERVE: return "scrub-unreserve"; + case CEPH_OSD_OP_SCRUB_STOP: return "scrub-stop"; + case CEPH_OSD_OP_SCRUB_MAP: return "scrub-map"; case CEPH_OSD_OP_WRLOCK: return "wrlock"; case CEPH_OSD_OP_WRUNLOCK: return "wrunlock"; @@ -64,10 +79,34 @@ const char *ceph_osd_op_name(int op) case CEPH_OSD_OP_CALL: return "call"; case CEPH_OSD_OP_PGLS: return "pgls"; + case CEPH_OSD_OP_PGLS_FILTER: return "pgls-filter"; + case CEPH_OSD_OP_OMAPGETKEYS: return "omap-get-keys"; + case CEPH_OSD_OP_OMAPGETVALS: return "omap-get-vals"; + case CEPH_OSD_OP_OMAPGETHEADER: return "omap-get-header"; + case CEPH_OSD_OP_OMAPGETVALSBYKEYS: return "omap-get-vals-by-keys"; + case CEPH_OSD_OP_OMAPSETVALS: return "omap-set-vals"; + case CEPH_OSD_OP_OMAPSETHEADER: return "omap-set-header"; + case CEPH_OSD_OP_OMAPCLEAR: return "omap-clear"; + case CEPH_OSD_OP_OMAPRMKEYS: return "omap-rm-keys"; } return "???"; } +const char *ceph_osd_state_name(int s) +{ + switch (s) { + case CEPH_OSD_EXISTS: + return "exists"; + case CEPH_OSD_UP: + return "up"; + case CEPH_OSD_AUTOOUT: + return "autoout"; + case CEPH_OSD_NEW: + return "new"; + default: + return "???"; + } +} const char *ceph_pool_op_name(int op) { diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 35fce755ce10..cbd06a91941c 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -287,6 +287,7 @@ static int is_out(const struct crush_map *map, const __u32 *weight, int item, in * @outpos: our position in that vector * @firstn: true if choosing "first n" items, false if choosing "indep" * @recurse_to_leaf: true if we want one device under each item of given type + * @descend_once: true if we should only try one descent before giving up * @out2: second output vector for leaf items (if @recurse_to_leaf) */ static int crush_choose(const struct crush_map *map, @@ -295,7 +296,7 @@ static int crush_choose(const struct crush_map *map, int x, int numrep, int type, int *out, int outpos, int firstn, int recurse_to_leaf, - int *out2) + int descend_once, int *out2) { int rep; unsigned int ftotal, flocal; @@ -391,7 +392,7 @@ static int crush_choose(const struct crush_map *map, } reject = 0; - if (recurse_to_leaf) { + if (!collide && recurse_to_leaf) { if (item < 0) { if (crush_choose(map, map->buckets[-1-item], @@ -399,6 +400,7 @@ static int crush_choose(const struct crush_map *map, x, outpos+1, 0, out2, outpos, firstn, 0, + map->chooseleaf_descend_once, NULL) <= outpos) /* didn't get leaf */ reject = 1; @@ -422,7 +424,10 @@ reject: ftotal++; flocal++; - if (collide && flocal <= map->choose_local_tries) + if (reject && descend_once) + /* let outer call try again */ + skip_rep = 1; + else if (collide && flocal <= map->choose_local_tries) /* retry locally a few times */ retry_bucket = 1; else if (map->choose_local_fallback_tries > 0 && @@ -485,6 +490,7 @@ int crush_do_rule(const struct crush_map *map, int i, j; int numrep; int firstn; + const int descend_once = 0; if ((__u32)ruleno >= map->max_rules) { dprintk(" bad ruleno %d\n", ruleno); @@ -544,7 +550,8 @@ int crush_do_rule(const struct crush_map *map, curstep->arg2, o+osize, j, firstn, - recurse_to_leaf, c+osize); + recurse_to_leaf, + descend_once, c+osize); } if (recurse_to_leaf) diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index af14cb425164..6e7a236525b6 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -423,7 +423,8 @@ int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len, } } -int ceph_key_instantiate(struct key *key, struct key_preparsed_payload *prep) +static int ceph_key_instantiate(struct key *key, + struct key_preparsed_payload *prep) { struct ceph_crypto_key *ckey; size_t datalen = prep->datalen; @@ -458,12 +459,12 @@ err: return ret; } -int ceph_key_match(const struct key *key, const void *description) +static int ceph_key_match(const struct key *key, const void *description) { return strcmp(key->description, description) == 0; } -void ceph_key_destroy(struct key *key) { +static void ceph_key_destroy(struct key *key) { struct ceph_crypto_key *ckey = key->payload.data; ceph_crypto_key_destroy(ckey); diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c index 38b5dc1823d4..00d051f4894e 100644 --- a/net/ceph/debugfs.c +++ b/net/ceph/debugfs.c @@ -66,9 +66,9 @@ static int osdmap_show(struct seq_file *s, void *p) for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) { struct ceph_pg_pool_info *pool = rb_entry(n, struct ceph_pg_pool_info, node); - seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n", - pool->id, pool->v.pg_num, pool->pg_num_mask, - pool->v.lpg_num, pool->lpg_num_mask); + seq_printf(s, "pg_pool %llu pg_num %d / %d\n", + (unsigned long long)pool->id, pool->pg_num, + pool->pg_num_mask); } for (i = 0; i < client->osdc.osdmap->max_osd; i++) { struct ceph_entity_addr *addr = @@ -123,26 +123,16 @@ static int osdc_show(struct seq_file *s, void *pp) mutex_lock(&osdc->request_mutex); for (p = rb_first(&osdc->requests); p; p = rb_next(p)) { struct ceph_osd_request *req; - struct ceph_osd_request_head *head; - struct ceph_osd_op *op; - int num_ops; - int opcode, olen; + int opcode; int i; req = rb_entry(p, struct ceph_osd_request, r_node); - seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid, + seq_printf(s, "%lld\tosd%d\t%lld.%x\t", req->r_tid, req->r_osd ? req->r_osd->o_osd : -1, - le32_to_cpu(req->r_pgid.pool), - le16_to_cpu(req->r_pgid.ps)); + req->r_pgid.pool, req->r_pgid.seed); - head = req->r_request->front.iov_base; - op = (void *)(head + 1); - - num_ops = le16_to_cpu(head->num_ops); - olen = le32_to_cpu(head->object_len); - seq_printf(s, "%.*s", olen, - (const char *)(head->ops + num_ops)); + seq_printf(s, "%.*s", req->r_oid_len, req->r_oid); if (req->r_reassert_version.epoch) seq_printf(s, "\t%u'%llu", @@ -151,10 +141,9 @@ static int osdc_show(struct seq_file *s, void *pp) else seq_printf(s, "\t"); - for (i = 0; i < num_ops; i++) { - opcode = le16_to_cpu(op->op); + for (i = 0; i < req->r_num_ops; i++) { + opcode = le16_to_cpu(req->r_request_ops[i].op); seq_printf(s, "\t%s", ceph_osd_op_name(opcode)); - op++; } seq_printf(s, "\n"); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 5ccf87ed8d68..2c0669fb54e3 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -9,8 +9,9 @@ #include <linux/slab.h> #include <linux/socket.h> #include <linux/string.h> +#ifdef CONFIG_BLOCK #include <linux/bio.h> -#include <linux/blkdev.h> +#endif /* CONFIG_BLOCK */ #include <linux/dns_resolver.h> #include <net/tcp.h> @@ -97,6 +98,57 @@ #define CON_FLAG_SOCK_CLOSED 3 /* socket state changed to closed */ #define CON_FLAG_BACKOFF 4 /* need to retry queuing delayed work */ +static bool con_flag_valid(unsigned long con_flag) +{ + switch (con_flag) { + case CON_FLAG_LOSSYTX: + case CON_FLAG_KEEPALIVE_PENDING: + case CON_FLAG_WRITE_PENDING: + case CON_FLAG_SOCK_CLOSED: + case CON_FLAG_BACKOFF: + return true; + default: + return false; + } +} + +static void con_flag_clear(struct ceph_connection *con, unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + clear_bit(con_flag, &con->flags); +} + +static void con_flag_set(struct ceph_connection *con, unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + set_bit(con_flag, &con->flags); +} + +static bool con_flag_test(struct ceph_connection *con, unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + return test_bit(con_flag, &con->flags); +} + +static bool con_flag_test_and_clear(struct ceph_connection *con, + unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + return test_and_clear_bit(con_flag, &con->flags); +} + +static bool con_flag_test_and_set(struct ceph_connection *con, + unsigned long con_flag) +{ + BUG_ON(!con_flag_valid(con_flag)); + + return test_and_set_bit(con_flag, &con->flags); +} + /* static tag bytes (protocol control messages) */ static char tag_msg = CEPH_MSGR_TAG_MSG; static char tag_ack = CEPH_MSGR_TAG_ACK; @@ -114,7 +166,7 @@ static struct lock_class_key socket_class; static void queue_con(struct ceph_connection *con); static void con_work(struct work_struct *); -static void ceph_fault(struct ceph_connection *con); +static void con_fault(struct ceph_connection *con); /* * Nicely render a sockaddr as a string. An array of formatted @@ -171,7 +223,7 @@ static void encode_my_addr(struct ceph_messenger *msgr) */ static struct workqueue_struct *ceph_msgr_wq; -void _ceph_msgr_exit(void) +static void _ceph_msgr_exit(void) { if (ceph_msgr_wq) { destroy_workqueue(ceph_msgr_wq); @@ -308,7 +360,7 @@ static void ceph_sock_write_space(struct sock *sk) * buffer. See net/ipv4/tcp_input.c:tcp_check_space() * and net/core/stream.c:sk_stream_write_space(). */ - if (test_bit(CON_FLAG_WRITE_PENDING, &con->flags)) { + if (con_flag_test(con, CON_FLAG_WRITE_PENDING)) { if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { dout("%s %p queueing write work\n", __func__, con); clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); @@ -333,7 +385,7 @@ static void ceph_sock_state_change(struct sock *sk) case TCP_CLOSE_WAIT: dout("%s TCP_CLOSE_WAIT\n", __func__); con_sock_state_closing(con); - set_bit(CON_FLAG_SOCK_CLOSED, &con->flags); + con_flag_set(con, CON_FLAG_SOCK_CLOSED); queue_con(con); break; case TCP_ESTABLISHED: @@ -474,7 +526,7 @@ static int con_close_socket(struct ceph_connection *con) * received a socket close event before we had the chance to * shut the socket down. */ - clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags); + con_flag_clear(con, CON_FLAG_SOCK_CLOSED); con_sock_state_closed(con); return rc; @@ -538,11 +590,10 @@ void ceph_con_close(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr)); con->state = CON_STATE_CLOSED; - clear_bit(CON_FLAG_LOSSYTX, &con->flags); /* so we retry next connect */ - clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags); - clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); - clear_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags); - clear_bit(CON_FLAG_BACKOFF, &con->flags); + con_flag_clear(con, CON_FLAG_LOSSYTX); /* so we retry next connect */ + con_flag_clear(con, CON_FLAG_KEEPALIVE_PENDING); + con_flag_clear(con, CON_FLAG_WRITE_PENDING); + con_flag_clear(con, CON_FLAG_BACKOFF); reset_connection(con); con->peer_global_seq = 0; @@ -798,7 +849,7 @@ static void prepare_write_message(struct ceph_connection *con) /* no, queue up footer too and be done */ prepare_write_message_footer(con); - set_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con_flag_set(con, CON_FLAG_WRITE_PENDING); } /* @@ -819,7 +870,7 @@ static void prepare_write_ack(struct ceph_connection *con) &con->out_temp_ack); con->out_more = 1; /* more will follow.. eventually.. */ - set_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con_flag_set(con, CON_FLAG_WRITE_PENDING); } /* @@ -830,7 +881,7 @@ static void prepare_write_keepalive(struct ceph_connection *con) dout("prepare_write_keepalive %p\n", con); con_out_kvec_reset(con); con_out_kvec_add(con, sizeof (tag_keepalive), &tag_keepalive); - set_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con_flag_set(con, CON_FLAG_WRITE_PENDING); } /* @@ -873,7 +924,7 @@ static void prepare_write_banner(struct ceph_connection *con) &con->msgr->my_enc_addr); con->out_more = 0; - set_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con_flag_set(con, CON_FLAG_WRITE_PENDING); } static int prepare_write_connect(struct ceph_connection *con) @@ -923,7 +974,7 @@ static int prepare_write_connect(struct ceph_connection *con) auth->authorizer_buf); con->out_more = 0; - set_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con_flag_set(con, CON_FLAG_WRITE_PENDING); return 0; } @@ -1643,7 +1694,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->in_reply.connect_seq)); if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY) - set_bit(CON_FLAG_LOSSYTX, &con->flags); + con_flag_set(con, CON_FLAG_LOSSYTX); con->delay = 0; /* reset backoff memory */ @@ -2080,15 +2131,14 @@ do_next: prepare_write_ack(con); goto more; } - if (test_and_clear_bit(CON_FLAG_KEEPALIVE_PENDING, - &con->flags)) { + if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) { prepare_write_keepalive(con); goto more; } } /* Nothing to do! */ - clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con_flag_clear(con, CON_FLAG_WRITE_PENDING); dout("try_write nothing else to write.\n"); ret = 0; out: @@ -2268,7 +2318,7 @@ static void queue_con(struct ceph_connection *con) static bool con_sock_closed(struct ceph_connection *con) { - if (!test_and_clear_bit(CON_FLAG_SOCK_CLOSED, &con->flags)) + if (!con_flag_test_and_clear(con, CON_FLAG_SOCK_CLOSED)) return false; #define CASE(x) \ @@ -2295,6 +2345,41 @@ static bool con_sock_closed(struct ceph_connection *con) return true; } +static bool con_backoff(struct ceph_connection *con) +{ + int ret; + + if (!con_flag_test_and_clear(con, CON_FLAG_BACKOFF)) + return false; + + ret = queue_con_delay(con, round_jiffies_relative(con->delay)); + if (ret) { + dout("%s: con %p FAILED to back off %lu\n", __func__, + con, con->delay); + BUG_ON(ret == -ENOENT); + con_flag_set(con, CON_FLAG_BACKOFF); + } + + return true; +} + +/* Finish fault handling; con->mutex must *not* be held here */ + +static void con_fault_finish(struct ceph_connection *con) +{ + /* + * in case we faulted due to authentication, invalidate our + * current tickets so that we can get new ones. + */ + if (con->auth_retry && con->ops->invalidate_authorizer) { + dout("calling invalidate_authorizer()\n"); + con->ops->invalidate_authorizer(con); + } + + if (con->ops->fault) + con->ops->fault(con); +} + /* * Do some work on a connection. Drop a connection ref when we're done. */ @@ -2302,73 +2387,68 @@ static void con_work(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); - int ret; + bool fault; mutex_lock(&con->mutex); -restart: - if (con_sock_closed(con)) - goto fault; + while (true) { + int ret; - if (test_and_clear_bit(CON_FLAG_BACKOFF, &con->flags)) { - dout("con_work %p backing off\n", con); - ret = queue_con_delay(con, round_jiffies_relative(con->delay)); - if (ret) { - dout("con_work %p FAILED to back off %lu\n", con, - con->delay); - BUG_ON(ret == -ENOENT); - set_bit(CON_FLAG_BACKOFF, &con->flags); + if ((fault = con_sock_closed(con))) { + dout("%s: con %p SOCK_CLOSED\n", __func__, con); + break; + } + if (con_backoff(con)) { + dout("%s: con %p BACKOFF\n", __func__, con); + break; + } + if (con->state == CON_STATE_STANDBY) { + dout("%s: con %p STANDBY\n", __func__, con); + break; + } + if (con->state == CON_STATE_CLOSED) { + dout("%s: con %p CLOSED\n", __func__, con); + BUG_ON(con->sock); + break; + } + if (con->state == CON_STATE_PREOPEN) { + dout("%s: con %p PREOPEN\n", __func__, con); + BUG_ON(con->sock); } - goto done; - } - if (con->state == CON_STATE_STANDBY) { - dout("con_work %p STANDBY\n", con); - goto done; - } - if (con->state == CON_STATE_CLOSED) { - dout("con_work %p CLOSED\n", con); - BUG_ON(con->sock); - goto done; - } - if (con->state == CON_STATE_PREOPEN) { - dout("con_work OPENING\n"); - BUG_ON(con->sock); - } + ret = try_read(con); + if (ret < 0) { + if (ret == -EAGAIN) + continue; + con->error_msg = "socket error on read"; + fault = true; + break; + } - ret = try_read(con); - if (ret == -EAGAIN) - goto restart; - if (ret < 0) { - con->error_msg = "socket error on read"; - goto fault; - } + ret = try_write(con); + if (ret < 0) { + if (ret == -EAGAIN) + continue; + con->error_msg = "socket error on write"; + fault = true; + } - ret = try_write(con); - if (ret == -EAGAIN) - goto restart; - if (ret < 0) { - con->error_msg = "socket error on write"; - goto fault; + break; /* If we make it to here, we're done */ } - -done: + if (fault) + con_fault(con); mutex_unlock(&con->mutex); -done_unlocked: - con->ops->put(con); - return; -fault: - ceph_fault(con); /* error/fault path */ - goto done_unlocked; -} + if (fault) + con_fault_finish(con); + con->ops->put(con); +} /* * Generic error/fault handler. A retry mechanism is used with * exponential backoff */ -static void ceph_fault(struct ceph_connection *con) - __releases(con->mutex) +static void con_fault(struct ceph_connection *con) { pr_warning("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg); @@ -2381,10 +2461,10 @@ static void ceph_fault(struct ceph_connection *con) con_close_socket(con); - if (test_bit(CON_FLAG_LOSSYTX, &con->flags)) { + if (con_flag_test(con, CON_FLAG_LOSSYTX)) { dout("fault on LOSSYTX channel, marking CLOSED\n"); con->state = CON_STATE_CLOSED; - goto out_unlock; + return; } if (con->in_msg) { @@ -2401,9 +2481,9 @@ static void ceph_fault(struct ceph_connection *con) /* If there are no messages queued or keepalive pending, place * the connection in a STANDBY state */ if (list_empty(&con->out_queue) && - !test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)) { + !con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING)) { dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); - clear_bit(CON_FLAG_WRITE_PENDING, &con->flags); + con_flag_clear(con, CON_FLAG_WRITE_PENDING); con->state = CON_STATE_STANDBY; } else { /* retry after a delay. */ @@ -2412,23 +2492,9 @@ static void ceph_fault(struct ceph_connection *con) con->delay = BASE_DELAY_INTERVAL; else if (con->delay < MAX_DELAY_INTERVAL) con->delay *= 2; - set_bit(CON_FLAG_BACKOFF, &con->flags); + con_flag_set(con, CON_FLAG_BACKOFF); queue_con(con); } - -out_unlock: - mutex_unlock(&con->mutex); - /* - * in case we faulted due to authentication, invalidate our - * current tickets so that we can get new ones. - */ - if (con->auth_retry && con->ops->invalidate_authorizer) { - dout("calling invalidate_authorizer()\n"); - con->ops->invalidate_authorizer(con); - } - - if (con->ops->fault) - con->ops->fault(con); } @@ -2469,8 +2535,8 @@ static void clear_standby(struct ceph_connection *con) dout("clear_standby %p and ++connect_seq\n", con); con->state = CON_STATE_PREOPEN; con->connect_seq++; - WARN_ON(test_bit(CON_FLAG_WRITE_PENDING, &con->flags)); - WARN_ON(test_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags)); + WARN_ON(con_flag_test(con, CON_FLAG_WRITE_PENDING)); + WARN_ON(con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING)); } } @@ -2511,7 +2577,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) /* if there wasn't anything waiting to send before, queue * new work */ - if (test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0) + if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_send); @@ -2600,8 +2666,8 @@ void ceph_con_keepalive(struct ceph_connection *con) mutex_lock(&con->mutex); clear_standby(con); mutex_unlock(&con->mutex); - if (test_and_set_bit(CON_FLAG_KEEPALIVE_PENDING, &con->flags) == 0 && - test_and_set_bit(CON_FLAG_WRITE_PENDING, &con->flags) == 0) + if (con_flag_test_and_set(con, CON_FLAG_KEEPALIVE_PENDING) == 0 && + con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_keepalive); @@ -2651,9 +2717,11 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, m->page_alignment = 0; m->pages = NULL; m->pagelist = NULL; +#ifdef CONFIG_BLOCK m->bio = NULL; m->bio_iter = NULL; m->bio_seg = 0; +#endif /* CONFIG_BLOCK */ m->trail = NULL; /* front */ diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 812eb3b46c1f..aef5b1062bee 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -697,7 +697,7 @@ int ceph_monc_delete_snapid(struct ceph_mon_client *monc, u32 pool, u64 snapid) { return do_poolop(monc, POOL_OP_CREATE_UNMANAGED_SNAP, - pool, snapid, 0, 0); + pool, snapid, NULL, 0); } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index eb9a44478764..d730dd4d8eb2 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -23,7 +23,7 @@ static const struct ceph_connection_operations osd_con_ops; -static void send_queued(struct ceph_osd_client *osdc); +static void __send_queued(struct ceph_osd_client *osdc); static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd); static void __register_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); @@ -32,64 +32,12 @@ static void __unregister_linger_request(struct ceph_osd_client *osdc, static void __send_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); -static int op_needs_trail(int op) -{ - switch (op) { - case CEPH_OSD_OP_GETXATTR: - case CEPH_OSD_OP_SETXATTR: - case CEPH_OSD_OP_CMPXATTR: - case CEPH_OSD_OP_CALL: - case CEPH_OSD_OP_NOTIFY: - return 1; - default: - return 0; - } -} - static int op_has_extent(int op) { return (op == CEPH_OSD_OP_READ || op == CEPH_OSD_OP_WRITE); } -int ceph_calc_raw_layout(struct ceph_osd_client *osdc, - struct ceph_file_layout *layout, - u64 snapid, - u64 off, u64 *plen, u64 *bno, - struct ceph_osd_request *req, - struct ceph_osd_req_op *op) -{ - struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; - u64 orig_len = *plen; - u64 objoff, objlen; /* extent in object */ - int r; - - reqhead->snapid = cpu_to_le64(snapid); - - /* object extent? */ - r = ceph_calc_file_object_mapping(layout, off, plen, bno, - &objoff, &objlen); - if (r < 0) - return r; - if (*plen < orig_len) - dout(" skipping last %llu, final file extent %llu~%llu\n", - orig_len - *plen, off, *plen); - - if (op_has_extent(op->op)) { - op->extent.offset = objoff; - op->extent.length = objlen; - } - req->r_num_pages = calc_pages_for(off, *plen); - req->r_page_alignment = off & ~PAGE_MASK; - if (op->op == CEPH_OSD_OP_WRITE) - op->payload_len = *plen; - - dout("calc_layout bno=%llx %llu~%llu (%d pages)\n", - *bno, objoff, objlen, req->r_num_pages); - return 0; -} -EXPORT_SYMBOL(ceph_calc_raw_layout); - /* * Implement client access to distributed object storage cluster. * @@ -115,20 +63,48 @@ EXPORT_SYMBOL(ceph_calc_raw_layout); * * fill osd op in request message. */ -static int calc_layout(struct ceph_osd_client *osdc, - struct ceph_vino vino, +static int calc_layout(struct ceph_vino vino, struct ceph_file_layout *layout, u64 off, u64 *plen, struct ceph_osd_request *req, struct ceph_osd_req_op *op) { - u64 bno; + u64 orig_len = *plen; + u64 bno = 0; + u64 objoff = 0; + u64 objlen = 0; int r; - r = ceph_calc_raw_layout(osdc, layout, vino.snap, off, - plen, &bno, req, op); + /* object extent? */ + r = ceph_calc_file_object_mapping(layout, off, orig_len, &bno, + &objoff, &objlen); if (r < 0) return r; + if (objlen < orig_len) { + *plen = objlen; + dout(" skipping last %llu, final file extent %llu~%llu\n", + orig_len - *plen, off, *plen); + } + + if (op_has_extent(op->op)) { + u32 osize = le32_to_cpu(layout->fl_object_size); + op->extent.offset = objoff; + op->extent.length = objlen; + if (op->extent.truncate_size <= off - objoff) { + op->extent.truncate_size = 0; + } else { + op->extent.truncate_size -= off - objoff; + if (op->extent.truncate_size > osize) + op->extent.truncate_size = osize; + } + } + req->r_num_pages = calc_pages_for(off, *plen); + req->r_page_alignment = off & ~PAGE_MASK; + if (op->op == CEPH_OSD_OP_WRITE) + op->payload_len = *plen; + + dout("calc_layout bno=%llx %llu~%llu (%d pages)\n", + bno, objoff, objlen, req->r_num_pages); snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", vino.ino, bno); req->r_oid_len = strlen(req->r_oid); @@ -148,25 +124,19 @@ void ceph_osdc_release_request(struct kref *kref) if (req->r_request) ceph_msg_put(req->r_request); if (req->r_con_filling_msg) { - dout("%s revoking pages %p from con %p\n", __func__, - req->r_pages, req->r_con_filling_msg); + dout("%s revoking msg %p from con %p\n", __func__, + req->r_reply, req->r_con_filling_msg); ceph_msg_revoke_incoming(req->r_reply); req->r_con_filling_msg->ops->put(req->r_con_filling_msg); + req->r_con_filling_msg = NULL; } if (req->r_reply) ceph_msg_put(req->r_reply); if (req->r_own_pages) ceph_release_page_vector(req->r_pages, req->r_num_pages); -#ifdef CONFIG_BLOCK - if (req->r_bio) - bio_put(req->r_bio); -#endif ceph_put_snap_context(req->r_snapc); - if (req->r_trail) { - ceph_pagelist_release(req->r_trail); - kfree(req->r_trail); - } + ceph_pagelist_release(&req->r_trail); if (req->r_mempool) mempool_free(req, req->r_osdc->req_mempool); else @@ -174,37 +144,25 @@ void ceph_osdc_release_request(struct kref *kref) } EXPORT_SYMBOL(ceph_osdc_release_request); -static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail) -{ - int i = 0; - - if (needs_trail) - *needs_trail = 0; - while (ops[i].op) { - if (needs_trail && op_needs_trail(ops[i].op)) - *needs_trail = 1; - i++; - } - - return i; -} - struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, - int flags, struct ceph_snap_context *snapc, - struct ceph_osd_req_op *ops, + unsigned int num_ops, bool use_mempool, - gfp_t gfp_flags, - struct page **pages, - struct bio *bio) + gfp_t gfp_flags) { struct ceph_osd_request *req; struct ceph_msg *msg; - int needs_trail; - int num_op = get_num_ops(ops, &needs_trail); - size_t msg_size = sizeof(struct ceph_osd_request_head); - - msg_size += num_op*sizeof(struct ceph_osd_op); + size_t msg_size; + + msg_size = 4 + 4 + 8 + 8 + 4+8; + msg_size += 2 + 4 + 8 + 4 + 4; /* oloc */ + msg_size += 1 + 8 + 4 + 4; /* pg_t */ + msg_size += 4 + MAX_OBJ_NAME_SIZE; + msg_size += 2 + num_ops*sizeof(struct ceph_osd_op); + msg_size += 8; /* snapid */ + msg_size += 8; /* snap_seq */ + msg_size += 8 * (snapc ? snapc->num_snaps : 0); /* snaps */ + msg_size += 4; if (use_mempool) { req = mempool_alloc(osdc->req_mempool, gfp_flags); @@ -228,10 +186,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, INIT_LIST_HEAD(&req->r_req_lru_item); INIT_LIST_HEAD(&req->r_osd_item); - req->r_flags = flags; - - WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0); - /* create reply message */ if (use_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0); @@ -244,20 +198,9 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, } req->r_reply = msg; - /* allocate space for the trailing data */ - if (needs_trail) { - req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags); - if (!req->r_trail) { - ceph_osdc_put_request(req); - return NULL; - } - ceph_pagelist_init(req->r_trail); - } + ceph_pagelist_init(&req->r_trail); /* create request message; allow space for oid */ - msg_size += MAX_OBJ_NAME_SIZE; - if (snapc) - msg_size += sizeof(u64) * snapc->num_snaps; if (use_mempool) msg = ceph_msgpool_get(&osdc->msgpool_op, 0); else @@ -270,13 +213,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, memset(msg->front.iov_base, 0, msg->front.iov_len); req->r_request = msg; - req->r_pages = pages; -#ifdef CONFIG_BLOCK - if (bio) { - req->r_bio = bio; - bio_get(req->r_bio); - } -#endif return req; } @@ -289,6 +225,8 @@ static void osd_req_encode_op(struct ceph_osd_request *req, dst->op = cpu_to_le16(src->op); switch (src->op) { + case CEPH_OSD_OP_STAT: + break; case CEPH_OSD_OP_READ: case CEPH_OSD_OP_WRITE: dst->extent.offset = @@ -300,52 +238,20 @@ static void osd_req_encode_op(struct ceph_osd_request *req, dst->extent.truncate_seq = cpu_to_le32(src->extent.truncate_seq); break; - - case CEPH_OSD_OP_GETXATTR: - case CEPH_OSD_OP_SETXATTR: - case CEPH_OSD_OP_CMPXATTR: - BUG_ON(!req->r_trail); - - dst->xattr.name_len = cpu_to_le32(src->xattr.name_len); - dst->xattr.value_len = cpu_to_le32(src->xattr.value_len); - dst->xattr.cmp_op = src->xattr.cmp_op; - dst->xattr.cmp_mode = src->xattr.cmp_mode; - ceph_pagelist_append(req->r_trail, src->xattr.name, - src->xattr.name_len); - ceph_pagelist_append(req->r_trail, src->xattr.val, - src->xattr.value_len); - break; case CEPH_OSD_OP_CALL: - BUG_ON(!req->r_trail); - dst->cls.class_len = src->cls.class_len; dst->cls.method_len = src->cls.method_len; dst->cls.indata_len = cpu_to_le32(src->cls.indata_len); - ceph_pagelist_append(req->r_trail, src->cls.class_name, + ceph_pagelist_append(&req->r_trail, src->cls.class_name, src->cls.class_len); - ceph_pagelist_append(req->r_trail, src->cls.method_name, + ceph_pagelist_append(&req->r_trail, src->cls.method_name, src->cls.method_len); - ceph_pagelist_append(req->r_trail, src->cls.indata, + ceph_pagelist_append(&req->r_trail, src->cls.indata, src->cls.indata_len); break; - case CEPH_OSD_OP_ROLLBACK: - dst->snap.snapid = cpu_to_le64(src->snap.snapid); - break; case CEPH_OSD_OP_STARTSYNC: break; - case CEPH_OSD_OP_NOTIFY: - { - __le32 prot_ver = cpu_to_le32(src->watch.prot_ver); - __le32 timeout = cpu_to_le32(src->watch.timeout); - - BUG_ON(!req->r_trail); - - ceph_pagelist_append(req->r_trail, - &prot_ver, sizeof(prot_ver)); - ceph_pagelist_append(req->r_trail, - &timeout, sizeof(timeout)); - } case CEPH_OSD_OP_NOTIFY_ACK: case CEPH_OSD_OP_WATCH: dst->watch.cookie = cpu_to_le64(src->watch.cookie); @@ -356,6 +262,64 @@ static void osd_req_encode_op(struct ceph_osd_request *req, pr_err("unrecognized osd opcode %d\n", dst->op); WARN_ON(1); break; + case CEPH_OSD_OP_MAPEXT: + case CEPH_OSD_OP_MASKTRUNC: + case CEPH_OSD_OP_SPARSE_READ: + case CEPH_OSD_OP_NOTIFY: + case CEPH_OSD_OP_ASSERT_VER: + case CEPH_OSD_OP_WRITEFULL: + case CEPH_OSD_OP_TRUNCATE: + case CEPH_OSD_OP_ZERO: + case CEPH_OSD_OP_DELETE: + case CEPH_OSD_OP_APPEND: + case CEPH_OSD_OP_SETTRUNC: + case CEPH_OSD_OP_TRIMTRUNC: + case CEPH_OSD_OP_TMAPUP: + case CEPH_OSD_OP_TMAPPUT: + case CEPH_OSD_OP_TMAPGET: + case CEPH_OSD_OP_CREATE: + case CEPH_OSD_OP_ROLLBACK: + case CEPH_OSD_OP_OMAPGETKEYS: + case CEPH_OSD_OP_OMAPGETVALS: + case CEPH_OSD_OP_OMAPGETHEADER: + case CEPH_OSD_OP_OMAPGETVALSBYKEYS: + case CEPH_OSD_OP_MODE_RD: + case CEPH_OSD_OP_OMAPSETVALS: + case CEPH_OSD_OP_OMAPSETHEADER: + case CEPH_OSD_OP_OMAPCLEAR: + case CEPH_OSD_OP_OMAPRMKEYS: + case CEPH_OSD_OP_OMAP_CMP: + case CEPH_OSD_OP_CLONERANGE: + case CEPH_OSD_OP_ASSERT_SRC_VERSION: + case CEPH_OSD_OP_SRC_CMPXATTR: + case CEPH_OSD_OP_GETXATTR: + case CEPH_OSD_OP_GETXATTRS: + case CEPH_OSD_OP_CMPXATTR: + case CEPH_OSD_OP_SETXATTR: + case CEPH_OSD_OP_SETXATTRS: + case CEPH_OSD_OP_RESETXATTRS: + case CEPH_OSD_OP_RMXATTR: + case CEPH_OSD_OP_PULL: + case CEPH_OSD_OP_PUSH: + case CEPH_OSD_OP_BALANCEREADS: + case CEPH_OSD_OP_UNBALANCEREADS: + case CEPH_OSD_OP_SCRUB: + case CEPH_OSD_OP_SCRUB_RESERVE: + case CEPH_OSD_OP_SCRUB_UNRESERVE: + case CEPH_OSD_OP_SCRUB_STOP: + case CEPH_OSD_OP_SCRUB_MAP: + case CEPH_OSD_OP_WRLOCK: + case CEPH_OSD_OP_WRUNLOCK: + case CEPH_OSD_OP_RDLOCK: + case CEPH_OSD_OP_RDUNLOCK: + case CEPH_OSD_OP_UPLOCK: + case CEPH_OSD_OP_DNLOCK: + case CEPH_OSD_OP_PGLS: + case CEPH_OSD_OP_PGLS_FILTER: + pr_err("unsupported osd opcode %s\n", + ceph_osd_op_name(dst->op)); + WARN_ON(1); + break; } dst->payload_len = cpu_to_le32(src->payload_len); } @@ -365,75 +329,95 @@ static void osd_req_encode_op(struct ceph_osd_request *req, * */ void ceph_osdc_build_request(struct ceph_osd_request *req, - u64 off, u64 *plen, + u64 off, u64 len, unsigned int num_ops, struct ceph_osd_req_op *src_ops, - struct ceph_snap_context *snapc, - struct timespec *mtime, - const char *oid, - int oid_len) + struct ceph_snap_context *snapc, u64 snap_id, + struct timespec *mtime) { struct ceph_msg *msg = req->r_request; - struct ceph_osd_request_head *head; struct ceph_osd_req_op *src_op; - struct ceph_osd_op *op; void *p; - int num_op = get_num_ops(src_ops, NULL); - size_t msg_size = sizeof(*head) + num_op*sizeof(*op); + size_t msg_size; int flags = req->r_flags; - u64 data_len = 0; + u64 data_len; int i; - head = msg->front.iov_base; - op = (void *)(head + 1); - p = (void *)(op + num_op); - + req->r_num_ops = num_ops; + req->r_snapid = snap_id; req->r_snapc = ceph_get_snap_context(snapc); - head->client_inc = cpu_to_le32(1); /* always, for now. */ - head->flags = cpu_to_le32(flags); - if (flags & CEPH_OSD_FLAG_WRITE) - ceph_encode_timespec(&head->mtime, mtime); - head->num_ops = cpu_to_le16(num_op); - - - /* fill in oid */ - head->object_len = cpu_to_le32(oid_len); - memcpy(p, oid, oid_len); - p += oid_len; + /* encode request */ + msg->hdr.version = cpu_to_le16(4); + p = msg->front.iov_base; + ceph_encode_32(&p, 1); /* client_inc is always 1 */ + req->r_request_osdmap_epoch = p; + p += 4; + req->r_request_flags = p; + p += 4; + if (req->r_flags & CEPH_OSD_FLAG_WRITE) + ceph_encode_timespec(p, mtime); + p += sizeof(struct ceph_timespec); + req->r_request_reassert_version = p; + p += sizeof(struct ceph_eversion); /* will get filled in */ + + /* oloc */ + ceph_encode_8(&p, 4); + ceph_encode_8(&p, 4); + ceph_encode_32(&p, 8 + 4 + 4); + req->r_request_pool = p; + p += 8; + ceph_encode_32(&p, -1); /* preferred */ + ceph_encode_32(&p, 0); /* key len */ + + ceph_encode_8(&p, 1); + req->r_request_pgid = p; + p += 8 + 4; + ceph_encode_32(&p, -1); /* preferred */ + + /* oid */ + ceph_encode_32(&p, req->r_oid_len); + memcpy(p, req->r_oid, req->r_oid_len); + dout("oid '%.*s' len %d\n", req->r_oid_len, req->r_oid, req->r_oid_len); + p += req->r_oid_len; + + /* ops */ + ceph_encode_16(&p, num_ops); src_op = src_ops; - while (src_op->op) { - osd_req_encode_op(req, op, src_op); - src_op++; - op++; + req->r_request_ops = p; + for (i = 0; i < num_ops; i++, src_op++) { + osd_req_encode_op(req, p, src_op); + p += sizeof(struct ceph_osd_op); } - if (req->r_trail) - data_len += req->r_trail->length; - - if (snapc) { - head->snap_seq = cpu_to_le64(snapc->seq); - head->num_snaps = cpu_to_le32(snapc->num_snaps); + /* snaps */ + ceph_encode_64(&p, req->r_snapid); + ceph_encode_64(&p, req->r_snapc ? req->r_snapc->seq : 0); + ceph_encode_32(&p, req->r_snapc ? req->r_snapc->num_snaps : 0); + if (req->r_snapc) { for (i = 0; i < snapc->num_snaps; i++) { - put_unaligned_le64(snapc->snaps[i], p); - p += sizeof(u64); + ceph_encode_64(&p, req->r_snapc->snaps[i]); } } + req->r_request_attempts = p; + p += 4; + + data_len = req->r_trail.length; if (flags & CEPH_OSD_FLAG_WRITE) { req->r_request->hdr.data_off = cpu_to_le16(off); - req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len); - } else if (data_len) { - req->r_request->hdr.data_off = 0; - req->r_request->hdr.data_len = cpu_to_le32(data_len); + data_len += len; } - + req->r_request->hdr.data_len = cpu_to_le32(data_len); req->r_request->page_alignment = req->r_page_alignment; BUG_ON(p > msg->front.iov_base + msg->front.iov_len); msg_size = p - msg->front.iov_base; msg->front.iov_len = msg_size; msg->hdr.front_len = cpu_to_le32(msg_size); + + dout("build_request msg_size was %d num_ops %d\n", (int)msg_size, + num_ops); return; } EXPORT_SYMBOL(ceph_osdc_build_request); @@ -459,34 +443,33 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, - bool use_mempool, int num_reply, + bool use_mempool, int page_align) { - struct ceph_osd_req_op ops[3]; + struct ceph_osd_req_op ops[2]; struct ceph_osd_request *req; + unsigned int num_op = 1; int r; + memset(&ops, 0, sizeof ops); + ops[0].op = opcode; ops[0].extent.truncate_seq = truncate_seq; ops[0].extent.truncate_size = truncate_size; - ops[0].payload_len = 0; if (do_sync) { ops[1].op = CEPH_OSD_OP_STARTSYNC; - ops[1].payload_len = 0; - ops[2].op = 0; - } else - ops[1].op = 0; - - req = ceph_osdc_alloc_request(osdc, flags, - snapc, ops, - use_mempool, - GFP_NOFS, NULL, NULL); + num_op++; + } + + req = ceph_osdc_alloc_request(osdc, snapc, num_op, use_mempool, + GFP_NOFS); if (!req) return ERR_PTR(-ENOMEM); + req->r_flags = flags; /* calculate max write size */ - r = calc_layout(osdc, vino, layout, off, plen, req, ops); + r = calc_layout(vino, layout, off, plen, req, ops); if (r < 0) return ERR_PTR(r); req->r_file_layout = *layout; /* keep a copy */ @@ -496,10 +479,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, req->r_num_pages = calc_pages_for(page_align, *plen); req->r_page_alignment = page_align; - ceph_osdc_build_request(req, off, plen, ops, - snapc, - mtime, - req->r_oid, req->r_oid_len); + ceph_osdc_build_request(req, off, *plen, num_op, ops, + snapc, vino.snap, mtime); return req; } @@ -623,8 +604,8 @@ static void osd_reset(struct ceph_connection *con) down_read(&osdc->map_sem); mutex_lock(&osdc->request_mutex); __kick_osd_requests(osdc, osd); + __send_queued(osdc); mutex_unlock(&osdc->request_mutex); - send_queued(osdc); up_read(&osdc->map_sem); } @@ -739,31 +720,35 @@ static void remove_old_osds(struct ceph_osd_client *osdc) */ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd) { - struct ceph_osd_request *req; - int ret = 0; + struct ceph_entity_addr *peer_addr; dout("__reset_osd %p osd%d\n", osd, osd->o_osd); if (list_empty(&osd->o_requests) && list_empty(&osd->o_linger_requests)) { __remove_osd(osdc, osd); - ret = -ENODEV; - } else if (memcmp(&osdc->osdmap->osd_addr[osd->o_osd], - &osd->o_con.peer_addr, - sizeof(osd->o_con.peer_addr)) == 0 && - !ceph_con_opened(&osd->o_con)) { + + return -ENODEV; + } + + peer_addr = &osdc->osdmap->osd_addr[osd->o_osd]; + if (!memcmp(peer_addr, &osd->o_con.peer_addr, sizeof (*peer_addr)) && + !ceph_con_opened(&osd->o_con)) { + struct ceph_osd_request *req; + dout(" osd addr hasn't changed and connection never opened," " letting msgr retry"); /* touch each r_stamp for handle_timeout()'s benfit */ list_for_each_entry(req, &osd->o_requests, r_osd_item) req->r_stamp = jiffies; - ret = -EAGAIN; - } else { - ceph_con_close(&osd->o_con); - ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, - &osdc->osdmap->osd_addr[osd->o_osd]); - osd->o_incarnation++; + + return -EAGAIN; } - return ret; + + ceph_con_close(&osd->o_con); + ceph_con_open(&osd->o_con, CEPH_ENTITY_TYPE_OSD, osd->o_osd, peer_addr); + osd->o_incarnation++; + + return 0; } static void __insert_osd(struct ceph_osd_client *osdc, struct ceph_osd *new) @@ -961,20 +946,18 @@ EXPORT_SYMBOL(ceph_osdc_set_request_linger); static int __map_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req, int force_resend) { - struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base; struct ceph_pg pgid; int acting[CEPH_PG_MAX_SIZE]; int o = -1, num = 0; int err; dout("map_request %p tid %lld\n", req, req->r_tid); - err = ceph_calc_object_layout(&reqhead->layout, req->r_oid, + err = ceph_calc_object_layout(&pgid, req->r_oid, &req->r_file_layout, osdc->osdmap); if (err) { list_move(&req->r_req_lru_item, &osdc->req_notarget); return err; } - pgid = reqhead->layout.ol_pgid; req->r_pgid = pgid; err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting); @@ -991,8 +974,8 @@ static int __map_request(struct ceph_osd_client *osdc, (req->r_osd == NULL && o == -1)) return 0; /* no change */ - dout("map_request tid %llu pgid %d.%x osd%d (was osd%d)\n", - req->r_tid, le32_to_cpu(pgid.pool), le16_to_cpu(pgid.ps), o, + dout("map_request tid %llu pgid %lld.%x osd%d (was osd%d)\n", + req->r_tid, pgid.pool, pgid.seed, o, req->r_osd ? req->r_osd->o_osd : -1); /* record full pg acting set */ @@ -1041,15 +1024,22 @@ out: static void __send_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req) { - struct ceph_osd_request_head *reqhead; - - dout("send_request %p tid %llu to osd%d flags %d\n", - req, req->r_tid, req->r_osd->o_osd, req->r_flags); + void *p; - reqhead = req->r_request->front.iov_base; - reqhead->osdmap_epoch = cpu_to_le32(osdc->osdmap->epoch); - reqhead->flags |= cpu_to_le32(req->r_flags); /* e.g., RETRY */ - reqhead->reassert_version = req->r_reassert_version; + dout("send_request %p tid %llu to osd%d flags %d pg %lld.%x\n", + req, req->r_tid, req->r_osd->o_osd, req->r_flags, + (unsigned long long)req->r_pgid.pool, req->r_pgid.seed); + + /* fill in message content that changes each time we send it */ + put_unaligned_le32(osdc->osdmap->epoch, req->r_request_osdmap_epoch); + put_unaligned_le32(req->r_flags, req->r_request_flags); + put_unaligned_le64(req->r_pgid.pool, req->r_request_pool); + p = req->r_request_pgid; + ceph_encode_64(&p, req->r_pgid.pool); + ceph_encode_32(&p, req->r_pgid.seed); + put_unaligned_le64(1, req->r_request_attempts); /* FIXME */ + memcpy(req->r_request_reassert_version, &req->r_reassert_version, + sizeof(req->r_reassert_version)); req->r_stamp = jiffies; list_move_tail(&req->r_req_lru_item, &osdc->req_lru); @@ -1062,16 +1052,13 @@ static void __send_request(struct ceph_osd_client *osdc, /* * Send any requests in the queue (req_unsent). */ -static void send_queued(struct ceph_osd_client *osdc) +static void __send_queued(struct ceph_osd_client *osdc) { struct ceph_osd_request *req, *tmp; - dout("send_queued\n"); - mutex_lock(&osdc->request_mutex); - list_for_each_entry_safe(req, tmp, &osdc->req_unsent, r_req_lru_item) { + dout("__send_queued\n"); + list_for_each_entry_safe(req, tmp, &osdc->req_unsent, r_req_lru_item) __send_request(osdc, req); - } - mutex_unlock(&osdc->request_mutex); } /* @@ -1123,8 +1110,8 @@ static void handle_timeout(struct work_struct *work) } __schedule_osd_timeout(osdc); + __send_queued(osdc); mutex_unlock(&osdc->request_mutex); - send_queued(osdc); up_read(&osdc->map_sem); } @@ -1152,6 +1139,26 @@ static void complete_request(struct ceph_osd_request *req) complete_all(&req->r_safe_completion); /* fsync waiter */ } +static int __decode_pgid(void **p, void *end, struct ceph_pg *pgid) +{ + __u8 v; + + ceph_decode_need(p, end, 1 + 8 + 4 + 4, bad); + v = ceph_decode_8(p); + if (v > 1) { + pr_warning("do not understand pg encoding %d > 1", v); + return -EINVAL; + } + pgid->pool = ceph_decode_64(p); + pgid->seed = ceph_decode_32(p); + *p += 4; + return 0; + +bad: + pr_warning("incomplete pg encoding"); + return -EINVAL; +} + /* * handle osd op reply. either call the callback if it is specified, * or do the completion to wake up the waiting thread. @@ -1159,22 +1166,42 @@ static void complete_request(struct ceph_osd_request *req) static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, struct ceph_connection *con) { - struct ceph_osd_reply_head *rhead = msg->front.iov_base; + void *p, *end; struct ceph_osd_request *req; u64 tid; - int numops, object_len, flags; + int object_len; + int numops, payload_len, flags; s32 result; + s32 retry_attempt; + struct ceph_pg pg; + int err; + u32 reassert_epoch; + u64 reassert_version; + u32 osdmap_epoch; + int i; tid = le64_to_cpu(msg->hdr.tid); - if (msg->front.iov_len < sizeof(*rhead)) - goto bad; - numops = le32_to_cpu(rhead->num_ops); - object_len = le32_to_cpu(rhead->object_len); - result = le32_to_cpu(rhead->result); - if (msg->front.iov_len != sizeof(*rhead) + object_len + - numops * sizeof(struct ceph_osd_op)) + dout("handle_reply %p tid %llu\n", msg, tid); + + p = msg->front.iov_base; + end = p + msg->front.iov_len; + + ceph_decode_need(&p, end, 4, bad); + object_len = ceph_decode_32(&p); + ceph_decode_need(&p, end, object_len, bad); + p += object_len; + + err = __decode_pgid(&p, end, &pg); + if (err) goto bad; - dout("handle_reply %p tid %llu result %d\n", msg, tid, (int)result); + + ceph_decode_need(&p, end, 8 + 4 + 4 + 8 + 4, bad); + flags = ceph_decode_64(&p); + result = ceph_decode_32(&p); + reassert_epoch = ceph_decode_32(&p); + reassert_version = ceph_decode_64(&p); + osdmap_epoch = ceph_decode_32(&p); + /* lookup */ mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); @@ -1184,7 +1211,38 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, return; } ceph_osdc_get_request(req); - flags = le32_to_cpu(rhead->flags); + + dout("handle_reply %p tid %llu req %p result %d\n", msg, tid, + req, result); + + ceph_decode_need(&p, end, 4, bad); + numops = ceph_decode_32(&p); + if (numops > CEPH_OSD_MAX_OP) + goto bad_put; + if (numops != req->r_num_ops) + goto bad_put; + payload_len = 0; + ceph_decode_need(&p, end, numops * sizeof(struct ceph_osd_op), bad); + for (i = 0; i < numops; i++) { + struct ceph_osd_op *op = p; + int len; + + len = le32_to_cpu(op->payload_len); + req->r_reply_op_len[i] = len; + dout(" op %d has %d bytes\n", i, len); + payload_len += len; + p += sizeof(*op); + } + if (payload_len != le32_to_cpu(msg->hdr.data_len)) { + pr_warning("sum of op payload lens %d != data_len %d", + payload_len, le32_to_cpu(msg->hdr.data_len)); + goto bad_put; + } + + ceph_decode_need(&p, end, 4 + numops * 4, bad); + retry_attempt = ceph_decode_32(&p); + for (i = 0; i < numops; i++) + req->r_reply_op_result[i] = ceph_decode_32(&p); /* * if this connection filled our message, drop our reference now, to @@ -1199,7 +1257,7 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, if (!req->r_got_reply) { unsigned int bytes; - req->r_result = le32_to_cpu(rhead->result); + req->r_result = result; bytes = le32_to_cpu(msg->hdr.data_len); dout("handle_reply result %d bytes %d\n", req->r_result, bytes); @@ -1207,7 +1265,8 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, req->r_result = bytes; /* in case this is a write and we need to replay, */ - req->r_reassert_version = rhead->reassert_version; + req->r_reassert_version.epoch = cpu_to_le32(reassert_epoch); + req->r_reassert_version.version = cpu_to_le64(reassert_version); req->r_got_reply = 1; } else if ((flags & CEPH_OSD_FLAG_ONDISK) == 0) { @@ -1242,10 +1301,11 @@ done: ceph_osdc_put_request(req); return; +bad_put: + ceph_osdc_put_request(req); bad: - pr_err("corrupt osd_op_reply got %d %d expected %d\n", - (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len), - (int)sizeof(*rhead)); + pr_err("corrupt osd_op_reply got %d %d\n", + (int)msg->front.iov_len, le32_to_cpu(msg->hdr.front_len)); ceph_msg_dump(msg); } @@ -1462,7 +1522,9 @@ done: if (ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_FULL)) ceph_monc_request_next_osdmap(&osdc->client->monc); - send_queued(osdc); + mutex_lock(&osdc->request_mutex); + __send_queued(osdc); + mutex_unlock(&osdc->request_mutex); up_read(&osdc->map_sem); wake_up_all(&osdc->client->auth_wq); return; @@ -1556,8 +1618,7 @@ static void __remove_event(struct ceph_osd_event *event) int ceph_osdc_create_event(struct ceph_osd_client *osdc, void (*event_cb)(u64, u64, u8, void *), - int one_shot, void *data, - struct ceph_osd_event **pevent) + void *data, struct ceph_osd_event **pevent) { struct ceph_osd_event *event; @@ -1567,14 +1628,13 @@ int ceph_osdc_create_event(struct ceph_osd_client *osdc, dout("create_event %p\n", event); event->cb = event_cb; - event->one_shot = one_shot; + event->one_shot = 0; event->data = data; event->osdc = osdc; INIT_LIST_HEAD(&event->osd_node); RB_CLEAR_NODE(&event->node); kref_init(&event->kref); /* one ref for us */ kref_get(&event->kref); /* one ref for the caller */ - init_completion(&event->completion); spin_lock(&osdc->event_lock); event->cookie = ++osdc->event_count; @@ -1610,7 +1670,6 @@ static void do_event_work(struct work_struct *work) dout("do_event_work completing %p\n", event); event->cb(ver, notify_id, opcode, event->data); - complete(&event->completion); dout("do_event_work completed %p\n", event); ceph_osdc_put_event(event); kfree(event_work); @@ -1620,7 +1679,8 @@ static void do_event_work(struct work_struct *work) /* * Process osd watch notifications */ -void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) +static void handle_watch_notify(struct ceph_osd_client *osdc, + struct ceph_msg *msg) { void *p, *end; u8 proto_ver; @@ -1641,9 +1701,8 @@ void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) spin_lock(&osdc->event_lock); event = __find_event(osdc, cookie); if (event) { + BUG_ON(event->one_shot); get_event(event); - if (event->one_shot) - __remove_event(event); } spin_unlock(&osdc->event_lock); dout("handle_watch_notify cookie %lld ver %lld event %p\n", @@ -1668,7 +1727,6 @@ void handle_watch_notify(struct ceph_osd_client *osdc, struct ceph_msg *msg) return; done_err: - complete(&event->completion); ceph_osdc_put_event(event); return; @@ -1677,21 +1735,6 @@ bad: return; } -int ceph_osdc_wait_event(struct ceph_osd_event *event, unsigned long timeout) -{ - int err; - - dout("wait_event %p\n", event); - err = wait_for_completion_interruptible_timeout(&event->completion, - timeout * HZ); - ceph_osdc_put_event(event); - if (err > 0) - err = 0; - dout("wait_event %p returns %d\n", event, err); - return err; -} -EXPORT_SYMBOL(ceph_osdc_wait_event); - /* * Register request, send initial attempt. */ @@ -1706,7 +1749,7 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc, #ifdef CONFIG_BLOCK req->r_request->bio = req->r_bio; #endif - req->r_request->trail = req->r_trail; + req->r_request->trail = &req->r_trail; register_request(osdc, req); @@ -1865,7 +1908,6 @@ out_mempool: out: return err; } -EXPORT_SYMBOL(ceph_osdc_init); void ceph_osdc_stop(struct ceph_osd_client *osdc) { @@ -1882,7 +1924,6 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc) ceph_msgpool_destroy(&osdc->msgpool_op); ceph_msgpool_destroy(&osdc->msgpool_op_reply); } -EXPORT_SYMBOL(ceph_osdc_stop); /* * Read some contiguous pages. If we cross a stripe boundary, shorten @@ -1902,7 +1943,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc, req = ceph_osdc_new_request(osdc, layout, vino, off, plen, CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ, NULL, 0, truncate_seq, truncate_size, NULL, - false, 1, page_align); + false, page_align); if (IS_ERR(req)) return PTR_ERR(req); @@ -1931,8 +1972,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, u64 off, u64 len, u32 truncate_seq, u64 truncate_size, struct timespec *mtime, - struct page **pages, int num_pages, - int flags, int do_sync, bool nofail) + struct page **pages, int num_pages) { struct ceph_osd_request *req; int rc = 0; @@ -1941,11 +1981,10 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, BUG_ON(vino.snap != CEPH_NOSNAP); req = ceph_osdc_new_request(osdc, layout, vino, off, &len, CEPH_OSD_OP_WRITE, - flags | CEPH_OSD_FLAG_ONDISK | - CEPH_OSD_FLAG_WRITE, - snapc, do_sync, + CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE, + snapc, 0, truncate_seq, truncate_size, mtime, - nofail, 1, page_align); + true, page_align); if (IS_ERR(req)) return PTR_ERR(req); @@ -1954,7 +1993,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino, dout("writepages %llu~%llu (%d pages)\n", off, len, req->r_num_pages); - rc = ceph_osdc_start_request(osdc, req, nofail); + rc = ceph_osdc_start_request(osdc, req, true); if (!rc) rc = ceph_osdc_wait_request(osdc, req); @@ -2047,7 +2086,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, if (data_len > 0) { int want = calc_pages_for(req->r_page_alignment, data_len); - if (unlikely(req->r_num_pages < want)) { + if (req->r_pages && unlikely(req->r_num_pages < want)) { pr_warning("tid %lld reply has %d bytes %d pages, we" " had only %d pages ready\n", tid, data_len, want, req->r_num_pages); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index de73214b5d26..4543b9aba40c 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -13,26 +13,18 @@ char *ceph_osdmap_state_str(char *str, int len, int state) { - int flag = 0; - if (!len) - goto done; - - *str = '\0'; - if (state) { - if (state & CEPH_OSD_EXISTS) { - snprintf(str, len, "exists"); - flag = 1; - } - if (state & CEPH_OSD_UP) { - snprintf(str, len, "%s%s%s", str, (flag ? ", " : ""), - "up"); - flag = 1; - } - } else { + return str; + + if ((state & CEPH_OSD_EXISTS) && (state & CEPH_OSD_UP)) + snprintf(str, len, "exists, up"); + else if (state & CEPH_OSD_EXISTS) + snprintf(str, len, "exists"); + else if (state & CEPH_OSD_UP) + snprintf(str, len, "up"); + else snprintf(str, len, "doesn't exist"); - } -done: + return str; } @@ -53,13 +45,8 @@ static int calc_bits_of(unsigned int t) */ static void calc_pg_masks(struct ceph_pg_pool_info *pi) { - pi->pg_num_mask = (1 << calc_bits_of(le32_to_cpu(pi->v.pg_num)-1)) - 1; - pi->pgp_num_mask = - (1 << calc_bits_of(le32_to_cpu(pi->v.pgp_num)-1)) - 1; - pi->lpg_num_mask = - (1 << calc_bits_of(le32_to_cpu(pi->v.lpg_num)-1)) - 1; - pi->lpgp_num_mask = - (1 << calc_bits_of(le32_to_cpu(pi->v.lpgp_num)-1)) - 1; + pi->pg_num_mask = (1 << calc_bits_of(pi->pg_num-1)) - 1; + pi->pgp_num_mask = (1 << calc_bits_of(pi->pgp_num-1)) - 1; } /* @@ -170,6 +157,7 @@ static struct crush_map *crush_decode(void *pbyval, void *end) c->choose_local_tries = 2; c->choose_local_fallback_tries = 5; c->choose_total_tries = 19; + c->chooseleaf_descend_once = 0; ceph_decode_need(p, end, 4*sizeof(u32), bad); magic = ceph_decode_32(p); @@ -336,6 +324,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end) dout("crush decode tunable choose_total_tries = %d", c->choose_total_tries); + ceph_decode_need(p, end, sizeof(u32), done); + c->chooseleaf_descend_once = ceph_decode_32(p); + dout("crush decode tunable chooseleaf_descend_once = %d", + c->chooseleaf_descend_once); + done: dout("crush_decode success\n"); return c; @@ -354,12 +347,13 @@ bad: */ static int pgid_cmp(struct ceph_pg l, struct ceph_pg r) { - u64 a = *(u64 *)&l; - u64 b = *(u64 *)&r; - - if (a < b) + if (l.pool < r.pool) + return -1; + if (l.pool > r.pool) + return 1; + if (l.seed < r.seed) return -1; - if (a > b) + if (l.seed > r.seed) return 1; return 0; } @@ -405,8 +399,8 @@ static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root, } else if (c > 0) { n = n->rb_right; } else { - dout("__lookup_pg_mapping %llx got %p\n", - *(u64 *)&pgid, pg); + dout("__lookup_pg_mapping %lld.%x got %p\n", + pgid.pool, pgid.seed, pg); return pg; } } @@ -418,12 +412,13 @@ static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid) struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid); if (pg) { - dout("__remove_pg_mapping %llx %p\n", *(u64 *)&pgid, pg); + dout("__remove_pg_mapping %lld.%x %p\n", pgid.pool, pgid.seed, + pg); rb_erase(&pg->node, root); kfree(pg); return 0; } - dout("__remove_pg_mapping %llx dne\n", *(u64 *)&pgid); + dout("__remove_pg_mapping %lld.%x dne\n", pgid.pool, pgid.seed); return -ENOENT; } @@ -452,7 +447,7 @@ static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new) return 0; } -static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id) +static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, u64 id) { struct ceph_pg_pool_info *pi; struct rb_node *n = root->rb_node; @@ -508,24 +503,57 @@ static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) static int __decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) { - unsigned int n, m; + u8 ev, cv; + unsigned len, num; + void *pool_end; + + ceph_decode_need(p, end, 2 + 4, bad); + ev = ceph_decode_8(p); /* encoding version */ + cv = ceph_decode_8(p); /* compat version */ + if (ev < 5) { + pr_warning("got v %d < 5 cv %d of ceph_pg_pool\n", ev, cv); + return -EINVAL; + } + if (cv > 7) { + pr_warning("got v %d cv %d > 7 of ceph_pg_pool\n", ev, cv); + return -EINVAL; + } + len = ceph_decode_32(p); + ceph_decode_need(p, end, len, bad); + pool_end = *p + len; - ceph_decode_copy(p, &pi->v, sizeof(pi->v)); - calc_pg_masks(pi); + pi->type = ceph_decode_8(p); + pi->size = ceph_decode_8(p); + pi->crush_ruleset = ceph_decode_8(p); + pi->object_hash = ceph_decode_8(p); + + pi->pg_num = ceph_decode_32(p); + pi->pgp_num = ceph_decode_32(p); - /* num_snaps * snap_info_t */ - n = le32_to_cpu(pi->v.num_snaps); - while (n--) { - ceph_decode_need(p, end, sizeof(u64) + 1 + sizeof(u64) + - sizeof(struct ceph_timespec), bad); - *p += sizeof(u64) + /* key */ - 1 + sizeof(u64) + /* u8, snapid */ - sizeof(struct ceph_timespec); - m = ceph_decode_32(p); /* snap name */ - *p += m; + *p += 4 + 4; /* skip lpg* */ + *p += 4; /* skip last_change */ + *p += 8 + 4; /* skip snap_seq, snap_epoch */ + + /* skip snaps */ + num = ceph_decode_32(p); + while (num--) { + *p += 8; /* snapid key */ + *p += 1 + 1; /* versions */ + len = ceph_decode_32(p); + *p += len; } - *p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2; + /* skip removed snaps */ + num = ceph_decode_32(p); + *p += num * (8 + 8); + + *p += 8; /* skip auid */ + pi->flags = ceph_decode_64(p); + + /* ignore the rest */ + + *p = pool_end; + calc_pg_masks(pi); return 0; bad: @@ -535,14 +563,15 @@ bad: static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map) { struct ceph_pg_pool_info *pi; - u32 num, len, pool; + u32 num, len; + u64 pool; ceph_decode_32_safe(p, end, num, bad); dout(" %d pool names\n", num); while (num--) { - ceph_decode_32_safe(p, end, pool, bad); + ceph_decode_64_safe(p, end, pool, bad); ceph_decode_32_safe(p, end, len, bad); - dout(" pool %d len %d\n", pool, len); + dout(" pool %llu len %d\n", pool, len); ceph_decode_need(p, end, len, bad); pi = __lookup_pg_pool(&map->pg_pools, pool); if (pi) { @@ -625,6 +654,24 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) return 0; } +static int __decode_pgid(void **p, void *end, struct ceph_pg *pg) +{ + u8 v; + + ceph_decode_need(p, end, 1+8+4+4, bad); + v = ceph_decode_8(p); + if (v != 1) + goto bad; + pg->pool = ceph_decode_64(p); + pg->seed = ceph_decode_32(p); + *p += 4; /* skip preferred */ + return 0; + +bad: + dout("error decoding pgid\n"); + return -EINVAL; +} + /* * decode a full map. */ @@ -633,7 +680,6 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) struct ceph_osdmap *map; u16 version; u32 len, max, i; - u8 ev; int err = -EINVAL; void *start = *p; struct ceph_pg_pool_info *pi; @@ -646,9 +692,12 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) map->pg_temp = RB_ROOT; ceph_decode_16_safe(p, end, version, bad); - if (version > CEPH_OSDMAP_VERSION) { - pr_warning("got unknown v %d > %d of osdmap\n", version, - CEPH_OSDMAP_VERSION); + if (version > 6) { + pr_warning("got unknown v %d > 6 of osdmap\n", version); + goto bad; + } + if (version < 6) { + pr_warning("got old v %d < 6 of osdmap\n", version); goto bad; } @@ -660,20 +709,12 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) ceph_decode_32_safe(p, end, max, bad); while (max--) { - ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad); + ceph_decode_need(p, end, 8 + 2, bad); err = -ENOMEM; pi = kzalloc(sizeof(*pi), GFP_NOFS); if (!pi) goto bad; - pi->id = ceph_decode_32(p); - err = -EINVAL; - ev = ceph_decode_8(p); /* encoding version */ - if (ev > CEPH_PG_POOL_VERSION) { - pr_warning("got unknown v %d > %d of ceph_pg_pool\n", - ev, CEPH_PG_POOL_VERSION); - kfree(pi); - goto bad; - } + pi->id = ceph_decode_64(p); err = __decode_pool(p, end, pi); if (err < 0) { kfree(pi); @@ -682,12 +723,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) __insert_pg_pool(&map->pg_pools, pi); } - if (version >= 5) { - err = __decode_pool_names(p, end, map); - if (err < 0) { - dout("fail to decode pool names"); - goto bad; - } + err = __decode_pool_names(p, end, map); + if (err < 0) { + dout("fail to decode pool names"); + goto bad; } ceph_decode_32_safe(p, end, map->pool_max, bad); @@ -726,8 +765,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) struct ceph_pg pgid; struct ceph_pg_mapping *pg; - ceph_decode_need(p, end, sizeof(u32) + sizeof(u64), bad); - ceph_decode_copy(p, &pgid, sizeof(pgid)); + err = __decode_pgid(p, end, &pgid); + if (err) + goto bad; + ceph_decode_need(p, end, sizeof(u32), bad); n = ceph_decode_32(p); err = -EINVAL; if (n > (UINT_MAX - sizeof(*pg)) / sizeof(u32)) @@ -745,7 +786,8 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end) err = __insert_pg_mapping(pg, &map->pg_temp); if (err) goto bad; - dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, len); + dout(" added pg_temp %lld.%x len %d\n", pgid.pool, pgid.seed, + len); } /* crush */ @@ -784,16 +826,17 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, struct ceph_fsid fsid; u32 epoch = 0; struct ceph_timespec modified; - u32 len, pool; - __s32 new_pool_max, new_flags, max; + s32 len; + u64 pool; + __s64 new_pool_max; + __s32 new_flags, max; void *start = *p; int err = -EINVAL; u16 version; ceph_decode_16_safe(p, end, version, bad); - if (version > CEPH_OSDMAP_INC_VERSION) { - pr_warning("got unknown v %d > %d of inc osdmap\n", version, - CEPH_OSDMAP_INC_VERSION); + if (version != 6) { + pr_warning("got unknown v %d != 6 of inc osdmap\n", version); goto bad; } @@ -803,7 +846,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, epoch = ceph_decode_32(p); BUG_ON(epoch != map->epoch+1); ceph_decode_copy(p, &modified, sizeof(modified)); - new_pool_max = ceph_decode_32(p); + new_pool_max = ceph_decode_64(p); new_flags = ceph_decode_32(p); /* full map? */ @@ -853,18 +896,9 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, /* new_pool */ ceph_decode_32_safe(p, end, len, bad); while (len--) { - __u8 ev; struct ceph_pg_pool_info *pi; - ceph_decode_32_safe(p, end, pool, bad); - ceph_decode_need(p, end, 1 + sizeof(pi->v), bad); - ev = ceph_decode_8(p); /* encoding version */ - if (ev > CEPH_PG_POOL_VERSION) { - pr_warning("got unknown v %d > %d of ceph_pg_pool\n", - ev, CEPH_PG_POOL_VERSION); - err = -EINVAL; - goto bad; - } + ceph_decode_64_safe(p, end, pool, bad); pi = __lookup_pg_pool(&map->pg_pools, pool); if (!pi) { pi = kzalloc(sizeof(*pi), GFP_NOFS); @@ -890,7 +924,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, while (len--) { struct ceph_pg_pool_info *pi; - ceph_decode_32_safe(p, end, pool, bad); + ceph_decode_64_safe(p, end, pool, bad); pi = __lookup_pg_pool(&map->pg_pools, pool); if (pi) __remove_pg_pool(&map->pg_pools, pi); @@ -948,10 +982,12 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, int j; struct ceph_pg pgid; u32 pglen; - ceph_decode_need(p, end, sizeof(u64) + sizeof(u32), bad); - ceph_decode_copy(p, &pgid, sizeof(pgid)); - pglen = ceph_decode_32(p); + err = __decode_pgid(p, end, &pgid); + if (err) + goto bad; + ceph_decode_need(p, end, sizeof(u32), bad); + pglen = ceph_decode_32(p); if (pglen) { ceph_decode_need(p, end, pglen*sizeof(u32), bad); @@ -975,8 +1011,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, kfree(pg); goto bad; } - dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid, - pglen); + dout(" added pg_temp %lld.%x len %d\n", pgid.pool, + pgid.seed, pglen); } else { /* remove */ __remove_pg_mapping(&map->pg_temp, pgid); @@ -1010,7 +1046,7 @@ bad: * pass a stride back to the caller. */ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, - u64 off, u64 *plen, + u64 off, u64 len, u64 *ono, u64 *oxoff, u64 *oxlen) { @@ -1021,7 +1057,7 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u32 su_per_object; u64 t, su_offset; - dout("mapping %llu~%llu osize %u fl_su %u\n", off, *plen, + dout("mapping %llu~%llu osize %u fl_su %u\n", off, len, osize, su); if (su == 0 || sc == 0) goto invalid; @@ -1054,11 +1090,10 @@ int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, /* * Calculate the length of the extent being written to the selected - * object. This is the minimum of the full length requested (plen) or + * object. This is the minimum of the full length requested (len) or * the remainder of the current stripe being written to. */ - *oxlen = min_t(u64, *plen, su - su_offset); - *plen = *oxlen; + *oxlen = min_t(u64, len, su - su_offset); dout(" obj extent %llu~%llu\n", *oxoff, *oxlen); return 0; @@ -1076,33 +1111,24 @@ EXPORT_SYMBOL(ceph_calc_file_object_mapping); * calculate an object layout (i.e. pgid) from an oid, * file_layout, and osdmap */ -int ceph_calc_object_layout(struct ceph_object_layout *ol, +int ceph_calc_object_layout(struct ceph_pg *pg, const char *oid, struct ceph_file_layout *fl, struct ceph_osdmap *osdmap) { unsigned int num, num_mask; - struct ceph_pg pgid; - int poolid = le32_to_cpu(fl->fl_pg_pool); struct ceph_pg_pool_info *pool; - unsigned int ps; BUG_ON(!osdmap); - - pool = __lookup_pg_pool(&osdmap->pg_pools, poolid); + pg->pool = le32_to_cpu(fl->fl_pg_pool); + pool = __lookup_pg_pool(&osdmap->pg_pools, pg->pool); if (!pool) return -EIO; - ps = ceph_str_hash(pool->v.object_hash, oid, strlen(oid)); - num = le32_to_cpu(pool->v.pg_num); + pg->seed = ceph_str_hash(pool->object_hash, oid, strlen(oid)); + num = pool->pg_num; num_mask = pool->pg_num_mask; - pgid.ps = cpu_to_le16(ps); - pgid.preferred = cpu_to_le16(-1); - pgid.pool = fl->fl_pg_pool; - dout("calc_object_layout '%s' pgid %d.%x\n", oid, poolid, ps); - - ol->ol_pgid = pgid; - ol->ol_stripe_unit = fl->fl_object_stripe_unit; + dout("calc_object_layout '%s' pgid %lld.%x\n", oid, pg->pool, pg->seed); return 0; } EXPORT_SYMBOL(ceph_calc_object_layout); @@ -1117,19 +1143,16 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, struct ceph_pg_mapping *pg; struct ceph_pg_pool_info *pool; int ruleno; - unsigned int poolid, ps, pps, t, r; + int r; + u32 pps; - poolid = le32_to_cpu(pgid.pool); - ps = le16_to_cpu(pgid.ps); - - pool = __lookup_pg_pool(&osdmap->pg_pools, poolid); + pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool); if (!pool) return NULL; /* pg_temp? */ - t = ceph_stable_mod(ps, le32_to_cpu(pool->v.pg_num), - pool->pgp_num_mask); - pgid.ps = cpu_to_le16(t); + pgid.seed = ceph_stable_mod(pgid.seed, pool->pg_num, + pool->pgp_num_mask); pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid); if (pg) { *num = pg->len; @@ -1137,26 +1160,39 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid, } /* crush */ - ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset, - pool->v.type, pool->v.size); + ruleno = crush_find_rule(osdmap->crush, pool->crush_ruleset, + pool->type, pool->size); if (ruleno < 0) { - pr_err("no crush rule pool %d ruleset %d type %d size %d\n", - poolid, pool->v.crush_ruleset, pool->v.type, - pool->v.size); + pr_err("no crush rule pool %lld ruleset %d type %d size %d\n", + pgid.pool, pool->crush_ruleset, pool->type, + pool->size); return NULL; } - pps = ceph_stable_mod(ps, - le32_to_cpu(pool->v.pgp_num), - pool->pgp_num_mask); - pps += poolid; + if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) { + /* hash pool id and seed sothat pool PGs do not overlap */ + pps = crush_hash32_2(CRUSH_HASH_RJENKINS1, + ceph_stable_mod(pgid.seed, pool->pgp_num, + pool->pgp_num_mask), + pgid.pool); + } else { + /* + * legacy ehavior: add ps and pool together. this is + * not a great approach because the PGs from each pool + * will overlap on top of each other: 0.5 == 1.4 == + * 2.3 == ... + */ + pps = ceph_stable_mod(pgid.seed, pool->pgp_num, + pool->pgp_num_mask) + + (unsigned)pgid.pool; + } r = crush_do_rule(osdmap->crush, ruleno, pps, osds, - min_t(int, pool->v.size, *num), + min_t(int, pool->size, *num), osdmap->osd_weight); if (r < 0) { - pr_err("error %d from crush rule: pool %d ruleset %d type %d" - " size %d\n", r, poolid, pool->v.crush_ruleset, - pool->v.type, pool->v.size); + pr_err("error %d from crush rule: pool %lld ruleset %d type %d" + " size %d\n", r, pgid.pool, pool->crush_ruleset, + pool->type, pool->size); return NULL; } *num = r; diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c index cd9c21df87d1..815a2249cfa9 100644 --- a/net/ceph/pagevec.c +++ b/net/ceph/pagevec.c @@ -12,7 +12,7 @@ /* * build a vector of user pages */ -struct page **ceph_get_direct_page_vector(const char __user *data, +struct page **ceph_get_direct_page_vector(const void __user *data, int num_pages, bool write_page) { struct page **pages; @@ -93,7 +93,7 @@ EXPORT_SYMBOL(ceph_alloc_page_vector); * copy user data into a page vector */ int ceph_copy_user_to_page_vector(struct page **pages, - const char __user *data, + const void __user *data, loff_t off, size_t len) { int i = 0; @@ -118,17 +118,17 @@ int ceph_copy_user_to_page_vector(struct page **pages, } EXPORT_SYMBOL(ceph_copy_user_to_page_vector); -int ceph_copy_to_page_vector(struct page **pages, - const char *data, +void ceph_copy_to_page_vector(struct page **pages, + const void *data, loff_t off, size_t len) { int i = 0; size_t po = off & ~PAGE_CACHE_MASK; size_t left = len; - size_t l; while (left > 0) { - l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + memcpy(page_address(pages[i]) + po, data, l); data += l; left -= l; @@ -138,21 +138,20 @@ int ceph_copy_to_page_vector(struct page **pages, i++; } } - return len; } EXPORT_SYMBOL(ceph_copy_to_page_vector); -int ceph_copy_from_page_vector(struct page **pages, - char *data, +void ceph_copy_from_page_vector(struct page **pages, + void *data, loff_t off, size_t len) { int i = 0; size_t po = off & ~PAGE_CACHE_MASK; size_t left = len; - size_t l; while (left > 0) { - l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + size_t l = min_t(size_t, PAGE_CACHE_SIZE-po, left); + memcpy(data, page_address(pages[i]) + po, l); data += l; left -= l; @@ -162,7 +161,6 @@ int ceph_copy_from_page_vector(struct page **pages, i++; } } - return len; } EXPORT_SYMBOL(ceph_copy_from_page_vector); @@ -170,7 +168,7 @@ EXPORT_SYMBOL(ceph_copy_from_page_vector); * copy user data from a page vector into a user pointer */ int ceph_copy_page_vector_to_user(struct page **pages, - char __user *data, + void __user *data, loff_t off, size_t len) { int i = 0; diff --git a/net/core/dev.c b/net/core/dev.c index 17bc535115d3..b24ab0e98eb4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -658,11 +658,10 @@ __setup("netdev=", netdev_boot_setup); struct net_device *__dev_get_by_name(struct net *net, const char *name) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each_entry(dev, p, head, name_hlist) + hlist_for_each_entry(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -684,11 +683,10 @@ EXPORT_SYMBOL(__dev_get_by_name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each_entry_rcu(dev, p, head, name_hlist) + hlist_for_each_entry_rcu(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -735,11 +733,10 @@ EXPORT_SYMBOL(dev_get_by_name); struct net_device *__dev_get_by_index(struct net *net, int ifindex) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each_entry(dev, p, head, index_hlist) + hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -760,11 +757,10 @@ EXPORT_SYMBOL(__dev_get_by_index); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { - struct hlist_node *p; struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each_entry_rcu(dev, p, head, index_hlist) + hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -1549,7 +1545,6 @@ void net_enable_timestamp(void) return; } #endif - WARN_ON(in_interrupt()); static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); @@ -1629,7 +1624,6 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) } skb_orphan(skb); - nf_reset(skb); if (unlikely(!is_skb_forwardable(dev, skb))) { atomic_long_inc(&dev->rx_dropped); @@ -1645,6 +1639,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb->mark = 0; secpath_reset(skb); nf_reset(skb); + nf_reset_trace(skb); return netif_rx(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -1882,8 +1877,10 @@ int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index) if (!new_dev_maps) new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); - if (!new_dev_maps) + if (!new_dev_maps) { + mutex_unlock(&xps_map_mutex); return -ENOMEM; + } map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; @@ -2151,6 +2148,9 @@ static void skb_warn_bad_offload(const struct sk_buff *skb) struct net_device *dev = skb->dev; const char *driver = ""; + if (!net_ratelimit()) + return; + if (dev && dev->dev.parent) driver = dev_driver_string(dev->dev.parent); @@ -2221,9 +2221,9 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; __be16 type = skb->protocol; + int vlan_depth = ETH_HLEN; while (type == htons(ETH_P_8021Q)) { - int vlan_depth = ETH_HLEN; struct vlan_hdr *vh; if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) @@ -3317,6 +3317,7 @@ int netdev_rx_handler_register(struct net_device *dev, if (dev->rx_handler) return -EBUSY; + /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); @@ -3337,6 +3338,11 @@ void netdev_rx_handler_unregister(struct net_device *dev) ASSERT_RTNL(); RCU_INIT_POINTER(dev->rx_handler, NULL); + /* a reader seeing a non NULL rx_handler in a rcu_read_lock() + * section has a guarantee to see a non NULL rx_handler_data + * as well. + */ + synchronize_net(); RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); @@ -3446,6 +3452,7 @@ ncls: } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: + ret = NET_RX_SUCCESS; goto unlock; case RX_HANDLER_ANOTHER: goto another_round; @@ -4105,7 +4112,7 @@ static void net_rx_action(struct softirq_action *h) * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ - if (unlikely(budget <= 0 || time_after(jiffies, time_limit))) + if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) goto softnet_break; local_irq_enable(); @@ -4782,7 +4789,7 @@ EXPORT_SYMBOL(dev_set_mac_address); /** * dev_change_carrier - Change device carrier * @dev: device - * @new_carries: new value + * @new_carrier: new value * * Change device carrier */ diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index bd2eb9d3e369..abdc9e6ef33e 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -37,7 +37,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, ha->type = addr_type; ha->refcount = 1; ha->global_use = global; - ha->synced = false; + ha->synced = 0; list_add_tail_rcu(&ha->list, &list->list); list->count++; @@ -165,7 +165,7 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, addr_len, ha->type); if (err) break; - ha->synced = true; + ha->synced++; ha->refcount++; } else if (ha->refcount == 1) { __hw_addr_del(to_list, ha->addr, addr_len, ha->type); @@ -186,7 +186,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, if (ha->synced) { __hw_addr_del(to_list, ha->addr, addr_len, ha->type); - ha->synced = false; + ha->synced--; __hw_addr_del(from_list, ha->addr, addr_len, ha->type); } diff --git a/net/core/flow.c b/net/core/flow.c index 43f7495df27a..2bfd081c59f7 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -132,14 +132,14 @@ static void __flow_cache_shrink(struct flow_cache *fc, int shrink_to) { struct flow_cache_entry *fle; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; for (i = 0; i < flow_cache_hash_size(fc); i++) { int saved = 0; - hlist_for_each_entry_safe(fle, entry, tmp, + hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (saved < shrink_to && flow_entry_valid(fle)) { @@ -211,7 +211,6 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, struct flow_cache *fc = &flow_cache_global; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, *tfle; - struct hlist_node *entry; struct flow_cache_object *flo; size_t keysize; unsigned int hash; @@ -235,7 +234,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_new_hash_rnd(fc, fcp); hash = flow_hash_code(fc, fcp, key, keysize); - hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) { + hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) { if (tfle->net == net && tfle->family == family && tfle->dir == dir && @@ -301,13 +300,13 @@ static void flow_cache_flush_tasklet(unsigned long data) struct flow_cache *fc = info->cache; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { - hlist_for_each_entry_safe(fle, entry, tmp, + hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (flow_entry_valid(fle)) continue; @@ -329,7 +328,7 @@ static void flow_cache_flush_per_cpu(void *data) struct flow_flush_info *info = data; struct tasklet_struct *tasklet; - tasklet = this_cpu_ptr(&info->cache->percpu->flush_tasklet); + tasklet = &this_cpu_ptr(info->cache->percpu)->flush_tasklet; tasklet->data = (unsigned long)info; tasklet_schedule(tasklet); } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 9d4c7201400d..e187bf06d673 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -140,6 +140,8 @@ ipv6: flow->ports = *ports; } + flow->thoff = (u16) nhoff; + return true; } EXPORT_SYMBOL(skb_flow_dissect); diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 0f6bb6f8d391..3174f1998ee6 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -16,12 +16,11 @@ static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff { struct net *net = seq_file_net(seq); struct net_device *dev; - struct hlist_node *p; struct hlist_head *h; unsigned int count = 0, offset = get_offset(*pos); h = &net->dev_name_head[get_bucket(*pos)]; - hlist_for_each_entry_rcu(dev, p, h, name_hlist) { + hlist_for_each_entry_rcu(dev, h, name_hlist) { if (++count == offset) return dev; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 8acce01b6dab..80e271d9e64b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -344,7 +344,7 @@ struct net *get_net_ns_by_fd(int fd) if (IS_ERR(file)) return ERR_CAST(file); - ei = PROC_I(file->f_dentry->d_inode); + ei = PROC_I(file_inode(file)); if (ei->ns_ops == &netns_operations) net = get_net(ei->ns); else diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d8aa20f6a46e..23854b51a259 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -496,8 +496,10 @@ static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) } if (ops->fill_info) { data = nla_nest_start(skb, IFLA_INFO_DATA); - if (data == NULL) + if (data == NULL) { + err = -EMSGSIZE; goto err_cancel_link; + } err = ops->fill_info(skb, dev); if (err < 0) goto err_cancel_data; @@ -979,6 +981,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, * report anything. */ ivi.spoofchk = -1; + memset(ivi.mac, 0, sizeof(ivi.mac)); if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) break; vf_mac.vf = @@ -1060,7 +1063,6 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) int idx = 0, s_idx; struct net_device *dev; struct hlist_head *head; - struct hlist_node *node; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; @@ -1070,7 +1072,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; - if (nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) @@ -1080,7 +1082,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, @@ -1920,7 +1922,7 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) u32 ext_filter_mask = 0; u16 min_ifinfo_dump_size = 0; - if (nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + if (nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, ifla_policy) >= 0) { if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -2621,7 +2623,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); while (RTA_OK(attr, attrlen)) { - unsigned int flavor = attr->rta_type; + unsigned int flavor = attr->rta_type & NLA_TYPE_MASK; if (flavor) { if (flavor > rta_max[sz_idx]) return -EINVAL; diff --git a/net/core/scm.c b/net/core/scm.c index 905dcc6ad1e3..2dc6cdaaae8a 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -24,6 +24,7 @@ #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/security.h> +#include <linux/pid_namespace.h> #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/slab.h> @@ -52,7 +53,8 @@ static __inline__ int scm_check_creds(struct ucred *creds) if (!uid_valid(uid) || !gid_valid(gid)) return -EINVAL; - if ((creds->pid == task_tgid_vnr(current) || nsown_capable(CAP_SYS_ADMIN)) && + if ((creds->pid == task_tgid_vnr(current) || + ns_capable(current->nsproxy->pid_ns->user_ns, CAP_SYS_ADMIN)) && ((uid_eq(uid, cred->uid) || uid_eq(uid, cred->euid) || uid_eq(uid, cred->suid)) || nsown_capable(CAP_SETUID)) && ((gid_eq(gid, cred->gid) || gid_eq(gid, cred->egid) || diff --git a/net/core/sock.c b/net/core/sock.c index fe96c5d34299..b261a7977746 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -186,8 +186,10 @@ void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; +#if defined(CONFIG_MEMCG_KMEM) struct static_key memcg_socket_limit_enabled; EXPORT_SYMBOL(memcg_socket_limit_enabled); +#endif /* * Make lock validator output more readable. (we pre-construct these diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 602cd637182e..a29e90cf36b7 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -97,21 +97,6 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld) } EXPORT_SYMBOL_GPL(sock_diag_unregister); -static const inline struct sock_diag_handler *sock_diag_lock_handler(int family) -{ - if (sock_diag_handlers[family] == NULL) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_SOCK_DIAG, family); - - mutex_lock(&sock_diag_table_mutex); - return sock_diag_handlers[family]; -} - -static inline void sock_diag_unlock_handler(const struct sock_diag_handler *h) -{ - mutex_unlock(&sock_diag_table_mutex); -} - static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; @@ -121,12 +106,20 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlmsg_len(nlh) < sizeof(*req)) return -EINVAL; - hndl = sock_diag_lock_handler(req->sdiag_family); + if (req->sdiag_family >= AF_MAX) + return -EINVAL; + + if (sock_diag_handlers[req->sdiag_family] == NULL) + request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, req->sdiag_family); + + mutex_lock(&sock_diag_table_mutex); + hndl = sock_diag_handlers[req->sdiag_family]; if (hndl == NULL) err = -ENOENT; else err = hndl->dump(skb, nlh); - sock_diag_unlock_handler(hndl); + mutex_unlock(&sock_diag_table_mutex); return err; } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 1b588e23cf80..21291f1abcd6 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -284,6 +284,7 @@ static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh, if (!netdev->dcbnl_ops->getpermhwaddr) return -EOPNOTSUPP; + memset(perm_addr, 0, sizeof(perm_addr)); netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr); return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr); @@ -1042,6 +1043,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getets) { struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); err = ops->ieee_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets)) @@ -1050,6 +1052,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getmaxrate) { struct ieee_maxrate maxrate; + memset(&maxrate, 0, sizeof(maxrate)); err = ops->ieee_getmaxrate(netdev, &maxrate); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE, @@ -1061,6 +1064,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_getpfc) { struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc)) @@ -1094,6 +1098,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); err = ops->ieee_peer_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets)) @@ -1102,6 +1107,7 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->ieee_peer_getpfc) { struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc)) @@ -1280,6 +1286,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) /* peer info if available */ if (ops->cee_peer_getpg) { struct cee_pg pg; + memset(&pg, 0, sizeof(pg)); err = ops->cee_peer_getpg(netdev, &pg); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg)) @@ -1288,6 +1295,7 @@ static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) if (ops->cee_peer_getpfc) { struct cee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); err = ops->cee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc)) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index c4a2def5b7bd..c21f200eed93 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -175,12 +175,11 @@ static struct hlist_head *dn_find_list(struct sock *sk) static int check_port(__le16 port) { struct sock *sk; - struct hlist_node *node; if (port == 0) return -1; - sk_for_each(sk, node, &dn_sk_hash[le16_to_cpu(port) & DN_SK_HASH_MASK]) { + sk_for_each(sk, &dn_sk_hash[le16_to_cpu(port) & DN_SK_HASH_MASK]) { struct dn_scp *scp = DN_SK(sk); if (scp->addrloc == port) return -1; @@ -374,11 +373,10 @@ int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *sdn, struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr) { struct hlist_head *list = listen_hash(addr); - struct hlist_node *node; struct sock *sk; read_lock(&dn_hash_lock); - sk_for_each(sk, node, list) { + sk_for_each(sk, list) { struct dn_scp *scp = DN_SK(sk); if (sk->sk_state != TCP_LISTEN) continue; @@ -414,11 +412,10 @@ struct sock *dn_find_by_skb(struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct sock *sk; - struct hlist_node *node; struct dn_scp *scp; read_lock(&dn_hash_lock); - sk_for_each(sk, node, &dn_sk_hash[le16_to_cpu(cb->dst_port) & DN_SK_HASH_MASK]) { + sk_for_each(sk, &dn_sk_hash[le16_to_cpu(cb->dst_port) & DN_SK_HASH_MASK]) { scp = DN_SK(sk); if (cb->src != dn_saddr2dn(&scp->peer)) continue; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index f968c1b58f47..6c2445bcaba1 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -483,7 +483,6 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) unsigned int h, s_h; unsigned int e = 0, s_e; struct dn_fib_table *tb; - struct hlist_node *node; int dumped = 0; if (!net_eq(net, &init_net)) @@ -498,7 +497,7 @@ int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < DN_FIB_TABLE_HASHSZ; h++, s_h = 0) { e = 0; - hlist_for_each_entry(tb, node, &dn_fib_table_hash[h], hlist) { + hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) { if (e < s_e) goto next; if (dumped) @@ -828,7 +827,6 @@ out: struct dn_fib_table *dn_fib_get_table(u32 n, int create) { struct dn_fib_table *t; - struct hlist_node *node; unsigned int h; if (n < RT_TABLE_MIN) @@ -839,7 +837,7 @@ struct dn_fib_table *dn_fib_get_table(u32 n, int create) h = n & (DN_FIB_TABLE_HASHSZ - 1); rcu_read_lock(); - hlist_for_each_entry_rcu(t, node, &dn_fib_table_hash[h], hlist) { + hlist_for_each_entry_rcu(t, &dn_fib_table_hash[h], hlist) { if (t->n == n) { rcu_read_unlock(); return t; @@ -885,11 +883,10 @@ void dn_fib_flush(void) { int flushed = 0; struct dn_fib_table *tb; - struct hlist_node *node; unsigned int h; for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry(tb, node, &dn_fib_table_hash[h], hlist) + hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) flushed += tb->flush(tb); } @@ -908,12 +905,12 @@ void __init dn_fib_table_init(void) void __exit dn_fib_table_cleanup(void) { struct dn_fib_table *t; - struct hlist_node *node, *next; + struct hlist_node *next; unsigned int h; write_lock(&dn_fib_tables_lock); for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry_safe(t, node, next, &dn_fib_table_hash[h], + hlist_for_each_entry_safe(t, next, &dn_fib_table_hash[h], hlist) { hlist_del(&t->hlist); kfree(t); diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h index 8c2251fb0a3f..bba5f8336317 100644 --- a/net/ieee802154/6lowpan.h +++ b/net/ieee802154/6lowpan.h @@ -84,7 +84,7 @@ (memcmp(addr1, addr2, length >> 3) == 0) /* local link, i.e. FE80::/10 */ -#define is_addr_link_local(a) (((a)->s6_addr16[0]) == 0x80FE) +#define is_addr_link_local(a) (((a)->s6_addr16[0]) == htons(0xFE80)) /* * check whether we can compress the IID to 16 bits, diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 16705611589a..e0da175f8e5b 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -350,7 +350,6 @@ static inline int ieee802154_match_sock(u8 *hw_addr, u16 pan_id, int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) { struct sock *sk, *prev = NULL; - struct hlist_node *node; int ret = NET_RX_SUCCESS; u16 pan_id, short_addr; @@ -361,7 +360,7 @@ int ieee802154_dgram_deliver(struct net_device *dev, struct sk_buff *skb) short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev); read_lock(&dgram_lock); - sk_for_each(sk, node, &dgram_head) { + sk_for_each(sk, &dgram_head) { if (ieee802154_match_sock(dev->dev_addr, pan_id, short_addr, dgram_sk(sk))) { if (prev) { diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 50e823927d49..41f538b8e59c 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -221,10 +221,9 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) void ieee802154_raw_deliver(struct net_device *dev, struct sk_buff *skb) { struct sock *sk; - struct hlist_node *node; read_lock(&raw_lock); - sk_for_each(sk, node, &raw_head) { + sk_for_each(sk, &raw_head) { bh_lock_sock(sk); if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) { diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e225a4e5b572..c929d9c1c4b6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -248,8 +248,12 @@ EXPORT_SYMBOL(inet_listen); u32 inet_ehash_secret __read_mostly; EXPORT_SYMBOL(inet_ehash_secret); +u32 ipv6_hash_secret __read_mostly; +EXPORT_SYMBOL(ipv6_hash_secret); + /* - * inet_ehash_secret must be set exactly once + * inet_ehash_secret must be set exactly once, and to a non nul value + * ipv6_hash_secret must be set exactly once. */ void build_ehash_secret(void) { @@ -259,7 +263,8 @@ void build_ehash_secret(void) get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - cmpxchg(&inet_ehash_secret, 0, rnd); + if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0) + get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); } EXPORT_SYMBOL(build_ehash_secret); @@ -1327,8 +1332,9 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (skb->next != NULL) iph->frag_off |= htons(IP_MF); offset += (skb->len - skb->mac_len - iph->ihl * 4); - } else + } else { iph->id = htons(id++); + } iph->tot_len = htons(skb->len - skb->mac_len); iph->check = 0; iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl); @@ -1572,7 +1578,7 @@ static const struct net_offload udp_offload = { static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, - .err_handler = ping_err, + .err_handler = icmp_err, .no_policy = 1, .netns_ok = 1, }; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 5281314886c1..c6287cd978c2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -139,10 +139,9 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; - struct hlist_node *node; rcu_read_lock(); - hlist_for_each_entry_rcu(ifa, node, &inet_addr_lst[hash], hash) { + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) { if (ifa->ifa_local == addr) { struct net_device *dev = ifa->ifa_dev->dev; @@ -588,16 +587,17 @@ static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; - struct hlist_node *node; + struct hlist_node *n; int i; now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); - rcu_read_lock(); for (i = 0; i < IN4_ADDR_HSIZE; i++) { - hlist_for_each_entry_rcu(ifa, node, - &inet_addr_lst[i], hash) { + bool change_needed = false; + + rcu_read_lock(); + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) @@ -609,16 +609,7 @@ static void check_lifetime(struct work_struct *work) if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { - struct in_ifaddr **ifap ; - - rtnl_lock(); - for (ifap = &ifa->ifa_dev->ifa_list; - *ifap != NULL; ifap = &ifa->ifa_next) { - if (*ifap == ifa) - inet_del_ifa(ifa->ifa_dev, - ifap, 1); - } - rtnl_unlock(); + change_needed = true; } else if (ifa->ifa_preferred_lft == INFINITY_LIFE_TIME) { continue; @@ -628,10 +619,8 @@ static void check_lifetime(struct work_struct *work) next = ifa->ifa_tstamp + ifa->ifa_valid_lft * HZ; - if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) { - ifa->ifa_flags |= IFA_F_DEPRECATED; - rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); - } + if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) + change_needed = true; } else if (time_before(ifa->ifa_tstamp + ifa->ifa_preferred_lft * HZ, next)) { @@ -639,8 +628,42 @@ static void check_lifetime(struct work_struct *work) ifa->ifa_preferred_lft * HZ; } } + rcu_read_unlock(); + if (!change_needed) + continue; + rtnl_lock(); + hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) { + unsigned long age; + + if (ifa->ifa_flags & IFA_F_PERMANENT) + continue; + + /* We try to batch several events at once. */ + age = (now - ifa->ifa_tstamp + + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + + if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && + age >= ifa->ifa_valid_lft) { + struct in_ifaddr **ifap; + + for (ifap = &ifa->ifa_dev->ifa_list; + *ifap != NULL; ifap = &(*ifap)->ifa_next) { + if (*ifap == ifa) { + inet_del_ifa(ifa->ifa_dev, + ifap, 1); + break; + } + } + } else if (ifa->ifa_preferred_lft != + INFINITY_LIFE_TIME && + age >= ifa->ifa_preferred_lft && + !(ifa->ifa_flags & IFA_F_DEPRECATED)) { + ifa->ifa_flags |= IFA_F_DEPRECATED; + rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); + } + } + rtnl_unlock(); } - rcu_read_unlock(); next_sec = round_jiffies_up(next); next_sched = next; @@ -805,8 +828,12 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) return -EEXIST; - - set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft); + ifa = ifa_existing; + set_ifa_lifetime(ifa, valid_lft, prefered_lft); + cancel_delayed_work(&check_lifetime_work); + schedule_delayed_work(&check_lifetime_work, 0); + rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); + blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); } return 0; } @@ -1493,7 +1520,6 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) struct in_device *in_dev; struct in_ifaddr *ifa; struct hlist_head *head; - struct hlist_node *node; s_h = cb->args[0]; s_idx = idx = cb->args[1]; @@ -1503,7 +1529,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (h > s_h || idx > s_idx) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 3b4f0cd2e63e..4cfe34d4cc96 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -139,8 +139,6 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) /* skb is pure payload to encrypt */ - err = -ENOMEM; - esp = x->data; aead = esp->aead; alen = crypto_aead_authsize(aead); @@ -176,8 +174,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) } tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen); - if (!tmp) + if (!tmp) { + err = -ENOMEM; goto error; + } seqhi = esp_tmp_seqhi(tmp); iv = esp_tmp_iv(aead, tmp, seqhilen); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 99f00d39d10b..eb4bb12b3eb4 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -112,7 +112,6 @@ struct fib_table *fib_new_table(struct net *net, u32 id) struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; unsigned int h; @@ -122,7 +121,7 @@ struct fib_table *fib_get_table(struct net *net, u32 id) rcu_read_lock(); head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (tb->tb_id == id) { rcu_read_unlock(); return tb; @@ -137,13 +136,12 @@ static void fib_flush(struct net *net) { int flushed = 0; struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, node, head, tb_hlist) + hlist_for_each_entry(tb, head, tb_hlist) flushed += fib_table_flush(tb); } @@ -656,7 +654,6 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; - struct hlist_node *node; struct hlist_head *head; int dumped = 0; @@ -670,7 +667,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry(tb, node, head, tb_hlist) { + hlist_for_each_entry(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) @@ -1117,11 +1114,11 @@ static void ip_fib_net_exit(struct net *net) for (i = 0; i < FIB_TABLE_HASHSZ; i++) { struct fib_table *tb; struct hlist_head *head; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; head = &net->ipv4.fib_table_hash[i]; - hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) { - hlist_del(node); + hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { + hlist_del(&tb->tb_hlist); fib_table_flush(tb); fib_free_table(tb); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 4797a800faf8..8f6cb7a87cd6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -298,14 +298,13 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi) static struct fib_info *fib_find_info(const struct fib_info *nfi) { struct hlist_head *head; - struct hlist_node *node; struct fib_info *fi; unsigned int hash; hash = fib_info_hashfn(nfi); head = &fib_info_hash[hash]; - hlist_for_each_entry(fi, node, head, fib_hash) { + hlist_for_each_entry(fi, head, fib_hash) { if (!net_eq(fi->fib_net, nfi->fib_net)) continue; if (fi->fib_nhs != nfi->fib_nhs) @@ -331,7 +330,6 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; - struct hlist_node *node; struct fib_nh *nh; unsigned int hash; @@ -339,7 +337,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) hash = fib_devindex_hashfn(dev->ifindex); head = &fib_info_devhash[hash]; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { if (nh->nh_dev == dev && nh->nh_gw == gw && !(nh->nh_flags & RTNH_F_DEAD)) { @@ -721,10 +719,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, for (i = 0; i < old_size; i++) { struct hlist_head *head = &fib_info_hash[i]; - struct hlist_node *node, *n; + struct hlist_node *n; struct fib_info *fi; - hlist_for_each_entry_safe(fi, node, n, head, fib_hash) { + hlist_for_each_entry_safe(fi, n, head, fib_hash) { struct hlist_head *dest; unsigned int new_hash; @@ -739,10 +737,10 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, for (i = 0; i < old_size; i++) { struct hlist_head *lhead = &fib_info_laddrhash[i]; - struct hlist_node *node, *n; + struct hlist_node *n; struct fib_info *fi; - hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) { + hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) { struct hlist_head *ldest; unsigned int new_hash; @@ -1096,13 +1094,12 @@ int fib_sync_down_addr(struct net *net, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; - struct hlist_node *node; struct fib_info *fi; if (fib_info_laddrhash == NULL || local == 0) return 0; - hlist_for_each_entry(fi, node, head, fib_lhash) { + hlist_for_each_entry(fi, head, fib_lhash) { if (!net_eq(fi->fib_net, net)) continue; if (fi->fib_prefsrc == local) { @@ -1120,13 +1117,12 @@ int fib_sync_down_dev(struct net_device *dev, int force) struct fib_info *prev_fi = NULL; unsigned int hash = fib_devindex_hashfn(dev->ifindex); struct hlist_head *head = &fib_info_devhash[hash]; - struct hlist_node *node; struct fib_nh *nh; if (force) scope = -1; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int dead; @@ -1232,7 +1228,6 @@ int fib_sync_up(struct net_device *dev) struct fib_info *prev_fi; unsigned int hash; struct hlist_head *head; - struct hlist_node *node; struct fib_nh *nh; int ret; @@ -1244,7 +1239,7 @@ int fib_sync_up(struct net_device *dev) head = &fib_info_devhash[hash]; ret = 0; - hlist_for_each_entry(nh, node, head, nh_hash) { + hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int alive; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 61e03da3e1f5..ff06b7543d9f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -920,10 +920,9 @@ nomem: static struct leaf_info *find_leaf_info(struct leaf *l, int plen) { struct hlist_head *head = &l->list; - struct hlist_node *node; struct leaf_info *li; - hlist_for_each_entry_rcu(li, node, head, hlist) + hlist_for_each_entry_rcu(li, head, hlist) if (li->plen == plen) return li; @@ -943,12 +942,11 @@ static inline struct list_head *get_fa_head(struct leaf *l, int plen) static void insert_leaf_info(struct hlist_head *head, struct leaf_info *new) { struct leaf_info *li = NULL, *last = NULL; - struct hlist_node *node; if (hlist_empty(head)) { hlist_add_head_rcu(&new->hlist, head); } else { - hlist_for_each_entry(li, node, head, hlist) { + hlist_for_each_entry(li, head, hlist) { if (new->plen > li->plen) break; @@ -1354,9 +1352,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, { struct leaf_info *li; struct hlist_head *hhead = &l->list; - struct hlist_node *node; - hlist_for_each_entry_rcu(li, node, hhead, hlist) { + hlist_for_each_entry_rcu(li, hhead, hlist) { struct fib_alias *fa; if (l->key != (key & li->mask_plen)) @@ -1740,10 +1737,10 @@ static int trie_flush_leaf(struct leaf *l) { int found = 0; struct hlist_head *lih = &l->list; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct leaf_info *li = NULL; - hlist_for_each_entry_safe(li, node, tmp, lih, hlist) { + hlist_for_each_entry_safe(li, tmp, lih, hlist) { found += trie_flush_list(&li->falh); if (list_empty(&li->falh)) { @@ -1895,14 +1892,13 @@ static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) { struct leaf_info *li; - struct hlist_node *node; int i, s_i; s_i = cb->args[4]; i = 0; /* rcu_read_lock is hold by caller */ - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { if (i < s_i) { i++; continue; @@ -2092,14 +2088,13 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s) if (IS_LEAF(n)) { struct leaf *l = (struct leaf *)n; struct leaf_info *li; - struct hlist_node *tmp; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; - hlist_for_each_entry_rcu(li, tmp, &l->list, hlist) + hlist_for_each_entry_rcu(li, &l->list, hlist) ++s->prefixes; } else { const struct tnode *tn = (const struct tnode *) n; @@ -2200,10 +2195,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; @@ -2245,10 +2239,9 @@ static struct rt_trie_node *fib_trie_get_idx(struct seq_file *seq, loff_t pos) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *node; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct rt_trie_node *n; for (n = fib_trie_get_first(iter, @@ -2298,7 +2291,7 @@ static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, tb_node, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; @@ -2381,13 +2374,12 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) } else { struct leaf *l = (struct leaf *) n; struct leaf_info *li; - struct hlist_node *node; __be32 val = htonl(l->key); seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; list_for_each_entry_rcu(fa, &li->falh, fa_list) { @@ -2532,7 +2524,6 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct leaf *l = v; struct leaf_info *li; - struct hlist_node *node; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " @@ -2541,7 +2532,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) return 0; } - hlist_for_each_entry_rcu(li, node, &l->list, hlist) { + hlist_for_each_entry_rcu(li, &l->list, hlist) { struct fib_alias *fa; __be32 mask, prefix; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 17ff9fd7cdda..3ac5dff79627 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -934,6 +934,29 @@ error: goto drop; } +void icmp_err(struct sk_buff *skb, u32 info) +{ + struct iphdr *iph = (struct iphdr *)skb->data; + struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; + struct net *net = dev_net(skb->dev); + + /* + * Use ping_err to handle all icmp errors except those + * triggered by ICMP_ECHOREPLY which sent from kernel. + */ + if (icmph->type != ICMP_ECHOREPLY) { + ping_err(skb, info); + return; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ICMP, 0); + else if (type == ICMP_REDIRECT) + ipv4_redirect(skb, net, 0, 0, IPPROTO_ICMP, 0); +} + /* * This table is the definition of how we handle ICMP. */ diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 11cb4979a465..786d97aee751 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -57,7 +57,6 @@ int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax) { struct sock *sk2; - struct hlist_node *node; int reuse = sk->sk_reuse; int reuseport = sk->sk_reuseport; kuid_t uid = sock_i_uid((struct sock *)sk); @@ -69,7 +68,7 @@ int inet_csk_bind_conflict(const struct sock *sk, * one this bucket belongs to. */ - sk_for_each_bound(sk2, node, &tb->owners) { + sk_for_each_bound(sk2, &tb->owners) { if (sk != sk2 && !inet_v6_ipv6only(sk2) && (!sk->sk_bound_dev_if || @@ -95,7 +94,7 @@ int inet_csk_bind_conflict(const struct sock *sk, } } } - return node != NULL; + return sk2 != NULL; } EXPORT_SYMBOL_GPL(inet_csk_bind_conflict); @@ -106,7 +105,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_bind_hashbucket *head; - struct hlist_node *node; struct inet_bind_bucket *tb; int ret, attempts = 5; struct net *net = sock_net(sk); @@ -129,7 +127,7 @@ again: head = &hashinfo->bhash[inet_bhashfn(net, rover, hashinfo->bhash_size)]; spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) + inet_bind_bucket_for_each(tb, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == rover) { if (((tb->fastreuse > 0 && sk->sk_reuse && @@ -183,7 +181,7 @@ have_snum: head = &hashinfo->bhash[inet_bhashfn(net, snum, hashinfo->bhash_size)]; spin_lock(&head->lock); - inet_bind_bucket_for_each(tb, node, &head->chain) + inet_bind_bucket_for_each(tb, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == snum) goto tb_found; } @@ -737,6 +735,7 @@ EXPORT_SYMBOL(inet_csk_destroy_sock); * tcp/dccp_create_openreq_child(). */ void inet_csk_prepare_forced_close(struct sock *sk) + __releases(&sk->sk_lock.slock) { /* sk_clone_lock locked the socket and set refcnt to 2 */ bh_unlock_sock(sk); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 2e453bde6992..f4fd23de9b13 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -21,6 +21,7 @@ #include <linux/rtnetlink.h> #include <linux/slab.h> +#include <net/sock.h> #include <net/inet_frag.h> static void inet_frag_secret_rebuild(unsigned long dummy) @@ -33,9 +34,9 @@ static void inet_frag_secret_rebuild(unsigned long dummy) get_random_bytes(&f->rnd, sizeof(u32)); for (i = 0; i < INETFRAGS_HASHSZ; i++) { struct inet_frag_queue *q; - struct hlist_node *p, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(q, p, n, &f->hash[i], list) { + hlist_for_each_entry_safe(q, n, &f->hash[i], list) { unsigned int hval = f->hashfn(q); if (hval != i) { @@ -203,7 +204,6 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, { struct inet_frag_queue *qp; #ifdef CONFIG_SMP - struct hlist_node *n; #endif unsigned int hash; @@ -219,7 +219,7 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, * such entry could be created on other cpu, while we * promoted read lock to write lock. */ - hlist_for_each_entry(qp, n, &f->hash[hash], list) { + hlist_for_each_entry(qp, &f->hash[hash], list) { if (qp->net == nf && f->match(qp, arg)) { atomic_inc(&qp->refcnt); write_unlock(&f->lock); @@ -278,17 +278,33 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, __releases(&f->lock) { struct inet_frag_queue *q; - struct hlist_node *n; + int depth = 0; - hlist_for_each_entry(q, n, &f->hash[hash], list) { + hlist_for_each_entry(q, &f->hash[hash], list) { if (q->net == nf && f->match(q, key)) { atomic_inc(&q->refcnt); read_unlock(&f->lock); return q; } + depth++; } read_unlock(&f->lock); - return inet_frag_create(nf, f, key); + if (depth <= INETFRAGS_MAXDEPTH) + return inet_frag_create(nf, f, key); + else + return ERR_PTR(-ENOBUFS); } EXPORT_SYMBOL(inet_frag_find); + +void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, + const char *prefix) +{ + static const char msg[] = "inet_frag_find: Fragment hash bucket" + " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH) + ". Dropping fragment.\n"; + + if (PTR_ERR(q) == -ENOBUFS) + LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg); +} +EXPORT_SYMBOL(inet_frag_maybe_warn_overflow); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0ce0595d9861..6af375afeeef 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -120,13 +120,12 @@ int __inet_inherit_port(struct sock *sk, struct sock *child) * that the listener socket's icsk_bind_hash is the same * as that of the child socket. We have to look up or * create a new bind bucket for the child here. */ - struct hlist_node *node; - inet_bind_bucket_for_each(tb, node, &head->chain) { + inet_bind_bucket_for_each(tb, &head->chain) { if (net_eq(ib_net(tb), sock_net(sk)) && tb->port == port) break; } - if (!node) { + if (!tb) { tb = inet_bind_bucket_create(table->bind_bucket_cachep, sock_net(sk), head, port); if (!tb) { @@ -493,7 +492,6 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, int i, remaining, low, high, port; static u32 hint; u32 offset = hint + port_offset; - struct hlist_node *node; struct inet_timewait_sock *tw = NULL; inet_get_local_port_range(&low, &high); @@ -512,7 +510,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, * because the established check is already * unique enough. */ - inet_bind_bucket_for_each(tb, node, &head->chain) { + inet_bind_bucket_for_each(tb, &head->chain) { if (net_eq(ib_net(tb), net) && tb->port == port) { if (tb->fastreuse >= 0 || diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2784db3155fb..1f27c9f4afd0 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -216,7 +216,6 @@ static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr, const int slot) { struct inet_timewait_sock *tw; - struct hlist_node *node; unsigned int killed; int ret; @@ -229,7 +228,7 @@ static int inet_twdr_do_twkill_work(struct inet_timewait_death_row *twdr, killed = 0; ret = 0; rescan: - inet_twsk_for_each_inmate(tw, node, &twdr->cells[slot]) { + inet_twsk_for_each_inmate(tw, &twdr->cells[slot]) { __inet_twsk_del_dead_node(tw); spin_unlock(&twdr->death_lock); __inet_twsk_kill(tw, twdr->hashinfo); @@ -438,10 +437,10 @@ void inet_twdr_twcal_tick(unsigned long data) for (n = 0; n < INET_TWDR_RECYCLE_SLOTS; n++) { if (time_before_eq(j, now)) { - struct hlist_node *node, *safe; + struct hlist_node *safe; struct inet_timewait_sock *tw; - inet_twsk_for_each_inmate_safe(tw, node, safe, + inet_twsk_for_each_inmate_safe(tw, safe, &twdr->twcal_row[slot]) { __inet_twsk_del_dead_node(tw); __inet_twsk_kill(tw, twdr->hashinfo); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b6d30acb600c..52c273ea05c3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -248,8 +248,7 @@ static void ip_expire(unsigned long arg) if (!head->dev) goto out_rcu_unlock; - /* skb dst is stale, drop it, and perform route lookup again */ - skb_dst_drop(head); + /* skb has no dst, perform route lookup again */ iph = ip_hdr(head); err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); @@ -292,14 +291,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); - if (q == NULL) - goto out_nomem; - + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } return container_of(q, struct ipq, q); - -out_nomem: - LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n")); - return NULL; } /* Is the fragment too far ahead to be part of ipq? */ @@ -526,9 +522,16 @@ found: qp->q.max_size = skb->len + ihl; if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - qp->q.meat == qp->q.len) - return ip_frag_reasm(qp, prev, dev); + qp->q.meat == qp->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + err = ip_frag_reasm(qp, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + skb_dst_drop(skb); inet_frag_lru_move(&qp->q); return -EINPROGRESS; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5ef4da780ac1..91d66dbde9c0 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -735,7 +735,7 @@ drop: return 0; } -static struct sk_buff *handle_offloads(struct sk_buff *skb) +static struct sk_buff *handle_offloads(struct ip_tunnel *tunnel, struct sk_buff *skb) { int err; @@ -745,8 +745,12 @@ static struct sk_buff *handle_offloads(struct sk_buff *skb) goto error; skb_shinfo(skb)->gso_type |= SKB_GSO_GRE; return skb; - } - if (skb->ip_summed != CHECKSUM_PARTIAL) + } else if (skb->ip_summed == CHECKSUM_PARTIAL && + tunnel->parms.o_flags&GRE_CSUM) { + err = skb_checksum_help(skb); + if (unlikely(err)) + goto error; + } else if (skb->ip_summed != CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_NONE; return skb; @@ -776,7 +780,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev int err; int pkt_len; - skb = handle_offloads(skb); + skb = handle_offloads(tunnel, skb); if (IS_ERR(skb)) { dev->stats.tx_dropped++; return NETDEV_TX_OK; @@ -794,10 +798,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (dev->header_ops && dev->type == ARPHRD_IPGRE) { gre_hlen = 0; - if (skb->protocol == htons(ETH_P_IP)) - tiph = (const struct iphdr *)skb->data; - else - tiph = &tunnel->parms.iph; + tiph = (const struct iphdr *)skb->data; } else { gre_hlen = tunnel->hlen; tiph = &tunnel->parms.iph; @@ -970,7 +971,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ttl; - iph->id = 0; + + tunnel_ip_select_ident(skb, old_iph, &rt->dst); if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) @@ -1101,14 +1103,8 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) tunnel->hlen = addend; /* TCP offload with GRE SEQ is not supported. */ if (!(tunnel->parms.o_flags & GRE_SEQ)) { - /* device supports enc gso offload*/ - if (tdev->hw_enc_features & NETIF_F_GRE_GSO) { - dev->features |= NETIF_F_TSO; - dev->hw_features |= NETIF_F_TSO; - } else { - dev->features |= NETIF_F_GSO_SOFTWARE; - dev->hw_features |= NETIF_F_GSO_SOFTWARE; - } + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; } return mtu; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 87abd3e2bd32..2bdf802e28e2 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -228,9 +228,11 @@ static int ip_local_deliver_finish(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); } - } else + kfree_skb(skb); + } else { IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS); - kfree_skb(skb); + consume_skb(skb); + } } } out: diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index f6289bf6f332..ec7264514a82 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -370,7 +370,6 @@ int ip_options_compile(struct net *net, } switch (optptr[3]&0xF) { case IPOPT_TS_TSONLY: - opt->ts = optptr - iph; if (skb) timeptr = &optptr[optptr[2]-1]; opt->ts_needtime = 1; @@ -381,7 +380,6 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - opt->ts = optptr - iph; if (rt) { spec_dst_fill(&spec_dst, skb); memcpy(&optptr[optptr[2]-1], &spec_dst, 4); @@ -396,7 +394,6 @@ int ip_options_compile(struct net *net, pp_ptr = optptr + 2; goto error; } - opt->ts = optptr - iph; { __be32 addr; memcpy(&addr, &optptr[optptr[2]-1], 4); @@ -423,18 +420,18 @@ int ip_options_compile(struct net *net, put_unaligned_be32(midtime, timeptr); opt->is_changed = 1; } - } else { + } else if ((optptr[3]&0xF) != IPOPT_TS_PRESPEC) { unsigned int overflow = optptr[3]>>4; if (overflow == 15) { pp_ptr = optptr + 3; goto error; } - opt->ts = optptr - iph; if (skb) { optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4); opt->is_changed = 1; } } + opt->ts = optptr - iph; break; case IPOPT_RA: if (optlen < 4) { diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 98cbc6877019..bf6c5cf31aed 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1522,7 +1522,8 @@ static int __init ip_auto_config(void) } for (i++; i < CONF_NAMESERVERS_MAX; i++) if (ic_nameservers[i] != NONE) - pr_cont(", nameserver%u=%pI4\n", i, &ic_nameservers[i]); + pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]); + pr_cont("\n"); #endif /* !SILENT */ return 0; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index ce2d43e1f09f..0d755c50994b 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -36,19 +36,6 @@ config NF_CONNTRACK_PROC_COMPAT If unsure, say Y. -config IP_NF_QUEUE - tristate "IP Userspace queueing via NETLINK (OBSOLETE)" - depends on NETFILTER_ADVANCED - help - Netfilter has the ability to queue packets to user space: the - netlink device can be used to access them using this driver. - - This option enables the old IPv4-only "ip_queue" implementation - which has been obsoleted by the new "nfnetlink_queue" code (see - CONFIG_NETFILTER_NETLINK_QUEUE). - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 75e33a7048f8..5852b249054f 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -657,7 +657,7 @@ static int clusterip_proc_release(struct inode *inode, struct file *file) static ssize_t clusterip_proc_write(struct file *file, const char __user *input, size_t size, loff_t *ofs) { - struct clusterip_config *c = PDE(file->f_path.dentry->d_inode)->data; + struct clusterip_config *c = PDE(file_inode(file))->data; #define PROC_WRITELEN 10 char buffer[PROC_WRITELEN+1]; unsigned long nodenum; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index c30130062cd6..c49dcd0284a0 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -66,6 +66,12 @@ static bool rpfilter_lookup_reverse(struct flowi4 *fl4, return dev_match; } +static bool rpfilter_is_local(const struct sk_buff *skb) +{ + const struct rtable *rt = skb_rtable(skb); + return rt && (rt->rt_flags & RTCF_LOCAL); +} + static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rpfilter_info *info; @@ -76,7 +82,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) info = par->matchinfo; invert = info->flags & XT_RPFILTER_INVERT; - if (par->in->flags & IFF_LOOPBACK) + if (rpfilter_is_local(skb)) return true ^ invert; iph = ip_hdr(skb); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 55c4ee1bba06..2e91006d6076 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -322,8 +322,8 @@ void ping_err(struct sk_buff *skb, u32 info) struct iphdr *iph = (struct iphdr *)skb->data; struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2)); struct inet_sock *inet_sock; - int type = icmph->type; - int code = icmph->code; + int type = icmp_hdr(skb)->type; + int code = icmp_hdr(skb)->code; struct net *net = dev_net(skb->dev); struct sock *sk; int harderr; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 53ddebc292b6..dd44e0ab600c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -111,9 +111,7 @@ EXPORT_SYMBOL_GPL(raw_unhash_sk); static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, unsigned short num, __be32 raddr, __be32 laddr, int dif) { - struct hlist_node *node; - - sk_for_each_from(sk, node) { + sk_for_each_from(sk) { struct inet_sock *inet = inet_sk(sk); if (net_eq(sock_net(sk), net) && inet->inet_num == num && @@ -914,9 +912,7 @@ static struct sock *raw_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { - struct hlist_node *node; - - sk_for_each(sk, node, &state->h->ht[state->bucket]) + sk_for_each(sk, &state->h->ht[state->bucket]) if (sock_net(sk) == seq_file_net(seq)) goto found; } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index ef54377fb11c..397e0f69435f 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -349,8 +349,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * hasn't changed since we received the original syn, but I see * no easy way to do this. */ - flowi4_init_output(&fl4, 0, sk->sk_mark, RT_CONN_FLAGS(sk), - RT_SCOPE_UNIVERSE, IPPROTO_TCP, + flowi4_init_output(&fl4, sk->sk_bound_dev_if, sk->sk_mark, + RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP, inet_sk_flowi_flags(sk), (opt && opt->srr) ? opt->faddr : ireq->rmt_addr, ireq->loc_addr, th->source, th->dest); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7a5ba48c2cc9..e22020790709 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -775,7 +775,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp) * Make sure that we have exactly size bytes * available to the caller, no more, no less. */ - skb->avail_size = size; + skb->reserved_tailroom = skb->end - skb->tail - size; return skb; } __kfree_skb(skb); @@ -1409,10 +1409,10 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) return; last_issued = tp->ucopy.dma_cookie; - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); do { - if (dma_async_memcpy_complete(tp->ucopy.dma_chan, + if (dma_async_is_tx_complete(tp->ucopy.dma_chan, last_issued, &done, &used) == DMA_SUCCESS) { /* Safe to free early-copied skbs now */ @@ -1754,7 +1754,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, tcp_service_net_dma(sk, true); tcp_cleanup_rbuf(sk, copied); } else - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); } #endif if (copied >= target) { @@ -1847,7 +1847,7 @@ do_prequeue: break; } - dma_async_memcpy_issue_pending(tp->ucopy.dma_chan); + dma_async_issue_pending(tp->ucopy.dma_chan); if ((offset + used) == skb->len) copied_early = true; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a759e19496d2..13b9c08fc158 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -113,6 +113,7 @@ int sysctl_tcp_early_retrans __read_mostly = 2; #define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */ #define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */ #define FLAG_SACK_RENEGING 0x2000 /* snd_una advanced to a sacked seq */ +#define FLAG_UPDATE_TS_RECENT 0x4000 /* tcp_replace_ts_recent() */ #define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED) #define FLAG_NOT_DUP (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED) @@ -2059,11 +2060,8 @@ void tcp_enter_loss(struct sock *sk, int how) if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); - if (!how) { - /* Push undo marker, if it was plain RTO and nothing - * was retransmitted. */ - tp->undo_marker = tp->snd_una; - } else { + tp->undo_marker = tp->snd_una; + if (how) { tp->sacked_out = 0; tp->fackets_out = 0; } @@ -3567,6 +3565,27 @@ static void tcp_send_challenge_ack(struct sock *sk) } } +static void tcp_store_ts_recent(struct tcp_sock *tp) +{ + tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; + tp->rx_opt.ts_recent_stamp = get_seconds(); +} + +static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) +{ + if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { + /* PAWS bug workaround wrt. ACK frames, the PAWS discard + * extra check below makes sure this can only happen + * for pure ACK frames. -DaveM + * + * Not only, also it occurs for expired timestamps. + */ + + if (tcp_paws_check(&tp->rx_opt, 0)) + tcp_store_ts_recent(tp); + } +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3610,6 +3629,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); + /* ts_recent update must be made after we are sure that the packet + * is in window. + */ + if (flag & FLAG_UPDATE_TS_RECENT) + tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); + if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) { /* Window is constant, pure forward advance. * No more checks are required. @@ -3930,27 +3955,6 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) EXPORT_SYMBOL(tcp_parse_md5sig_option); #endif -static inline void tcp_store_ts_recent(struct tcp_sock *tp) -{ - tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval; - tp->rx_opt.ts_recent_stamp = get_seconds(); -} - -static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) -{ - if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) { - /* PAWS bug workaround wrt. ACK frames, the PAWS discard - * extra check below makes sure this can only happen - * for pure ACK frames. -DaveM - * - * Not only, also it occurs for expired timestamps. - */ - - if (tcp_paws_check(&tp->rx_opt, 0)) - tcp_store_ts_recent(tp); - } -} - /* Sorry, PAWS as specified is broken wrt. pure-ACKs -DaveM * * It is not fatal. If this ACK does _not_ change critical state (seqs, window) @@ -5485,6 +5489,9 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, if (tcp_checksum_complete_user(sk, skb)) goto csum_error; + if ((int)skb->truesize > sk->sk_forward_alloc) + goto step5; + /* Predicted packet is in window by definition. * seq == rcv_nxt and rcv_wup <= rcv_nxt. * Hence, check seq<=rcv_wup reduces to: @@ -5496,9 +5503,6 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); - if ((int)skb->truesize > sk->sk_forward_alloc) - goto step5; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ @@ -5546,14 +5550,9 @@ slow_path: return 0; step5: - if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) + if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0) goto discard; - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - tcp_rcv_rtt_measure_ts(sk, skb); /* Process urgent data. */ @@ -5989,7 +5988,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* step 5: check the ACK field */ if (true) { - int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0; + int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH | + FLAG_UPDATE_TS_RECENT) > 0; switch (sk->sk_state) { case TCP_SYN_RECV: @@ -6140,11 +6140,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } } - /* ts_recent update must be made after we are sure that the packet - * is in window. - */ - tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq); - /* step 6: check the URG bit */ tcp_urg(sk, skb, th); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 145d3bf8df86..d09203c63264 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -274,13 +274,6 @@ static void tcp_v4_mtu_reduced(struct sock *sk) struct inet_sock *inet = inet_sk(sk); u32 mtu = tcp_sk(sk)->mtu_info; - /* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs - * send out by Linux are always <576bytes so they should go through - * unfragmented). - */ - if (sk->sk_state == TCP_LISTEN) - return; - dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -408,6 +401,13 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ + /* We are not interested in TCP_LISTEN and open_requests + * (SYN-ACKs send out by Linux are always <576bytes so + * they should go through unfragmented). + */ + if (sk->sk_state == TCP_LISTEN) + goto out; + tp->mtu_info = info; if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); @@ -954,7 +954,6 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos; unsigned int size = sizeof(struct in_addr); struct tcp_md5sig_info *md5sig; @@ -968,7 +967,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, if (family == AF_INET6) size = sizeof(struct in6_addr); #endif - hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; if (!memcmp(&key->addr, addr, size)) @@ -1069,14 +1068,14 @@ static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; - struct hlist_node *pos, *n; + struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); if (!hlist_empty(&md5sig->head)) tcp_free_md5sig_pool(); - hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) { + hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fd0cea114b5d..509912a5ff98 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1298,7 +1298,6 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); - skb->avail_size -= eat; len -= eat; if (!len) return; @@ -1351,8 +1350,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) return 0; } -/* Calculate MSS. Not accounting for SACKs here. */ -int tcp_mtu_to_mss(struct sock *sk, int pmtu) +/* Calculate MSS not accounting any TCP options. */ +static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1381,13 +1380,17 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) /* Then reserve room for full set of TCP options and 8 bytes of data */ if (mss_now < 48) mss_now = 48; - - /* Now subtract TCP options size, not including SACKs */ - mss_now -= tp->tcp_header_len - sizeof(struct tcphdr); - return mss_now; } +/* Calculate MSS. Not accounting for SACKs here. */ +int tcp_mtu_to_mss(struct sock *sk, int pmtu) +{ + /* Subtract TCP options size, not including SACKs */ + return __tcp_mtu_to_mss(sk, pmtu) - + (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); +} + /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { @@ -1806,8 +1809,11 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) goto send_now; } - /* Ok, it looks like it is advisable to defer. */ - tp->tso_deferred = 1 | (jiffies << 1); + /* Ok, it looks like it is advisable to defer. + * Do not rearm the timer if already set to not break TCP ACK clocking. + */ + if (!tp->tso_deferred) + tp->tso_deferred = 1 | (jiffies << 1); return true; @@ -2382,8 +2388,12 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - /* make sure skb->data is aligned on arches that require it */ - if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { + /* make sure skb->data is aligned on arches that require it + * and check if ack-trimming & collapsing extended the headroom + * beyond what csum_start can cover. + */ + if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || + skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : @@ -2703,6 +2713,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_reserve(skb, MAX_TCP_HEADER); skb_dst_set(skb, dst); + security_skb_owned_by(skb, sk); mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) @@ -2930,7 +2941,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) */ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; - space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; syn_data = skb_copy_expand(syn, skb_headroom(syn), space, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 265c42cf963c..0a073a263720 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1762,9 +1762,16 @@ int udp_rcv(struct sk_buff *skb) void udp_destroy_sock(struct sock *sk) { + struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); + if (static_key_false(&udp_encap_needed) && up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = ACCESS_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } } /* diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4dc0d44a5d31..dae802c0af7c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -168,8 +168,6 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev); -static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); - static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, @@ -837,7 +835,7 @@ out2: rcu_read_unlock_bh(); if (likely(err == 0)) - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); ifa = ERR_PTR(err); @@ -927,7 +925,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ipv6_ifa_notify(RTM_DELADDR, ifp); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifp); /* * Purge or update corresponding prefix @@ -1419,11 +1417,10 @@ int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { struct inet6_ifaddr *ifp; - struct hlist_node *node; unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); - hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -1445,9 +1442,8 @@ static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, { unsigned int hash = inet6_addr_hash(addr); struct inet6_ifaddr *ifp; - struct hlist_node *node; - hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -1487,10 +1483,9 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add { struct inet6_ifaddr *ifp, *result = NULL; unsigned int hash = inet6_addr_hash(addr); - struct hlist_node *node; rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, node, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -2532,6 +2527,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) static void init_loopback(struct net_device *dev) { struct inet6_dev *idev; + struct net_device *sp_dev; + struct inet6_ifaddr *sp_ifa; + struct rt6_info *sp_rt; /* ::1 */ @@ -2543,6 +2541,30 @@ static void init_loopback(struct net_device *dev) } add_addr(idev, &in6addr_loopback, 128, IFA_HOST); + + /* Add routes to other interface's IPv6 addresses */ + for_each_netdev(dev_net(dev), sp_dev) { + if (!strcmp(sp_dev->name, dev->name)) + continue; + + idev = __in6_dev_get(sp_dev); + if (!idev) + continue; + + read_lock_bh(&idev->lock); + list_for_each_entry(sp_ifa, &idev->addr_list, if_list) { + + if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE)) + continue; + + sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0); + + /* Failure cases are ignored */ + if (!IS_ERR(sp_rt)) + ip6_ins_rt(sp_rt); + } + read_unlock_bh(&idev->lock); + } } static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr *addr) @@ -2907,11 +2929,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; - struct hlist_node *n; spin_lock_bh(&addrconf_hash_lock); restart: - hlist_for_each_entry_rcu(ifa, n, h, addr_lst) { + hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_timer(ifa); @@ -2965,7 +2986,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } in6_ifa_put(ifa); @@ -3218,8 +3239,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos) } for (; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - struct hlist_node *n; - hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket], + hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -3244,9 +3264,8 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - struct hlist_node *n = &ifa->addr_lst; - hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) { + hlist_for_each_entry_continue_rcu_bh(ifa, addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; state->offset++; @@ -3255,7 +3274,7 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, while (++state->bucket < IN6_ADDR_HSIZE) { state->offset = 0; - hlist_for_each_entry_rcu_bh(ifa, n, + hlist_for_each_entry_rcu_bh(ifa, &inet6_addr_lst[state->bucket], addr_lst) { if (!net_eq(dev_net(ifa->idev->dev), net)) continue; @@ -3357,11 +3376,10 @@ int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr) { int ret = 0; struct inet6_ifaddr *ifp = NULL; - struct hlist_node *n; unsigned int hash = inet6_addr_hash(addr); rcu_read_lock_bh(); - hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) { + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -3383,7 +3401,6 @@ static void addrconf_verify(unsigned long foo) { unsigned long now, next, next_sec, next_sched; struct inet6_ifaddr *ifp; - struct hlist_node *node; int i; rcu_read_lock_bh(); @@ -3395,7 +3412,7 @@ static void addrconf_verify(unsigned long foo) for (i = 0; i < IN6_ADDR_HSIZE; i++) { restart: - hlist_for_each_entry_rcu_bh(ifp, node, + hlist_for_each_entry_rcu_bh(ifp, &inet6_addr_lst[i], addr_lst) { unsigned long age; @@ -3866,7 +3883,6 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; - struct hlist_node *node; s_h = cb->args[0]; s_idx = idx = cb->args[1]; @@ -3876,7 +3892,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (h > s_h || idx > s_idx) @@ -4222,7 +4238,6 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct inet6_dev *idev; struct hlist_head *head; - struct hlist_node *node; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -4231,7 +4246,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; idev = __in6_dev_get(dev); @@ -4794,26 +4809,20 @@ static void addrconf_sysctl_unregister(struct inet6_dev *idev) static int __net_init addrconf_init_net(struct net *net) { - int err; + int err = -ENOMEM; struct ipv6_devconf *all, *dflt; - err = -ENOMEM; - all = &ipv6_devconf; - dflt = &ipv6_devconf_dflt; + all = kmemdup(&ipv6_devconf, sizeof(ipv6_devconf), GFP_KERNEL); + if (all == NULL) + goto err_alloc_all; - if (!net_eq(net, &init_net)) { - all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL); - if (all == NULL) - goto err_alloc_all; + dflt = kmemdup(&ipv6_devconf_dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); + if (dflt == NULL) + goto err_alloc_dflt; - dflt = kmemdup(dflt, sizeof(ipv6_devconf_dflt), GFP_KERNEL); - if (dflt == NULL) - goto err_alloc_dflt; - } else { - /* these will be inherited by all namespaces */ - dflt->autoconf = ipv6_defaults.autoconf; - dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; - } + /* these will be inherited by all namespaces */ + dflt->autoconf = ipv6_defaults.autoconf; + dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; net->ipv6.devconf_all = all; net->ipv6.devconf_dflt = dflt; @@ -4858,22 +4867,6 @@ static struct pernet_operations addrconf_ops = { .exit = addrconf_exit_net, }; -/* - * Device notifier - */ - -int register_inet6addr_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&inet6addr_chain, nb); -} -EXPORT_SYMBOL(register_inet6addr_notifier); - -int unregister_inet6addr_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&inet6addr_chain, nb); -} -EXPORT_SYMBOL(unregister_inet6addr_notifier); - static struct rtnl_af_ops inet6_ops = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index d051e5f4bf34..72104562c864 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -78,3 +78,22 @@ int __ipv6_addr_type(const struct in6_addr *addr) } EXPORT_SYMBOL(__ipv6_addr_type); +static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); + +int register_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(register_inet6addr_notifier); + +int unregister_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(unregister_inet6addr_notifier); + +int inet6addr_notifier_call_chain(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&inet6addr_chain, val, v); +} +EXPORT_SYMBOL(inet6addr_notifier_call_chain); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index ff76eecfd622..aad64352cb60 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -173,9 +173,8 @@ static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, const struct in6_addr *addr, int type, int ifindex) { - struct hlist_node *pos; struct ip6addrlbl_entry *p; - hlist_for_each_entry_rcu(p, pos, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { if (__ip6addrlbl_match(net, p, addr, type, ifindex)) return p; } @@ -261,9 +260,9 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) if (hlist_empty(&ip6addrlbl_table.head)) { hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); } else { - struct hlist_node *pos, *n; + struct hlist_node *n; struct ip6addrlbl_entry *p = NULL; - hlist_for_each_entry_safe(p, pos, n, + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { if (p->prefixlen == newp->prefixlen && net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && @@ -319,13 +318,13 @@ static int __ip6addrlbl_del(struct net *net, int ifindex) { struct ip6addrlbl_entry *p = NULL; - struct hlist_node *pos, *n; + struct hlist_node *n; int ret = -ESRCH; ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); - hlist_for_each_entry_safe(p, pos, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && net_eq(ip6addrlbl_net(p), net) && p->ifindex == ifindex && @@ -380,11 +379,11 @@ static int __net_init ip6addrlbl_net_init(struct net *net) static void __net_exit ip6addrlbl_net_exit(struct net *net) { struct ip6addrlbl_entry *p = NULL; - struct hlist_node *pos, *n; + struct hlist_node *n; /* Remove all labels belonging to the exiting net */ spin_lock(&ip6addrlbl_table.lock); - hlist_for_each_entry_safe(p, pos, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { if (net_eq(ip6addrlbl_net(p), net)) { hlist_del_rcu(&p->list); ip6addrlbl_put(p); @@ -505,12 +504,11 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct ip6addrlbl_entry *p; - struct hlist_node *pos; int idx = 0, s_idx = cb->args[0]; int err; rcu_read_lock(); - hlist_for_each_entry_rcu(p, pos, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { if (idx >= s_idx && net_eq(ip6addrlbl_net(p), net)) { if ((err = ip6addrlbl_fill(skb, p, diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index b386a2ce4c6f..9bfab19ff3c0 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -31,7 +31,6 @@ int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax) { const struct sock *sk2; - const struct hlist_node *node; int reuse = sk->sk_reuse; int reuseport = sk->sk_reuseport; kuid_t uid = sock_i_uid((struct sock *)sk); @@ -41,7 +40,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, * See comment in inet_csk_bind_conflict about sock lookup * vs net namespaces issues. */ - sk_for_each_bound(sk2, node, &tb->owners) { + sk_for_each_bound(sk2, &tb->owners) { if (sk != sk2 && (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || @@ -58,7 +57,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, } } - return node != NULL; + return sk2 != NULL; } EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 710cafd2e1a9..192dd1a0e188 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -224,7 +224,6 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct fib6_table *tb; struct hlist_head *head; - struct hlist_node *node; unsigned int h; if (id == 0) @@ -232,7 +231,7 @@ struct fib6_table *fib6_get_table(struct net *net, u32 id) h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (tb->tb6_id == id) { rcu_read_unlock(); return tb; @@ -363,7 +362,6 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) struct rt6_rtnl_dump_arg arg; struct fib6_walker_t *w; struct fib6_table *tb; - struct hlist_node *node; struct hlist_head *head; int res = 0; @@ -398,7 +396,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; res = fib6_dump_table(tb, skb, cb); @@ -1520,14 +1518,13 @@ void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg int prune, void *arg) { struct fib6_table *table; - struct hlist_node *node; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(table, head, tb6_hlist) { read_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, prune, arg); @@ -1540,14 +1537,13 @@ void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), int prune, void *arg) { struct fib6_table *table; - struct hlist_node *node; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, node, head, tb6_hlist) { + hlist_for_each_entry_rcu(table, head, tb6_hlist) { write_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, prune, arg); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 5b10414e619e..2bab2aa59745 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -118,6 +118,18 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt ipv6_addr_loopback(&hdr->daddr)) goto err; + /* RFC4291 Errata ID: 3480 + * Interface-Local scope spans only a single interface on a + * node and is useful only for loopback transmission of + * multicast. Packets with interface-local scope received + * from another node must be discarded. + */ + if (!(skb->pkt_type == PACKET_LOOPBACK || + dev->flags & IFF_LOOPBACK) && + ipv6_addr_is_multicast(&hdr->daddr) && + IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 1) + goto err; + /* RFC4291 2.7 * Nodes must not originate a packet to a multicast address whose scope * field contains the reserved value 0; if such a packet is received, it @@ -241,9 +253,11 @@ resubmit: icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_UNK_NEXTHDR, nhoff); } - } else + kfree_skb(skb); + } else { IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDELIVERS); - kfree_skb(skb); + consume_skb(skb); + } } rcu_read_unlock(); return 0; @@ -279,7 +293,8 @@ int ip6_mc_input(struct sk_buff *skb) * IPv6 multicast router mode is now supported ;) */ if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && - !(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) && + !(ipv6_addr_type(&hdr->daddr) & + (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { /* * Okay, we try to forward - split and duplicate diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c index 83acc1405a18..cb631143721c 100644 --- a/net/ipv6/netfilter/ip6t_NPT.c +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -57,7 +57,7 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, if (pfx_len - i >= 32) mask = 0; else - mask = htonl(~((1 << (pfx_len - i)) - 1)); + mask = htonl((1 << (i - pfx_len + 32)) - 1); idx = i / 32; addr->s6_addr32[idx] &= mask; @@ -114,6 +114,7 @@ ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par) static struct xt_target ip6t_npt_target_reg[] __read_mostly = { { .name = "SNPT", + .table = "mangle", .target = ip6t_snpt_tg, .targetsize = sizeof(struct ip6t_npt_tginfo), .checkentry = ip6t_npt_checkentry, @@ -124,6 +125,7 @@ static struct xt_target ip6t_npt_target_reg[] __read_mostly = { }, { .name = "DNPT", + .table = "mangle", .target = ip6t_dnpt_tg, .targetsize = sizeof(struct ip6t_npt_tginfo), .checkentry = ip6t_npt_checkentry, diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 5060d54199ab..e0983f3648a6 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -71,6 +71,12 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, return ret; } +static bool rpfilter_is_local(const struct sk_buff *skb) +{ + const struct rt6_info *rt = (const void *) skb_dst(skb); + return rt && (rt->rt6i_flags & RTF_LOCAL); +} + static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rpfilter_info *info = par->matchinfo; @@ -78,7 +84,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) struct ipv6hdr *iph; bool invert = info->flags & XT_RPFILTER_INVERT; - if (par->in->flags & IFF_LOOPBACK) + if (rpfilter_is_local(skb)) return true ^ invert; iph = ipv6_hdr(skb); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 54087e96d7b8..6700069949dd 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -14,6 +14,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "IPv6-nf: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> @@ -180,13 +182,11 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); local_bh_enable(); - if (q == NULL) - goto oom; - + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } return container_of(q, struct frag_queue, q); - -oom: - return NULL; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c65907db8c44..330b5e7b7df6 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -71,10 +71,9 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif) { - struct hlist_node *node; bool is_multicast = ipv6_addr_is_multicast(loc_addr); - sk_for_each_from(sk, node) + sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 3c6a77290c6e..0ba10e53a629 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -26,6 +26,9 @@ * YOSHIFUJI,H. @USAGI Always remove fragment header to * calculate ICV correctly. */ + +#define pr_fmt(fmt) "IPv6: " fmt + #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> @@ -185,9 +188,10 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6 hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); - if (q == NULL) + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); return NULL; - + } return container_of(q, struct frag_queue, q); } @@ -326,9 +330,17 @@ found: } if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) - return ip6_frag_reasm(fq, prev, dev); + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + res = ip6_frag_reasm(fq, prev, dev); + skb->_skb_refdst = orefdst; + return res; + } + skb_dst_drop(skb); inet_frag_lru_move(&fq->q); return -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 928266569689..e5fe0041adfa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1915,7 +1915,8 @@ void rt6_purge_dflt_routers(struct net *net) restart: read_lock_bh(&table->tb6_lock); for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); ip6_del_rt(rt); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9b6460055df5..46a5be85be87 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -386,9 +386,17 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (dst) dst->ops->redirect(dst, sk, skb); + goto out; } if (type == ICMPV6_PKT_TOOBIG) { + /* We are not interested in TCP_LISTEN and open_requests + * (SYN-ACKs send out by Linux are always <576bytes so + * they should go through unfragmented). + */ + if (sk->sk_state == TCP_LISTEN) + goto out; + tp->mtu_info = ntohl(info); if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 599e1ba6d1ce..d8e5e852fc7a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1285,10 +1285,18 @@ do_confirm: void udpv6_destroy_sock(struct sock *sk) { + struct udp_sock *up = udp_sk(sk); lock_sock(sk); udp_v6_flush_pending_frames(sk); release_sock(sk); + if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = ACCESS_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } + inet6_destroy_sock(sk); } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 6cc48012b730..de2bcfaaf759 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -89,9 +89,8 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, const { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; - struct hlist_node *pos; - hlist_for_each_entry_rcu(x6spi, pos, + hlist_for_each_entry_rcu(x6spi, &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (xfrm6_addr_equal(&x6spi->addr, saddr)) @@ -120,9 +119,8 @@ static int __xfrm6_tunnel_spi_check(struct net *net, u32 spi) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; int index = xfrm6_tunnel_spi_hash_byspi(spi); - struct hlist_node *pos; - hlist_for_each_entry(x6spi, pos, + hlist_for_each_entry(x6spi, &xfrm6_tn->spi_byspi[index], list_byspi) { if (x6spi->spi == spi) @@ -203,11 +201,11 @@ static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) { struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); struct xfrm6_tunnel_spi *x6spi; - struct hlist_node *pos, *n; + struct hlist_node *n; spin_lock_bh(&xfrm6_tunnel_spi_lock); - hlist_for_each_entry_safe(x6spi, pos, n, + hlist_for_each_entry_safe(x6spi, n, &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c index dfd6faaf0ea7..f547a47d381c 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -228,9 +228,8 @@ static struct sock *__ipxitf_find_socket(struct ipx_interface *intrfc, __be16 port) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &intrfc->if_sklist) + sk_for_each(s, &intrfc->if_sklist) if (ipx_sk(s)->port == port) goto found; s = NULL; @@ -259,12 +258,11 @@ static struct sock *ipxitf_find_internal_socket(struct ipx_interface *intrfc, __be16 port) { struct sock *s; - struct hlist_node *node; ipxitf_hold(intrfc); spin_lock_bh(&intrfc->if_sklist_lock); - sk_for_each(s, node, &intrfc->if_sklist) { + sk_for_each(s, &intrfc->if_sklist) { struct ipx_sock *ipxs = ipx_sk(s); if (ipxs->port == port && @@ -282,14 +280,14 @@ found: static void __ipxitf_down(struct ipx_interface *intrfc) { struct sock *s; - struct hlist_node *node, *t; + struct hlist_node *t; /* Delete all routes associated with this interface */ ipxrtr_del_routes(intrfc); spin_lock_bh(&intrfc->if_sklist_lock); /* error sockets */ - sk_for_each_safe(s, node, t, &intrfc->if_sklist) { + sk_for_each_safe(s, t, &intrfc->if_sklist) { struct ipx_sock *ipxs = ipx_sk(s); s->sk_err = ENOLINK; @@ -385,12 +383,11 @@ static int ipxitf_demux_socket(struct ipx_interface *intrfc, int is_broadcast = !memcmp(ipx->ipx_dest.node, ipx_broadcast_node, IPX_NODE_LEN); struct sock *s; - struct hlist_node *node; int rc; spin_lock_bh(&intrfc->if_sklist_lock); - sk_for_each(s, node, &intrfc->if_sklist) { + sk_for_each(s, &intrfc->if_sklist) { struct ipx_sock *ipxs = ipx_sk(s); if (ipxs->port == ipx->ipx_dest.sock && @@ -446,12 +443,11 @@ static struct sock *ncp_connection_hack(struct ipx_interface *intrfc, connection = (((int) *(ncphdr + 9)) << 8) | (int) *(ncphdr + 8); if (connection) { - struct hlist_node *node; /* Now we have to look for a special NCP connection handling * socket. Only these sockets have ipx_ncp_conn != 0, set by * SIOCIPXNCPCONN. */ spin_lock_bh(&intrfc->if_sklist_lock); - sk_for_each(sk, node, &intrfc->if_sklist) + sk_for_each(sk, &intrfc->if_sklist) if (ipx_sk(sk)->ipx_ncp_conn == connection) { sock_hold(sk); goto found; diff --git a/net/ipx/ipx_proc.c b/net/ipx/ipx_proc.c index 02ff7f2f60d4..65e8833a2510 100644 --- a/net/ipx/ipx_proc.c +++ b/net/ipx/ipx_proc.c @@ -103,19 +103,18 @@ out: static __inline__ struct sock *ipx_get_socket_idx(loff_t pos) { struct sock *s = NULL; - struct hlist_node *node; struct ipx_interface *i; list_for_each_entry(i, &ipx_interfaces, node) { spin_lock_bh(&i->if_sklist_lock); - sk_for_each(s, node, &i->if_sklist) { + sk_for_each(s, &i->if_sklist) { if (!pos) break; --pos; } spin_unlock_bh(&i->if_sklist_lock); if (!pos) { - if (node) + if (s) goto found; break; } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index d07e3a626446..e493b3397ae3 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1386,6 +1386,8 @@ static int irda_recvmsg_dgram(struct kiocb *iocb, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __func__); + msg->msg_namelen = 0; + skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &err); if (!skb) @@ -2583,8 +2585,10 @@ bed: NULL, NULL, NULL); /* Check if the we got some results */ - if (!self->cachedaddr) - return -EAGAIN; /* Didn't find any devices */ + if (!self->cachedaddr) { + err = -EAGAIN; /* Didn't find any devices */ + goto out; + } daddr = self->cachedaddr; /* Cleanup */ self->cachedaddr = 0; diff --git a/net/irda/ircomm/ircomm_tty.c b/net/irda/ircomm/ircomm_tty.c index 9a5fd3c3e530..362ba47968e4 100644 --- a/net/irda/ircomm/ircomm_tty.c +++ b/net/irda/ircomm/ircomm_tty.c @@ -280,7 +280,7 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self, struct tty_port *port = &self->port; DECLARE_WAITQUEUE(wait, current); int retval; - int do_clocal = 0, extra_count = 0; + int do_clocal = 0; unsigned long flags; IRDA_DEBUG(2, "%s()\n", __func__ ); @@ -289,8 +289,15 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self, * If non-blocking mode is set, or the port is not enabled, * then make the check up front and then exit. */ - if (filp->f_flags & O_NONBLOCK || tty->flags & (1 << TTY_IO_ERROR)){ - /* nonblock mode is set or port is not enabled */ + if (test_bit(TTY_IO_ERROR, &tty->flags)) { + port->flags |= ASYNC_NORMAL_ACTIVE; + return 0; + } + + if (filp->f_flags & O_NONBLOCK) { + /* nonblock mode is set */ + if (tty->termios.c_cflag & CBAUD) + tty_port_raise_dtr_rts(port); port->flags |= ASYNC_NORMAL_ACTIVE; IRDA_DEBUG(1, "%s(), O_NONBLOCK requested!\n", __func__ ); return 0; @@ -315,18 +322,16 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self, __FILE__, __LINE__, tty->driver->name, port->count); spin_lock_irqsave(&port->lock, flags); - if (!tty_hung_up_p(filp)) { - extra_count = 1; + if (!tty_hung_up_p(filp)) port->count--; - } - spin_unlock_irqrestore(&port->lock, flags); port->blocked_open++; + spin_unlock_irqrestore(&port->lock, flags); while (1) { if (tty->termios.c_cflag & CBAUD) tty_port_raise_dtr_rts(port); - current->state = TASK_INTERRUPTIBLE; + set_current_state(TASK_INTERRUPTIBLE); if (tty_hung_up_p(filp) || !test_bit(ASYNCB_INITIALIZED, &port->flags)) { @@ -361,13 +366,11 @@ static int ircomm_tty_block_til_ready(struct ircomm_tty_cb *self, __set_current_state(TASK_RUNNING); remove_wait_queue(&port->open_wait, &wait); - if (extra_count) { - /* ++ is not atomic, so this should be protected - Jean II */ - spin_lock_irqsave(&port->lock, flags); + spin_lock_irqsave(&port->lock, flags); + if (!tty_hung_up_p(filp)) port->count++; - spin_unlock_irqrestore(&port->lock, flags); - } port->blocked_open--; + spin_unlock_irqrestore(&port->lock, flags); IRDA_DEBUG(1, "%s(%d):block_til_ready after blocking on %s open_count=%d\n", __FILE__, __LINE__, tty->driver->name, port->count); diff --git a/net/irda/iriap.c b/net/irda/iriap.c index e71e85ba2bf1..e1b37f5a2691 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -303,7 +303,8 @@ static void iriap_disconnect_indication(void *instance, void *sap, { struct iriap_cb *self; - IRDA_DEBUG(4, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]); + IRDA_DEBUG(4, "%s(), reason=%s [%d]\n", __func__, + irlmp_reason_str(reason), reason); self = instance; @@ -495,8 +496,11 @@ static void iriap_getvaluebyclass_confirm(struct iriap_cb *self, /* case CS_ISO_8859_9: */ /* case CS_UNICODE: */ default: - IRDA_DEBUG(0, "%s(), charset %s, not supported\n", - __func__, ias_charset_types[charset]); + IRDA_DEBUG(0, "%s(), charset [%d] %s, not supported\n", + __func__, charset, + charset < ARRAY_SIZE(ias_charset_types) ? + ias_charset_types[charset] : + "(unknown)"); /* Aborting, close connection! */ iriap_disconnect_request(self); diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index 6115a44c0a24..1064621da6f6 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -66,8 +66,15 @@ const char *irlmp_reasons[] = { "LM_LAP_RESET", "LM_INIT_DISCONNECT", "ERROR, NOT USED", + "UNKNOWN", }; +const char *irlmp_reason_str(LM_REASON reason) +{ + reason = min_t(size_t, reason, ARRAY_SIZE(irlmp_reasons) - 1); + return irlmp_reasons[reason]; +} + /* * Function irlmp_init (void) * @@ -747,7 +754,8 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason, { struct lsap_cb *lsap; - IRDA_DEBUG(1, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]); + IRDA_DEBUG(1, "%s(), reason=%s [%d]\n", __func__, + irlmp_reason_str(reason), reason); IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index cd6f7a991d80..206ce6db2c36 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -49,12 +49,6 @@ static const u8 iprm_shutdown[8] = #define TRGCLS_SIZE (sizeof(((struct iucv_message *)0)->class)) -/* macros to set/get socket control buffer at correct offset */ -#define CB_TAG(skb) ((skb)->cb) /* iucv message tag */ -#define CB_TAG_LEN (sizeof(((struct iucv_message *) 0)->tag)) -#define CB_TRGCLS(skb) ((skb)->cb + CB_TAG_LEN) /* iucv msg target class */ -#define CB_TRGCLS_LEN (TRGCLS_SIZE) - #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ DEFINE_WAIT(__wait); \ @@ -156,14 +150,13 @@ static int afiucv_pm_freeze(struct device *dev) { struct iucv_sock *iucv; struct sock *sk; - struct hlist_node *node; int err = 0; #ifdef CONFIG_PM_DEBUG printk(KERN_WARNING "afiucv_pm_freeze\n"); #endif read_lock(&iucv_sk_list.lock); - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { iucv = iucv_sk(sk); switch (sk->sk_state) { case IUCV_DISCONN: @@ -194,13 +187,12 @@ static int afiucv_pm_freeze(struct device *dev) static int afiucv_pm_restore_thaw(struct device *dev) { struct sock *sk; - struct hlist_node *node; #ifdef CONFIG_PM_DEBUG printk(KERN_WARNING "afiucv_pm_restore_thaw\n"); #endif read_lock(&iucv_sk_list.lock); - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { switch (sk->sk_state) { case IUCV_CONNECTED: sk->sk_err = EPIPE; @@ -390,9 +382,8 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, static struct sock *__iucv_get_sock_by_name(char *nm) { struct sock *sk; - struct hlist_node *node; - sk_for_each(sk, node, &iucv_sk_list.head) + sk_for_each(sk, &iucv_sk_list.head) if (!memcmp(&iucv_sk(sk)->src_name, nm, 8)) return sk; @@ -1144,7 +1135,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, /* increment and save iucv message tag for msg_completion cbk */ txmsg.tag = iucv->send_tag++; - memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN); + IUCV_SKB_CB(skb)->tag = txmsg.tag; if (iucv->transport == AF_IUCV_TRANS_HIPER) { atomic_inc(&iucv->msg_sent); @@ -1227,7 +1218,7 @@ static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len) return -ENOMEM; /* copy target class to control buffer of new skb */ - memcpy(CB_TRGCLS(nskb), CB_TRGCLS(skb), CB_TRGCLS_LEN); + IUCV_SKB_CB(nskb)->class = IUCV_SKB_CB(skb)->class; /* copy data fragment */ memcpy(nskb->data, skb->data + copied, size); @@ -1259,7 +1250,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, /* store msg target class in the second 4 bytes of skb ctrl buffer */ /* Note: the first 4 bytes are reserved for msg tag */ - memcpy(CB_TRGCLS(skb), &msg->class, CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = msg->class; /* check for special IPRM messages (e.g. iucv_sock_shutdown) */ if ((msg->flags & IUCV_IPRMDATA) && len > 7) { @@ -1295,6 +1286,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, } } + IUCV_SKB_CB(skb)->offset = 0; if (sock_queue_rcv_skb(sk, skb)) skb_queue_head(&iucv_sk(sk)->backlog_skb_q, skb); } @@ -1330,6 +1322,9 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; int err = 0; + u32 offset; + + msg->msg_namelen = 0; if ((sk->sk_state == IUCV_DISCONN) && skb_queue_empty(&iucv->backlog_skb_q) && @@ -1349,13 +1344,14 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - rlen = skb->len; /* real length of skb */ + offset = IUCV_SKB_CB(skb)->offset; + rlen = skb->len - offset; /* real length of skb */ copied = min_t(unsigned int, rlen, len); if (!rlen) sk->sk_shutdown = sk->sk_shutdown | RCV_SHUTDOWN; cskb = skb; - if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) { + if (skb_copy_datagram_iovec(cskb, offset, msg->msg_iov, copied)) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); return -EFAULT; @@ -1373,7 +1369,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, * get the trgcls from the control buffer of the skb due to * fragmentation of original iucv message. */ err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS, - CB_TRGCLS_LEN, CB_TRGCLS(skb)); + sizeof(IUCV_SKB_CB(skb)->class), + (void *)&IUCV_SKB_CB(skb)->class); if (err) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); @@ -1385,9 +1382,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, /* SOCK_STREAM: re-queue skb if it contains unreceived data */ if (sk->sk_type == SOCK_STREAM) { - skb_pull(skb, copied); - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); + if (copied < rlen) { + IUCV_SKB_CB(skb)->offset = offset + copied; goto done; } } @@ -1406,6 +1402,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, spin_lock_bh(&iucv->message_q.lock); rskb = skb_dequeue(&iucv->backlog_skb_q); while (rskb) { + IUCV_SKB_CB(rskb)->offset = 0; if (sock_queue_rcv_skb(sk, rskb)) { skb_queue_head(&iucv->backlog_skb_q, rskb); @@ -1678,7 +1675,6 @@ static int iucv_callback_connreq(struct iucv_path *path, unsigned char user_data[16]; unsigned char nuser_data[16]; unsigned char src_name[8]; - struct hlist_node *node; struct sock *sk, *nsk; struct iucv_sock *iucv, *niucv; int err; @@ -1689,7 +1685,7 @@ static int iucv_callback_connreq(struct iucv_path *path, read_lock(&iucv_sk_list.lock); iucv = NULL; sk = NULL; - sk_for_each(sk, node, &iucv_sk_list.head) + sk_for_each(sk, &iucv_sk_list.head) if (sk->sk_state == IUCV_LISTEN && !memcmp(&iucv_sk(sk)->src_name, src_name, 8)) { /* @@ -1834,7 +1830,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (!memcmp(&msg->tag, CB_TAG(list_skb), CB_TAG_LEN)) { + if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } @@ -2095,6 +2091,7 @@ static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb) skb_pull(skb, sizeof(struct af_iucv_trans_hdr)); skb_reset_transport_header(skb); skb_reset_network_header(skb); + IUCV_SKB_CB(skb)->offset = 0; spin_lock(&iucv->message_q.lock); if (skb_queue_empty(&iucv->backlog_skb_q)) { if (sock_queue_rcv_skb(sk, skb)) { @@ -2115,7 +2112,6 @@ static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb) static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct hlist_node *node; struct sock *sk; struct iucv_sock *iucv; struct af_iucv_trans_hdr *trans_hdr; @@ -2132,7 +2128,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, iucv = NULL; sk = NULL; read_lock(&iucv_sk_list.lock); - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { if (trans_hdr->flags == AF_IUCV_FLAG_SYN) { if ((!memcmp(&iucv_sk(sk)->src_name, trans_hdr->destAppName, 8)) && @@ -2200,8 +2196,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, /* fall through and receive zero length data */ case 0: /* plain data frame */ - memcpy(CB_TRGCLS(skb), &trans_hdr->iucv_hdr.class, - CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; err = afiucv_hs_callback_rx(sk, skb); break; default: @@ -2225,10 +2220,9 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *skb, struct sk_buff *list_skb; struct sk_buff *nskb; unsigned long flags; - struct hlist_node *node; read_lock_irqsave(&iucv_sk_list.lock, flags); - sk_for_each(sk, node, &iucv_sk_list.head) + sk_for_each(sk, &iucv_sk_list.head) if (sk == isk) { iucv = iucv_sk(sk); break; @@ -2299,14 +2293,13 @@ static int afiucv_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = (struct net_device *)ptr; - struct hlist_node *node; struct sock *sk; struct iucv_sock *iucv; switch (event) { case NETDEV_REBOOT: case NETDEV_GOING_DOWN: - sk_for_each(sk, node, &iucv_sk_list.head) { + sk_for_each(sk, &iucv_sk_list.head) { iucv = iucv_sk(sk); if ((iucv->hs_dev == event_dev) && (sk->sk_state == IUCV_CONNECTED)) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 9ef79851f297..5b1e5af25713 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -225,7 +225,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; - struct hlist_node *node; struct sk_buff *skb2 = NULL; int err = -ESRCH; @@ -236,7 +235,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, return -ENOMEM; rcu_read_lock(); - sk_for_each_rcu(sk, node, &net_pfkey->table) { + sk_for_each_rcu(sk, &net_pfkey->table) { struct pfkey_sock *pfk = pfkey_sk(sk); int err2; @@ -2202,7 +2201,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_ XFRM_POLICY_BLOCK : XFRM_POLICY_ALLOW); xp->priority = pol->sadb_x_policy_priority; - sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1], + sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; xp->family = pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.saddr); if (!xp->family) { err = -EINVAL; @@ -2215,7 +2214,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_ if (xp->selector.sport) xp->selector.sport_mask = htons(0xffff); - sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1], + sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &xp->selector.daddr); xp->selector.prefixlen_d = sa->sadb_address_prefixlen; @@ -2316,7 +2315,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa memset(&sel, 0, sizeof(sel)); - sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1], + sa = ext_hdrs[SADB_EXT_ADDRESS_SRC-1]; sel.family = pfkey_sadb_addr2xfrm_addr(sa, &sel.saddr); sel.prefixlen_s = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); @@ -2324,7 +2323,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa if (sel.sport) sel.sport_mask = htons(0xffff); - sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1], + sa = ext_hdrs[SADB_EXT_ADDRESS_DST-1]; pfkey_sadb_addr2xfrm_addr(sa, &sel.daddr); sel.prefixlen_d = sa->sadb_address_prefixlen; sel.proto = pfkey_proto_to_xfrm(sa->sadb_address_proto); @@ -2694,6 +2693,7 @@ static int key_notify_policy_flush(const struct km_event *c) hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; + hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index dcfd64e83ab7..8aecf5df6656 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -114,7 +114,6 @@ struct l2tp_net { static void l2tp_session_set_header_len(struct l2tp_session *session, int version); static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); -static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); static inline struct l2tp_net *l2tp_pernet(struct net *net) { @@ -192,6 +191,7 @@ struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) } else { /* Socket is owned by kernelspace */ sk = tunnel->sock; + sock_hold(sk); } out: @@ -210,6 +210,7 @@ void l2tp_tunnel_sock_put(struct sock *sk) } sock_put(sk); } + sock_put(sk); } EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put); @@ -221,10 +222,9 @@ static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id) struct hlist_head *session_list = l2tp_session_id_hash_2(pn, session_id); struct l2tp_session *session; - struct hlist_node *walk; rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, walk, session_list, global_hlist) { + hlist_for_each_entry_rcu(session, session_list, global_hlist) { if (session->session_id == session_id) { rcu_read_unlock_bh(); return session; @@ -253,7 +253,6 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn { struct hlist_head *session_list; struct l2tp_session *session; - struct hlist_node *walk; /* In L2TPv3, session_ids are unique over all tunnels and we * sometimes need to look them up before we know the @@ -264,7 +263,7 @@ struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunn session_list = l2tp_session_id_hash(tunnel, session_id); read_lock_bh(&tunnel->hlist_lock); - hlist_for_each_entry(session, walk, session_list, hlist) { + hlist_for_each_entry(session, session_list, hlist) { if (session->session_id == session_id) { read_unlock_bh(&tunnel->hlist_lock); return session; @@ -279,13 +278,12 @@ EXPORT_SYMBOL_GPL(l2tp_session_find); struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth) { int hash; - struct hlist_node *walk; struct l2tp_session *session; int count = 0; read_lock_bh(&tunnel->hlist_lock); for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry(session, walk, &tunnel->session_hlist[hash], hlist) { + hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) { if (++count > nth) { read_unlock_bh(&tunnel->hlist_lock); return session; @@ -306,12 +304,11 @@ struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); int hash; - struct hlist_node *walk; struct l2tp_session *session; rcu_read_lock_bh(); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) { - hlist_for_each_entry_rcu(session, walk, &pn->l2tp_session_hlist[hash], global_hlist) { + hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { if (!strcmp(session->ifname, ifname)) { rcu_read_unlock_bh(); return session; @@ -377,10 +374,8 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk struct sk_buff *skbp; struct sk_buff *tmp; u32 ns = L2TP_SKB_CB(skb)->ns; - struct l2tp_stats *sstats; spin_lock_bh(&session->reorder_q.lock); - sstats = &session->stats; skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); @@ -388,9 +383,7 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n", session->name, ns, L2TP_SKB_CB(skbp)->ns, skb_queue_len(&session->reorder_q)); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_oos_packets++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_oos_packets); goto out; } } @@ -407,23 +400,16 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff * { struct l2tp_tunnel *tunnel = session->tunnel; int length = L2TP_SKB_CB(skb)->length; - struct l2tp_stats *tstats, *sstats; /* We're about to requeue the skb, so return resources * to its current owner (a socket receive buffer). */ skb_orphan(skb); - tstats = &tunnel->stats; - u64_stats_update_begin(&tstats->syncp); - sstats = &session->stats; - u64_stats_update_begin(&sstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += length; - sstats->rx_packets++; - sstats->rx_bytes += length; - u64_stats_update_end(&tstats->syncp); - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&tunnel->stats.rx_packets); + atomic_long_add(length, &tunnel->stats.rx_bytes); + atomic_long_inc(&session->stats.rx_packets); + atomic_long_add(length, &session->stats.rx_bytes); if (L2TP_SKB_CB(skb)->has_seq) { /* Bump our Nr */ @@ -454,7 +440,6 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) { struct sk_buff *skb; struct sk_buff *tmp; - struct l2tp_stats *sstats; /* If the pkt at the head of the queue has the nr that we * expect to send up next, dequeue it and any other @@ -462,13 +447,10 @@ static void l2tp_recv_dequeue(struct l2tp_session *session) */ start: spin_lock_bh(&session->reorder_q.lock); - sstats = &session->stats; skb_queue_walk_safe(&session->reorder_q, skb, tmp) { if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) { - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - sstats->rx_errors++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); + atomic_long_inc(&session->stats.rx_errors); l2tp_dbg(session, L2TP_MSG_SEQ, "%s: oos pkt %u len %d discarded (too old), waiting for %u, reorder_q_len=%d\n", session->name, L2TP_SKB_CB(skb)->ns, @@ -627,7 +609,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, struct l2tp_tunnel *tunnel = session->tunnel; int offset; u32 ns, nr; - struct l2tp_stats *sstats = &session->stats; /* The ref count is increased since we now hold a pointer to * the session. Take care to decrement the refcnt when exiting @@ -644,9 +625,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, "%s: cookie mismatch (%u/%u). Discarding.\n", tunnel->name, tunnel->tunnel_id, session->session_id); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_cookie_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } ptr += session->peer_cookie_len; @@ -715,9 +694,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, l2tp_warn(session, L2TP_MSG_SEQ, "%s: recv data has no seq numbers when required. Discarding.\n", session->name); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -736,9 +713,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, l2tp_warn(session, L2TP_MSG_SEQ, "%s: recv data has no seq numbers when required. Discarding.\n", session->name); - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } } @@ -792,9 +767,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, * packets */ if (L2TP_SKB_CB(skb)->ns != session->nr) { - u64_stats_update_begin(&sstats->syncp); - sstats->rx_seq_discards++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_seq_discards); l2tp_dbg(session, L2TP_MSG_SEQ, "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n", session->name, L2TP_SKB_CB(skb)->ns, @@ -820,9 +793,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, return; discard: - u64_stats_update_begin(&sstats->syncp); - sstats->rx_errors++; - u64_stats_update_end(&sstats->syncp); + atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); if (session->deref) @@ -832,6 +803,23 @@ discard: } EXPORT_SYMBOL(l2tp_recv_common); +/* Drop skbs from the session's reorder_q + */ +int l2tp_session_queue_purge(struct l2tp_session *session) +{ + struct sk_buff *skb = NULL; + BUG_ON(!session); + BUG_ON(session->magic != L2TP_SESSION_MAGIC); + while ((skb = skb_dequeue(&session->reorder_q))) { + atomic_long_inc(&session->stats.rx_errors); + kfree_skb(skb); + if (session->deref) + (*session->deref)(session); + } + return 0; +} +EXPORT_SYMBOL_GPL(l2tp_session_queue_purge); + /* Internal UDP receive frame. Do the real work of receiving an L2TP data frame * here. The skb is not on a list when we get here. * Returns 0 if the packet was a data packet and was successfully passed on. @@ -847,7 +835,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, u32 tunnel_id, session_id; u16 version; int length; - struct l2tp_stats *tstats; if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb)) goto discard_bad_csum; @@ -936,10 +923,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, discard_bad_csum: LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name); UDP_INC_STATS_USER(tunnel->l2tp_net, UDP_MIB_INERRORS, 0); - tstats = &tunnel->stats; - u64_stats_update_begin(&tstats->syncp); - tstats->rx_errors++; - u64_stats_update_end(&tstats->syncp); + atomic_long_inc(&tunnel->stats.rx_errors); kfree_skb(skb); return 0; @@ -1066,7 +1050,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, struct l2tp_tunnel *tunnel = session->tunnel; unsigned int len = skb->len; int error; - struct l2tp_stats *tstats, *sstats; /* Debug */ if (session->send_seq) @@ -1095,21 +1078,15 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, error = ip_queue_xmit(skb, fl); /* Update stats */ - tstats = &tunnel->stats; - u64_stats_update_begin(&tstats->syncp); - sstats = &session->stats; - u64_stats_update_begin(&sstats->syncp); if (error >= 0) { - tstats->tx_packets++; - tstats->tx_bytes += len; - sstats->tx_packets++; - sstats->tx_bytes += len; + atomic_long_inc(&tunnel->stats.tx_packets); + atomic_long_add(len, &tunnel->stats.tx_bytes); + atomic_long_inc(&session->stats.tx_packets); + atomic_long_add(len, &session->stats.tx_bytes); } else { - tstats->tx_errors++; - sstats->tx_errors++; + atomic_long_inc(&tunnel->stats.tx_errors); + atomic_long_inc(&session->stats.tx_errors); } - u64_stats_update_end(&tstats->syncp); - u64_stats_update_end(&sstats->syncp); return 0; } @@ -1286,6 +1263,7 @@ static void l2tp_tunnel_destruct(struct sock *sk) /* No longer an encapsulation socket. See net/ipv4/udp.c */ (udp_sk(sk))->encap_type = 0; (udp_sk(sk))->encap_rcv = NULL; + (udp_sk(sk))->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; @@ -1315,7 +1293,7 @@ end: /* When the tunnel is closed, all the attached sessions need to go too. */ -static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) +void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { int hash; struct hlist_node *walk; @@ -1338,25 +1316,13 @@ again: hlist_del_init(&session->hlist); - /* Since we should hold the sock lock while - * doing any unbinding, we need to release the - * lock we're holding before taking that lock. - * Hold a reference to the sock so it doesn't - * disappear as we're jumping between locks. - */ if (session->ref != NULL) (*session->ref)(session); write_unlock_bh(&tunnel->hlist_lock); - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_del_init_rcu(&session->global_hlist); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); - synchronize_rcu(); - } + __l2tp_session_unhash(session); + l2tp_session_queue_purge(session); if (session->session_close != NULL) (*session->session_close)(session); @@ -1364,6 +1330,8 @@ again: if (session->deref != NULL) (*session->deref)(session); + l2tp_session_dec_refcount(session); + write_lock_bh(&tunnel->hlist_lock); /* Now restart from the beginning of this hash @@ -1376,6 +1344,17 @@ again: } write_unlock_bh(&tunnel->hlist_lock); } +EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall); + +/* Tunnel socket destroy hook for UDP encapsulation */ +static void l2tp_udp_encap_destroy(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + if (tunnel) { + l2tp_tunnel_closeall(tunnel); + sock_put(sk); + } +} /* Really kill the tunnel. * Come here only when all sessions have been cleared from the tunnel. @@ -1401,19 +1380,21 @@ static void l2tp_tunnel_del_work(struct work_struct *work) return; sock = sk->sk_socket; - BUG_ON(!sock); - /* If the tunnel socket was created directly by the kernel, use the - * sk_* API to release the socket now. Otherwise go through the - * inet_* layer to shut the socket down, and let userspace close it. + /* If the tunnel socket was created by userspace, then go through the + * inet layer to shut the socket down, and let userspace close it. + * Otherwise, if we created the socket directly within the kernel, use + * the sk API to release it here. * In either case the tunnel resources are freed in the socket * destructor when the tunnel socket goes away. */ - if (sock->file == NULL) { - kernel_sock_shutdown(sock, SHUT_RDWR); - sk_release_kernel(sk); + if (tunnel->fd >= 0) { + if (sock) + inet_shutdown(sock, 2); } else { - inet_shutdown(sock, 2); + if (sock) + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sk); } l2tp_tunnel_sock_put(sk); @@ -1672,6 +1653,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */ udp_sk(sk)->encap_type = UDP_ENCAP_L2TPINUDP; udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv; + udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy; #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET6) udpv6_encap_enable(); @@ -1727,6 +1709,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); */ int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { + l2tp_tunnel_closeall(tunnel); return (false == queue_work(l2tp_wq, &tunnel->del_work)); } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); @@ -1735,62 +1718,71 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); */ void l2tp_session_free(struct l2tp_session *session) { - struct l2tp_tunnel *tunnel; + struct l2tp_tunnel *tunnel = session->tunnel; BUG_ON(atomic_read(&session->ref_count) != 0); - tunnel = session->tunnel; - if (tunnel != NULL) { + if (tunnel) { BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); + if (session->session_id != 0) + atomic_dec(&l2tp_session_count); + sock_put(tunnel->sock); + session->tunnel = NULL; + l2tp_tunnel_dec_refcount(tunnel); + } + + kfree(session); + + return; +} +EXPORT_SYMBOL_GPL(l2tp_session_free); - /* Delete the session from the hash */ +/* Remove an l2tp session from l2tp_core's hash lists. + * Provides a tidyup interface for pseudowire code which can't just route all + * shutdown via. l2tp_session_delete and a pseudowire-specific session_close + * callback. + */ +void __l2tp_session_unhash(struct l2tp_session *session) +{ + struct l2tp_tunnel *tunnel = session->tunnel; + + /* Remove the session from core hashes */ + if (tunnel) { + /* Remove from the per-tunnel hash */ write_lock_bh(&tunnel->hlist_lock); hlist_del_init(&session->hlist); write_unlock_bh(&tunnel->hlist_lock); - /* Unlink from the global hash if not L2TPv2 */ + /* For L2TPv3 we have a per-net hash: remove from there, too */ if (tunnel->version != L2TP_HDR_VER_2) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_session_hlist_lock); hlist_del_init_rcu(&session->global_hlist); spin_unlock_bh(&pn->l2tp_session_hlist_lock); synchronize_rcu(); } - - if (session->session_id != 0) - atomic_dec(&l2tp_session_count); - - sock_put(tunnel->sock); - - /* This will delete the tunnel context if this - * is the last session on the tunnel. - */ - session->tunnel = NULL; - l2tp_tunnel_dec_refcount(tunnel); } - - kfree(session); - - return; } -EXPORT_SYMBOL_GPL(l2tp_session_free); +EXPORT_SYMBOL_GPL(__l2tp_session_unhash); /* This function is used by the netlink SESSION_DELETE command and by pseudowire modules. */ int l2tp_session_delete(struct l2tp_session *session) { + if (session->ref) + (*session->ref)(session); + __l2tp_session_unhash(session); + l2tp_session_queue_purge(session); if (session->session_close != NULL) (*session->session_close)(session); - + if (session->deref) + (*session->ref)(session); l2tp_session_dec_refcount(session); - return 0; } EXPORT_SYMBOL_GPL(l2tp_session_delete); - /* We come here whenever a session's send_seq, cookie_len or * l2specific_len parameters are set. */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 8eb8f1d47f3a..485a490fd990 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -36,16 +36,15 @@ enum { struct sk_buff; struct l2tp_stats { - u64 tx_packets; - u64 tx_bytes; - u64 tx_errors; - u64 rx_packets; - u64 rx_bytes; - u64 rx_seq_discards; - u64 rx_oos_packets; - u64 rx_errors; - u64 rx_cookie_discards; - struct u64_stats_sync syncp; + atomic_long_t tx_packets; + atomic_long_t tx_bytes; + atomic_long_t tx_errors; + atomic_long_t rx_packets; + atomic_long_t rx_bytes; + atomic_long_t rx_seq_discards; + atomic_long_t rx_oos_packets; + atomic_long_t rx_errors; + atomic_long_t rx_cookie_discards; }; struct l2tp_tunnel; @@ -240,11 +239,14 @@ extern struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id); extern struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth); extern int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); +extern void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel); extern int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); extern struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); +extern void __l2tp_session_unhash(struct l2tp_session *session); extern int l2tp_session_delete(struct l2tp_session *session); extern void l2tp_session_free(struct l2tp_session *session); extern void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length, int (*payload_hook)(struct sk_buff *skb)); +extern int l2tp_session_queue_purge(struct l2tp_session *session); extern int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); extern int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index c3813bc84552..072d7202e182 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -146,14 +146,14 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0, atomic_read(&tunnel->ref_count)); - seq_printf(m, " %08x rx %llu/%llu/%llu rx %llu/%llu/%llu\n", + seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n", tunnel->debug, - (unsigned long long)tunnel->stats.tx_packets, - (unsigned long long)tunnel->stats.tx_bytes, - (unsigned long long)tunnel->stats.tx_errors, - (unsigned long long)tunnel->stats.rx_packets, - (unsigned long long)tunnel->stats.rx_bytes, - (unsigned long long)tunnel->stats.rx_errors); + atomic_long_read(&tunnel->stats.tx_packets), + atomic_long_read(&tunnel->stats.tx_bytes), + atomic_long_read(&tunnel->stats.tx_errors), + atomic_long_read(&tunnel->stats.rx_packets), + atomic_long_read(&tunnel->stats.rx_bytes), + atomic_long_read(&tunnel->stats.rx_errors)); if (tunnel->show != NULL) tunnel->show(m, tunnel); @@ -203,14 +203,14 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v) seq_printf(m, "\n"); } - seq_printf(m, " %hu/%hu tx %llu/%llu/%llu rx %llu/%llu/%llu\n", + seq_printf(m, " %hu/%hu tx %ld/%ld/%ld rx %ld/%ld/%ld\n", session->nr, session->ns, - (unsigned long long)session->stats.tx_packets, - (unsigned long long)session->stats.tx_bytes, - (unsigned long long)session->stats.tx_errors, - (unsigned long long)session->stats.rx_packets, - (unsigned long long)session->stats.rx_bytes, - (unsigned long long)session->stats.rx_errors); + atomic_long_read(&session->stats.tx_packets), + atomic_long_read(&session->stats.tx_bytes), + atomic_long_read(&session->stats.tx_errors), + atomic_long_read(&session->stats.rx_packets), + atomic_long_read(&session->stats.rx_bytes), + atomic_long_read(&session->stats.rx_errors)); if (session->show != NULL) session->show(m, session); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index f7ac8f42fee2..571db8dd2292 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -49,10 +49,9 @@ static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif, u32 tunnel_id) { - struct hlist_node *node; struct sock *sk; - sk_for_each_bound(sk, node, &l2tp_ip_bind_table) { + sk_for_each_bound(sk, &l2tp_ip_bind_table) { struct inet_sock *inet = inet_sk(sk); struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); @@ -229,10 +228,16 @@ static void l2tp_ip_close(struct sock *sk, long timeout) static void l2tp_ip_destroy_sock(struct sock *sk) { struct sk_buff *skb; + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) kfree_skb(skb); + if (tunnel) { + l2tp_tunnel_closeall(tunnel); + sock_put(sk); + } + sk_refcnt_debug_dec(sk); } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 8ee4a86ae996..b8a6039314e8 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -60,10 +60,9 @@ static struct sock *__l2tp_ip6_bind_lookup(struct net *net, struct in6_addr *laddr, int dif, u32 tunnel_id) { - struct hlist_node *node; struct sock *sk; - sk_for_each_bound(sk, node, &l2tp_ip6_bind_table) { + sk_for_each_bound(sk, &l2tp_ip6_bind_table) { struct in6_addr *addr = inet6_rcv_saddr(sk); struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); @@ -242,10 +241,17 @@ static void l2tp_ip6_close(struct sock *sk, long timeout) static void l2tp_ip6_destroy_sock(struct sock *sk) { + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); + if (tunnel) { + l2tp_tunnel_closeall(tunnel); + sock_put(sk); + } + inet6_destroy_sock(sk); } @@ -684,6 +690,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, lsa->l2tp_addr = ipv6_hdr(skb)->saddr; lsa->l2tp_flowinfo = 0; lsa->l2tp_scope_id = 0; + lsa->l2tp_conn_id = 0; if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = IP6CB(skb)->iif; } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index c1bab22db85e..0825ff26e113 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -246,8 +246,6 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *np = NULL; #endif - struct l2tp_stats stats; - unsigned int start; hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, L2TP_CMD_TUNNEL_GET); @@ -265,28 +263,22 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla if (nest == NULL) goto nla_put_failure; - do { - start = u64_stats_fetch_begin(&tunnel->stats.syncp); - stats.tx_packets = tunnel->stats.tx_packets; - stats.tx_bytes = tunnel->stats.tx_bytes; - stats.tx_errors = tunnel->stats.tx_errors; - stats.rx_packets = tunnel->stats.rx_packets; - stats.rx_bytes = tunnel->stats.rx_bytes; - stats.rx_errors = tunnel->stats.rx_errors; - stats.rx_seq_discards = tunnel->stats.rx_seq_discards; - stats.rx_oos_packets = tunnel->stats.rx_oos_packets; - } while (u64_stats_fetch_retry(&tunnel->stats.syncp, start)); - - if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) || - nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) || - nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) || - nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) || + if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, + atomic_long_read(&tunnel->stats.tx_packets)) || + nla_put_u64(skb, L2TP_ATTR_TX_BYTES, + atomic_long_read(&tunnel->stats.tx_bytes)) || + nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, + atomic_long_read(&tunnel->stats.tx_errors)) || + nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, + atomic_long_read(&tunnel->stats.rx_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_BYTES, + atomic_long_read(&tunnel->stats.rx_bytes)) || nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, - stats.rx_seq_discards) || + atomic_long_read(&tunnel->stats.rx_seq_discards)) || nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS, - stats.rx_oos_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors)) + atomic_long_read(&tunnel->stats.rx_oos_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, + atomic_long_read(&tunnel->stats.rx_errors))) goto nla_put_failure; nla_nest_end(skb, nest); @@ -612,8 +604,6 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl struct nlattr *nest; struct l2tp_tunnel *tunnel = session->tunnel; struct sock *sk = NULL; - struct l2tp_stats stats; - unsigned int start; sk = tunnel->sock; @@ -656,28 +646,22 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl if (nest == NULL) goto nla_put_failure; - do { - start = u64_stats_fetch_begin(&session->stats.syncp); - stats.tx_packets = session->stats.tx_packets; - stats.tx_bytes = session->stats.tx_bytes; - stats.tx_errors = session->stats.tx_errors; - stats.rx_packets = session->stats.rx_packets; - stats.rx_bytes = session->stats.rx_bytes; - stats.rx_errors = session->stats.rx_errors; - stats.rx_seq_discards = session->stats.rx_seq_discards; - stats.rx_oos_packets = session->stats.rx_oos_packets; - } while (u64_stats_fetch_retry(&session->stats.syncp, start)); - - if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) || - nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) || - nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) || - nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) || + if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, + atomic_long_read(&session->stats.tx_packets)) || + nla_put_u64(skb, L2TP_ATTR_TX_BYTES, + atomic_long_read(&session->stats.tx_bytes)) || + nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, + atomic_long_read(&session->stats.tx_errors)) || + nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, + atomic_long_read(&session->stats.rx_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_BYTES, + atomic_long_read(&session->stats.rx_bytes)) || nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, - stats.rx_seq_discards) || + atomic_long_read(&session->stats.rx_seq_discards)) || nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS, - stats.rx_oos_packets) || - nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors)) + atomic_long_read(&session->stats.rx_oos_packets)) || + nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, + atomic_long_read(&session->stats.rx_errors))) goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 3f4e3afc191a..637a341c1e2d 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -97,6 +97,7 @@ #include <net/ip.h> #include <net/udp.h> #include <net/xfrm.h> +#include <net/inet_common.h> #include <asm/byteorder.h> #include <linux/atomic.h> @@ -259,7 +260,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int session->name); /* Not bound. Nothing we can do, so discard. */ - session->stats.rx_errors++; + atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } @@ -355,6 +356,7 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh l2tp_xmit_skb(session, skb, session->hdr_len); sock_put(ps->tunnel_sock); + sock_put(sk); return error; @@ -446,34 +448,16 @@ static void pppol2tp_session_close(struct l2tp_session *session) { struct pppol2tp_session *ps = l2tp_session_priv(session); struct sock *sk = ps->sock; - struct sk_buff *skb; + struct socket *sock = sk->sk_socket; BUG_ON(session->magic != L2TP_SESSION_MAGIC); - if (session->session_id == 0) - goto out; - - if (sk != NULL) { - lock_sock(sk); - - if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) { - pppox_unbind_sock(sk); - sk->sk_state = PPPOX_DEAD; - sk->sk_state_change(sk); - } - - /* Purge any queued data */ - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); - while ((skb = skb_dequeue(&session->reorder_q))) { - kfree_skb(skb); - sock_put(sk); - } - release_sock(sk); + if (sock) { + inet_shutdown(sock, 2); + /* Don't let the session go away before our socket does */ + l2tp_session_inc_refcount(session); } - -out: return; } @@ -482,19 +466,12 @@ out: */ static void pppol2tp_session_destruct(struct sock *sk) { - struct l2tp_session *session; - - if (sk->sk_user_data != NULL) { - session = sk->sk_user_data; - if (session == NULL) - goto out; - + struct l2tp_session *session = sk->sk_user_data; + if (session) { sk->sk_user_data = NULL; BUG_ON(session->magic != L2TP_SESSION_MAGIC); l2tp_session_dec_refcount(session); } - -out: return; } @@ -524,16 +501,13 @@ static int pppol2tp_release(struct socket *sock) session = pppol2tp_sock_to_session(sk); /* Purge any queued data */ - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); if (session != NULL) { - struct sk_buff *skb; - while ((skb = skb_dequeue(&session->reorder_q))) { - kfree_skb(skb); - sock_put(sk); - } + __l2tp_session_unhash(session); + l2tp_session_queue_purge(session); sock_put(sk); } + skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge(&sk->sk_write_queue); release_sock(sk); @@ -879,18 +853,6 @@ out: return error; } -/* Called when deleting sessions via the netlink interface. - */ -static int pppol2tp_session_delete(struct l2tp_session *session) -{ - struct pppol2tp_session *ps = l2tp_session_priv(session); - - if (ps->sock == NULL) - l2tp_session_dec_refcount(session); - - return 0; -} - #endif /* CONFIG_L2TP_V3 */ /* getname() support. @@ -1024,14 +986,14 @@ end: static void pppol2tp_copy_stats(struct pppol2tp_ioc_stats *dest, struct l2tp_stats *stats) { - dest->tx_packets = stats->tx_packets; - dest->tx_bytes = stats->tx_bytes; - dest->tx_errors = stats->tx_errors; - dest->rx_packets = stats->rx_packets; - dest->rx_bytes = stats->rx_bytes; - dest->rx_seq_discards = stats->rx_seq_discards; - dest->rx_oos_packets = stats->rx_oos_packets; - dest->rx_errors = stats->rx_errors; + dest->tx_packets = atomic_long_read(&stats->tx_packets); + dest->tx_bytes = atomic_long_read(&stats->tx_bytes); + dest->tx_errors = atomic_long_read(&stats->tx_errors); + dest->rx_packets = atomic_long_read(&stats->rx_packets); + dest->rx_bytes = atomic_long_read(&stats->rx_bytes); + dest->rx_seq_discards = atomic_long_read(&stats->rx_seq_discards); + dest->rx_oos_packets = atomic_long_read(&stats->rx_oos_packets); + dest->rx_errors = atomic_long_read(&stats->rx_errors); } /* Session ioctl helper. @@ -1665,14 +1627,14 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) tunnel->name, (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', atomic_read(&tunnel->ref_count) - 1); - seq_printf(m, " %08x %llu/%llu/%llu %llu/%llu/%llu\n", + seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", tunnel->debug, - (unsigned long long)tunnel->stats.tx_packets, - (unsigned long long)tunnel->stats.tx_bytes, - (unsigned long long)tunnel->stats.tx_errors, - (unsigned long long)tunnel->stats.rx_packets, - (unsigned long long)tunnel->stats.rx_bytes, - (unsigned long long)tunnel->stats.rx_errors); + atomic_long_read(&tunnel->stats.tx_packets), + atomic_long_read(&tunnel->stats.tx_bytes), + atomic_long_read(&tunnel->stats.tx_errors), + atomic_long_read(&tunnel->stats.rx_packets), + atomic_long_read(&tunnel->stats.rx_bytes), + atomic_long_read(&tunnel->stats.rx_errors)); } static void pppol2tp_seq_session_show(struct seq_file *m, void *v) @@ -1707,14 +1669,14 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v) session->lns_mode ? "LNS" : "LAC", session->debug, jiffies_to_msecs(session->reorder_timeout)); - seq_printf(m, " %hu/%hu %llu/%llu/%llu %llu/%llu/%llu\n", + seq_printf(m, " %hu/%hu %ld/%ld/%ld %ld/%ld/%ld\n", session->nr, session->ns, - (unsigned long long)session->stats.tx_packets, - (unsigned long long)session->stats.tx_bytes, - (unsigned long long)session->stats.tx_errors, - (unsigned long long)session->stats.rx_packets, - (unsigned long long)session->stats.rx_bytes, - (unsigned long long)session->stats.rx_errors); + atomic_long_read(&session->stats.tx_packets), + atomic_long_read(&session->stats.tx_bytes), + atomic_long_read(&session->stats.tx_errors), + atomic_long_read(&session->stats.rx_packets), + atomic_long_read(&session->stats.rx_bytes), + atomic_long_read(&session->stats.rx_errors)); if (po) seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan)); @@ -1838,7 +1800,7 @@ static const struct pppox_proto pppol2tp_proto = { static const struct l2tp_nl_cmd_ops pppol2tp_nl_cmd_ops = { .session_create = pppol2tp_session_create, - .session_delete = pppol2tp_session_delete, + .session_delete = l2tp_session_delete, }; #endif /* CONFIG_L2TP_V3 */ diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 88709882c464..48aaa89253e0 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -720,6 +720,8 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, int target; /* Read at least this many bytes */ long timeo; + msg->msg_namelen = 0; + lock_sock(sk); copied = -ENOTCONN; if (unlikely(sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN)) diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 7c5073badc73..78be45cda5c1 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -393,12 +393,11 @@ static void llc_sap_mcast(struct llc_sap *sap, { int i = 0, count = 256 / sizeof(struct sock *); struct sock *sk, *stack[count]; - struct hlist_node *node; struct llc_sock *llc; struct hlist_head *dev_hb = llc_sk_dev_hash(sap, skb->dev->ifindex); spin_lock_bh(&sap->sk_lock); - hlist_for_each_entry(llc, node, dev_hb, dev_hash_node) { + hlist_for_each_entry(llc, dev_hb, dev_hash_node) { sk = &llc->sk; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 09d96a8f6c2c..a6893602f87a 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2582,7 +2582,7 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local, list_del(&dep->list); mutex_unlock(&local->mtx); - ieee80211_roc_notify_destroy(dep); + ieee80211_roc_notify_destroy(dep, true); return 0; } @@ -2622,7 +2622,7 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local, ieee80211_start_next_roc(local); mutex_unlock(&local->mtx); - ieee80211_roc_notify_destroy(found); + ieee80211_roc_notify_destroy(found, true); } else { /* work may be pending so use it all the time */ found->abort = true; @@ -2632,6 +2632,8 @@ static int ieee80211_cancel_roc(struct ieee80211_local *local, /* work will clean up etc */ flush_delayed_work(&found->work); + WARN_ON(!found->to_be_freed); + kfree(found); } return 0; @@ -3285,6 +3287,7 @@ static int ieee80211_cfg_get_channel(struct wiphy *wiphy, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_chanctx_conf *chanctx_conf; int ret = -ENODATA; @@ -3293,6 +3296,16 @@ static int ieee80211_cfg_get_channel(struct wiphy *wiphy, if (chanctx_conf) { *chandef = chanctx_conf->def; ret = 0; + } else if (local->open_count > 0 && + local->open_count == local->monitors && + sdata->vif.type == NL80211_IFTYPE_MONITOR) { + if (local->use_chanctx) + *chandef = local->monitor_chandef; + else + cfg80211_chandef_create(chandef, + local->_oper_channel, + local->_oper_channel_type); + ret = 0; } rcu_read_unlock(); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 78c0d90dd641..931be419ab5a 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -63,6 +63,7 @@ ieee80211_new_chanctx(struct ieee80211_local *local, enum ieee80211_chanctx_mode mode) { struct ieee80211_chanctx *ctx; + u32 changed; int err; lockdep_assert_held(&local->chanctx_mtx); @@ -76,6 +77,13 @@ ieee80211_new_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; + /* acquire mutex to prevent idle from changing */ + mutex_lock(&local->mtx); + /* turn idle off *before* setting channel -- some drivers need that */ + changed = ieee80211_idle_off(local); + if (changed) + ieee80211_hw_config(local, changed); + if (!local->use_chanctx) { local->_oper_channel_type = cfg80211_get_chandef_type(chandef); @@ -85,14 +93,17 @@ ieee80211_new_chanctx(struct ieee80211_local *local, err = drv_add_chanctx(local, ctx); if (err) { kfree(ctx); - return ERR_PTR(err); + ctx = ERR_PTR(err); + + ieee80211_recalc_idle(local); + goto out; } } + /* and keep the mutex held until the new chanctx is on the list */ list_add_rcu(&ctx->list, &local->chanctx_list); - mutex_lock(&local->mtx); - ieee80211_recalc_idle(local); + out: mutex_unlock(&local->mtx); return ctx; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 388580a1bada..5672533a0832 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -309,6 +309,7 @@ struct ieee80211_roc_work { struct ieee80211_channel *chan; bool started, abort, hw_begun, notified; + bool to_be_freed; unsigned long hw_start_time; @@ -1347,7 +1348,7 @@ void ieee80211_offchannel_return(struct ieee80211_local *local); void ieee80211_roc_setup(struct ieee80211_local *local); void ieee80211_start_next_roc(struct ieee80211_local *local); void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata); -void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc); +void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc, bool free); void ieee80211_sw_roc_work(struct work_struct *work); void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc); @@ -1361,6 +1362,7 @@ int ieee80211_if_change_type(struct ieee80211_sub_if_data *sdata, enum nl80211_iftype type); void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata); void ieee80211_remove_interfaces(struct ieee80211_local *local); +u32 ieee80211_idle_off(struct ieee80211_local *local); void ieee80211_recalc_idle(struct ieee80211_local *local); void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, const int offset); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 2c059e54e885..9ed49ad0380f 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -78,7 +78,7 @@ void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata) ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_TXPOWER); } -static u32 ieee80211_idle_off(struct ieee80211_local *local) +static u32 __ieee80211_idle_off(struct ieee80211_local *local) { if (!(local->hw.conf.flags & IEEE80211_CONF_IDLE)) return 0; @@ -87,7 +87,7 @@ static u32 ieee80211_idle_off(struct ieee80211_local *local) return IEEE80211_CONF_CHANGE_IDLE; } -static u32 ieee80211_idle_on(struct ieee80211_local *local) +static u32 __ieee80211_idle_on(struct ieee80211_local *local) { if (local->hw.conf.flags & IEEE80211_CONF_IDLE) return 0; @@ -98,16 +98,18 @@ static u32 ieee80211_idle_on(struct ieee80211_local *local) return IEEE80211_CONF_CHANGE_IDLE; } -void ieee80211_recalc_idle(struct ieee80211_local *local) +static u32 __ieee80211_recalc_idle(struct ieee80211_local *local, + bool force_active) { bool working = false, scanning, active; unsigned int led_trig_start = 0, led_trig_stop = 0; struct ieee80211_roc_work *roc; - u32 change; lockdep_assert_held(&local->mtx); - active = !list_empty(&local->chanctx_list); + active = force_active || + !list_empty(&local->chanctx_list) || + local->monitors; if (!local->ops->remain_on_channel) { list_for_each_entry(roc, &local->roc_list, list) { @@ -132,9 +134,18 @@ void ieee80211_recalc_idle(struct ieee80211_local *local) ieee80211_mod_tpt_led_trig(local, led_trig_start, led_trig_stop); if (working || scanning || active) - change = ieee80211_idle_off(local); - else - change = ieee80211_idle_on(local); + return __ieee80211_idle_off(local); + return __ieee80211_idle_on(local); +} + +u32 ieee80211_idle_off(struct ieee80211_local *local) +{ + return __ieee80211_recalc_idle(local, true); +} + +void ieee80211_recalc_idle(struct ieee80211_local *local) +{ + u32 change = __ieee80211_recalc_idle(local, false); if (change) ieee80211_hw_config(local, change); } @@ -349,21 +360,19 @@ static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata) static int ieee80211_add_virtual_monitor(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; - int ret = 0; + int ret; if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF)) return 0; - mutex_lock(&local->iflist_mtx); + ASSERT_RTNL(); if (local->monitor_sdata) - goto out_unlock; + return 0; sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); - if (!sdata) { - ret = -ENOMEM; - goto out_unlock; - } + if (!sdata) + return -ENOMEM; /* set up data */ sdata->local = local; @@ -377,13 +386,13 @@ static int ieee80211_add_virtual_monitor(struct ieee80211_local *local) if (WARN_ON(ret)) { /* ok .. stupid driver, it asked for this! */ kfree(sdata); - goto out_unlock; + return ret; } ret = ieee80211_check_queues(sdata); if (ret) { kfree(sdata); - goto out_unlock; + return ret; } ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef, @@ -391,13 +400,14 @@ static int ieee80211_add_virtual_monitor(struct ieee80211_local *local) if (ret) { drv_remove_interface(local, sdata); kfree(sdata); - goto out_unlock; + return ret; } + mutex_lock(&local->iflist_mtx); rcu_assign_pointer(local->monitor_sdata, sdata); - out_unlock: mutex_unlock(&local->iflist_mtx); - return ret; + + return 0; } static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) @@ -407,14 +417,20 @@ static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) if (!(local->hw.flags & IEEE80211_HW_WANT_MONITOR_VIF)) return; + ASSERT_RTNL(); + mutex_lock(&local->iflist_mtx); sdata = rcu_dereference_protected(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx)); - if (!sdata) - goto out_unlock; + if (!sdata) { + mutex_unlock(&local->iflist_mtx); + return; + } rcu_assign_pointer(local->monitor_sdata, NULL); + mutex_unlock(&local->iflist_mtx); + synchronize_net(); ieee80211_vif_release_channel(sdata); @@ -422,8 +438,6 @@ static void ieee80211_del_virtual_monitor(struct ieee80211_local *local) drv_remove_interface(local, sdata); kfree(sdata); - out_unlock: - mutex_unlock(&local->iflist_mtx); } /* @@ -541,6 +555,9 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); + mutex_lock(&local->mtx); + ieee80211_recalc_idle(local); + mutex_unlock(&local->mtx); netif_carrier_on(dev); break; @@ -812,6 +829,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_adjust_monitor_flags(sdata, -1); ieee80211_configure_filter(local); + mutex_lock(&local->mtx); + ieee80211_recalc_idle(local); + mutex_unlock(&local->mtx); break; case NL80211_IFTYPE_P2P_DEVICE: /* relies on synchronize_rcu() below */ diff --git a/net/mac80211/main.c b/net/mac80211/main.c index d0dd11153a6c..1a8591b77a13 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -647,8 +647,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, spin_lock_init(&local->ack_status_lock); idr_init(&local->ack_status_frames); - /* preallocate at least one entry */ - idr_pre_get(&local->ack_status_frames, GFP_KERNEL); sta_info_init(local); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 29ce2aa87e7b..4749b3858695 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1060,7 +1060,8 @@ void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) rcu_read_lock(); list_for_each_entry_rcu(sdata, &local->interfaces, list) - if (ieee80211_vif_is_mesh(&sdata->vif)) + if (ieee80211_vif_is_mesh(&sdata->vif) && + ieee80211_sdata_running(sdata)) ieee80211_queue_work(&local->hw, &sdata->work); rcu_read_unlock(); } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 6b3c4e119c63..dc7c8df40c2c 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -72,9 +72,9 @@ static inline struct mesh_table *resize_dereference_mpp_paths(void) * it's used twice. So it is illegal to do * for_each_mesh_entry(rcu_dereference(...), ...) */ -#define for_each_mesh_entry(tbl, p, node, i) \ +#define for_each_mesh_entry(tbl, node, i) \ for (i = 0; i <= tbl->hash_mask; i++) \ - hlist_for_each_entry_rcu(node, p, &tbl->hash_buckets[i], list) + hlist_for_each_entry_rcu(node, &tbl->hash_buckets[i], list) static struct mesh_table *mesh_table_alloc(int size_order) @@ -139,7 +139,7 @@ static void mesh_table_free(struct mesh_table *tbl, bool free_leafs) } if (free_leafs) { spin_lock_bh(&tbl->gates_lock); - hlist_for_each_entry_safe(gate, p, q, + hlist_for_each_entry_safe(gate, q, tbl->known_gates, list) { hlist_del(&gate->list); kfree(gate); @@ -333,12 +333,11 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, const u8 *dst, struct ieee80211_sub_if_data *sdata) { struct mesh_path *mpath; - struct hlist_node *n; struct hlist_head *bucket; struct mpath_node *node; bucket = &tbl->hash_buckets[mesh_table_hash(dst, sdata, tbl)]; - hlist_for_each_entry_rcu(node, n, bucket, list) { + hlist_for_each_entry_rcu(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(dst, mpath->dst)) { @@ -389,11 +388,10 @@ mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { struct mesh_table *tbl = rcu_dereference(mesh_paths); struct mpath_node *node; - struct hlist_node *p; int i; int j = 0; - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { if (sdata && node->mpath->sdata != sdata) continue; if (j++ == idx) { @@ -417,13 +415,12 @@ int mesh_path_add_gate(struct mesh_path *mpath) { struct mesh_table *tbl; struct mpath_node *gate, *new_gate; - struct hlist_node *n; int err; rcu_read_lock(); tbl = rcu_dereference(mesh_paths); - hlist_for_each_entry_rcu(gate, n, tbl->known_gates, list) + hlist_for_each_entry_rcu(gate, tbl->known_gates, list) if (gate->mpath == mpath) { err = -EEXIST; goto err_rcu; @@ -460,9 +457,9 @@ err_rcu: static void mesh_gate_del(struct mesh_table *tbl, struct mesh_path *mpath) { struct mpath_node *gate; - struct hlist_node *p, *q; + struct hlist_node *q; - hlist_for_each_entry_safe(gate, p, q, tbl->known_gates, list) { + hlist_for_each_entry_safe(gate, q, tbl->known_gates, list) { if (gate->mpath != mpath) continue; spin_lock_bh(&tbl->gates_lock); @@ -504,7 +501,6 @@ int mesh_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst) struct mesh_path *mpath, *new_mpath; struct mpath_node *node, *new_node; struct hlist_head *bucket; - struct hlist_node *n; int grow = 0; int err = 0; u32 hash_idx; @@ -550,7 +546,7 @@ int mesh_path_add(struct ieee80211_sub_if_data *sdata, const u8 *dst) spin_lock(&tbl->hashwlock[hash_idx]); err = -EEXIST; - hlist_for_each_entry(node, n, bucket, list) { + hlist_for_each_entry(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(dst, mpath->dst)) @@ -640,7 +636,6 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, struct mesh_path *mpath, *new_mpath; struct mpath_node *node, *new_node; struct hlist_head *bucket; - struct hlist_node *n; int grow = 0; int err = 0; u32 hash_idx; @@ -680,7 +675,7 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, spin_lock(&tbl->hashwlock[hash_idx]); err = -EEXIST; - hlist_for_each_entry(node, n, bucket, list) { + hlist_for_each_entry(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(dst, mpath->dst)) @@ -725,14 +720,13 @@ void mesh_plink_broken(struct sta_info *sta) static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; struct ieee80211_sub_if_data *sdata = sta->sdata; int i; __le16 reason = cpu_to_le16(WLAN_REASON_MESH_PATH_DEST_UNREACHABLE); rcu_read_lock(); tbl = rcu_dereference(mesh_paths); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { mpath = node->mpath; if (rcu_dereference(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && @@ -792,13 +786,12 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) struct mesh_table *tbl; struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; int i; rcu_read_lock(); read_lock_bh(&pathtbl_resize_lock); tbl = resize_dereference_mesh_paths(); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { mpath = node->mpath; if (rcu_dereference(mpath->next_hop) == sta) { spin_lock(&tbl->hashwlock[i]); @@ -815,11 +808,10 @@ static void table_flush_by_iface(struct mesh_table *tbl, { struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; int i; WARN_ON(!rcu_read_lock_held()); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { mpath = node->mpath; if (mpath->sdata != sdata) continue; @@ -865,7 +857,6 @@ int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr) struct mesh_path *mpath; struct mpath_node *node; struct hlist_head *bucket; - struct hlist_node *n; int hash_idx; int err = 0; @@ -875,7 +866,7 @@ int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr) bucket = &tbl->hash_buckets[hash_idx]; spin_lock(&tbl->hashwlock[hash_idx]); - hlist_for_each_entry(node, n, bucket, list) { + hlist_for_each_entry(node, bucket, list) { mpath = node->mpath; if (mpath->sdata == sdata && ether_addr_equal(addr, mpath->dst)) { @@ -920,7 +911,6 @@ void mesh_path_tx_pending(struct mesh_path *mpath) int mesh_path_send_to_gates(struct mesh_path *mpath) { struct ieee80211_sub_if_data *sdata = mpath->sdata; - struct hlist_node *n; struct mesh_table *tbl; struct mesh_path *from_mpath = mpath; struct mpath_node *gate = NULL; @@ -935,7 +925,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) if (!known_gates) return -EHOSTUNREACH; - hlist_for_each_entry_rcu(gate, n, known_gates, list) { + hlist_for_each_entry_rcu(gate, known_gates, list) { if (gate->mpath->sdata != sdata) continue; @@ -951,7 +941,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) } } - hlist_for_each_entry_rcu(gate, n, known_gates, list) + hlist_for_each_entry_rcu(gate, known_gates, list) if (gate->mpath->sdata == sdata) { mpath_dbg(sdata, "Sending to %pM\n", gate->mpath->dst); mesh_path_tx_pending(gate->mpath); @@ -1096,12 +1086,11 @@ void mesh_path_expire(struct ieee80211_sub_if_data *sdata) struct mesh_table *tbl; struct mesh_path *mpath; struct mpath_node *node; - struct hlist_node *p; int i; rcu_read_lock(); tbl = rcu_dereference(mesh_paths); - for_each_mesh_entry(tbl, p, node, i) { + for_each_mesh_entry(tbl, node, i) { if (node->mpath->sdata != sdata) continue; mpath = node->mpath; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9f6464f3e05f..346ad4cfb013 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -647,6 +647,9 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, our_mcs = (le16_to_cpu(vht_cap.vht_mcs.rx_mcs_map) & mask) >> shift; + if (our_mcs == IEEE80211_VHT_MCS_NOT_SUPPORTED) + continue; + switch (ap_mcs) { default: if (our_mcs <= ap_mcs) @@ -3503,6 +3506,14 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; /* + * Stop timers before deleting work items, as timers + * could race and re-add the work-items. They will be + * re-established on connection. + */ + del_timer_sync(&ifmgd->conn_mon_timer); + del_timer_sync(&ifmgd->bcn_mon_timer); + + /* * we need to use atomic bitops for the running bits * only because both timers might fire at the same * time -- the code here is properly synchronised. @@ -3516,13 +3527,9 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) if (del_timer_sync(&ifmgd->timer)) set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); - cancel_work_sync(&ifmgd->chswitch_work); if (del_timer_sync(&ifmgd->chswitch_timer)) set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); - - /* these will just be re-established on connection */ - del_timer_sync(&ifmgd->conn_mon_timer); - del_timer_sync(&ifmgd->bcn_mon_timer); + cancel_work_sync(&ifmgd->chswitch_work); } void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) @@ -3601,8 +3608,10 @@ void ieee80211_mlme_notify_scan_completed(struct ieee80211_local *local) /* Restart STA timers */ rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - ieee80211_restart_sta_timer(sdata); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (ieee80211_sdata_running(sdata)) + ieee80211_restart_sta_timer(sdata); + } rcu_read_unlock(); } @@ -3955,8 +3964,16 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, /* prep auth_data so we don't go into idle on disassoc */ ifmgd->auth_data = auth_data; - if (ifmgd->associated) - ieee80211_set_disassoc(sdata, 0, 0, false, NULL); + if (ifmgd->associated) { + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, + WLAN_REASON_UNSPECIFIED, + false, frame_buf); + + __cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); + } sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid); @@ -4016,8 +4033,16 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, mutex_lock(&ifmgd->mtx); - if (ifmgd->associated) - ieee80211_set_disassoc(sdata, 0, 0, false, NULL); + if (ifmgd->associated) { + u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + + ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, + WLAN_REASON_UNSPECIFIED, + false, frame_buf); + + __cfg80211_send_deauth(sdata->dev, frame_buf, + sizeof(frame_buf)); + } if (ifmgd->auth_data && !ifmgd->auth_data->done) { err = -EBUSY; @@ -4315,6 +4340,17 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + /* + * Make sure some work items will not run after this, + * they will not do anything but might not have been + * cancelled when disconnecting. + */ + cancel_work_sync(&ifmgd->monitor_work); + cancel_work_sync(&ifmgd->beacon_connection_loss_work); + cancel_work_sync(&ifmgd->request_smps_work); + cancel_work_sync(&ifmgd->csa_connection_drop_work); + cancel_work_sync(&ifmgd->chswitch_work); + mutex_lock(&ifmgd->mtx); if (ifmgd->assoc_data) ieee80211_destroy_assoc_data(sdata, false); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index cc79b4a2e821..430bd254e496 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -297,10 +297,13 @@ void ieee80211_start_next_roc(struct ieee80211_local *local) } } -void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc) +void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc, bool free) { struct ieee80211_roc_work *dep, *tmp; + if (WARN_ON(roc->to_be_freed)) + return; + /* was never transmitted */ if (roc->frame) { cfg80211_mgmt_tx_status(&roc->sdata->wdev, @@ -316,9 +319,12 @@ void ieee80211_roc_notify_destroy(struct ieee80211_roc_work *roc) GFP_KERNEL); list_for_each_entry_safe(dep, tmp, &roc->dependents, list) - ieee80211_roc_notify_destroy(dep); + ieee80211_roc_notify_destroy(dep, true); - kfree(roc); + if (free) + kfree(roc); + else + roc->to_be_freed = true; } void ieee80211_sw_roc_work(struct work_struct *work) @@ -331,6 +337,9 @@ void ieee80211_sw_roc_work(struct work_struct *work) mutex_lock(&local->mtx); + if (roc->to_be_freed) + goto out_unlock; + if (roc->abort) goto finish; @@ -370,7 +379,7 @@ void ieee80211_sw_roc_work(struct work_struct *work) finish: list_del(&roc->list); started = roc->started; - ieee80211_roc_notify_destroy(roc); + ieee80211_roc_notify_destroy(roc, !roc->abort); if (started) { drv_flush(local, false); @@ -410,7 +419,7 @@ static void ieee80211_hw_roc_done(struct work_struct *work) list_del(&roc->list); - ieee80211_roc_notify_destroy(roc); + ieee80211_roc_notify_destroy(roc, true); /* if there's another roc, start it now */ ieee80211_start_next_roc(local); @@ -460,12 +469,14 @@ void ieee80211_roc_purge(struct ieee80211_sub_if_data *sdata) list_for_each_entry_safe(roc, tmp, &tmp_list, list) { if (local->ops->remain_on_channel) { list_del(&roc->list); - ieee80211_roc_notify_destroy(roc); + ieee80211_roc_notify_destroy(roc, true); } else { ieee80211_queue_delayed_work(&local->hw, &roc->work, 0); /* work will clean up etc */ flush_delayed_work(&roc->work); + WARN_ON(!roc->to_be_freed); + kfree(roc); } } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bb73ed2d20b9..c6844ad080be 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2675,7 +2675,19 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx) memset(nskb->cb, 0, sizeof(nskb->cb)); - ieee80211_tx_skb(rx->sdata, nskb); + if (rx->sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(nskb); + + info->flags = IEEE80211_TX_CTL_TX_OFFCHAN | + IEEE80211_TX_INTFL_OFFCHAN_TX_OK | + IEEE80211_TX_CTL_NO_CCK_RATE; + if (local->hw.flags & IEEE80211_HW_QUEUE_CONTROL) + info->hw_queue = + local->hw.offchannel_tx_hw_queue; + } + + __ieee80211_tx_skb_tid_band(rx->sdata, nskb, 7, + status->band); } dev_kfree_skb(rx->skb); return RX_QUEUED; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index a79ce820cb50..238a0cca320e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -766,6 +766,7 @@ int __must_check __sta_info_destroy(struct sta_info *sta) struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; int ret, i; + bool have_key = false; might_sleep(); @@ -793,12 +794,19 @@ int __must_check __sta_info_destroy(struct sta_info *sta) list_del_rcu(&sta->list); mutex_lock(&local->key_mtx); - for (i = 0; i < NUM_DEFAULT_KEYS; i++) + for (i = 0; i < NUM_DEFAULT_KEYS; i++) { __ieee80211_key_free(key_mtx_dereference(local, sta->gtk[i])); - if (sta->ptk) + have_key = true; + } + if (sta->ptk) { __ieee80211_key_free(key_mtx_dereference(local, sta->ptk)); + have_key = true; + } mutex_unlock(&local->key_mtx); + if (!have_key) + synchronize_net(); + sta->dead = true; local->num_sta--; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 5b9602b62405..8914d2d2881a 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1231,34 +1231,40 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local, if (local->queue_stop_reasons[q] || (!txpending && !skb_queue_empty(&local->pending[q]))) { if (unlikely(info->flags & - IEEE80211_TX_INTFL_OFFCHAN_TX_OK && - local->queue_stop_reasons[q] & - ~BIT(IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL))) { + IEEE80211_TX_INTFL_OFFCHAN_TX_OK)) { + if (local->queue_stop_reasons[q] & + ~BIT(IEEE80211_QUEUE_STOP_REASON_OFFCHANNEL)) { + /* + * Drop off-channel frames if queues + * are stopped for any reason other + * than off-channel operation. Never + * queue them. + */ + spin_unlock_irqrestore( + &local->queue_stop_reason_lock, + flags); + ieee80211_purge_tx_queue(&local->hw, + skbs); + return true; + } + } else { + /* - * Drop off-channel frames if queues are stopped - * for any reason other than off-channel - * operation. Never queue them. + * Since queue is stopped, queue up frames for + * later transmission from the tx-pending + * tasklet when the queue is woken again. */ - spin_unlock_irqrestore( - &local->queue_stop_reason_lock, flags); - ieee80211_purge_tx_queue(&local->hw, skbs); - return true; + if (txpending) + skb_queue_splice_init(skbs, + &local->pending[q]); + else + skb_queue_splice_tail_init(skbs, + &local->pending[q]); + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, + flags); + return false; } - - /* - * Since queue is stopped, queue up frames for later - * transmission from the tx-pending tasklet when the - * queue is woken again. - */ - if (txpending) - skb_queue_splice_init(skbs, &local->pending[q]); - else - skb_queue_splice_tail_init(skbs, - &local->pending[q]); - - spin_unlock_irqrestore(&local->queue_stop_reason_lock, - flags); - return false; } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); @@ -1844,9 +1850,24 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, } if (!is_multicast_ether_addr(skb->data)) { + struct sta_info *next_hop; + bool mpp_lookup = true; + mpath = mesh_path_lookup(sdata, skb->data); - if (!mpath) + if (mpath) { + mpp_lookup = false; + next_hop = rcu_dereference(mpath->next_hop); + if (!next_hop || + !(mpath->flags & (MESH_PATH_ACTIVE | + MESH_PATH_RESOLVING))) + mpp_lookup = true; + } + + if (mpp_lookup) mppath = mpp_path_lookup(sdata, skb->data); + + if (mppath && mpath) + mesh_path_del(mpath->sdata, mpath->dst); } /* @@ -2017,24 +2038,14 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, skb = skb_clone(skb, GFP_ATOMIC); if (skb) { unsigned long flags; - int id, r; + int id; spin_lock_irqsave(&local->ack_status_lock, flags); - r = idr_get_new_above(&local->ack_status_frames, - orig_skb, 1, &id); - if (r == -EAGAIN) { - idr_pre_get(&local->ack_status_frames, - GFP_ATOMIC); - r = idr_get_new_above(&local->ack_status_frames, - orig_skb, 1, &id); - } - if (WARN_ON(!id) || id > 0xffff) { - idr_remove(&local->ack_status_frames, id); - r = -ERANGE; - } + id = idr_alloc(&local->ack_status_frames, orig_skb, + 1, 0x10000, GFP_ATOMIC); spin_unlock_irqrestore(&local->ack_status_lock, flags); - if (!r) { + if (id >= 0) { info_id = id; info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS; } else if (skb_shared(skb)) { @@ -2360,9 +2371,9 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata, if (local->tim_in_locked_section) { __ieee80211_beacon_add_tim(sdata, ps, skb); } else { - spin_lock(&local->tim_lock); + spin_lock_bh(&local->tim_lock); __ieee80211_beacon_add_tim(sdata, ps, skb); - spin_unlock(&local->tim_lock); + spin_unlock_bh(&local->tim_lock); } return 0; @@ -2734,7 +2745,8 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, cpu_to_le16(IEEE80211_FCTL_MOREDATA); } - sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); if (!ieee80211_tx_prepare(sdata, &tx, skb)) break; dev_kfree_skb_any(skb); diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index 0f92dc24cb89..d7df6ac2c6f1 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -339,7 +339,11 @@ bitmap_ipmac_tlist(const struct ip_set *set, nla_put_failure: nla_nest_cancel(skb, nested); ipset_nest_end(skb, atd); - return -EMSGSIZE; + if (unlikely(id == first)) { + cb->args[2] = 0; + return -EMSGSIZE; + } + return 0; } static int diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index f82b2e606cfd..1ba9dbc0e107 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1470,7 +1470,8 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, if (ret == -EAGAIN) ret = 1; - return ret < 0 ? ret : ret > 0 ? 0 : -IPSET_ERR_EXIST; + return (ret < 0 && ret != -ENOTEMPTY) ? ret : + ret > 0 ? 0 : -IPSET_ERR_EXIST; } /* Get headed data of a set */ diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index f2627226a087..10a30b4fc7db 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -104,6 +104,15 @@ hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem) { @@ -414,6 +423,15 @@ hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem) { diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 4b677cf6bf7d..d6a59154d710 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -87,7 +87,16 @@ hash_net4_data_copy(struct hash_net4_elem *dst, static inline void hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_net4_data_reset_flags(struct hash_net4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int @@ -308,7 +317,16 @@ hash_net6_data_copy(struct hash_net6_elem *dst, static inline void hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_net6_data_reset_flags(struct hash_net6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 6ba985f1c96f..f2b0a3c30130 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -198,7 +198,16 @@ hash_netiface4_data_copy(struct hash_netiface4_elem *dst, static inline void hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_netiface4_data_reset_flags(struct hash_netiface4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int @@ -494,7 +503,7 @@ hash_netiface6_data_copy(struct hash_netiface6_elem *dst, static inline void hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } static inline int @@ -504,6 +513,15 @@ hash_netiface6_data_match(const struct hash_netiface6_elem *elem) } static inline void +hash_netiface6_data_reset_flags(struct hash_netiface6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + +static inline void hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem) { elem->elem = 0; diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index af20c0c5ced2..349deb672a2d 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -104,6 +104,15 @@ hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_netport4_data_reset_flags(struct hash_netport4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_netport4_data_match(const struct hash_netport4_elem *elem) { @@ -375,6 +384,15 @@ hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_netport6_data_reset_flags(struct hash_netport6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_netport6_data_match(const struct hash_netport6_elem *elem) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 8371c2bac2e4..09c744aa8982 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -174,9 +174,13 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, { const struct set_elem *e = list_set_elem(map, i); - if (i == map->size - 1 && e->id != IPSET_INVALID_ID) - /* Last element replaced: e.g. add new,before,last */ - ip_set_put_byindex(e->id); + if (e->id != IPSET_INVALID_ID) { + const struct set_elem *x = list_set_elem(map, map->size - 1); + + /* Last element replaced or pushed off */ + if (x->id != IPSET_INVALID_ID) + ip_set_put_byindex(x->id); + } if (with_timeout(map->timeout)) list_elem_tadd(map, i, id, ip_set_timeout_set(timeout)); else diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 9f00db7e03f2..704e514e02ab 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -259,13 +259,12 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp; - struct hlist_node *n; hash = ip_vs_conn_hashkey_param(p, false); ct_read_lock(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && p->cport == cp->cport && p->vport == cp->vport && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && @@ -344,13 +343,12 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp; - struct hlist_node *n; hash = ip_vs_conn_hashkey_param(p, false); ct_read_lock(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (!ip_vs_conn_net_eq(cp, p->net)) continue; if (p->pe_data && p->pe->ct_match) { @@ -394,7 +392,6 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) { unsigned int hash; struct ip_vs_conn *cp, *ret=NULL; - struct hlist_node *n; /* * Check for "full" addressed entries @@ -403,7 +400,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) ct_read_lock(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && p->vport == cp->cport && p->cport == cp->dport && ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && @@ -953,11 +950,10 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) int idx; struct ip_vs_conn *cp; struct ip_vs_iter_state *iter = seq->private; - struct hlist_node *n; for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { ct_read_lock_bh(idx); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (pos-- == 0) { iter->l = &ip_vs_conn_tab[idx]; return cp; @@ -981,7 +977,6 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_conn *cp = v; struct ip_vs_iter_state *iter = seq->private; - struct hlist_node *e; struct hlist_head *l = iter->l; int idx; @@ -990,15 +985,15 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) return ip_vs_conn_array(seq, 0); /* more on same hash chain? */ - if ((e = cp->c_list.next)) - return hlist_entry(e, struct ip_vs_conn, c_list); + if (cp->c_list.next) + return hlist_entry(cp->c_list.next, struct ip_vs_conn, c_list); idx = l - ip_vs_conn_tab; ct_read_unlock_bh(idx); while (++idx < ip_vs_conn_tab_size) { ct_read_lock_bh(idx); - hlist_for_each_entry(cp, e, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { iter->l = &ip_vs_conn_tab[idx]; return cp; } @@ -1200,14 +1195,13 @@ void ip_vs_random_dropentry(struct net *net) */ for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) { unsigned int hash = net_random() & ip_vs_conn_tab_mask; - struct hlist_node *n; /* * Lock is actually needed in this loop. */ ct_write_lock_bh(hash); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; @@ -1255,14 +1249,12 @@ static void ip_vs_conn_flush(struct net *net) flush_again: for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { - struct hlist_node *n; - /* * Lock is actually needed in this loop. */ ct_write_lock_bh(idx); - hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (!ip_vs_conn_net_eq(cp, net)) continue; IP_VS_DBG(4, "del connection\n"); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 47edf5a40a59..61f49d241712 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1394,10 +1394,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); - rcu_read_lock(); ipv4_update_pmtu(skb, dev_net(skb->dev), mtu, 0, 0, 0, 0); - rcu_read_unlock(); /* Client uses PMTUD? */ if (!(cih->frag_off & htons(IP_DF))) goto ignore_ipip; @@ -1577,7 +1575,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, &iph); @@ -1654,7 +1653,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ @@ -1815,13 +1813,15 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, { int r; struct net *net; + struct netns_ipvs *ipvs; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp(skb, &r, hooknum); @@ -1835,6 +1835,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, { int r; struct net *net; + struct netns_ipvs *ipvs; struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr); @@ -1843,7 +1844,8 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c68198bf9128..9e2d1cccd1eb 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1808,6 +1808,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "backup_only", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -3741,6 +3747,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; ipvs->sysctl_pmtu_disc = 1; tbl[idx++].data = &ipvs->sysctl_pmtu_disc; + tbl[idx++].data = &ipvs->sysctl_backup_only; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index ae8ec6f27688..cd1d7298f7ba 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -906,7 +906,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, sctp_chunkhdr_t _sctpch, *sch; unsigned char chunk_type; int event, next_state; - int ihl; + int ihl, cofs; #ifdef CONFIG_IP_VS_IPV6 ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); @@ -914,8 +914,8 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, ihl = ip_hdrlen(skb); #endif - sch = skb_header_pointer(skb, ihl + sizeof(sctp_sctphdr_t), - sizeof(_sctpch), &_sctpch); + cofs = ihl + sizeof(sctp_sctphdr_t); + sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch); if (sch == NULL) return; @@ -933,10 +933,12 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, */ if ((sch->type == SCTP_CID_COOKIE_ECHO) || (sch->type == SCTP_CID_COOKIE_ACK)) { - sch = skb_header_pointer(skb, (ihl + sizeof(sctp_sctphdr_t) + - sch->length), sizeof(_sctpch), &_sctpch); - if (sch) { - if (sch->type == SCTP_CID_ABORT) + int clen = ntohs(sch->length); + + if (clen >= sizeof(sctp_chunkhdr_t)) { + sch = skb_header_pointer(skb, cofs + ALIGN(clen, 4), + sizeof(_sctpch), &_sctpch); + if (sch && sch->type == SCTP_CID_ABORT) chunk_type = sch->type; } } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 3921e5bc1235..8c10e3db3d9b 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -90,14 +90,13 @@ __nf_ct_expect_find(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i; - struct hlist_node *n; unsigned int h; if (!net->ct.expect_count) return NULL; h = nf_ct_expect_dst_hash(tuple); - hlist_for_each_entry_rcu(i, n, &net->ct.expect_hash[h], hnode) { + hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) { if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && nf_ct_zone(i->master) == zone) return i; @@ -130,14 +129,13 @@ nf_ct_find_expectation(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_expect *i, *exp = NULL; - struct hlist_node *n; unsigned int h; if (!net->ct.expect_count) return NULL; h = nf_ct_expect_dst_hash(tuple); - hlist_for_each_entry(i, n, &net->ct.expect_hash[h], hnode) { + hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) { if (!(i->flags & NF_CT_EXPECT_INACTIVE) && nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) && nf_ct_zone(i->master) == zone) { @@ -172,13 +170,13 @@ void nf_ct_remove_expectations(struct nf_conn *ct) { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_expect *exp; - struct hlist_node *n, *next; + struct hlist_node *next; /* Optimization: most connection never expect any others. */ if (!help) return; - hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) { + hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); @@ -348,9 +346,8 @@ static void evict_oldest_expect(struct nf_conn *master, { struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_expect *exp, *last = NULL; - struct hlist_node *n; - hlist_for_each_entry(exp, n, &master_help->expectations, lnode) { + hlist_for_each_entry(exp, &master_help->expectations, lnode) { if (exp->class == new->class) last = exp; } @@ -369,7 +366,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) struct nf_conn_help *master_help = nfct_help(master); struct nf_conntrack_helper *helper; struct net *net = nf_ct_exp_net(expect); - struct hlist_node *n, *next; + struct hlist_node *next; unsigned int h; int ret = 1; @@ -378,7 +375,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) goto out; } h = nf_ct_expect_dst_hash(&expect->tuple); - hlist_for_each_entry_safe(i, n, next, &net->ct.expect_hash[h], hnode) { + hlist_for_each_entry_safe(i, next, &net->ct.expect_hash[h], hnode) { if (expect_matches(i, expect)) { if (del_timer(&i->timeout)) { nf_ct_unlink_expect(i); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 013cdf69fe29..94b4b9853f60 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -116,14 +116,13 @@ __nf_ct_helper_find(const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_helper *helper; struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) }; - struct hlist_node *n; unsigned int h; if (!nf_ct_helper_count) return NULL; h = helper_hash(tuple); - hlist_for_each_entry_rcu(helper, n, &nf_ct_helper_hash[h], hnode) { + hlist_for_each_entry_rcu(helper, &nf_ct_helper_hash[h], hnode) { if (nf_ct_tuple_src_mask_cmp(tuple, &helper->tuple, &mask)) return helper; } @@ -134,11 +133,10 @@ struct nf_conntrack_helper * __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; - struct hlist_node *n; unsigned int i; for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_rcu(h, n, &nf_ct_helper_hash[i], hnode) { + hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) { if (!strcmp(h->name, name) && h->tuple.src.l3num == l3num && h->tuple.dst.protonum == protonum) @@ -341,6 +339,13 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, { const struct nf_conn_help *help; const struct nf_conntrack_helper *helper; + struct va_format vaf; + va_list args; + + va_start(args, fmt); + + vaf.fmt = fmt; + vaf.va = &args; /* Called from the helper function, this call never fails */ help = nfct_help(ct); @@ -349,7 +354,9 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, helper = rcu_dereference(help->helper); nf_log_packet(nf_ct_l3num(ct), 0, skb, NULL, NULL, NULL, - "nf_ct_%s: dropping packet: %s ", helper->name, fmt); + "nf_ct_%s: dropping packet: %pV ", helper->name, &vaf); + + va_end(args); } EXPORT_SYMBOL_GPL(nf_ct_helper_log); @@ -357,7 +364,6 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { int ret = 0; struct nf_conntrack_helper *cur; - struct hlist_node *n; unsigned int h = helper_hash(&me->tuple); BUG_ON(me->expect_policy == NULL); @@ -365,7 +371,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); mutex_lock(&nf_ct_helper_mutex); - hlist_for_each_entry(cur, n, &nf_ct_helper_hash[h], hnode) { + hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) { if (strncmp(cur->name, me->name, NF_CT_HELPER_NAME_LEN) == 0 && cur->tuple.src.l3num == me->tuple.src.l3num && cur->tuple.dst.protonum == me->tuple.dst.protonum) { @@ -386,13 +392,13 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_expect *exp; - const struct hlist_node *n, *next; + const struct hlist_node *next; const struct hlist_nulls_node *nn; unsigned int i; /* Get rid of expectations */ for (i = 0; i < nf_ct_expect_hsize; i++) { - hlist_for_each_entry_safe(exp, n, next, + hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { struct nf_conn_help *help = nfct_help(exp->master); if ((rcu_dereference_protected( diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 5d60e04f9679..9904b15f600e 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2370,14 +2370,13 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - struct hlist_node *n; u_int8_t l3proto = nfmsg->nfgen_family; rcu_read_lock(); last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: - hlist_for_each_entry(exp, n, &net->ct.expect_hash[cb->args[0]], + hlist_for_each_entry(exp, &net->ct.expect_hash[cb->args[0]], hnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; @@ -2510,7 +2509,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nfgenmsg *nfmsg = nlmsg_data(nlh); - struct hlist_node *n, *next; + struct hlist_node *next; u_int8_t u3 = nfmsg->nfgen_family; unsigned int i; u16 zone; @@ -2557,7 +2556,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* delete all expectations for this helper */ spin_lock_bh(&nf_conntrack_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { - hlist_for_each_entry_safe(exp, n, next, + hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { m_help = nfct_help(exp->master); @@ -2575,7 +2574,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* This basically means we have to flush everything*/ spin_lock_bh(&nf_conntrack_lock); for (i = 0; i < nf_ct_expect_hsize; i++) { - hlist_for_each_entry_safe(exp, n, next, + hlist_for_each_entry_safe(exp, next, &net->ct.expect_hash[i], hnode) { if (del_timer(&exp->timeout)) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 432f95780003..ba65b2041eb4 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -969,6 +969,10 @@ static int __init nf_conntrack_proto_dccp_init(void) { int ret; + ret = register_pernet_subsys(&dccp_net_ops); + if (ret < 0) + goto out_pernet; + ret = nf_ct_l4proto_register(&dccp_proto4); if (ret < 0) goto out_dccp4; @@ -977,16 +981,12 @@ static int __init nf_conntrack_proto_dccp_init(void) if (ret < 0) goto out_dccp6; - ret = register_pernet_subsys(&dccp_net_ops); - if (ret < 0) - goto out_pernet; - return 0; -out_pernet: - nf_ct_l4proto_unregister(&dccp_proto6); out_dccp6: nf_ct_l4proto_unregister(&dccp_proto4); out_dccp4: + unregister_pernet_subsys(&dccp_net_ops); +out_pernet: return ret; } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index bd7d01d9c7e7..155ce9f8a0db 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -420,18 +420,18 @@ static int __init nf_ct_proto_gre_init(void) { int ret; - ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4); - if (ret < 0) - goto out_gre4; - ret = register_pernet_subsys(&proto_gre_net_ops); if (ret < 0) goto out_pernet; + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4); + if (ret < 0) + goto out_gre4; + return 0; -out_pernet: - nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); out_gre4: + unregister_pernet_subsys(&proto_gre_net_ops); +out_pernet: return ret; } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 480f616d5936..ec83536def9a 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -888,6 +888,10 @@ static int __init nf_conntrack_proto_sctp_init(void) { int ret; + ret = register_pernet_subsys(&sctp_net_ops); + if (ret < 0) + goto out_pernet; + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp4); if (ret < 0) goto out_sctp4; @@ -896,16 +900,12 @@ static int __init nf_conntrack_proto_sctp_init(void) if (ret < 0) goto out_sctp6; - ret = register_pernet_subsys(&sctp_net_ops); - if (ret < 0) - goto out_pernet; - return 0; -out_pernet: - nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); out_sctp6: nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); out_sctp4: + unregister_pernet_subsys(&sctp_net_ops); +out_pernet: return ret; } diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 157489581c31..ca969f6273f7 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -371,6 +371,10 @@ static int __init nf_conntrack_proto_udplite_init(void) { int ret; + ret = register_pernet_subsys(&udplite_net_ops); + if (ret < 0) + goto out_pernet; + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite4); if (ret < 0) goto out_udplite4; @@ -379,16 +383,12 @@ static int __init nf_conntrack_proto_udplite_init(void) if (ret < 0) goto out_udplite6; - ret = register_pernet_subsys(&udplite_net_ops); - if (ret < 0) - goto out_pernet; - return 0; -out_pernet: - nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); out_udplite6: nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); out_udplite4: + unregister_pernet_subsys(&udplite_net_ops); +out_pernet: return ret; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 069229d919b6..e0c4373b4747 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -855,11 +855,11 @@ static int refresh_signalling_expectation(struct nf_conn *ct, { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_expect *exp; - struct hlist_node *n, *next; + struct hlist_node *next; int found = 0; spin_lock_bh(&nf_conntrack_lock); - hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) { + hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if (exp->class != SIP_EXPECT_SIGNALLING || !nf_inet_addr_cmp(&exp->tuple.dst.u3, addr) || exp->tuple.dst.protonum != proto || @@ -881,10 +881,10 @@ static void flush_expectations(struct nf_conn *ct, bool media) { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_expect *exp; - struct hlist_node *n, *next; + struct hlist_node *next; spin_lock_bh(&nf_conntrack_lock); - hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) { + hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) { if ((exp->class != SIP_EXPECT_SIGNALLING) ^ media) continue; if (!del_timer(&exp->timeout)) @@ -1593,10 +1593,8 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, end += strlen("\r\n\r\n") + clen; msglen = origlen = end - dptr; - if (msglen > datalen) { - nf_ct_helper_log(skb, ct, "incomplete/bad SIP message"); - return NF_DROP; - } + if (msglen > datalen) + return NF_ACCEPT; ret = process_sip_msg(skb, ct, protoff, dataoff, &dptr, &msglen); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 6bcce401fd1c..fedee3943661 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -568,6 +568,7 @@ static int __init nf_conntrack_standalone_init(void) register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); if (!nf_ct_netfilter_header) { pr_err("nf_conntrack: can't register to sysctl.\n"); + ret = -ENOMEM; goto out_sysctl; } #endif diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 5f2f9109f461..ad24be070e53 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -191,9 +191,8 @@ find_appropriate_src(struct net *net, u16 zone, unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn_nat *nat; const struct nf_conn *ct; - const struct hlist_node *n; - hlist_for_each_entry_rcu(nat, n, &net->ct.nat_bysource[h], bysource) { + hlist_for_each_entry_rcu(nat, &net->ct.nat_bysource[h], bysource) { ct = nat->ct; if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { /* Copy source part from reply tuple. */ @@ -468,33 +467,22 @@ EXPORT_SYMBOL_GPL(nf_nat_packet); struct nf_nat_proto_clean { u8 l3proto; u8 l4proto; - bool hash; }; -/* Clear NAT section of all conntracks, in case we're loaded again. */ -static int nf_nat_proto_clean(struct nf_conn *i, void *data) +/* kill conntracks with affected NAT section */ +static int nf_nat_proto_remove(struct nf_conn *i, void *data) { const struct nf_nat_proto_clean *clean = data; struct nf_conn_nat *nat = nfct_nat(i); if (!nat) return 0; - if (!(i->status & IPS_SRC_NAT_DONE)) - return 0; + if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) return 0; - if (clean->hash) { - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); - spin_unlock_bh(&nf_nat_lock); - } else { - memset(nat, 0, sizeof(*nat)); - i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | - IPS_SEQ_ADJUST); - } - return 0; + return i->status & IPS_NAT_MASK ? 1 : 0; } static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) @@ -506,16 +494,8 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) struct net *net; rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu(); - - /* Step 2 - clean NAT section */ - clean.hash = false; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); } @@ -527,16 +507,9 @@ static void nf_nat_l3proto_clean(u8 l3proto) struct net *net; rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu(); - /* Step 2 - clean NAT section */ - clean.hash = false; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); } @@ -774,7 +747,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index d578ec251712..0b1b32cda307 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -62,11 +62,6 @@ void nfnl_unlock(__u8 subsys_id) } EXPORT_SYMBOL_GPL(nfnl_unlock); -static struct mutex *nfnl_get_lock(__u8 subsys_id) -{ - return &table[subsys_id].mutex; -} - int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { nfnl_lock(n->subsys_id); @@ -199,7 +194,7 @@ replay: rcu_read_unlock(); nfnl_lock(subsys_id); if (rcu_dereference_protected(table[subsys_id].subsys, - lockdep_is_held(nfnl_get_lock(subsys_id))) != ss || + lockdep_is_held(&table[subsys_id].mutex)) != ss || nfnetlink_find_client(type, ss) != nc) err = -EAGAIN; else if (nc->call) diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 589d686f0b4c..dc3fd5d44464 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -49,6 +49,8 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, return -EINVAL; acct_name = nla_data(tb[NFACCT_NAME]); + if (strlen(acct_name) == 0) + return -EINVAL; list_for_each_entry(nfacct, &nfnl_acct_list, head) { if (strncmp(nfacct->name, acct_name, NFACCT_NAME_MAX) != 0) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 945950a8b1f1..a191b6db657e 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -282,7 +282,6 @@ nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb, const char *helper_name; struct nf_conntrack_helper *cur, *helper = NULL; struct nf_conntrack_tuple tuple; - struct hlist_node *n; int ret = 0, i; if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE]) @@ -296,7 +295,7 @@ nfnl_cthelper_new(struct sock *nfnl, struct sk_buff *skb, rcu_read_lock(); for (i = 0; i < nf_ct_helper_hsize && !helper; i++) { - hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) @@ -452,13 +451,12 @@ static int nfnl_cthelper_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct nf_conntrack_helper *cur, *last; - struct hlist_node *n; rcu_read_lock(); last = (struct nf_conntrack_helper *)cb->args[1]; for (; cb->args[0] < nf_ct_helper_hsize; cb->args[0]++) { restart: - hlist_for_each_entry_rcu(cur, n, + hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[cb->args[0]], hnode) { /* skip non-userspace conntrack helpers. */ @@ -495,7 +493,6 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, { int ret = -ENOENT, i; struct nf_conntrack_helper *cur; - struct hlist_node *n; struct sk_buff *skb2; char *helper_name = NULL; struct nf_conntrack_tuple tuple; @@ -520,7 +517,7 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, } for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_rcu(cur, n, &nf_ct_helper_hash[i], hnode) { + hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) @@ -568,7 +565,7 @@ nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb, { char *helper_name = NULL; struct nf_conntrack_helper *cur; - struct hlist_node *n, *tmp; + struct hlist_node *tmp; struct nf_conntrack_tuple tuple; bool tuple_set = false, found = false; int i, j = 0, ret; @@ -585,7 +582,7 @@ nfnl_cthelper_del(struct sock *nfnl, struct sk_buff *skb, } for (i = 0; i < nf_ct_helper_hsize; i++) { - hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i], + hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) @@ -654,13 +651,13 @@ err_out: static void __exit nfnl_cthelper_exit(void) { struct nf_conntrack_helper *cur; - struct hlist_node *n, *tmp; + struct hlist_node *tmp; int i; nfnetlink_subsys_unregister(&nfnl_cthelper_subsys); for (i=0; i<nf_ct_helper_hsize; i++) { - hlist_for_each_entry_safe(cur, n, tmp, &nf_ct_helper_hash[i], + hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i], hnode) { /* skip non-userspace conntrack helpers. */ if (!(cur->flags & NF_CT_HELPER_F_USERSPACE)) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 92fd8eca0d31..f248db572972 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -87,11 +87,10 @@ static struct nfulnl_instance * __instance_lookup(u_int16_t group_num) { struct hlist_head *head; - struct hlist_node *pos; struct nfulnl_instance *inst; head = &instance_table[instance_hashfn(group_num)]; - hlist_for_each_entry_rcu(inst, pos, head, hlist) { + hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->group_num == group_num) return inst; } @@ -717,11 +716,11 @@ nfulnl_rcv_nl_event(struct notifier_block *this, /* destroy all instances for this portid */ spin_lock_bh(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { - struct hlist_node *tmp, *t2; + struct hlist_node *t2; struct nfulnl_instance *inst; struct hlist_head *head = &instance_table[i]; - hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { + hlist_for_each_entry_safe(inst, t2, head, hlist) { if ((net_eq(n->net, &init_net)) && (n->portid == inst->peer_portid)) __instance_destroy(inst); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 3158d87b56a8..42680b2baa11 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -80,11 +80,10 @@ static struct nfqnl_instance * instance_lookup(u_int16_t queue_num) { struct hlist_head *head; - struct hlist_node *pos; struct nfqnl_instance *inst; head = &instance_table[instance_hashfn(queue_num)]; - hlist_for_each_entry_rcu(inst, pos, head, hlist) { + hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->queue_num == queue_num) return inst; } @@ -113,7 +112,7 @@ instance_create(u_int16_t queue_num, int portid) inst->queue_num = queue_num; inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; - inst->copy_range = 0xfffff; + inst->copy_range = 0xffff; inst->copy_mode = NFQNL_COPY_NONE; spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); @@ -583,11 +582,10 @@ nfqnl_dev_drop(int ifindex) rcu_read_lock(); for (i = 0; i < INSTANCE_BUCKETS; i++) { - struct hlist_node *tmp; struct nfqnl_instance *inst; struct hlist_head *head = &instance_table[i]; - hlist_for_each_entry_rcu(inst, tmp, head, hlist) + hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, dev_cmp, ifindex); } @@ -627,11 +625,11 @@ nfqnl_rcv_nl_event(struct notifier_block *this, /* destroy all instances for this portid */ spin_lock(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { - struct hlist_node *tmp, *t2; + struct hlist_node *t2; struct nfqnl_instance *inst; struct hlist_head *head = &instance_table[i]; - hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { + hlist_for_each_entry_safe(inst, t2, head, hlist) { if ((n->net == &init_net) && (n->portid == inst->peer_portid)) __instance_destroy(inst); @@ -1064,8 +1062,10 @@ static int __init nfnetlink_queue_init(void) #ifdef CONFIG_PROC_FS if (!proc_create("nfnetlink_queue", 0440, - proc_net_netfilter, &nfqnl_file_ops)) + proc_net_netfilter, &nfqnl_file_ops)) { + status = -ENOMEM; goto cleanup_subsys; + } #endif register_netdevice_notifier(&nfqnl_dev_notifier); diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index ba92824086f3..3228d7f24eb4 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -124,6 +124,9 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par) const struct xt_audit_info *info = par->targinfo; struct audit_buffer *ab; + if (audit_enabled == 0) + goto errout; + ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); if (ab == NULL) goto errout; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index f264032b8c56..370adf622cef 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -43,12 +43,11 @@ static void xt_rateest_hash_insert(struct xt_rateest *est) struct xt_rateest *xt_rateest_lookup(const char *name) { struct xt_rateest *est; - struct hlist_node *n; unsigned int h; h = xt_rateest_hash(name); mutex_lock(&xt_rateest_mutex); - hlist_for_each_entry(est, n, &rateest_hash[h], list) { + hlist_for_each_entry(est, &rateest_hash[h], list) { if (strcmp(est->name, name) == 0) { est->refcnt++; mutex_unlock(&xt_rateest_mutex); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 70b5591a2586..c40b2695633b 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -101,7 +101,7 @@ static int count_them(struct net *net, { const struct nf_conntrack_tuple_hash *found; struct xt_connlimit_conn *conn; - struct hlist_node *pos, *n; + struct hlist_node *n; struct nf_conn *found_ct; struct hlist_head *hash; bool addit = true; @@ -115,7 +115,7 @@ static int count_them(struct net *net, rcu_read_lock(); /* check the saved connections */ - hlist_for_each_entry_safe(conn, pos, n, hash, node) { + hlist_for_each_entry_safe(conn, n, hash, node) { found = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE, &conn->tuple); found_ct = NULL; @@ -258,14 +258,14 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_connlimit_info *info = par->matchinfo; struct xt_connlimit_conn *conn; - struct hlist_node *pos, *n; + struct hlist_node *n; struct hlist_head *hash = info->data->iphash; unsigned int i; nf_ct_l3proto_module_put(par->family); for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) { - hlist_for_each_entry_safe(conn, pos, n, &hash[i], node) { + hlist_for_each_entry_safe(conn, n, &hash[i], node) { hlist_del(&conn->node); kfree(conn); } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 98218c896d2e..f330e8beaf69 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -141,11 +141,10 @@ dsthash_find(const struct xt_hashlimit_htable *ht, const struct dsthash_dst *dst) { struct dsthash_ent *ent; - struct hlist_node *pos; u_int32_t hash = hash_dst(ht, dst); if (!hlist_empty(&ht->hash[hash])) { - hlist_for_each_entry_rcu(ent, pos, &ht->hash[hash], node) + hlist_for_each_entry_rcu(ent, &ht->hash[hash], node) if (dst_cmp(ent, dst)) { spin_lock(&ent->lock); return ent; @@ -297,8 +296,8 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, spin_lock_bh(&ht->lock); for (i = 0; i < ht->cfg.size; i++) { struct dsthash_ent *dh; - struct hlist_node *pos, *n; - hlist_for_each_entry_safe(dh, pos, n, &ht->hash[i], node) { + struct hlist_node *n; + hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { if ((*select)(ht, dh)) dsthash_free(ht, dh); } @@ -343,9 +342,8 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, { struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); struct xt_hashlimit_htable *hinfo; - struct hlist_node *pos; - hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) { + hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->pde->name) && hinfo->family == family) { hinfo->use++; @@ -821,10 +819,9 @@ static int dl_seq_show(struct seq_file *s, void *v) struct xt_hashlimit_htable *htable = s->private; unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; - struct hlist_node *pos; if (!hlist_empty(&htable->hash[*bucket])) { - hlist_for_each_entry(ent, pos, &htable->hash[*bucket], node) + hlist_for_each_entry(ent, &htable->hash[*bucket], node) if (dl_seq_real_show(ent, htable->family, s)) return -1; } @@ -877,7 +874,6 @@ static int __net_init hashlimit_proc_net_init(struct net *net) static void __net_exit hashlimit_proc_net_exit(struct net *net) { struct xt_hashlimit_htable *hinfo; - struct hlist_node *pos; struct proc_dir_entry *pde; struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); @@ -890,7 +886,7 @@ static void __net_exit hashlimit_proc_net_exit(struct net *net) if (pde == NULL) pde = hashlimit_net->ip6t_hashlimit; - hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) + hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) remove_proc_entry(hinfo->pde->name, pde); hashlimit_net->ipt_hashlimit = NULL; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 31bf233dae97..d9cad315229d 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -540,7 +540,7 @@ static ssize_t recent_mt_proc_write(struct file *file, const char __user *input, size_t size, loff_t *loff) { - const struct proc_dir_entry *pde = PDE(file->f_path.dentry->d_inode); + const struct proc_dir_entry *pde = PDE(file_inode(file)); struct recent_table *t = pde->data; struct recent_entry *e; char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")]; diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 847d495cd4de..8a6c6ea466d8 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1189,8 +1189,6 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; - u32 skip_addr4 = cb->args[2]; - u32 skip_addr6 = cb->args[3]; u32 iter_bkt; u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; @@ -1215,7 +1213,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < skip_addr4) + if (iter_addr4++ < cb->args[2]) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1231,7 +1229,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < skip_addr6) + if (iter_addr6++ < cb->args[3]) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1250,10 +1248,10 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, unlabel_staticlist_return: rcu_read_unlock(); - cb->args[0] = skip_bkt; - cb->args[1] = skip_chain; - cb->args[2] = skip_addr4; - cb->args[3] = skip_addr6; + cb->args[0] = iter_bkt; + cb->args[1] = iter_chain; + cb->args[2] = iter_addr4; + cb->args[3] = iter_addr6; return skb->len; } @@ -1273,12 +1271,9 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, { struct netlbl_unlhsh_walk_arg cb_arg; struct netlbl_unlhsh_iface *iface; - u32 skip_addr4 = cb->args[0]; - u32 skip_addr6 = cb->args[1]; - u32 iter_addr4 = 0; + u32 iter_addr4 = 0, iter_addr6 = 0; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) - u32 iter_addr6 = 0; struct netlbl_af6list *addr6; #endif @@ -1292,7 +1287,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, goto unlabel_staticlistdef_return; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < skip_addr4) + if (iter_addr4++ < cb->args[0]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, @@ -1305,7 +1300,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, } #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < skip_addr6) + if (iter_addr6++ < cb->args[1]) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, @@ -1320,8 +1315,8 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, unlabel_staticlistdef_return: rcu_read_unlock(); - cb->args[0] = skip_addr4; - cb->args[1] = skip_addr6; + cb->args[0] = iter_addr4; + cb->args[1] = iter_addr6; return skb->len; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3d55e0c713e2..1e3fd5bfcd86 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -248,11 +248,10 @@ static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) struct nl_portid_hash *hash = &nl_table[protocol].hash; struct hlist_head *head; struct sock *sk; - struct hlist_node *node; read_lock(&nl_table_lock); head = nl_portid_hashfn(hash, portid); - sk_for_each(sk, node, head) { + sk_for_each(sk, head) { if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->portid == portid)) { sock_hold(sk); goto found; @@ -312,9 +311,9 @@ static int nl_portid_hash_rehash(struct nl_portid_hash *hash, int grow) for (i = 0; i <= omask; i++) { struct sock *sk; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; - sk_for_each_safe(sk, node, tmp, &otable[i]) + sk_for_each_safe(sk, tmp, &otable[i]) __sk_add_node(sk, nl_portid_hashfn(hash, nlk_sk(sk)->portid)); } @@ -344,7 +343,6 @@ static void netlink_update_listeners(struct sock *sk) { struct netlink_table *tbl = &nl_table[sk->sk_protocol]; - struct hlist_node *node; unsigned long mask; unsigned int i; struct listeners *listeners; @@ -355,7 +353,7 @@ netlink_update_listeners(struct sock *sk) for (i = 0; i < NLGRPLONGS(tbl->groups); i++) { mask = 0; - sk_for_each_bound(sk, node, &tbl->mc_list) { + sk_for_each_bound(sk, &tbl->mc_list) { if (i < NLGRPLONGS(nlk_sk(sk)->ngroups)) mask |= nlk_sk(sk)->groups[i]; } @@ -371,18 +369,17 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 portid) struct hlist_head *head; int err = -EADDRINUSE; struct sock *osk; - struct hlist_node *node; int len; netlink_table_grab(); head = nl_portid_hashfn(hash, portid); len = 0; - sk_for_each(osk, node, head) { + sk_for_each(osk, head) { if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->portid == portid)) break; len++; } - if (node) + if (osk) goto err; err = -EBUSY; @@ -575,7 +572,6 @@ static int netlink_autobind(struct socket *sock) struct nl_portid_hash *hash = &nl_table[sk->sk_protocol].hash; struct hlist_head *head; struct sock *osk; - struct hlist_node *node; s32 portid = task_tgid_vnr(current); int err; static s32 rover = -4097; @@ -584,7 +580,7 @@ retry: cond_resched(); netlink_table_grab(); head = nl_portid_hashfn(hash, portid); - sk_for_each(osk, node, head) { + sk_for_each(osk, head) { if (!net_eq(sock_net(osk), net)) continue; if (nlk_sk(osk)->portid == portid) { @@ -809,7 +805,7 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) struct sock *netlink_getsockbyfilp(struct file *filp) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); struct sock *sock; if (!S_ISSOCK(inode->i_mode)) @@ -1101,7 +1097,6 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; - struct hlist_node *node; struct sock *sk; skb = netlink_trim(skb, allocation); @@ -1124,7 +1119,7 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid netlink_lock_table(); - sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) + sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); consume_skb(skb); @@ -1200,7 +1195,6 @@ out: int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; - struct hlist_node *node; struct sock *sk; int ret = 0; @@ -1212,7 +1206,7 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) read_lock(&nl_table_lock); - sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) + sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); read_unlock(&nl_table_lock); @@ -1676,10 +1670,9 @@ int netlink_change_ngroups(struct sock *sk, unsigned int groups) void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group) { struct sock *sk; - struct hlist_node *node; struct netlink_table *tbl = &nl_table[ksk->sk_protocol]; - sk_for_each_bound(sk, node, &tbl->mc_list) + sk_for_each_bound(sk, &tbl->mc_list) netlink_update_socket_mc(nlk_sk(sk), group, 0); } @@ -1974,14 +1967,13 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) struct nl_seq_iter *iter = seq->private; int i, j; struct sock *s; - struct hlist_node *node; loff_t off = 0; for (i = 0; i < MAX_LINKS; i++) { struct nl_portid_hash *hash = &nl_table[i].hash; for (j = 0; j <= hash->mask; j++) { - sk_for_each(s, node, &hash->table[j]) { + sk_for_each(s, &hash->table[j]) { if (sock_net(s) != seq_file_net(seq)) continue; if (off == pos) { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index f2aabb6f4105..5a55be3f17a5 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -142,6 +142,7 @@ int genl_register_mc_group(struct genl_family *family, int err = 0; BUG_ON(grp->name[0] == '\0'); + BUG_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL); genl_lock(); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 297b07a029de..103bd704b5fc 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -104,10 +104,9 @@ static void nr_remove_socket(struct sock *sk) static void nr_kill_by_device(struct net_device *dev) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) + sk_for_each(s, &nr_list) if (nr_sk(s)->device == dev) nr_disconnect(s, ENETUNREACH); spin_unlock_bh(&nr_list_lock); @@ -149,10 +148,9 @@ static void nr_insert_socket(struct sock *sk) static struct sock *nr_find_listener(ax25_address *addr) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) + sk_for_each(s, &nr_list) if (!ax25cmp(&nr_sk(s)->source_addr, addr) && s->sk_state == TCP_LISTEN) { bh_lock_sock(s); @@ -170,10 +168,9 @@ found: static struct sock *nr_find_socket(unsigned char index, unsigned char id) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) { + sk_for_each(s, &nr_list) { struct nr_sock *nr = nr_sk(s); if (nr->my_index == index && nr->my_id == id) { @@ -194,10 +191,9 @@ static struct sock *nr_find_peer(unsigned char index, unsigned char id, ax25_address *dest) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&nr_list_lock); - sk_for_each(s, node, &nr_list) { + sk_for_each(s, &nr_list) { struct nr_sock *nr = nr_sk(s); if (nr->your_index == index && nr->your_id == id && @@ -1177,6 +1173,7 @@ static int nr_recvmsg(struct kiocb *iocb, struct socket *sock, } if (sax != NULL) { + memset(sax, 0, sizeof(*sax)); sax->sax25_family = AF_NETROM; skb_copy_from_linear_data_offset(skb, 7, sax->sax25_call.ax25_call, AX25_ADDR_LEN); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 70ffff76a967..b976d5eff2de 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -49,10 +49,9 @@ static struct nr_node *nr_node_get(ax25_address *callsign) { struct nr_node *found = NULL; struct nr_node *nr_node; - struct hlist_node *node; spin_lock_bh(&nr_node_list_lock); - nr_node_for_each(nr_node, node, &nr_node_list) + nr_node_for_each(nr_node, &nr_node_list) if (ax25cmp(callsign, &nr_node->callsign) == 0) { nr_node_hold(nr_node); found = nr_node; @@ -67,10 +66,9 @@ static struct nr_neigh *nr_neigh_get_dev(ax25_address *callsign, { struct nr_neigh *found = NULL; struct nr_neigh *nr_neigh; - struct hlist_node *node; spin_lock_bh(&nr_neigh_list_lock); - nr_neigh_for_each(nr_neigh, node, &nr_neigh_list) + nr_neigh_for_each(nr_neigh, &nr_neigh_list) if (ax25cmp(callsign, &nr_neigh->callsign) == 0 && nr_neigh->dev == dev) { nr_neigh_hold(nr_neigh); @@ -114,10 +112,9 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, */ if (nr_neigh != NULL && nr_neigh->failed != 0 && quality == 0) { struct nr_node *nr_nodet; - struct hlist_node *node; spin_lock_bh(&nr_node_list_lock); - nr_node_for_each(nr_nodet, node, &nr_node_list) { + nr_node_for_each(nr_nodet, &nr_node_list) { nr_node_lock(nr_nodet); for (i = 0; i < nr_nodet->count; i++) if (nr_nodet->routes[i].neighbour == nr_neigh) @@ -485,11 +482,11 @@ static int nr_dec_obs(void) { struct nr_neigh *nr_neigh; struct nr_node *s; - struct hlist_node *node, *nodet; + struct hlist_node *nodet; int i; spin_lock_bh(&nr_node_list_lock); - nr_node_for_each_safe(s, node, nodet, &nr_node_list) { + nr_node_for_each_safe(s, nodet, &nr_node_list) { nr_node_lock(s); for (i = 0; i < s->count; i++) { switch (s->routes[i].obs_count) { @@ -540,15 +537,15 @@ static int nr_dec_obs(void) void nr_rt_device_down(struct net_device *dev) { struct nr_neigh *s; - struct hlist_node *node, *nodet, *node2, *node2t; + struct hlist_node *nodet, *node2t; struct nr_node *t; int i; spin_lock_bh(&nr_neigh_list_lock); - nr_neigh_for_each_safe(s, node, nodet, &nr_neigh_list) { + nr_neigh_for_each_safe(s, nodet, &nr_neigh_list) { if (s->dev == dev) { spin_lock_bh(&nr_node_list_lock); - nr_node_for_each_safe(t, node2, node2t, &nr_node_list) { + nr_node_for_each_safe(t, node2t, &nr_node_list) { nr_node_lock(t); for (i = 0; i < t->count; i++) { if (t->routes[i].neighbour == s) { @@ -737,11 +734,10 @@ int nr_rt_ioctl(unsigned int cmd, void __user *arg) void nr_link_failed(ax25_cb *ax25, int reason) { struct nr_neigh *s, *nr_neigh = NULL; - struct hlist_node *node; struct nr_node *nr_node = NULL; spin_lock_bh(&nr_neigh_list_lock); - nr_neigh_for_each(s, node, &nr_neigh_list) { + nr_neigh_for_each(s, &nr_neigh_list) { if (s->ax25 == ax25) { nr_neigh_hold(s); nr_neigh = s; @@ -761,7 +757,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) return; } spin_lock_bh(&nr_node_list_lock); - nr_node_for_each(nr_node, node, &nr_node_list) { + nr_node_for_each(nr_node, &nr_node_list) { nr_node_lock(nr_node); if (nr_node->which < nr_node->count && nr_node->routes[nr_node->which].neighbour == nr_neigh) @@ -1013,16 +1009,16 @@ void __exit nr_rt_free(void) { struct nr_neigh *s = NULL; struct nr_node *t = NULL; - struct hlist_node *node, *nodet; + struct hlist_node *nodet; spin_lock_bh(&nr_neigh_list_lock); spin_lock_bh(&nr_node_list_lock); - nr_node_for_each_safe(t, node, nodet, &nr_node_list) { + nr_node_for_each_safe(t, nodet, &nr_node_list) { nr_node_lock(t); nr_remove_node_locked(t); nr_node_unlock(t); } - nr_neigh_for_each_safe(s, node, nodet, &nr_neigh_list) { + nr_neigh_for_each_safe(s, nodet, &nr_neigh_list) { while(s->count) { s->count--; nr_neigh_put(s); diff --git a/net/nfc/llcp/llcp.c b/net/nfc/llcp/llcp.c index 746f5a2f9804..ee25f25f0cd6 100644 --- a/net/nfc/llcp/llcp.c +++ b/net/nfc/llcp/llcp.c @@ -68,17 +68,18 @@ static void nfc_llcp_socket_purge(struct nfc_llcp_sock *sock) } } -static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) +static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen, + int err) { struct sock *sk; - struct hlist_node *node, *tmp; + struct hlist_node *tmp; struct nfc_llcp_sock *llcp_sock; skb_queue_purge(&local->tx_queue); write_lock(&local->sockets.lock); - sk_for_each_safe(sk, node, tmp, &local->sockets.head) { + sk_for_each_safe(sk, tmp, &local->sockets.head) { llcp_sock = nfc_llcp_sock(sk); bh_lock_sock(sk); @@ -100,11 +101,12 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) nfc_llcp_accept_unlink(accept_sk); + if (err) + accept_sk->sk_err = err; accept_sk->sk_state = LLCP_CLOSED; + accept_sk->sk_state_change(sk); bh_unlock_sock(accept_sk); - - sock_orphan(accept_sk); } if (listen == true) { @@ -123,16 +125,45 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool listen) continue; } + if (err) + sk->sk_err = err; sk->sk_state = LLCP_CLOSED; + sk->sk_state_change(sk); bh_unlock_sock(sk); - sock_orphan(sk); - sk_del_node_init(sk); } write_unlock(&local->sockets.lock); + + /* + * If we want to keep the listening sockets alive, + * we don't touch the RAW ones. + */ + if (listen == true) + return; + + write_lock(&local->raw_sockets.lock); + + sk_for_each_safe(sk, tmp, &local->raw_sockets.head) { + llcp_sock = nfc_llcp_sock(sk); + + bh_lock_sock(sk); + + nfc_llcp_socket_purge(llcp_sock); + + if (err) + sk->sk_err = err; + sk->sk_state = LLCP_CLOSED; + sk->sk_state_change(sk); + + bh_unlock_sock(sk); + + sk_del_node_init(sk); + } + + write_unlock(&local->raw_sockets.lock); } struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) @@ -142,20 +173,25 @@ struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) return local; } -static void local_release(struct kref *ref) +static void local_cleanup(struct nfc_llcp_local *local, bool listen) { - struct nfc_llcp_local *local; - - local = container_of(ref, struct nfc_llcp_local, ref); - - list_del(&local->list); - nfc_llcp_socket_release(local, false); + nfc_llcp_socket_release(local, listen, ENXIO); del_timer_sync(&local->link_timer); skb_queue_purge(&local->tx_queue); cancel_work_sync(&local->tx_work); cancel_work_sync(&local->rx_work); cancel_work_sync(&local->timeout_work); kfree_skb(local->rx_pending); +} + +static void local_release(struct kref *ref) +{ + struct nfc_llcp_local *local; + + local = container_of(ref, struct nfc_llcp_local, ref); + + list_del(&local->list); + local_cleanup(local, false); kfree(local); } @@ -171,7 +207,6 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, u8 ssap, u8 dsap) { struct sock *sk; - struct hlist_node *node; struct nfc_llcp_sock *llcp_sock, *tmp_sock; pr_debug("ssap dsap %d %d\n", ssap, dsap); @@ -183,7 +218,7 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, llcp_sock = NULL; - sk_for_each(sk, node, &local->sockets.head) { + sk_for_each(sk, &local->sockets.head) { tmp_sock = nfc_llcp_sock(sk); if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) { @@ -272,7 +307,6 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, u8 *sn, size_t sn_len) { struct sock *sk; - struct hlist_node *node; struct nfc_llcp_sock *llcp_sock, *tmp_sock; pr_debug("sn %zd %p\n", sn_len, sn); @@ -284,7 +318,7 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, llcp_sock = NULL; - sk_for_each(sk, node, &local->sockets.head) { + sk_for_each(sk, &local->sockets.head) { tmp_sock = nfc_llcp_sock(sk); pr_debug("llcp sock %p\n", tmp_sock); @@ -601,14 +635,13 @@ static void nfc_llcp_set_nrns(struct nfc_llcp_sock *sock, struct sk_buff *pdu) void nfc_llcp_send_to_raw_sock(struct nfc_llcp_local *local, struct sk_buff *skb, u8 direction) { - struct hlist_node *node; struct sk_buff *skb_copy = NULL, *nskb; struct sock *sk; u8 *data; read_lock(&local->raw_sockets.lock); - sk_for_each(sk, node, &local->raw_sockets.head) { + sk_for_each(sk, &local->raw_sockets.head) { if (sk->sk_state != LLCP_BOUND) continue; @@ -697,11 +730,10 @@ static struct nfc_llcp_sock *nfc_llcp_connecting_sock_get(struct nfc_llcp_local { struct sock *sk; struct nfc_llcp_sock *llcp_sock; - struct hlist_node *node; read_lock(&local->connecting_sockets.lock); - sk_for_each(sk, node, &local->connecting_sockets.head) { + sk_for_each(sk, &local->connecting_sockets.head) { llcp_sock = nfc_llcp_sock(sk); if (llcp_sock->ssap == ssap) { @@ -789,7 +821,6 @@ static void nfc_llcp_recv_ui(struct nfc_llcp_local *local, skb_get(skb); } else { pr_err("Receive queue is full\n"); - kfree_skb(skb); } nfc_llcp_sock_put(llcp_sock); @@ -990,7 +1021,6 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, skb_get(skb); } else { pr_err("Receive queue is full\n"); - kfree_skb(skb); } } @@ -1352,7 +1382,7 @@ void nfc_llcp_mac_is_down(struct nfc_dev *dev) return; /* Close and purge all existing sockets */ - nfc_llcp_socket_release(local, true); + nfc_llcp_socket_release(local, true, 0); } void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, @@ -1431,6 +1461,8 @@ void nfc_llcp_unregister_device(struct nfc_dev *dev) return; } + local_cleanup(local, false); + nfc_llcp_local_put(local); } diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index 5332751943a9..6c94447ec414 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -270,7 +270,9 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent, } if (sk->sk_state == LLCP_CONNECTED || !newsock) { - nfc_llcp_accept_unlink(sk); + list_del_init(&lsk->accept_queue); + sock_put(sk); + if (newsock) sock_graft(sk, newsock); @@ -278,6 +280,8 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent, pr_debug("Returning sk state %d\n", sk->sk_state); + sk_acceptq_removed(parent); + return sk; } @@ -462,8 +466,6 @@ static int llcp_sock_release(struct socket *sock) nfc_llcp_accept_unlink(accept_sk); release_sock(accept_sk); - - sock_orphan(accept_sk); } } @@ -644,6 +646,8 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, pr_debug("%p %zu\n", sk, len); + msg->msg_namelen = 0; + lock_sock(sk); if (sk->sk_state == LLCP_CLOSED && @@ -689,6 +693,7 @@ static int llcp_sock_recvmsg(struct kiocb *iocb, struct socket *sock, pr_debug("Datagram socket %d %d\n", ui_cb->dsap, ui_cb->ssap); + memset(sockaddr, 0, sizeof(*sockaddr)); sockaddr->sa_family = AF_NFC; sockaddr->nfc_protocol = NFC_PROTO_NFC_DEP; sockaddr->dsap = ui_cb->dsap; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ac2defeeba83..d4d5363c7ba7 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -58,7 +58,7 @@ static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci) if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(skb->data - + ETH_HLEN, VLAN_HLEN, 0)); + + (2 * ETH_ALEN), VLAN_HLEN, 0)); vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *current_tci = vhdr->h_vlan_TCI; @@ -115,7 +115,7 @@ static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vla if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_add(skb->csum, csum_partial(skb->data - + ETH_HLEN, VLAN_HLEN, 0)); + + (2 * ETH_ALEN), VLAN_HLEN, 0)); } __vlan_hwaccel_put_tag(skb, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9dc537df46c4..6980c3e6f066 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -158,11 +158,10 @@ static struct hlist_head *vport_hash_bucket(const struct datapath *dp, struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) { struct vport *vport; - struct hlist_node *n; struct hlist_head *head; head = vport_hash_bucket(dp, port_no); - hlist_for_each_entry_rcu(vport, n, head, dp_hash_node) { + hlist_for_each_entry_rcu(vport, head, dp_hash_node) { if (vport->port_no == port_no) return vport; } @@ -395,6 +394,7 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex, skb_copy_and_csum_dev(skb, nla_data(nla)); + genlmsg_end(user_skb, upcall); err = genlmsg_unicast(net, user_skb, upcall_info->portid); out: @@ -1386,9 +1386,9 @@ static void __dp_destroy(struct datapath *dp) for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; - struct hlist_node *node, *n; + struct hlist_node *n; - hlist_for_each_entry_safe(vport, node, n, &dp->ports[i], dp_hash_node) + hlist_for_each_entry_safe(vport, n, &dp->ports[i], dp_hash_node) if (vport->port_no != OVSP_LOCAL) ovs_dp_detach_port(vport); } @@ -1593,10 +1593,8 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, return ERR_PTR(-ENOMEM); retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); - if (retval < 0) { - kfree_skb(skb); - return ERR_PTR(retval); - } + BUG_ON(retval < 0); + return skb; } @@ -1691,6 +1689,7 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(vport)) goto exit_unlock; + err = 0; reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, OVS_VPORT_CMD_NEW); if (IS_ERR(reply)) { @@ -1725,24 +1724,32 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) err = -EINVAL; + reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!reply) { + err = -ENOMEM; + goto exit_unlock; + } + if (!err && a[OVS_VPORT_ATTR_OPTIONS]) err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); if (err) - goto exit_unlock; + goto exit_free; + if (a[OVS_VPORT_ATTR_UPCALL_PID]) vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, - OVS_VPORT_CMD_NEW); - if (IS_ERR(reply)) { - netlink_set_err(sock_net(skb->sk)->genl_sock, 0, - ovs_dp_vport_multicast_group.id, PTR_ERR(reply)); - goto exit_unlock; - } + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_NEW); + BUG_ON(err < 0); genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); + rtnl_unlock(); + return 0; + +exit_free: + kfree_skb(reply); exit_unlock: rtnl_unlock(); return err; @@ -1772,6 +1779,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(reply)) goto exit_unlock; + err = 0; ovs_dp_detach_port(vport); genl_notify(reply, genl_info_net(info), info->snd_portid, @@ -1825,10 +1833,9 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); for (i = bucket; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; - struct hlist_node *n; j = 0; - hlist_for_each_entry_rcu(vport, n, &dp->ports[i], dp_hash_node) { + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { if (j >= skip && ovs_vport_cmd_fill_info(vport, skb, NETLINK_CB(cb->skb).portid, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index c3294cebc4f2..67a2b783fe70 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -299,10 +299,10 @@ void ovs_flow_tbl_destroy(struct flow_table *table) for (i = 0; i < table->n_buckets; i++) { struct sw_flow *flow; struct hlist_head *head = flex_array_get(table->buckets, i); - struct hlist_node *node, *n; + struct hlist_node *n; int ver = table->node_ver; - hlist_for_each_entry_safe(flow, node, n, head, hash_node[ver]) { + hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) { hlist_del_rcu(&flow->hash_node[ver]); ovs_flow_free(flow); } @@ -332,7 +332,6 @@ struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *la { struct sw_flow *flow; struct hlist_head *head; - struct hlist_node *n; int ver; int i; @@ -340,7 +339,7 @@ struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *la while (*bucket < table->n_buckets) { i = 0; head = flex_array_get(table->buckets, *bucket); - hlist_for_each_entry_rcu(flow, n, head, hash_node[ver]) { + hlist_for_each_entry_rcu(flow, head, hash_node[ver]) { if (i < *last) { i++; continue; @@ -367,11 +366,10 @@ static void flow_table_copy_flows(struct flow_table *old, struct flow_table *new for (i = 0; i < old->n_buckets; i++) { struct sw_flow *flow; struct hlist_head *head; - struct hlist_node *n; head = flex_array_get(old->buckets, i); - hlist_for_each_entry(flow, n, head, hash_node[old_ver]) + hlist_for_each_entry(flow, head, hash_node[old_ver]) ovs_flow_tbl_insert(new, flow); } old->keep_flows = true; @@ -484,7 +482,11 @@ static __be16 parse_ethertype(struct sk_buff *skb) return htons(ETH_P_802_2); __skb_pull(skb, sizeof(struct llc_snap_hdr)); - return llc->ethertype; + + if (ntohs(llc->ethertype) >= 1536) + return llc->ethertype; + + return htons(ETH_P_802_2); } static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, @@ -766,14 +768,13 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table, struct sw_flow_key *key, int key_len) { struct sw_flow *flow; - struct hlist_node *n; struct hlist_head *head; u32 hash; hash = ovs_flow_hash(key, key_len); head = find_bucket(table, hash); - hlist_for_each_entry_rcu(flow, n, head, hash_node[table->node_ver]) { + hlist_for_each_entry_rcu(flow, head, hash_node[table->node_ver]) { if (flow->hash == hash && !memcmp(&flow->key, key, key_len)) { @@ -794,9 +795,9 @@ void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow) void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) { + BUG_ON(table->count == 0); hlist_del_rcu(&flow->hash_node[table->node_ver]); table->count--; - BUG_ON(table->count < 0); } /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 670cbc3518de..2130d61c384a 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -43,8 +43,7 @@ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) /* Make our own copy of the packet. Otherwise we will mangle the * packet for anyone who came before us (e.g. tcpdump via AF_PACKET). - * (No one comes after us, since we tell handle_bridge() that we took - * the packet.) */ + */ skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) return; diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 70af0bedbac4..f6b8132ce4cb 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -86,9 +86,8 @@ struct vport *ovs_vport_locate(struct net *net, const char *name) { struct hlist_head *bucket = hash_bucket(net, name); struct vport *vport; - struct hlist_node *node; - hlist_for_each_entry_rcu(vport, node, bucket, hash_node) + hlist_for_each_entry_rcu(vport, bucket, hash_node) if (!strcmp(name, vport->ops->get_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; @@ -326,8 +325,7 @@ int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb) * @skb: skb that was received * * Must be called with rcu_read_lock. The packet cannot be shared and - * skb->data should point to the Ethernet header. The caller must have already - * called compute_ip_summed() to initialize the checksumming fields. + * skb->data should point to the Ethernet header. */ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb) { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c7bfeff10767..1d6793dbfbae 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3263,12 +3263,11 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, static int packet_notifier(struct notifier_block *this, unsigned long msg, void *data) { struct sock *sk; - struct hlist_node *node; struct net_device *dev = data; struct net *net = dev_net(dev); rcu_read_lock(); - sk_for_each_rcu(sk, node, &net->packet.sklist) { + sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { diff --git a/net/packet/diag.c b/net/packet/diag.c index 8db6e21c46bd..d3fcd1ebef7e 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -172,13 +172,12 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct packet_diag_req *req; struct net *net; struct sock *sk; - struct hlist_node *node; net = sock_net(skb->sk); req = nlmsg_data(cb->nlh); mutex_lock(&net->packet.sklist_lock); - sk_for_each(sk, node, &net->packet.sklist) { + sk_for_each(sk, &net->packet.sklist) { if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 576f22c9c76e..e77411735de8 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -640,11 +640,10 @@ static struct sock *pep_find_pipe(const struct hlist_head *hlist, const struct sockaddr_pn *dst, u8 pipe_handle) { - struct hlist_node *node; struct sock *sknode; u16 dobj = pn_sockaddr_get_object(dst); - sk_for_each(sknode, node, hlist) { + sk_for_each(sknode, hlist) { struct pep_sock *pnnode = pep_sk(sknode); /* Ports match, but addresses might not: */ diff --git a/net/phonet/socket.c b/net/phonet/socket.c index b7e982782255..1afd1381cdc7 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -76,7 +76,6 @@ static struct hlist_head *pn_hash_list(u16 obj) */ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) { - struct hlist_node *node; struct sock *sknode; struct sock *rval = NULL; u16 obj = pn_sockaddr_get_object(spn); @@ -84,7 +83,7 @@ struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *spn) struct hlist_head *hlist = pn_hash_list(obj); rcu_read_lock(); - sk_for_each_rcu(sknode, node, hlist) { + sk_for_each_rcu(sknode, hlist) { struct pn_sock *pn = pn_sk(sknode); BUG_ON(!pn->sobject); /* unbound socket */ @@ -120,10 +119,9 @@ void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb) rcu_read_lock(); for (h = 0; h < PN_HASHSIZE; h++) { - struct hlist_node *node; struct sock *sknode; - sk_for_each(sknode, node, hlist) { + sk_for_each(sknode, hlist) { struct sk_buff *clone; if (!net_eq(sock_net(sknode), net)) @@ -543,12 +541,11 @@ static struct sock *pn_sock_get_idx(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); struct hlist_head *hlist = pnsocks.hlist; - struct hlist_node *node; struct sock *sknode; unsigned int h; for (h = 0; h < PN_HASHSIZE; h++) { - sk_for_each_rcu(sknode, node, hlist) { + sk_for_each_rcu(sknode, hlist) { if (!net_eq(net, sock_net(sknode))) continue; if (!pos) diff --git a/net/rds/bind.c b/net/rds/bind.c index 637bde56c9db..b5ad65a0067e 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -52,13 +52,12 @@ static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port, struct rds_sock *insert) { struct rds_sock *rs; - struct hlist_node *node; struct hlist_head *head = hash_to_bucket(addr, port); u64 cmp; u64 needle = ((u64)be32_to_cpu(addr) << 32) | be16_to_cpu(port); rcu_read_lock(); - hlist_for_each_entry_rcu(rs, node, head, rs_bound_node) { + hlist_for_each_entry_rcu(rs, head, rs_bound_node) { cmp = ((u64)be32_to_cpu(rs->rs_bound_addr) << 32) | be16_to_cpu(rs->rs_bound_port); diff --git a/net/rds/connection.c b/net/rds/connection.c index 9e07c756d1f9..642ad42c416b 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -69,9 +69,8 @@ static struct rds_connection *rds_conn_lookup(struct hlist_head *head, struct rds_transport *trans) { struct rds_connection *conn, *ret = NULL; - struct hlist_node *pos; - hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) { + hlist_for_each_entry_rcu(conn, head, c_hash_node) { if (conn->c_faddr == faddr && conn->c_laddr == laddr && conn->c_trans == trans) { ret = conn; @@ -376,7 +375,6 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, int want_send) { struct hlist_head *head; - struct hlist_node *pos; struct list_head *list; struct rds_connection *conn; struct rds_message *rm; @@ -390,7 +388,7 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len, for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash); i++, head++) { - hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) { + hlist_for_each_entry_rcu(conn, head, c_hash_node) { if (want_send) list = &conn->c_send_queue; else @@ -439,7 +437,6 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len, { uint64_t buffer[(item_len + 7) / 8]; struct hlist_head *head; - struct hlist_node *pos; struct rds_connection *conn; size_t i; @@ -450,7 +447,7 @@ void rds_for_each_conn_info(struct socket *sock, unsigned int len, for (i = 0, head = rds_conn_hash; i < ARRAY_SIZE(rds_conn_hash); i++, head++) { - hlist_for_each_entry_rcu(conn, pos, head, c_hash_node) { + hlist_for_each_entry_rcu(conn, head, c_hash_node) { /* XXX no c_lock usage.. */ if (!visitor(conn, buffer)) diff --git a/net/rds/message.c b/net/rds/message.c index f0a4658f3273..aba232f9f308 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -82,10 +82,7 @@ static void rds_message_purge(struct rds_message *rm) void rds_message_put(struct rds_message *rm) { rdsdebug("put rm %p ref %d\n", rm, atomic_read(&rm->m_refcount)); - if (atomic_read(&rm->m_refcount) == 0) { -printk(KERN_CRIT "danger refcount zero on %p\n", rm); -WARN_ON(1); - } + WARN(!atomic_read(&rm->m_refcount), "danger refcount zero on %p\n", rm); if (atomic_dec_and_test(&rm->m_refcount)) { BUG_ON(!list_empty(&rm->m_sock_item)); BUG_ON(!list_empty(&rm->m_conn_item)); @@ -197,6 +194,9 @@ struct rds_message *rds_message_alloc(unsigned int extra_len, gfp_t gfp) { struct rds_message *rm; + if (extra_len > KMALLOC_MAX_SIZE - sizeof(struct rds_message)) + return NULL; + rm = kzalloc(sizeof(struct rds_message) + extra_len, gfp); if (!rm) goto out; diff --git a/net/rds/stats.c b/net/rds/stats.c index 7be790d60b90..73be187d389e 100644 --- a/net/rds/stats.c +++ b/net/rds/stats.c @@ -87,6 +87,7 @@ void rds_stats_info_copy(struct rds_info_iterator *iter, for (i = 0; i < nr; i++) { BUG_ON(strlen(names[i]) >= sizeof(ctr.name)); strncpy(ctr.name, names[i], sizeof(ctr.name) - 1); + ctr.name[sizeof(ctr.name) - 1] = '\0'; ctr.value = values[i]; rds_info_copy(iter, &ctr, sizeof(ctr)); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index b768fe9d5e7a..9c8347451597 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -165,10 +165,9 @@ static void rose_remove_socket(struct sock *sk) void rose_kill_by_neigh(struct rose_neigh *neigh) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (rose->neighbour == neigh) { @@ -186,10 +185,9 @@ void rose_kill_by_neigh(struct rose_neigh *neigh) static void rose_kill_by_device(struct net_device *dev) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (rose->device == dev) { @@ -246,10 +244,9 @@ static void rose_insert_socket(struct sock *sk) static struct sock *rose_find_listener(rose_address *addr, ax25_address *call) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (!rosecmp(&rose->source_addr, addr) && @@ -258,7 +255,7 @@ static struct sock *rose_find_listener(rose_address *addr, ax25_address *call) goto found; } - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (!rosecmp(&rose->source_addr, addr) && @@ -278,10 +275,9 @@ found: struct sock *rose_find_socket(unsigned int lci, struct rose_neigh *neigh) { struct sock *s; - struct hlist_node *node; spin_lock_bh(&rose_list_lock); - sk_for_each(s, node, &rose_list) { + sk_for_each(s, &rose_list) { struct rose_sock *rose = rose_sk(s); if (rose->lci == lci && rose->neighbour == neigh) @@ -1257,6 +1253,7 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock, skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); if (srose != NULL) { + memset(srose, 0, msg->msg_namelen); srose->srose_family = AF_ROSE; srose->srose_addr = rose->dest_addr; srose->srose_call = rose->dest_call; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 1135d8227f9b..9b97172db84a 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -204,7 +204,6 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, if (err < 0) return err; - err = -EINVAL; if (tb[TCA_FW_CLASSID]) { f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); tcf_bind_filter(tp, &f->res, base); @@ -218,6 +217,7 @@ fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, } #endif /* CONFIG_NET_CLS_IND */ + err = -EINVAL; if (tb[TCA_FW_MASK]) { mask = nla_get_u32(tb[TCA_FW_MASK]); if (mask != head->mask) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a181b484812a..c297e2a8e2a1 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -545,7 +545,7 @@ static void qdisc_class_hash_free(struct hlist_head *h, unsigned int n) void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) { struct Qdisc_class_common *cl; - struct hlist_node *n, *next; + struct hlist_node *next; struct hlist_head *nhash, *ohash; unsigned int nsize, nmask, osize; unsigned int i, h; @@ -564,7 +564,7 @@ void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) sch_tree_lock(sch); for (i = 0; i < osize; i++) { - hlist_for_each_entry_safe(cl, n, next, &ohash[i], hnode) { + hlist_for_each_entry_safe(cl, next, &ohash[i], hnode) { h = qdisc_class_hash(cl->classid, nmask); hlist_add_head(&cl->hnode, &nhash[h]); } diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 0e19948470b8..1bc210ffcba2 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -962,8 +962,11 @@ cbq_dequeue(struct Qdisc *sch) cbq_update(q); if ((incr -= incr2) < 0) incr = 0; + q->now += incr; + } else { + if (now > q->now) + q->now = now; } - q->now += incr; q->now_rt = now; for (;;) { @@ -1041,14 +1044,13 @@ static void cbq_adjust_levels(struct cbq_class *this) static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) { struct cbq_class *cl; - struct hlist_node *n; unsigned int h; if (q->quanta[prio] == 0) return; for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { /* BUGGGG... Beware! This expression suffer of * arithmetic overflows! */ @@ -1087,10 +1089,9 @@ static void cbq_sync_defmap(struct cbq_class *cl) continue; for (h = 0; h < q->clhash.hashsize; h++) { - struct hlist_node *n; struct cbq_class *c; - hlist_for_each_entry(c, n, &q->clhash.hash[h], + hlist_for_each_entry(c, &q->clhash.hash[h], common.hnode) { if (c->split == split && c->level < level && c->defmap & (1<<i)) { @@ -1210,7 +1211,6 @@ cbq_reset(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; - struct hlist_node *n; int prio; unsigned int h; @@ -1228,7 +1228,7 @@ cbq_reset(struct Qdisc *sch) q->active[prio] = NULL; for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { qdisc_reset(cl->q); cl->next_alive = NULL; @@ -1697,7 +1697,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) static void cbq_destroy(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *n, *next; + struct hlist_node *next; struct cbq_class *cl; unsigned int h; @@ -1710,11 +1710,11 @@ static void cbq_destroy(struct Qdisc *sch) * be bound to classes which have been destroyed already. --TGR '04 */ for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) tcf_destroy_chain(&cl->filter_list); } for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[h], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], common.hnode) cbq_destroy_class(sch, cl); } @@ -2013,14 +2013,13 @@ static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; - struct hlist_node *n; unsigned int h; if (arg->stop) return; for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 71e50c80315f..759b308d1a8d 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -293,14 +293,13 @@ static void drr_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - struct hlist_node *n; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; @@ -451,11 +450,10 @@ static void drr_reset_qdisc(struct Qdisc *sch) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->qdisc->q.qlen) list_del(&cl->alist); qdisc_reset(cl->qdisc); @@ -468,13 +466,13 @@ static void drr_destroy_qdisc(struct Qdisc *sch) { struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; - struct hlist_node *n, *next; + struct hlist_node *next; unsigned int i; tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) drr_destroy_class(sch, cl); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 4e606fcb2534..55786283a3df 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -195,7 +195,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) flow->deficit = q->quantum; flow->dropped = 0; } - if (++sch->q.qlen < sch->limit) + if (++sch->q.qlen <= sch->limit) return NET_XMIT_SUCCESS; q->drop_overlimit++; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index ffad48109a22..eac7e0ee23c1 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -904,7 +904,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, u32 rate) u64 mult; int shift; - r->rate_bps = rate << 3; + r->rate_bps = (u64)rate << 3; r->shift = 0; r->mult = 1; /* diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 6c2ec4510540..9facea03faeb 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1389,7 +1389,6 @@ static void hfsc_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct hfsc_sched *q = qdisc_priv(sch); - struct hlist_node *n; struct hfsc_class *cl; unsigned int i; @@ -1397,7 +1396,7 @@ hfsc_walk(struct Qdisc *sch, struct qdisc_walker *arg) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { if (arg->count < arg->skip) { arg->count++; @@ -1523,11 +1522,10 @@ hfsc_reset_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); struct hfsc_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) hfsc_reset_class(cl); } q->eligible = RB_ROOT; @@ -1540,16 +1538,16 @@ static void hfsc_destroy_qdisc(struct Qdisc *sch) { struct hfsc_sched *q = qdisc_priv(sch); - struct hlist_node *n, *next; + struct hlist_node *next; struct hfsc_class *cl; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) tcf_destroy_chain(&cl->filter_list); } for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], cl_common.hnode) hfsc_destroy_class(sch, cl); } @@ -1564,12 +1562,11 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) unsigned char *b = skb_tail_pointer(skb); struct tc_hfsc_qopt qopt; struct hfsc_class *cl; - struct hlist_node *n; unsigned int i; sch->qstats.backlog = 0; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) sch->qstats.backlog += cl->qdisc->qstats.backlog; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 03c2692ca01e..571f1d211f4d 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -949,11 +949,10 @@ static void htb_reset(struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->level) memset(&cl->un.inner, 0, sizeof(cl->un.inner)); else { @@ -1218,7 +1217,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) static void htb_destroy(struct Qdisc *sch) { struct htb_sched *q = qdisc_priv(sch); - struct hlist_node *n, *next; + struct hlist_node *next; struct htb_class *cl; unsigned int i; @@ -1232,11 +1231,11 @@ static void htb_destroy(struct Qdisc *sch) tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) tcf_destroy_chain(&cl->filter_list); } for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) htb_destroy_class(sch, cl); } @@ -1516,14 +1515,13 @@ static void htb_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl; - struct hlist_node *n; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 6ed37652a4c3..d51852bba01c 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -276,9 +276,8 @@ static struct qfq_aggregate *qfq_find_agg(struct qfq_sched *q, u32 lmax, u32 weight) { struct qfq_aggregate *agg; - struct hlist_node *n; - hlist_for_each_entry(agg, n, &q->nonfull_aggs, nonfull_next) + hlist_for_each_entry(agg, &q->nonfull_aggs, nonfull_next) if (agg->lmax == lmax && agg->class_weight == weight) return agg; @@ -299,6 +298,10 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg, new_num_classes == q->max_agg_classes - 1) /* agg no more full */ hlist_add_head(&agg->nonfull_next, &q->nonfull_aggs); + /* The next assignment may let + * agg->initial_budget > agg->budgetmax + * hold, we will take it into account in charge_actual_service(). + */ agg->budgetmax = new_num_classes * agg->lmax; new_agg_weight = agg->class_weight * new_num_classes; agg->inv_w = ONE_FP/new_agg_weight; @@ -670,14 +673,13 @@ static void qfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; - struct hlist_node *n; unsigned int i; if (arg->stop) return; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (arg->count < arg->skip) { arg->count++; continue; @@ -819,7 +821,7 @@ static void qfq_make_eligible(struct qfq_sched *q) unsigned long old_vslot = q->oldV >> q->min_slot_shift; if (vslot != old_vslot) { - unsigned long mask = (1UL << fls(vslot ^ old_vslot)) - 1; + unsigned long mask = (1ULL << fls(vslot ^ old_vslot)) - 1; qfq_move_groups(q, mask, IR, ER); qfq_move_groups(q, mask, IB, EB); } @@ -990,12 +992,23 @@ static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, /* Update F according to the actual service received by the aggregate. */ static inline void charge_actual_service(struct qfq_aggregate *agg) { - /* compute the service received by the aggregate */ - u32 service_received = agg->initial_budget - agg->budget; + /* Compute the service received by the aggregate, taking into + * account that, after decreasing the number of classes in + * agg, it may happen that + * agg->initial_budget - agg->budget > agg->bugdetmax + */ + u32 service_received = min(agg->budgetmax, + agg->initial_budget - agg->budget); agg->F = agg->S + (u64)service_received * agg->inv_w; } +static inline void qfq_update_agg_ts(struct qfq_sched *q, + struct qfq_aggregate *agg, + enum update_reason reason); + +static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg); + static struct sk_buff *qfq_dequeue(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); @@ -1023,7 +1036,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) in_serv_agg->initial_budget = in_serv_agg->budget = in_serv_agg->budgetmax; - if (!list_empty(&in_serv_agg->active)) + if (!list_empty(&in_serv_agg->active)) { /* * Still active: reschedule for * service. Possible optimization: if no other @@ -1034,8 +1047,9 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) * handle it, we would need to maintain an * extra num_active_aggs field. */ - qfq_activate_agg(q, in_serv_agg, requeue); - else if (sch->q.qlen == 0) { /* no aggregate to serve */ + qfq_update_agg_ts(q, in_serv_agg, requeue); + qfq_schedule_agg(q, in_serv_agg); + } else if (sch->q.qlen == 0) { /* no aggregate to serve */ q->in_serv_agg = NULL; return NULL; } @@ -1054,7 +1068,15 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) qdisc_bstats_update(sch, skb); agg_dequeue(in_serv_agg, cl, len); - in_serv_agg->budget -= len; + /* If lmax is lowered, through qfq_change_class, for a class + * owning pending packets with larger size than the new value + * of lmax, then the following condition may hold. + */ + if (unlikely(in_serv_agg->budget < len)) + in_serv_agg->budget = 0; + else + in_serv_agg->budget -= len; + q->V += (u64)len * IWSUM; pr_debug("qfq dequeue: len %u F %lld now %lld\n", len, (unsigned long long) in_serv_agg->F, @@ -1219,17 +1241,11 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) cl->deficit = agg->lmax; list_add_tail(&cl->alist, &agg->active); - if (list_first_entry(&agg->active, struct qfq_class, alist) != cl) - return err; /* aggregate was not empty, nothing else to do */ + if (list_first_entry(&agg->active, struct qfq_class, alist) != cl || + q->in_serv_agg == agg) + return err; /* non-empty or in service, nothing else to do */ - /* recharge budget */ - agg->initial_budget = agg->budget = agg->budgetmax; - - qfq_update_agg_ts(q, agg, enqueue); - if (q->in_serv_agg == NULL) - q->in_serv_agg = agg; - else if (agg != q->in_serv_agg) - qfq_schedule_agg(q, agg); + qfq_activate_agg(q, agg, enqueue); return err; } @@ -1263,7 +1279,8 @@ static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg) /* group was surely ineligible, remove */ __clear_bit(grp->index, &q->bitmaps[IR]); __clear_bit(grp->index, &q->bitmaps[IB]); - } else if (!q->bitmaps[ER] && qfq_gt(roundedS, q->V)) + } else if (!q->bitmaps[ER] && qfq_gt(roundedS, q->V) && + q->in_serv_agg == NULL) q->V = roundedS; grp->S = roundedS; @@ -1286,8 +1303,15 @@ skip_update: static void qfq_activate_agg(struct qfq_sched *q, struct qfq_aggregate *agg, enum update_reason reason) { + agg->initial_budget = agg->budget = agg->budgetmax; /* recharge budg. */ + qfq_update_agg_ts(q, agg, reason); - qfq_schedule_agg(q, agg); + if (q->in_serv_agg == NULL) { /* no aggr. in service or scheduled */ + q->in_serv_agg = agg; /* start serving this aggregate */ + /* update V: to be in service, agg must be eligible */ + q->oldV = q->V = agg->S; + } else if (agg != q->in_serv_agg) + qfq_schedule_agg(q, agg); } static void qfq_slot_remove(struct qfq_sched *q, struct qfq_group *grp, @@ -1359,8 +1383,6 @@ static void qfq_deactivate_agg(struct qfq_sched *q, struct qfq_aggregate *agg) __set_bit(grp->index, &q->bitmaps[s]); } } - - qfq_update_eligible(q); } static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) @@ -1376,11 +1398,10 @@ static unsigned int qfq_drop_from_slot(struct qfq_sched *q, struct hlist_head *slot) { struct qfq_aggregate *agg; - struct hlist_node *n; struct qfq_class *cl; unsigned int len; - hlist_for_each_entry(agg, n, slot, next) { + hlist_for_each_entry(agg, slot, next) { list_for_each_entry(cl, &agg->active, alist) { if (!cl->qdisc->ops->drop) @@ -1459,11 +1480,10 @@ static void qfq_reset_qdisc(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; - struct hlist_node *n; unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, n, &q->clhash.hash[i], common.hnode) { + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->qdisc->q.qlen > 0) qfq_deactivate_class(q, cl); @@ -1477,13 +1497,13 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; - struct hlist_node *n, *next; + struct hlist_node *next; unsigned int i; tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry_safe(cl, n, next, &q->clhash.hash[i], + hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { qfq_destroy_class(sch, cl); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 2f95f5a5145d..d2709e2b7be6 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1079,7 +1079,7 @@ struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc, transports) { if (transport == active) - break; + continue; list_for_each_entry(chunk, &transport->transmitted, transmitted_list) { if (key == chunk->subh.data_hdr->tsn) { @@ -1591,32 +1591,31 @@ int sctp_assoc_lookup_laddr(struct sctp_association *asoc, /* Set an association id for a given association */ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) { - int assoc_id; - int error = 0; + bool preload = gfp & __GFP_WAIT; + int ret; /* If the id is already assigned, keep it. */ if (asoc->assoc_id) - return error; -retry: - if (unlikely(!idr_pre_get(&sctp_assocs_id, gfp))) - return -ENOMEM; + return 0; + if (preload) + idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); - error = idr_get_new_above(&sctp_assocs_id, (void *)asoc, - idr_low, &assoc_id); - if (!error) { - idr_low = assoc_id + 1; + /* 0 is not a valid id, idr_low is always >= 1 */ + ret = idr_alloc(&sctp_assocs_id, asoc, idr_low, 0, GFP_NOWAIT); + if (ret >= 0) { + idr_low = ret + 1; if (idr_low == INT_MAX) idr_low = 1; } spin_unlock_bh(&sctp_assocs_id_lock); - if (error == -EAGAIN) - goto retry; - else if (error) - return error; + if (preload) + idr_preload_end(); + if (ret < 0) + return ret; - asoc->assoc_id = (sctp_assoc_t) assoc_id; - return error; + asoc->assoc_id = (sctp_assoc_t)ret; + return 0; } /* Free the ASCONF queue */ diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 73aad3d16a45..12ed45dbe75d 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -155,7 +155,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* SCTP-AUTH extensions*/ INIT_LIST_HEAD(&ep->endpoint_shared_keys); - null_key = sctp_auth_shkey_create(0, GFP_KERNEL); + null_key = sctp_auth_shkey_create(0, gfp); if (!null_key) goto nomem; @@ -332,7 +332,6 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( struct sctp_transport *t = NULL; struct sctp_hashbucket *head; struct sctp_ep_common *epb; - struct hlist_node *node; int hash; int rport; @@ -350,7 +349,7 @@ static struct sctp_association *__sctp_endpoint_lookup_assoc( rport); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { tmp = sctp_assoc(epb); if (tmp->ep != ep || rport != tmp->peer.port) continue; diff --git a/net/sctp/input.c b/net/sctp/input.c index 965bbbbe48d4..4b2c83146aa7 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -784,13 +784,12 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net, struct sctp_hashbucket *head; struct sctp_ep_common *epb; struct sctp_endpoint *ep; - struct hlist_node *node; int hash; hash = sctp_ep_hashfn(net, ntohs(laddr->v4.sin_port)); head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { ep = sctp_ep(epb); if (sctp_endpoint_is_match(ep, net, laddr)) goto hit; @@ -876,7 +875,6 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_ep_common *epb; struct sctp_association *asoc; struct sctp_transport *transport; - struct hlist_node *node; int hash; /* Optimize here for direct hit, only listening connections can @@ -886,7 +884,7 @@ static struct sctp_association *__sctp_lookup_association( ntohs(peer->v4.sin_port)); head = &sctp_assoc_hashtable[hash]; read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { asoc = sctp_assoc(epb); transport = sctp_assoc_is_match(asoc, net, local, peer); if (transport) diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 8c19e97262ca..ab3bba8cb0a8 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -213,7 +213,6 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_endpoint *ep; struct sock *sk; - struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_ep_hashsize) @@ -222,7 +221,7 @@ static int sctp_eps_seq_show(struct seq_file *seq, void *v) head = &sctp_ep_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { ep = sctp_ep(epb); sk = epb->sk; if (!net_eq(sock_net(sk), seq_file_net(seq))) @@ -321,7 +320,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) struct sctp_ep_common *epb; struct sctp_association *assoc; struct sock *sk; - struct hlist_node *node; int hash = *(loff_t *)v; if (hash >= sctp_assoc_hashsize) @@ -330,7 +328,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) head = &sctp_assoc_hashtable[hash]; sctp_local_bh_disable(); read_lock(&head->lock); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { assoc = sctp_assoc(epb); sk = epb->sk; if (!net_eq(sock_net(sk), seq_file_net(seq))) @@ -436,7 +434,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) struct sctp_hashbucket *head; struct sctp_ep_common *epb; struct sctp_association *assoc; - struct hlist_node *node; struct sctp_transport *tsp; int hash = *(loff_t *)v; @@ -447,7 +444,7 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) sctp_local_bh_disable(); read_lock(&head->lock); rcu_read_lock(); - sctp_for_each_hentry(epb, node, &head->chain) { + sctp_for_each_hentry(epb, &head->chain) { if (!net_eq(sock_net(epb->sk), seq_file_net(seq))) continue; assoc = sctp_assoc(epb); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 5131fcfedb03..de1a0138317f 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2082,7 +2082,7 @@ sctp_disposition_t sctp_sf_do_5_2_4_dupcook(struct net *net, } /* Delete the tempory new association. */ - sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); + sctp_add_cmd_sf(commands, SCTP_CMD_SET_ASOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); /* Restore association pointer to provide SCTP command interpeter diff --git a/net/sctp/socket.c b/net/sctp/socket.c index cedd9bf67b8c..b9070736b8d9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5653,6 +5653,9 @@ static int sctp_getsockopt_assoc_stats(struct sock *sk, int len, if (len < sizeof(sctp_assoc_t)) return -EINVAL; + /* Allow the struct to grow and fill in as much as possible */ + len = min_t(size_t, len, sizeof(sas)); + if (copy_from_user(&sas, optval, len)) return -EFAULT; @@ -5686,9 +5689,6 @@ static int sctp_getsockopt_assoc_stats(struct sock *sk, int len, /* Mark beginning of a new observation period */ asoc->stats.max_obs_rto = asoc->rto_min; - /* Allow the struct to grow and fill in as much as possible */ - len = min_t(size_t, len, sizeof(sas)); - if (put_user(len, optlen)) return -EFAULT; @@ -5882,8 +5882,7 @@ static struct sctp_bind_bucket *sctp_bucket_create( static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) { struct sctp_bind_hashbucket *head; /* hash list */ - struct sctp_bind_bucket *pp; /* hash list port iterator */ - struct hlist_node *node; + struct sctp_bind_bucket *pp; unsigned short snum; int ret; @@ -5910,7 +5909,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) index = sctp_phashfn(sock_net(sk), rover); head = &sctp_port_hashtable[index]; sctp_spin_lock(&head->lock); - sctp_for_each_hentry(pp, node, &head->chain) + sctp_for_each_hentry(pp, &head->chain) if ((pp->port == rover) && net_eq(sock_net(sk), pp->net)) goto next; @@ -5938,7 +5937,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) */ head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)]; sctp_spin_lock(&head->lock); - sctp_for_each_hentry(pp, node, &head->chain) { + sctp_for_each_hentry(pp, &head->chain) { if ((pp->port == snum) && net_eq(pp->net, sock_net(sk))) goto pp_found; } @@ -5970,7 +5969,7 @@ pp_found: * that this port/socket (sk) combination are already * in an endpoint. */ - sk_for_each_bound(sk2, node, &pp->owner) { + sk_for_each_bound(sk2, &pp->owner) { struct sctp_endpoint *ep2; ep2 = sctp_sk(sk2)->ep; diff --git a/net/sctp/ssnmap.c b/net/sctp/ssnmap.c index 442ad4ed6315..825ea94415b3 100644 --- a/net/sctp/ssnmap.c +++ b/net/sctp/ssnmap.c @@ -41,8 +41,6 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> -#define MAX_KMALLOC_SIZE 131072 - static struct sctp_ssnmap *sctp_ssnmap_init(struct sctp_ssnmap *map, __u16 in, __u16 out); @@ -65,7 +63,7 @@ struct sctp_ssnmap *sctp_ssnmap_new(__u16 in, __u16 out, int size; size = sctp_ssnmap_size(in, out); - if (size <= MAX_KMALLOC_SIZE) + if (size <= KMALLOC_MAX_SIZE) retval = kmalloc(size, gfp); else retval = (struct sctp_ssnmap *) @@ -82,7 +80,7 @@ struct sctp_ssnmap *sctp_ssnmap_new(__u16 in, __u16 out, return retval; fail_map: - if (size <= MAX_KMALLOC_SIZE) + if (size <= KMALLOC_MAX_SIZE) kfree(retval); else free_pages((unsigned long)retval, get_order(size)); @@ -124,7 +122,7 @@ void sctp_ssnmap_free(struct sctp_ssnmap *map) int size; size = sctp_ssnmap_size(map->in.len, map->out.len); - if (size <= MAX_KMALLOC_SIZE) + if (size <= KMALLOC_MAX_SIZE) kfree(map); else free_pages((unsigned long)map, get_order(size)); diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index 5f25e0c92c31..396c45174e5b 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -51,7 +51,7 @@ static void sctp_tsnmap_update(struct sctp_tsnmap *map); static void sctp_tsnmap_find_gap_ack(unsigned long *map, __u16 off, __u16 len, __u16 *start, __u16 *end); -static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 gap); +static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 size); /* Initialize a block of memory as a tsnmap. */ struct sctp_tsnmap *sctp_tsnmap_init(struct sctp_tsnmap *map, __u16 len, @@ -124,7 +124,7 @@ int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn, gap = tsn - map->base_tsn; - if (gap >= map->len && !sctp_tsnmap_grow(map, gap)) + if (gap >= map->len && !sctp_tsnmap_grow(map, gap + 1)) return -ENOMEM; if (!sctp_tsnmap_has_gap(map) && gap == 0) { @@ -360,23 +360,24 @@ __u16 sctp_tsnmap_num_gabs(struct sctp_tsnmap *map, return ngaps; } -static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 gap) +static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 size) { unsigned long *new; unsigned long inc; u16 len; - if (gap >= SCTP_TSN_MAP_SIZE) + if (size > SCTP_TSN_MAP_SIZE) return 0; - inc = ALIGN((gap - map->len),BITS_PER_LONG) + SCTP_TSN_MAP_INCREMENT; + inc = ALIGN((size - map->len), BITS_PER_LONG) + SCTP_TSN_MAP_INCREMENT; len = min_t(u16, map->len + inc, SCTP_TSN_MAP_SIZE); new = kzalloc(len>>3, GFP_ATOMIC); if (!new) return 0; - bitmap_copy(new, map->tsn_map, map->max_tsn_seen - map->base_tsn); + bitmap_copy(new, map->tsn_map, + map->max_tsn_seen - map->cumulative_tsn_ack_point); kfree(map->tsn_map); map->tsn_map = new; map->len = len; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index ada17464b65b..0fd5b3d2df03 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -106,6 +106,7 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, { struct sk_buff_head temp; struct sctp_ulpevent *event; + int event_eor = 0; /* Create an event from the incoming chunk. */ event = sctp_ulpevent_make_rcvmsg(chunk->asoc, chunk, gfp); @@ -127,10 +128,12 @@ int sctp_ulpq_tail_data(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, /* Send event to the ULP. 'event' is the sctp_ulpevent for * very first SKB on the 'temp' list. */ - if (event) + if (event) { + event_eor = (event->msg_flags & MSG_EOR) ? 1 : 0; sctp_ulpq_tail_event(ulpq, event); + } - return 0; + return event_eor; } /* Add a new event for propagation to the ULP. */ @@ -540,14 +543,19 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_partial(struct sctp_ulpq *ulpq) ctsn = cevent->tsn; switch (cevent->msg_flags & SCTP_DATA_FRAG_MASK) { + case SCTP_DATA_FIRST_FRAG: + if (!first_frag) + return NULL; + goto done; case SCTP_DATA_MIDDLE_FRAG: if (!first_frag) { first_frag = pos; next_tsn = ctsn + 1; last_frag = pos; - } else if (next_tsn == ctsn) + } else if (next_tsn == ctsn) { next_tsn++; - else + last_frag = pos; + } else goto done; break; case SCTP_DATA_LAST_FRAG: @@ -651,6 +659,14 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_first(struct sctp_ulpq *ulpq) } else goto done; break; + + case SCTP_DATA_LAST_FRAG: + if (!first_frag) + return NULL; + else + goto done; + break; + default: return NULL; } @@ -962,20 +978,43 @@ static __u16 sctp_ulpq_renege_list(struct sctp_ulpq *ulpq, struct sk_buff_head *list, __u16 needed) { __u16 freed = 0; - __u32 tsn; - struct sk_buff *skb; + __u32 tsn, last_tsn; + struct sk_buff *skb, *flist, *last; struct sctp_ulpevent *event; struct sctp_tsnmap *tsnmap; tsnmap = &ulpq->asoc->peer.tsn_map; - while ((skb = __skb_dequeue_tail(list)) != NULL) { - freed += skb_headlen(skb); + while ((skb = skb_peek_tail(list)) != NULL) { event = sctp_skb2event(skb); tsn = event->tsn; + /* Don't renege below the Cumulative TSN ACK Point. */ + if (TSN_lte(tsn, sctp_tsnmap_get_ctsn(tsnmap))) + break; + + /* Events in ordering queue may have multiple fragments + * corresponding to additional TSNs. Sum the total + * freed space; find the last TSN. + */ + freed += skb_headlen(skb); + flist = skb_shinfo(skb)->frag_list; + for (last = flist; flist; flist = flist->next) { + last = flist; + freed += skb_headlen(last); + } + if (last) + last_tsn = sctp_skb2event(last)->tsn; + else + last_tsn = tsn; + + /* Unlink the event, then renege all applicable TSNs. */ + __skb_unlink(skb, list); sctp_ulpevent_free(event); - sctp_tsnmap_renege(tsnmap, tsn); + while (TSN_lte(tsn, last_tsn)) { + sctp_tsnmap_renege(tsnmap, tsn); + tsn++; + } if (freed >= needed) return freed; } @@ -1002,16 +1041,28 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event; struct sctp_association *asoc; struct sctp_sock *sp; + __u32 ctsn; + struct sk_buff *skb; asoc = ulpq->asoc; sp = sctp_sk(asoc->base.sk); /* If the association is already in Partial Delivery mode - * we have noting to do. + * we have nothing to do. */ if (ulpq->pd_mode) return; + /* Data must be at or below the Cumulative TSN ACK Point to + * start partial delivery. + */ + skb = skb_peek(&asoc->ulpq.reasm); + if (skb != NULL) { + ctsn = sctp_skb2event(skb)->tsn; + if (!TSN_lte(ctsn, sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map))) + return; + } + /* If the user enabled fragment interleave socket option, * multiple associations can enter partial delivery. * Otherwise, we can only enter partial delivery if the @@ -1054,12 +1105,16 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, } /* If able to free enough room, accept this chunk. */ if (chunk && (freed >= needed)) { - __u32 tsn; - tsn = ntohl(chunk->subh.data_hdr->tsn); - sctp_tsnmap_mark(&asoc->peer.tsn_map, tsn, chunk->transport); - sctp_ulpq_tail_data(ulpq, chunk, gfp); - - sctp_ulpq_partial_delivery(ulpq, gfp); + int retval; + retval = sctp_ulpq_tail_data(ulpq, chunk, gfp); + /* + * Enter partial delivery if chunk has not been + * delivered; otherwise, drain the reassembly queue. + */ + if (retval <= 0) + sctp_ulpq_partial_delivery(ulpq, gfp); + else if (retval == 1) + sctp_ulpq_reasm_drain(ulpq); } sk_mem_reclaim(asoc->base.sk); diff --git a/net/socket.c b/net/socket.c index ee0d029e5130..88f759adf3af 100644 --- a/net/socket.c +++ b/net/socket.c @@ -369,16 +369,15 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &socket_file_ops); - if (unlikely(!file)) { + if (unlikely(IS_ERR(file))) { /* drop dentry, keep inode */ ihold(path.dentry->d_inode); path_put(&path); - return ERR_PTR(-ENFILE); + return file; } sock->file = file; file->f_flags = O_RDWR | (flags & O_NONBLOCK); - file->f_pos = 0; file->private_data = sock; return file; } diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index d11418f97f1f..a622ad64acd8 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -17,7 +17,8 @@ */ #include <net/ipv6.h> -#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> +#include <linux/sunrpc/msg_prot.h> #include <linux/slab.h> #include <linux/export.h> diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index b5c067bccc45..f5294047df77 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -407,15 +407,14 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, { LIST_HEAD(free); struct rpc_cred_cache *cache = auth->au_credcache; - struct hlist_node *pos; struct rpc_cred *cred = NULL, *entry, *new; unsigned int nr; - nr = hash_long(acred->uid, cache->hashbits); + nr = hash_long(from_kuid(&init_user_ns, acred->uid), cache->hashbits); rcu_read_lock(); - hlist_for_each_entry_rcu(entry, pos, &cache->hashtable[nr], cr_hash) { + hlist_for_each_entry_rcu(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; spin_lock(&cache->lock); @@ -439,7 +438,7 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, } spin_lock(&cache->lock); - hlist_for_each_entry(entry, pos, &cache->hashtable[nr], cr_hash) { + hlist_for_each_entry(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; cred = get_rpccred(entry); @@ -519,8 +518,8 @@ rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { - .uid = 0, - .gid = 0, + .uid = GLOBAL_ROOT_UID, + .gid = GLOBAL_ROOT_GID, }; dprintk("RPC: %5u looking up %s cred\n", diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 6ed6f201b022..b6badafc6494 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -18,8 +18,8 @@ # define RPCDBG_FACILITY RPCDBG_AUTH #endif -#define RPC_MACHINE_CRED_USERID ((uid_t)0) -#define RPC_MACHINE_CRED_GROUPID ((gid_t)0) +#define RPC_MACHINE_CRED_USERID GLOBAL_ROOT_UID +#define RPC_MACHINE_CRED_GROUPID GLOBAL_ROOT_GID struct generic_cred { struct rpc_cred gc_base; @@ -96,7 +96,9 @@ generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) dprintk("RPC: allocated %s cred %p for uid %d gid %d\n", gcred->acred.machine_cred ? "machine" : "generic", - gcred, acred->uid, acred->gid); + gcred, + from_kuid(&init_user_ns, acred->uid), + from_kgid(&init_user_ns, acred->gid)); return &gcred->gc_base; } @@ -129,8 +131,8 @@ machine_cred_match(struct auth_cred *acred, struct generic_cred *gcred, int flag { if (!gcred->acred.machine_cred || gcred->acred.principal != acred->principal || - gcred->acred.uid != acred->uid || - gcred->acred.gid != acred->gid) + !uid_eq(gcred->acred.uid, acred->uid) || + !gid_eq(gcred->acred.gid, acred->gid)) return 0; return 1; } @@ -147,8 +149,8 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) if (acred->machine_cred) return machine_cred_match(acred, gcred, flags); - if (gcred->acred.uid != acred->uid || - gcred->acred.gid != acred->gid || + if (!uid_eq(gcred->acred.uid, acred->uid) || + !gid_eq(gcred->acred.gid, acred->gid) || gcred->acred.machine_cred != 0) goto out_nomatch; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 911ef008b701..5257d2982ba5 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -255,7 +255,7 @@ err: struct gss_upcall_msg { atomic_t count; - uid_t uid; + kuid_t uid; struct rpc_pipe_msg msg; struct list_head list; struct gss_auth *auth; @@ -302,11 +302,11 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) } static struct gss_upcall_msg * -__gss_find_upcall(struct rpc_pipe *pipe, uid_t uid) +__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid) { struct gss_upcall_msg *pos; list_for_each_entry(pos, &pipe->in_downcall, list) { - if (pos->uid != uid) + if (!uid_eq(pos->uid, uid)) continue; atomic_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); @@ -394,8 +394,11 @@ gss_upcall_callback(struct rpc_task *task) static void gss_encode_v0_msg(struct gss_upcall_msg *gss_msg) { - gss_msg->msg.data = &gss_msg->uid; - gss_msg->msg.len = sizeof(gss_msg->uid); + uid_t uid = from_kuid(&init_user_ns, gss_msg->uid); + memcpy(gss_msg->databuf, &uid, sizeof(uid)); + gss_msg->msg.data = gss_msg->databuf; + gss_msg->msg.len = sizeof(uid); + BUG_ON(sizeof(uid) > UPCALL_BUF_LEN); } static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, @@ -408,7 +411,7 @@ static void gss_encode_v1_msg(struct gss_upcall_msg *gss_msg, gss_msg->msg.len = sprintf(gss_msg->databuf, "mech=%s uid=%d ", mech->gm_name, - gss_msg->uid); + from_kuid(&init_user_ns, gss_msg->uid)); p += gss_msg->msg.len; if (clnt->cl_principal) { len = sprintf(p, "target=%s ", clnt->cl_principal); @@ -444,7 +447,7 @@ static void gss_encode_msg(struct gss_upcall_msg *gss_msg, static struct gss_upcall_msg * gss_alloc_msg(struct gss_auth *gss_auth, struct rpc_clnt *clnt, - uid_t uid, const char *service_name) + kuid_t uid, const char *service_name) { struct gss_upcall_msg *gss_msg; int vers; @@ -474,7 +477,7 @@ gss_setup_upcall(struct rpc_clnt *clnt, struct gss_auth *gss_auth, struct rpc_cr struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_upcall_msg *gss_new, *gss_msg; - uid_t uid = cred->cr_uid; + kuid_t uid = cred->cr_uid; gss_new = gss_alloc_msg(gss_auth, clnt, uid, gss_cred->gc_principal); if (IS_ERR(gss_new)) @@ -516,7 +519,7 @@ gss_refresh_upcall(struct rpc_task *task) int err = 0; dprintk("RPC: %5u %s for uid %u\n", - task->tk_pid, __func__, cred->cr_uid); + task->tk_pid, __func__, from_kuid(&init_user_ns, cred->cr_uid)); gss_msg = gss_setup_upcall(task->tk_client, gss_auth, cred); if (PTR_ERR(gss_msg) == -EAGAIN) { /* XXX: warning on the first, under the assumption we @@ -548,7 +551,8 @@ gss_refresh_upcall(struct rpc_task *task) gss_release_msg(gss_msg); out: dprintk("RPC: %5u %s for uid %u result %d\n", - task->tk_pid, __func__, cred->cr_uid, err); + task->tk_pid, __func__, + from_kuid(&init_user_ns, cred->cr_uid), err); return err; } @@ -561,7 +565,8 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred) DEFINE_WAIT(wait); int err = 0; - dprintk("RPC: %s for uid %u\n", __func__, cred->cr_uid); + dprintk("RPC: %s for uid %u\n", + __func__, from_kuid(&init_user_ns, cred->cr_uid)); retry: gss_msg = gss_setup_upcall(gss_auth->client, gss_auth, cred); if (PTR_ERR(gss_msg) == -EAGAIN) { @@ -603,7 +608,7 @@ out_intr: gss_release_msg(gss_msg); out: dprintk("RPC: %s for uid %u result %d\n", - __func__, cred->cr_uid, err); + __func__, from_kuid(&init_user_ns, cred->cr_uid), err); return err; } @@ -615,9 +620,10 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) const void *p, *end; void *buf; struct gss_upcall_msg *gss_msg; - struct rpc_pipe *pipe = RPC_I(filp->f_dentry->d_inode)->pipe; + struct rpc_pipe *pipe = RPC_I(file_inode(filp))->pipe; struct gss_cl_ctx *ctx; - uid_t uid; + uid_t id; + kuid_t uid; ssize_t err = -EFBIG; if (mlen > MSG_BUF_MAXSIZE) @@ -632,12 +638,18 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) goto err; end = (const void *)((char *)buf + mlen); - p = simple_get_bytes(buf, end, &uid, sizeof(uid)); + p = simple_get_bytes(buf, end, &id, sizeof(id)); if (IS_ERR(p)) { err = PTR_ERR(p); goto err; } + uid = make_kuid(&init_user_ns, id); + if (!uid_valid(uid)) { + err = -EINVAL; + goto err; + } + err = -ENOMEM; ctx = gss_alloc_context(); if (ctx == NULL) @@ -1058,7 +1070,8 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) int err = -ENOMEM; dprintk("RPC: %s for uid %d, flavor %d\n", - __func__, acred->uid, auth->au_flavor); + __func__, from_kuid(&init_user_ns, acred->uid), + auth->au_flavor); if (!(cred = kzalloc(sizeof(*cred), GFP_NOFS))) goto out_err; @@ -1114,7 +1127,7 @@ out: } if (gss_cred->gc_principal != NULL) return 0; - return rc->cr_uid == acred->uid; + return uid_eq(rc->cr_uid, acred->uid); } /* diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 107c4528654f..88edec929d73 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -574,6 +574,8 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; buf->len -= GSS_KRB5_TOK_HDR_LEN + headskip; + /* Trim off the checksum blob */ + xdr_buf_trim(buf, GSS_KRB5_TOK_HDR_LEN + tailskip); return GSS_S_COMPLETE; } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 73e957386600..5ead60550895 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -182,12 +182,6 @@ static void rsi_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } -static int rsi_upcall(struct cache_detail *cd, struct cache_head *h) -{ - return sunrpc_cache_pipe_upcall(cd, h, rsi_request); -} - - static int rsi_parse(struct cache_detail *cd, char *mesg, int mlen) { @@ -275,7 +269,7 @@ static struct cache_detail rsi_cache_template = { .hash_size = RSI_HASHMAX, .name = "auth.rpcsec.init", .cache_put = rsi_put, - .cache_upcall = rsi_upcall, + .cache_request = rsi_request, .cache_parse = rsi_parse, .match = rsi_match, .init = rsi_init, @@ -418,6 +412,7 @@ static int rsc_parse(struct cache_detail *cd, { /* contexthandle expiry [ uid gid N <n gids> mechname ...mechdata... ] */ char *buf = mesg; + int id; int len, rv; struct rsc rsci, *rscp = NULL; time_t expiry; @@ -444,7 +439,7 @@ static int rsc_parse(struct cache_detail *cd, goto out; /* uid, or NEGATIVE */ - rv = get_int(&mesg, &rsci.cred.cr_uid); + rv = get_int(&mesg, &id); if (rv == -EINVAL) goto out; if (rv == -ENOENT) @@ -452,9 +447,21 @@ static int rsc_parse(struct cache_detail *cd, else { int N, i; + /* + * NOTE: we skip uid_valid()/gid_valid() checks here: + * instead, * -1 id's are later mapped to the + * (export-specific) anonymous id by nfsd_setuser. + * + * (But supplementary gid's get no such special + * treatment so are checked for validity here.) + */ + /* uid */ + rsci.cred.cr_uid = make_kuid(&init_user_ns, id); + /* gid */ - if (get_int(&mesg, &rsci.cred.cr_gid)) + if (get_int(&mesg, &id)) goto out; + rsci.cred.cr_gid = make_kgid(&init_user_ns, id); /* number of additional gid's */ if (get_int(&mesg, &N)) @@ -467,11 +474,10 @@ static int rsc_parse(struct cache_detail *cd, /* gid's */ status = -EINVAL; for (i=0; i<N; i++) { - gid_t gid; kgid_t kgid; - if (get_int(&mesg, &gid)) + if (get_int(&mesg, &id)) goto out; - kgid = make_kgid(&init_user_ns, gid); + kgid = make_kgid(&init_user_ns, id); if (!gid_valid(kgid)) goto out; GROUP_AT(rsci.cred.cr_group_info, i) = kgid; @@ -817,13 +823,17 @@ read_u32_from_xdr_buf(struct xdr_buf *buf, int base, u32 *obj) * The server uses base of head iovec as read pointer, while the * client uses separate pointer. */ static int -unwrap_integ_data(struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) +unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) { int stat = -EINVAL; u32 integ_len, maj_stat; struct xdr_netobj mic; struct xdr_buf integ_buf; + /* Did we already verify the signature on the original pass through? */ + if (rqstp->rq_deferred) + return 0; + integ_len = svc_getnl(&buf->head[0]); if (integ_len & 3) return stat; @@ -846,6 +856,8 @@ unwrap_integ_data(struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) goto out; if (svc_getnl(&buf->head[0]) != seq) goto out; + /* trim off the mic at the end before returning */ + xdr_buf_trim(buf, mic.len + 4); stat = 0; out: kfree(mic.data); @@ -1190,7 +1202,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) /* placeholders for length and seq. number: */ svc_putnl(resv, 0); svc_putnl(resv, 0); - if (unwrap_integ_data(&rqstp->rq_arg, + if (unwrap_integ_data(rqstp, &rqstp->rq_arg, gc->gc_seq, rsci->mechctx)) goto garbage_args; break; diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 52c5abdee211..dc37021fc3e5 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -18,8 +18,8 @@ struct unx_cred { struct rpc_cred uc_base; - gid_t uc_gid; - gid_t uc_gids[NFS_NGROUPS]; + kgid_t uc_gid; + kgid_t uc_gids[NFS_NGROUPS]; }; #define uc_uid uc_base.cr_uid @@ -65,7 +65,8 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) unsigned int i; dprintk("RPC: allocating UNIX cred for uid %d gid %d\n", - acred->uid, acred->gid); + from_kuid(&init_user_ns, acred->uid), + from_kgid(&init_user_ns, acred->gid)); if (!(cred = kmalloc(sizeof(*cred), GFP_NOFS))) return ERR_PTR(-ENOMEM); @@ -79,13 +80,10 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) groups = NFS_NGROUPS; cred->uc_gid = acred->gid; - for (i = 0; i < groups; i++) { - gid_t gid; - gid = from_kgid(&init_user_ns, GROUP_AT(acred->group_info, i)); - cred->uc_gids[i] = gid; - } + for (i = 0; i < groups; i++) + cred->uc_gids[i] = GROUP_AT(acred->group_info, i); if (i < NFS_NGROUPS) - cred->uc_gids[i] = NOGROUP; + cred->uc_gids[i] = INVALID_GID; return &cred->uc_base; } @@ -123,21 +121,17 @@ unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) unsigned int i; - if (cred->uc_uid != acred->uid || cred->uc_gid != acred->gid) + if (!uid_eq(cred->uc_uid, acred->uid) || !gid_eq(cred->uc_gid, acred->gid)) return 0; if (acred->group_info != NULL) groups = acred->group_info->ngroups; if (groups > NFS_NGROUPS) groups = NFS_NGROUPS; - for (i = 0; i < groups ; i++) { - gid_t gid; - gid = from_kgid(&init_user_ns, GROUP_AT(acred->group_info, i)); - if (cred->uc_gids[i] != gid) + for (i = 0; i < groups ; i++) + if (!gid_eq(cred->uc_gids[i], GROUP_AT(acred->group_info, i))) return 0; - } - if (groups < NFS_NGROUPS && - cred->uc_gids[groups] != NOGROUP) + if (groups < NFS_NGROUPS && gid_valid(cred->uc_gids[groups])) return 0; return 1; } @@ -163,11 +157,11 @@ unx_marshal(struct rpc_task *task, __be32 *p) */ p = xdr_encode_array(p, clnt->cl_nodename, clnt->cl_nodelen); - *p++ = htonl((u32) cred->uc_uid); - *p++ = htonl((u32) cred->uc_gid); + *p++ = htonl((u32) from_kuid(&init_user_ns, cred->uc_uid)); + *p++ = htonl((u32) from_kgid(&init_user_ns, cred->uc_gid)); hold = p++; - for (i = 0; i < 16 && cred->uc_gids[i] != (gid_t) NOGROUP; i++) - *p++ = htonl((u32) cred->uc_gids[i]); + for (i = 0; i < 16 && gid_valid(cred->uc_gids[i]); i++) + *p++ = htonl((u32) from_kgid(&init_user_ns, cred->uc_gids[i])); *hold = htonl(p - hold - 1); /* gid array length */ *base = htonl((p - base - 1) << 2); /* cred length */ diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 9afa4393c217..25d58e766014 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -196,9 +196,9 @@ EXPORT_SYMBOL_GPL(sunrpc_cache_update); static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h) { - if (!cd->cache_upcall) - return -EINVAL; - return cd->cache_upcall(cd, h); + if (cd->cache_upcall) + return cd->cache_upcall(cd, h); + return sunrpc_cache_pipe_upcall(cd, h); } static inline int cache_is_valid(struct cache_detail *detail, struct cache_head *h) @@ -670,13 +670,13 @@ static void cache_revisit_request(struct cache_head *item) { struct cache_deferred_req *dreq; struct list_head pending; - struct hlist_node *lp, *tmp; + struct hlist_node *tmp; int hash = DFR_HASH(item); INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); - hlist_for_each_entry_safe(dreq, lp, tmp, &cache_defer_hash[hash], hash) + hlist_for_each_entry_safe(dreq, tmp, &cache_defer_hash[hash], hash) if (dreq->item == item) { __unhash_deferred_req(dreq); list_add(&dreq->recent, &pending); @@ -750,12 +750,24 @@ struct cache_reader { int offset; /* if non-0, we have a refcnt on next request */ }; +static int cache_request(struct cache_detail *detail, + struct cache_request *crq) +{ + char *bp = crq->buf; + int len = PAGE_SIZE; + + detail->cache_request(detail, crq->item, &bp, &len); + if (len < 0) + return -EAGAIN; + return PAGE_SIZE - len; +} + static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos, struct cache_detail *cd) { struct cache_reader *rp = filp->private_data; struct cache_request *rq; - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); int err; if (count == 0) @@ -784,6 +796,13 @@ static ssize_t cache_read(struct file *filp, char __user *buf, size_t count, rq->readers++; spin_unlock(&queue_lock); + if (rq->len == 0) { + err = cache_request(cd, rq); + if (err < 0) + goto out; + rq->len = err; + } + if (rp->offset == 0 && !test_bit(CACHE_PENDING, &rq->item->flags)) { err = -EAGAIN; spin_lock(&queue_lock); @@ -886,7 +905,7 @@ static ssize_t cache_write(struct file *filp, const char __user *buf, struct cache_detail *cd) { struct address_space *mapping = filp->f_mapping; - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); ssize_t ret = -EINVAL; if (!cd->cache_parse) @@ -1140,17 +1159,14 @@ static bool cache_listeners_exist(struct cache_detail *detail) * * Each request is at most one page long. */ -int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, - void (*cache_request)(struct cache_detail *, - struct cache_head *, - char **, - int *)) +int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h) { char *buf; struct cache_request *crq; - char *bp; - int len; + + if (!detail->cache_request) + return -EINVAL; if (!cache_listeners_exist(detail)) { warn_no_listener(detail); @@ -1167,19 +1183,10 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h, return -EAGAIN; } - bp = buf; len = PAGE_SIZE; - - cache_request(detail, h, &bp, &len); - - if (len < 0) { - kfree(buf); - kfree(crq); - return -EAGAIN; - } crq->q.reader = 0; crq->item = cache_get(h); crq->buf = buf; - crq->len = PAGE_SIZE - len; + crq->len = 0; crq->readers = 0; spin_lock(&queue_lock); list_add_tail(&crq->q.list, &detail->queue); @@ -1454,7 +1461,7 @@ static ssize_t write_flush(struct file *file, const char __user *buf, static ssize_t cache_read_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct cache_detail *cd = PDE(file_inode(filp))->data; return cache_read(filp, buf, count, ppos, cd); } @@ -1462,14 +1469,14 @@ static ssize_t cache_read_procfs(struct file *filp, char __user *buf, static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct cache_detail *cd = PDE(file_inode(filp))->data; return cache_write(filp, buf, count, ppos, cd); } static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait) { - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct cache_detail *cd = PDE(file_inode(filp))->data; return cache_poll(filp, wait, cd); } @@ -1477,7 +1484,7 @@ static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait) static long cache_ioctl_procfs(struct file *filp, unsigned int cmd, unsigned long arg) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); struct cache_detail *cd = PDE(inode)->data; return cache_ioctl(inode, filp, cmd, arg, cd); @@ -1546,7 +1553,7 @@ static int release_flush_procfs(struct inode *inode, struct file *filp) static ssize_t read_flush_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct cache_detail *cd = PDE(file_inode(filp))->data; return read_flush(filp, buf, count, ppos, cd); } @@ -1555,7 +1562,7 @@ static ssize_t write_flush_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data; + struct cache_detail *cd = PDE(file_inode(filp))->data; return write_flush(filp, buf, count, ppos, cd); } @@ -1605,7 +1612,7 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) if (p == NULL) goto out_nomem; - if (cd->cache_upcall || cd->cache_parse) { + if (cd->cache_request || cd->cache_parse) { p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR, cd->u.procfs.proc_ent, &cache_file_operations_procfs, cd); @@ -1614,7 +1621,7 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net) goto out_nomem; } if (cd->cache_show) { - p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR, + p = proc_create_data("content", S_IFREG|S_IRUSR, cd->u.procfs.proc_ent, &content_file_operations_procfs, cd); cd->u.procfs.content_ent = p; @@ -1686,7 +1693,7 @@ EXPORT_SYMBOL_GPL(cache_destroy_net); static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_read(filp, buf, count, ppos, cd); } @@ -1694,14 +1701,14 @@ static ssize_t cache_read_pipefs(struct file *filp, char __user *buf, static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_write(filp, buf, count, ppos, cd); } static unsigned int cache_poll_pipefs(struct file *filp, poll_table *wait) { - struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + struct cache_detail *cd = RPC_I(file_inode(filp))->private; return cache_poll(filp, wait, cd); } @@ -1709,7 +1716,7 @@ static unsigned int cache_poll_pipefs(struct file *filp, poll_table *wait) static long cache_ioctl_pipefs(struct file *filp, unsigned int cmd, unsigned long arg) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = file_inode(filp); struct cache_detail *cd = RPC_I(inode)->private; return cache_ioctl(inode, filp, cmd, arg, cd); @@ -1778,7 +1785,7 @@ static int release_flush_pipefs(struct inode *inode, struct file *filp) static ssize_t read_flush_pipefs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + struct cache_detail *cd = RPC_I(file_inode(filp))->private; return read_flush(filp, buf, count, ppos, cd); } @@ -1787,7 +1794,7 @@ static ssize_t write_flush_pipefs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private; + struct cache_detail *cd = RPC_I(file_inode(filp))->private; return write_flush(filp, buf, count, ppos, cd); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a9f7906c1a6a..d5f35f15af98 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -33,6 +33,7 @@ #include <linux/rcupdate.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/metrics.h> #include <linux/sunrpc/bc_xprt.h> @@ -303,10 +304,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru err = rpciod_up(); if (err) goto out_no_rpciod; - err = -EINVAL; - if (!xprt) - goto out_no_xprt; + err = -EINVAL; if (args->version >= program->nrvers) goto out_err; version = program->version[args->version]; @@ -381,10 +380,9 @@ out_no_principal: out_no_stats: kfree(clnt); out_err: - xprt_put(xprt); -out_no_xprt: rpciod_down(); out_no_rpciod: + xprt_put(xprt); return ERR_PTR(err); } @@ -511,7 +509,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, new = rpc_new_client(args, xprt); if (IS_ERR(new)) { err = PTR_ERR(new); - goto out_put; + goto out_err; } atomic_inc(&clnt->cl_count); @@ -524,8 +522,6 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, new->cl_chatty = clnt->cl_chatty; return new; -out_put: - xprt_put(xprt); out_err: dprintk("RPC: %s: returned error %d\n", __func__, err); return ERR_PTR(err); @@ -1196,6 +1192,21 @@ size_t rpc_max_payload(struct rpc_clnt *clnt) EXPORT_SYMBOL_GPL(rpc_max_payload); /** + * rpc_get_timeout - Get timeout for transport in units of HZ + * @clnt: RPC client to query + */ +unsigned long rpc_get_timeout(struct rpc_clnt *clnt) +{ + unsigned long ret; + + rcu_read_lock(); + ret = rcu_dereference(clnt->cl_xprt)->timeout->to_initval; + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(rpc_get_timeout); + +/** * rpc_force_rebind - force transport to check that remote port is unchanged * @clnt: client to rebind * diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index fd10981ea792..a9129f8d7070 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -284,7 +284,7 @@ out: static ssize_t rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); struct rpc_pipe *pipe; struct rpc_pipe_msg *msg; int res = 0; @@ -328,7 +328,7 @@ out_unlock: static ssize_t rpc_pipe_write(struct file *filp, const char __user *buf, size_t len, loff_t *offset) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); int res; mutex_lock(&inode->i_mutex); @@ -342,7 +342,7 @@ rpc_pipe_write(struct file *filp, const char __user *buf, size_t len, loff_t *of static unsigned int rpc_pipe_poll(struct file *filp, struct poll_table_struct *wait) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); struct rpc_inode *rpci = RPC_I(inode); unsigned int mask = POLLOUT | POLLWRNORM; @@ -360,7 +360,7 @@ rpc_pipe_poll(struct file *filp, struct poll_table_struct *wait) static long rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); struct rpc_pipe *pipe; int len; @@ -830,7 +830,7 @@ static int rpc_rmdir_depopulate(struct dentry *dentry, * responses to upcalls. They will result in calls to @msg->downcall. * * The @private argument passed here will be available to all these methods - * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private. + * from the file pointer, via RPC_I(file_inode(file))->private. */ struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name, void *private, struct rpc_pipe *pipe) @@ -1174,6 +1174,8 @@ static struct file_system_type rpc_pipe_fs_type = { .mount = rpc_mount, .kill_sb = rpc_kill_sb, }; +MODULE_ALIAS_FS("rpc_pipefs"); +MODULE_ALIAS("rpc_pipefs"); static void init_once(void *foo) @@ -1218,6 +1220,3 @@ void unregister_rpc_pipefs(void) kmem_cache_destroy(rpc_inode_cachep); unregister_filesystem(&rpc_pipe_fs_type); } - -/* Make 'mount -t rpc_pipefs ...' autoload this module. */ -MODULE_ALIAS("rpc_pipefs"); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 795a0f4e920b..3df764dc330c 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -26,6 +26,7 @@ #include <net/ipv6.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> #include <linux/sunrpc/sched.h> #include <linux/sunrpc/xprtsock.h> diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index fb20f25ddec9..f8529fc8e542 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -180,6 +180,8 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue, list_add_tail(&task->u.tk_wait.list, &queue->tasks[0]); task->tk_waitqueue = queue; queue->qlen++; + /* barrier matches the read in rpc_wake_up_task_queue_locked() */ + smp_wmb(); rpc_set_queued(task); dprintk("RPC: %5u added to queue %p \"%s\"\n", @@ -430,8 +432,11 @@ static void __rpc_do_wake_up_task(struct rpc_wait_queue *queue, struct rpc_task */ static void rpc_wake_up_task_queue_locked(struct rpc_wait_queue *queue, struct rpc_task *task) { - if (RPC_IS_QUEUED(task) && task->tk_waitqueue == queue) - __rpc_do_wake_up_task(queue, task); + if (RPC_IS_QUEUED(task)) { + smp_rmb(); + if (task->tk_waitqueue == queue) + __rpc_do_wake_up_task(queue, task); + } } /* diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index dbf12ac5ecb7..89a588b4478b 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -515,15 +515,6 @@ EXPORT_SYMBOL_GPL(svc_create_pooled); void svc_shutdown_net(struct svc_serv *serv, struct net *net) { - /* - * The set of xprts (contained in the sv_tempsocks and - * sv_permsocks lists) is now constant, since it is modified - * only by accepting new sockets (done by service threads in - * svc_recv) or aging old ones (done by sv_temptimer), or - * configuration changes (excluded by whatever locking the - * caller is using--nfsd_mutex in the case of nfsd). So it's - * safe to traverse those lists and shut everything down: - */ svc_close_net(serv, net); if (serv->sv_shutdown) @@ -1042,6 +1033,7 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) /* * dprintk the given error with the address of the client that caused it. */ +#ifdef RPC_DEBUG static __printf(2, 3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) { @@ -1058,6 +1050,9 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) va_end(args); } +#else +static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} +#endif /* * Common routine for processing the RPC request. diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b8e47fac7315..80a6640f329b 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -499,7 +499,8 @@ void svc_wake_up(struct svc_serv *serv) rqstp->rq_xprt = NULL; */ wake_up(&rqstp->rq_wait); - } + } else + pool->sp_task_pending = 1; spin_unlock_bh(&pool->sp_lock); } } @@ -634,7 +635,13 @@ struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) * long for cache updates. */ rqstp->rq_chandle.thread_wait = 1*HZ; + pool->sp_task_pending = 0; } else { + if (pool->sp_task_pending) { + pool->sp_task_pending = 0; + spin_unlock_bh(&pool->sp_lock); + return ERR_PTR(-EAGAIN); + } /* No data pending. Go to sleep */ svc_thread_enqueue(pool, rqstp); @@ -856,7 +863,6 @@ static void svc_age_temp_xprts(unsigned long closure) struct svc_serv *serv = (struct svc_serv *)closure; struct svc_xprt *xprt; struct list_head *le, *next; - LIST_HEAD(to_be_aged); dprintk("svc_age_temp_xprts\n"); @@ -877,25 +883,15 @@ static void svc_age_temp_xprts(unsigned long closure) if (atomic_read(&xprt->xpt_ref.refcount) > 1 || test_bit(XPT_BUSY, &xprt->xpt_flags)) continue; - svc_xprt_get(xprt); - list_move(le, &to_be_aged); + list_del_init(le); set_bit(XPT_CLOSE, &xprt->xpt_flags); set_bit(XPT_DETACHED, &xprt->xpt_flags); - } - spin_unlock_bh(&serv->sv_lock); - - while (!list_empty(&to_be_aged)) { - le = to_be_aged.next; - /* fiddling the xpt_list node is safe 'cos we're XPT_DETACHED */ - list_del_init(le); - xprt = list_entry(le, struct svc_xprt, xpt_list); - dprintk("queuing xprt %p for closing\n", xprt); /* a thread will dequeue and close it soon */ svc_xprt_enqueue(xprt); - svc_xprt_put(xprt); } + spin_unlock_bh(&serv->sv_lock); mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); } @@ -959,21 +955,24 @@ void svc_close_xprt(struct svc_xprt *xprt) } EXPORT_SYMBOL_GPL(svc_close_xprt); -static void svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, struct net *net) +static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, struct net *net) { struct svc_xprt *xprt; + int ret = 0; spin_lock(&serv->sv_lock); list_for_each_entry(xprt, xprt_list, xpt_list) { if (xprt->xpt_net != net) continue; + ret++; set_bit(XPT_CLOSE, &xprt->xpt_flags); - set_bit(XPT_BUSY, &xprt->xpt_flags); + svc_xprt_enqueue(xprt); } spin_unlock(&serv->sv_lock); + return ret; } -static void svc_clear_pools(struct svc_serv *serv, struct net *net) +static struct svc_xprt *svc_dequeue_net(struct svc_serv *serv, struct net *net) { struct svc_pool *pool; struct svc_xprt *xprt; @@ -988,42 +987,46 @@ static void svc_clear_pools(struct svc_serv *serv, struct net *net) if (xprt->xpt_net != net) continue; list_del_init(&xprt->xpt_ready); + spin_unlock_bh(&pool->sp_lock); + return xprt; } spin_unlock_bh(&pool->sp_lock); } + return NULL; } -static void svc_clear_list(struct svc_serv *serv, struct list_head *xprt_list, struct net *net) +static void svc_clean_up_xprts(struct svc_serv *serv, struct net *net) { struct svc_xprt *xprt; - struct svc_xprt *tmp; - LIST_HEAD(victims); - spin_lock(&serv->sv_lock); - list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) { - if (xprt->xpt_net != net) - continue; - list_move(&xprt->xpt_list, &victims); - } - spin_unlock(&serv->sv_lock); - - list_for_each_entry_safe(xprt, tmp, &victims, xpt_list) + while ((xprt = svc_dequeue_net(serv, net))) { + set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_delete_xprt(xprt); + } } +/* + * Server threads may still be running (especially in the case where the + * service is still running in other network namespaces). + * + * So we shut down sockets the same way we would on a running server, by + * setting XPT_CLOSE, enqueuing, and letting a thread pick it up to do + * the close. In the case there are no such other threads, + * threads running, svc_clean_up_xprts() does a simple version of a + * server's main event loop, and in the case where there are other + * threads, we may need to wait a little while and then check again to + * see if they're done. + */ void svc_close_net(struct svc_serv *serv, struct net *net) { - svc_close_list(serv, &serv->sv_tempsocks, net); - svc_close_list(serv, &serv->sv_permsocks, net); + int delay = 0; - svc_clear_pools(serv, net); - /* - * At this point the sp_sockets lists will stay empty, since - * svc_xprt_enqueue will not add new entries without taking the - * sp_lock and checking XPT_BUSY. - */ - svc_clear_list(serv, &serv->sv_tempsocks, net); - svc_clear_list(serv, &serv->sv_permsocks, net); + while (svc_close_list(serv, &serv->sv_permsocks, net) + + svc_close_list(serv, &serv->sv_tempsocks, net)) { + + svc_clean_up_xprts(serv, net); + msleep(delay++); + } } /* diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 7963569fc04f..2af7b0cba43a 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -138,13 +138,12 @@ auth_domain_lookup(char *name, struct auth_domain *new) { struct auth_domain *hp; struct hlist_head *head; - struct hlist_node *np; head = &auth_domain_table[hash_str(name, DN_HASHBITS)]; spin_lock(&auth_domain_lock); - hlist_for_each_entry(hp, np, head, hash) { + hlist_for_each_entry(hp, head, hash) { if (strcmp(hp->name, name)==0) { kref_get(&hp->ref); spin_unlock(&auth_domain_lock); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 4d0129203733..c3f9e1ef7f53 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -6,6 +6,7 @@ #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/svcauth.h> #include <linux/sunrpc/gss_api.h> +#include <linux/sunrpc/addr.h> #include <linux/err.h> #include <linux/seq_file.h> #include <linux/hash.h> @@ -17,7 +18,6 @@ #include <linux/user_namespace.h> #define RPCDBG_FACILITY RPCDBG_AUTH -#include <linux/sunrpc/clnt.h> #include "netns.h" @@ -157,11 +157,6 @@ static void ip_map_request(struct cache_detail *cd, (*bpp)[-1] = '\n'; } -static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h) -{ - return sunrpc_cache_pipe_upcall(cd, h, ip_map_request); -} - static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, struct in6_addr *addr); static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, struct unix_domain *udom, time_t expiry); @@ -415,10 +410,15 @@ svcauth_unix_info_release(struct svc_xprt *xpt) struct unix_gid { struct cache_head h; - uid_t uid; + kuid_t uid; struct group_info *gi; }; +static int unix_gid_hash(kuid_t uid) +{ + return hash_long(from_kuid(&init_user_ns, uid), GID_HASHBITS); +} + static void unix_gid_put(struct kref *kref) { struct cache_head *item = container_of(kref, struct cache_head, ref); @@ -433,7 +433,7 @@ static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew) { struct unix_gid *orig = container_of(corig, struct unix_gid, h); struct unix_gid *new = container_of(cnew, struct unix_gid, h); - return orig->uid == new->uid; + return uid_eq(orig->uid, new->uid); } static void unix_gid_init(struct cache_head *cnew, struct cache_head *citem) { @@ -465,23 +465,19 @@ static void unix_gid_request(struct cache_detail *cd, char tuid[20]; struct unix_gid *ug = container_of(h, struct unix_gid, h); - snprintf(tuid, 20, "%u", ug->uid); + snprintf(tuid, 20, "%u", from_kuid(&init_user_ns, ug->uid)); qword_add(bpp, blen, tuid); (*bpp)[-1] = '\n'; } -static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h) -{ - return sunrpc_cache_pipe_upcall(cd, h, unix_gid_request); -} - -static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, uid_t uid); +static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid); static int unix_gid_parse(struct cache_detail *cd, char *mesg, int mlen) { /* uid expiry Ngid gid0 gid1 ... gidN-1 */ - int uid; + int id; + kuid_t uid; int gids; int rv; int i; @@ -493,9 +489,12 @@ static int unix_gid_parse(struct cache_detail *cd, return -EINVAL; mesg[mlen-1] = 0; - rv = get_int(&mesg, &uid); + rv = get_int(&mesg, &id); if (rv) return -EINVAL; + uid = make_kuid(&init_user_ns, id); + if (!uid_valid(uid)) + return -EINVAL; ug.uid = uid; expiry = get_expiry(&mesg); @@ -530,7 +529,7 @@ static int unix_gid_parse(struct cache_detail *cd, ug.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ug.h, &ugp->h, - hash_long(uid, GID_HASHBITS)); + unix_gid_hash(uid)); if (!ch) err = -ENOMEM; else { @@ -549,7 +548,7 @@ static int unix_gid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { - struct user_namespace *user_ns = current_user_ns(); + struct user_namespace *user_ns = &init_user_ns; struct unix_gid *ug; int i; int glen; @@ -565,7 +564,7 @@ static int unix_gid_show(struct seq_file *m, else glen = 0; - seq_printf(m, "%u %d:", ug->uid, glen); + seq_printf(m, "%u %d:", from_kuid_munged(user_ns, ug->uid), glen); for (i = 0; i < glen; i++) seq_printf(m, " %d", from_kgid_munged(user_ns, GROUP_AT(ug->gi, i))); seq_printf(m, "\n"); @@ -577,7 +576,7 @@ static struct cache_detail unix_gid_cache_template = { .hash_size = GID_HASHMAX, .name = "auth.unix.gid", .cache_put = unix_gid_put, - .cache_upcall = unix_gid_upcall, + .cache_request = unix_gid_request, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, .match = unix_gid_match, @@ -615,20 +614,20 @@ void unix_gid_cache_destroy(struct net *net) cache_destroy_net(cd, net); } -static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, uid_t uid) +static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid) { struct unix_gid ug; struct cache_head *ch; ug.uid = uid; - ch = sunrpc_cache_lookup(cd, &ug.h, hash_long(uid, GID_HASHBITS)); + ch = sunrpc_cache_lookup(cd, &ug.h, unix_gid_hash(uid)); if (ch) return container_of(ch, struct unix_gid, h); else return NULL; } -static struct group_info *unix_gid_find(uid_t uid, struct svc_rqst *rqstp) +static struct group_info *unix_gid_find(kuid_t uid, struct svc_rqst *rqstp) { struct unix_gid *ug; struct group_info *gi; @@ -750,8 +749,8 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) } /* Signal that mapping to nobody uid/gid is required */ - cred->cr_uid = (uid_t) -1; - cred->cr_gid = (gid_t) -1; + cred->cr_uid = INVALID_UID; + cred->cr_gid = INVALID_GID; cred->cr_group_info = groups_alloc(0); if (cred->cr_group_info == NULL) return SVC_CLOSE; /* kmalloc failure - client must retry */ @@ -812,8 +811,10 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) argv->iov_base = (void*)((__be32*)argv->iov_base + slen); /* skip machname */ argv->iov_len -= slen*4; - cred->cr_uid = svc_getnl(argv); /* uid */ - cred->cr_gid = svc_getnl(argv); /* gid */ + cred->cr_uid = make_kuid(&init_user_ns, svc_getnl(argv)); /* uid */ + cred->cr_gid = make_kgid(&init_user_ns, svc_getnl(argv)); /* gid */ + if (!uid_valid(cred->cr_uid) || !gid_valid(cred->cr_gid)) + goto badcred; slen = svc_getnl(argv); /* gids length */ if (slen > 16 || (len -= (slen + 2)*4) < 0) goto badcred; @@ -874,7 +875,7 @@ static struct cache_detail ip_map_cache_template = { .hash_size = IP_HASHMAX, .name = "auth.unix.ip", .cache_put = ip_map_put, - .cache_upcall = ip_map_upcall, + .cache_request = ip_map_request, .cache_parse = ip_map_parse, .cache_show = ip_map_show, .match = ip_map_match, diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 56055632f151..75edcfad6e26 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -879,6 +879,47 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, } EXPORT_SYMBOL_GPL(xdr_buf_subsegment); +/** + * xdr_buf_trim - lop at most "len" bytes off the end of "buf" + * @buf: buf to be trimmed + * @len: number of bytes to reduce "buf" by + * + * Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note + * that it's possible that we'll trim less than that amount if the xdr_buf is + * too small, or if (for instance) it's all in the head and the parser has + * already read too far into it. + */ +void xdr_buf_trim(struct xdr_buf *buf, unsigned int len) +{ + size_t cur; + unsigned int trim = len; + + if (buf->tail[0].iov_len) { + cur = min_t(size_t, buf->tail[0].iov_len, trim); + buf->tail[0].iov_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->page_len) { + cur = min_t(unsigned int, buf->page_len, trim); + buf->page_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->head[0].iov_len) { + cur = min_t(size_t, buf->head[0].iov_len, trim); + buf->head[0].iov_len -= cur; + trim -= cur; + } +fix_len: + buf->len -= (len - trim); +} +EXPORT_SYMBOL_GPL(xdr_buf_trim); + static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len) { unsigned int this_len; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 846c34fdee9f..b7478d5e7ffd 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -487,13 +487,17 @@ EXPORT_SYMBOL_GPL(xprt_wake_pending_tasks); * xprt_wait_for_buffer_space - wait for transport output buffer to clear * @task: task to be put to sleep * @action: function pointer to be executed after wait + * + * Note that we only set the timer for the case of RPC_IS_SOFT(), since + * we don't in general want to force a socket disconnection due to + * an incomplete RPC call transmission. */ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; - task->tk_timeout = req->rq_timeout; + task->tk_timeout = RPC_IS_SOFT(task) ? req->rq_timeout : 0; rpc_sleep_on(&xprt->pending, task, action); } EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index d0074289708e..794312f22b9b 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -51,6 +51,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/seq_file.h> +#include <linux/sunrpc/addr.h> #include "xprt_rdma.h" diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 745973b729af..93726560eaa8 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1086,7 +1086,7 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep, case RPCRDMA_MEMWINDOWS: /* Allocate one extra request's worth, for full cycling */ for (i = (buf->rb_max_requests+1) * RPCRDMA_MAX_SEGS; i; i--) { - r->r.mw = ib_alloc_mw(ia->ri_pd); + r->r.mw = ib_alloc_mw(ia->ri_pd, IB_MW_TYPE_1); if (IS_ERR(r->r.mw)) { rc = PTR_ERR(r->r.mw); dprintk("RPC: %s: ib_alloc_mw" @@ -1673,12 +1673,12 @@ rpcrdma_register_memwin_external(struct rpcrdma_mr_seg *seg, *nsegs = 1; rpcrdma_map_one(ia, seg, writing); - param.mr = ia->ri_bind_mem; + param.bind_info.mr = ia->ri_bind_mem; param.wr_id = 0ULL; /* no send cookie */ - param.addr = seg->mr_dma; - param.length = seg->mr_len; + param.bind_info.addr = seg->mr_dma; + param.bind_info.length = seg->mr_len; param.send_flags = 0; - param.mw_access_flags = mem_priv; + param.bind_info.mw_access_flags = mem_priv; DECR_CQCOUNT(&r_xprt->rx_ep); rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, ¶m); @@ -1690,7 +1690,7 @@ rpcrdma_register_memwin_external(struct rpcrdma_mr_seg *seg, rpcrdma_unmap_one(ia, seg); } else { seg->mr_rkey = seg->mr_chunk.rl_mw->r.mw->rkey; - seg->mr_base = param.addr; + seg->mr_base = param.bind_info.addr; seg->mr_nsegs = 1; } return rc; @@ -1706,10 +1706,10 @@ rpcrdma_deregister_memwin_external(struct rpcrdma_mr_seg *seg, int rc; BUG_ON(seg->mr_nsegs != 1); - param.mr = ia->ri_bind_mem; - param.addr = 0ULL; /* unbind */ - param.length = 0; - param.mw_access_flags = 0; + param.bind_info.mr = ia->ri_bind_mem; + param.bind_info.addr = 0ULL; /* unbind */ + param.bind_info.length = 0; + param.bind_info.mw_access_flags = 0; if (*r) { param.wr_id = (u64) (unsigned long) *r; param.send_flags = IB_SEND_SIGNALED; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 37cbda63f45c..3d02130828da 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -33,6 +33,7 @@ #include <linux/udp.h> #include <linux/tcp.h> #include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/addr.h> #include <linux/sunrpc/sched.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprtsock.h> @@ -848,6 +849,14 @@ static void xs_tcp_close(struct rpc_xprt *xprt) xs_tcp_shutdown(xprt); } +static void xs_local_destroy(struct rpc_xprt *xprt) +{ + xs_close(xprt); + xs_free_peer_addresses(xprt); + xprt_free(xprt); + module_put(THIS_MODULE); +} + /** * xs_destroy - prepare to shutdown a transport * @xprt: doomed transport @@ -861,10 +870,7 @@ static void xs_destroy(struct rpc_xprt *xprt) cancel_delayed_work_sync(&transport->connect_worker); - xs_close(xprt); - xs_free_peer_addresses(xprt); - xprt_free(xprt); - module_put(THIS_MODULE); + xs_local_destroy(xprt); } static inline struct rpc_xprt *xprt_from_sock(struct sock *sk) @@ -1867,13 +1873,9 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, * @xprt: RPC transport to connect * @transport: socket transport to connect * @create_sock: function to create a socket of the correct type - * - * Invoked by a work queue tasklet. */ -static void xs_local_setup_socket(struct work_struct *work) +static int xs_local_setup_socket(struct sock_xprt *transport) { - struct sock_xprt *transport = - container_of(work, struct sock_xprt, connect_worker.work); struct rpc_xprt *xprt = &transport->xprt; struct socket *sock; int status = -EIO; @@ -1918,6 +1920,30 @@ out: xprt_clear_connecting(xprt); xprt_wake_pending_tasks(xprt, status); current->flags &= ~PF_FSTRANS; + return status; +} + +static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) +{ + struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + int ret; + + if (RPC_IS_ASYNC(task)) { + /* + * We want the AF_LOCAL connect to be resolved in the + * filesystem namespace of the process making the rpc + * call. Thus we connect synchronously. + * + * If we want to support asynchronous AF_LOCAL calls, + * we'll need to figure out how to pass a namespace to + * connect. + */ + rpc_exit(task, -ENOTCONN); + return; + } + ret = xs_local_setup_socket(transport); + if (ret && !RPC_IS_SOFTCONN(task)) + msleep_interruptible(15000); } #ifdef CONFIG_SUNRPC_SWAP @@ -2455,13 +2481,13 @@ static struct rpc_xprt_ops xs_local_ops = { .alloc_slot = xprt_alloc_slot, .rpcbind = xs_local_rpcbind, .set_port = xs_local_set_port, - .connect = xs_connect, + .connect = xs_local_connect, .buf_alloc = rpc_malloc, .buf_free = rpc_free, .send_request = xs_local_send_request, .set_retrans_timeout = xprt_set_retrans_timeout_def, .close = xs_close, - .destroy = xs_destroy, + .destroy = xs_local_destroy, .print_stats = xs_local_print_stats, }; @@ -2628,8 +2654,6 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) goto out_err; } xprt_set_bound(xprt); - INIT_DELAYED_WORK(&transport->connect_worker, - xs_local_setup_socket); xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL); break; default: diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 46754779fd3d..24b167914311 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -473,11 +473,10 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, static struct name_seq *nametbl_find_seq(u32 type) { struct hlist_head *seq_head; - struct hlist_node *seq_node; struct name_seq *ns; seq_head = &table.types[hash(type)]; - hlist_for_each_entry(ns, seq_node, seq_head, ns_list) { + hlist_for_each_entry(ns, seq_head, ns_list) { if (ns->type == type) return ns; } @@ -853,7 +852,6 @@ static int nametbl_list(char *buf, int len, u32 depth_info, u32 type, u32 lowbound, u32 upbound) { struct hlist_head *seq_head; - struct hlist_node *seq_node; struct name_seq *seq; int all_types; int ret = 0; @@ -873,7 +871,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info, upbound = ~0; for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { seq_head = &table.types[i]; - hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { + hlist_for_each_entry(seq, seq_head, ns_list) { ret += nameseq_list(seq, buf + ret, len - ret, depth, seq->type, lowbound, upbound, i); @@ -889,7 +887,7 @@ static int nametbl_list(char *buf, int len, u32 depth_info, ret += nametbl_header(buf + ret, len - ret, depth); i = hash(type); seq_head = &table.types[i]; - hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { + hlist_for_each_entry(seq, seq_head, ns_list) { if (seq->type == type) { ret += nameseq_list(seq, buf + ret, len - ret, depth, type, diff --git a/net/tipc/node.c b/net/tipc/node.c index 48f39dd3eae8..6e6c434872e8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -69,12 +69,11 @@ static unsigned int tipc_hashfn(u32 addr) struct tipc_node *tipc_node_find(u32 addr) { struct tipc_node *node; - struct hlist_node *pos; if (unlikely(!in_own_cluster_exact(addr))) return NULL; - hlist_for_each_entry(node, pos, &node_htable[tipc_hashfn(addr)], hash) { + hlist_for_each_entry(node, &node_htable[tipc_hashfn(addr)], hash) { if (node->addr == addr) return node; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index a9622b6cd916..515ce38e4f4c 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -790,6 +790,7 @@ static void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) if (addr) { addr->family = AF_TIPC; addr->addrtype = TIPC_ADDR_ID; + memset(&addr->addr, 0, sizeof(addr->addr)); addr->addr.id.ref = msg_origport(msg); addr->addr.id.node = msg_orignode(msg); addr->addr.name.domain = 0; /* could leave uninitialized */ @@ -904,6 +905,9 @@ static int recv_msg(struct kiocb *iocb, struct socket *sock, goto exit; } + /* will be updated in set_orig_addr() if needed */ + m->msg_namelen = 0; + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); restart: @@ -1013,6 +1017,9 @@ static int recv_stream(struct kiocb *iocb, struct socket *sock, goto exit; } + /* will be updated in set_orig_addr() if needed */ + m->msg_namelen = 0; + target = sock_rcvlowat(sk, flags & MSG_WAITALL, buf_len); timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 87d284289012..2db702d82e7d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -263,9 +263,8 @@ static struct sock *__unix_find_socket_byname(struct net *net, int len, int type, unsigned int hash) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &unix_socket_table[hash ^ type]) { + sk_for_each(s, &unix_socket_table[hash ^ type]) { struct unix_sock *u = unix_sk(s); if (!net_eq(sock_net(s), net)) @@ -298,10 +297,9 @@ static inline struct sock *unix_find_socket_byname(struct net *net, static struct sock *unix_find_socket_byinode(struct inode *i) { struct sock *s; - struct hlist_node *node; spin_lock(&unix_table_lock); - sk_for_each(s, node, + sk_for_each(s, &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) { struct dentry *dentry = unix_sk(s)->path.dentry; @@ -384,7 +382,7 @@ static void unix_sock_destructor(struct sock *sk) #endif } -static int unix_release_sock(struct sock *sk, int embrion) +static void unix_release_sock(struct sock *sk, int embrion) { struct unix_sock *u = unix_sk(sk); struct path path; @@ -453,8 +451,6 @@ static int unix_release_sock(struct sock *sk, int embrion) if (unix_tot_inflight) unix_gc(); /* Garbage collect fds */ - - return 0; } static void init_peercred(struct sock *sk) @@ -701,9 +697,10 @@ static int unix_release(struct socket *sock) if (!sk) return 0; + unix_release_sock(sk, 0); sock->sk = NULL; - return unix_release_sock(sk, 0); + return 0; } static int unix_autobind(struct socket *sock) @@ -1996,7 +1993,7 @@ again: if ((UNIXCB(skb).pid != siocb->scm->pid) || (UNIXCB(skb).cred != siocb->scm->cred)) break; - } else { + } else if (test_bit(SOCK_PASSCRED, &sock->flags)) { /* Copy credentials */ scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); check_creds = 1; diff --git a/net/unix/diag.c b/net/unix/diag.c index 5ac19dc1d5e4..d591091603bf 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -192,10 +192,9 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) slot < ARRAY_SIZE(unix_socket_table); s_num = 0, slot++) { struct sock *sk; - struct hlist_node *node; num = 0; - sk_for_each(sk, node, &unix_socket_table[slot]) { + sk_for_each(sk, &unix_socket_table[slot]) { if (!net_eq(sock_net(sk), net)) continue; if (num < s_num) @@ -226,9 +225,7 @@ static struct sock *unix_lookup_by_ino(int ino) spin_lock(&unix_table_lock); for (i = 0; i < ARRAY_SIZE(unix_socket_table); i++) { - struct hlist_node *node; - - sk_for_each(sk, node, &unix_socket_table[i]) + sk_for_each(sk, &unix_socket_table[i]) if (ino == sock_i_ino(sk)) { sock_hold(sk); spin_unlock(&unix_table_lock); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index b6f4b994eb35..d0f6545b0010 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -99,7 +99,7 @@ unsigned int unix_tot_inflight; struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); /* * Socket ? diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ca511c4f388a..7f93e2a42d7a 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -207,7 +207,7 @@ static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) struct vsock_sock *vsk; list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) - if (vsock_addr_equals_addr_any(addr, &vsk->local_addr)) + if (addr->svm_port == vsk->local_addr.svm_port) return sk_vsock(vsk); return NULL; @@ -220,8 +220,8 @@ static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, list_for_each_entry(vsk, vsock_connected_sockets(src, dst), connected_table) { - if (vsock_addr_equals_addr(src, &vsk->remote_addr) - && vsock_addr_equals_addr(dst, &vsk->local_addr)) { + if (vsock_addr_equals_addr(src, &vsk->remote_addr) && + dst->svm_port == vsk->local_addr.svm_port) { return sk_vsock(vsk); } } @@ -1670,6 +1670,8 @@ vsock_stream_recvmsg(struct kiocb *kiocb, vsk = vsock_sk(sk); err = 0; + msg->msg_namelen = 0; + lock_sock(sk); if (sk->sk_state != SS_CONNECTED) { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index a70ace83a153..5e04d3d96285 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -464,19 +464,16 @@ static struct sock *vmci_transport_get_pending( struct vsock_sock *vlistener; struct vsock_sock *vpending; struct sock *pending; + struct sockaddr_vm src; + + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); vlistener = vsock_sk(listener); list_for_each_entry(vpending, &vlistener->pending_links, pending_links) { - struct sockaddr_vm src; - struct sockaddr_vm dst; - - vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); - vsock_addr_init(&dst, pkt->dg.dst.context, pkt->dst_port); - if (vsock_addr_equals_addr(&src, &vpending->remote_addr) && - vsock_addr_equals_addr(&dst, &vpending->local_addr)) { + pkt->dst_port == vpending->local_addr.svm_port) { pending = sk_vsock(vpending); sock_hold(pending); goto found; @@ -739,10 +736,15 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) */ bh_lock_sock(sk); - if (!sock_owned_by_user(sk) && sk->sk_state == SS_CONNECTED) - vmci_trans(vsk)->notify_ops->handle_notify_pkt( - sk, pkt, true, &dst, &src, - &bh_process_pkt); + if (!sock_owned_by_user(sk)) { + /* The local context ID may be out of date, update it. */ + vsk->local_addr.svm_cid = dst.svm_cid; + + if (sk->sk_state == SS_CONNECTED) + vmci_trans(vsk)->notify_ops->handle_notify_pkt( + sk, pkt, true, &dst, &src, + &bh_process_pkt); + } bh_unlock_sock(sk); @@ -902,6 +904,9 @@ static void vmci_transport_recv_pkt_work(struct work_struct *work) lock_sock(sk); + /* The local context ID may be out of date. */ + vsock_sk(sk)->local_addr.svm_cid = pkt->dg.dst.context; + switch (sk->sk_state) { case SS_LISTEN: vmci_transport_recv_listen(sk, pkt); @@ -958,6 +963,10 @@ static int vmci_transport_recv_listen(struct sock *sk, pending = vmci_transport_get_pending(sk, pkt); if (pending) { lock_sock(pending); + + /* The local context ID may be out of date. */ + vsock_sk(pending)->local_addr.svm_cid = pkt->dg.dst.context; + switch (pending->sk_state) { case SS_CONNECTING: err = vmci_transport_recv_connecting_server(sk, @@ -1727,6 +1736,8 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, if (flags & MSG_OOB || flags & MSG_ERRQUEUE) return -EOPNOTSUPP; + msg->msg_namelen = 0; + /* Retrieve the head sk_buff from the socket's receive queue. */ err = 0; skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err); @@ -1759,7 +1770,6 @@ static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, if (err) goto out; - msg->msg_namelen = 0; if (msg->msg_name) { struct sockaddr_vm *vm_addr; diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c index b7df1aea7c59..ec2611b4ea0e 100644 --- a/net/vmw_vsock/vsock_addr.c +++ b/net/vmw_vsock/vsock_addr.c @@ -64,16 +64,6 @@ bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, } EXPORT_SYMBOL_GPL(vsock_addr_equals_addr); -bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr, - const struct sockaddr_vm *other) -{ - return (addr->svm_cid == VMADDR_CID_ANY || - other->svm_cid == VMADDR_CID_ANY || - addr->svm_cid == other->svm_cid) && - addr->svm_port == other->svm_port; -} -EXPORT_SYMBOL_GPL(vsock_addr_equals_addr_any); - int vsock_addr_cast(const struct sockaddr *addr, size_t len, struct sockaddr_vm **out_addr) { diff --git a/net/vmw_vsock/vsock_addr.h b/net/vmw_vsock/vsock_addr.h index cdfbcefdf843..9ccd5316eac0 100644 --- a/net/vmw_vsock/vsock_addr.h +++ b/net/vmw_vsock/vsock_addr.h @@ -24,8 +24,6 @@ bool vsock_addr_bound(const struct sockaddr_vm *addr); void vsock_addr_unbind(struct sockaddr_vm *addr); bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, const struct sockaddr_vm *other); -bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr, - const struct sockaddr_vm *other); int vsock_addr_cast(const struct sockaddr *addr, size_t len, struct sockaddr_vm **out_addr); diff --git a/net/wireless/core.c b/net/wireless/core.c index 5ffff039b017..6ddf74f0ae1e 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -212,6 +212,39 @@ static void cfg80211_rfkill_poll(struct rfkill *rfkill, void *data) rdev_rfkill_poll(rdev); } +void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev) +{ + lockdep_assert_held(&rdev->devlist_mtx); + lockdep_assert_held(&rdev->sched_scan_mtx); + + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_P2P_DEVICE)) + return; + + if (!wdev->p2p_started) + return; + + rdev_stop_p2p_device(rdev, wdev); + wdev->p2p_started = false; + + rdev->opencount--; + + if (rdev->scan_req && rdev->scan_req->wdev == wdev) { + bool busy = work_busy(&rdev->scan_done_wk); + + /* + * If the work isn't pending or running (in which case it would + * be waiting for the lock we hold) the driver didn't properly + * cancel the scan when the interface was removed. In this case + * warn and leak the scan request object to not crash later. + */ + WARN_ON(!busy); + + rdev->scan_req->aborted = true; + ___cfg80211_scan_done(rdev, !busy); + } +} + static int cfg80211_rfkill_set_block(void *data, bool blocked) { struct cfg80211_registered_device *rdev = data; @@ -221,7 +254,8 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked) return 0; rtnl_lock(); - mutex_lock(&rdev->devlist_mtx); + + /* read-only iteration need not hold the devlist_mtx */ list_for_each_entry(wdev, &rdev->wdev_list, list) { if (wdev->netdev) { @@ -231,18 +265,18 @@ static int cfg80211_rfkill_set_block(void *data, bool blocked) /* otherwise, check iftype */ switch (wdev->iftype) { case NL80211_IFTYPE_P2P_DEVICE: - if (!wdev->p2p_started) - break; - rdev_stop_p2p_device(rdev, wdev); - wdev->p2p_started = false; - rdev->opencount--; + /* but this requires it */ + mutex_lock(&rdev->devlist_mtx); + mutex_lock(&rdev->sched_scan_mtx); + cfg80211_stop_p2p_device(rdev, wdev); + mutex_unlock(&rdev->sched_scan_mtx); + mutex_unlock(&rdev->devlist_mtx); break; default: break; } } - mutex_unlock(&rdev->devlist_mtx); rtnl_unlock(); return 0; @@ -367,8 +401,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) rdev->wiphy.rts_threshold = (u32) -1; rdev->wiphy.coverage_class = 0; - rdev->wiphy.features = NL80211_FEATURE_SCAN_FLUSH | - NL80211_FEATURE_ADVERTISE_CHAN_LIMITS; + rdev->wiphy.features = NL80211_FEATURE_SCAN_FLUSH; return &rdev->wiphy; } @@ -746,17 +779,13 @@ static void wdev_cleanup_work(struct work_struct *work) wdev = container_of(work, struct wireless_dev, cleanup_work); rdev = wiphy_to_dev(wdev->wiphy); - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); if (WARN_ON(rdev->scan_req && rdev->scan_req->wdev == wdev)) { rdev->scan_req->aborted = true; ___cfg80211_scan_done(rdev, true); } - cfg80211_unlock_rdev(rdev); - - mutex_lock(&rdev->sched_scan_mtx); - if (WARN_ON(rdev->sched_scan_req && rdev->sched_scan_req->dev == wdev->netdev)) { __cfg80211_stop_sched_scan(rdev, false); @@ -782,21 +811,19 @@ void cfg80211_unregister_wdev(struct wireless_dev *wdev) return; mutex_lock(&rdev->devlist_mtx); + mutex_lock(&rdev->sched_scan_mtx); list_del_rcu(&wdev->list); rdev->devlist_generation++; switch (wdev->iftype) { case NL80211_IFTYPE_P2P_DEVICE: - if (!wdev->p2p_started) - break; - rdev_stop_p2p_device(rdev, wdev); - wdev->p2p_started = false; - rdev->opencount--; + cfg80211_stop_p2p_device(rdev, wdev); break; default: WARN_ON_ONCE(1); break; } + mutex_unlock(&rdev->sched_scan_mtx); mutex_unlock(&rdev->devlist_mtx); } EXPORT_SYMBOL(cfg80211_unregister_wdev); @@ -937,6 +964,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, cfg80211_update_iface_num(rdev, wdev->iftype, 1); cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); + mutex_lock(&rdev->sched_scan_mtx); wdev_lock(wdev); switch (wdev->iftype) { #ifdef CONFIG_CFG80211_WEXT @@ -968,6 +996,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, break; } wdev_unlock(wdev); + mutex_unlock(&rdev->sched_scan_mtx); rdev->opencount++; mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); diff --git a/net/wireless/core.h b/net/wireless/core.h index 3aec0e429d8a..5845c2b37aa8 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -503,6 +503,9 @@ int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, void cfg80211_update_iface_num(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype, int num); +void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev); + #define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 35545ccc30fd..58e13a8c95f9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -554,27 +554,8 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, if ((chan->flags & IEEE80211_CHAN_NO_IBSS) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_IBSS)) goto nla_put_failure; - if (chan->flags & IEEE80211_CHAN_RADAR) { - u32 time = elapsed_jiffies_msecs(chan->dfs_state_entered); - if (nla_put_flag(msg, NL80211_FREQUENCY_ATTR_RADAR)) - goto nla_put_failure; - if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_DFS_STATE, - chan->dfs_state)) - goto nla_put_failure; - if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_DFS_TIME, time)) - goto nla_put_failure; - } - if ((chan->flags & IEEE80211_CHAN_NO_HT40MINUS) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_HT40_MINUS)) - goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_HT40PLUS) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_HT40_PLUS)) - goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_80MHZ) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_80MHZ)) - goto nla_put_failure; - if ((chan->flags & IEEE80211_CHAN_NO_160MHZ) && - nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_160MHZ)) + if ((chan->flags & IEEE80211_CHAN_RADAR) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_RADAR)) goto nla_put_failure; if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -900,9 +881,6 @@ static int nl80211_put_iface_combinations(struct wiphy *wiphy, nla_put_u32(msg, NL80211_IFACE_COMB_MAXNUM, c->max_interfaces)) goto nla_put_failure; - if (nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS, - c->radar_detect_widths)) - goto nla_put_failure; nla_nest_end(msg, nl_combi); } @@ -914,48 +892,6 @@ nla_put_failure: return -ENOBUFS; } -#ifdef CONFIG_PM -static int nl80211_send_wowlan_tcp_caps(struct cfg80211_registered_device *rdev, - struct sk_buff *msg) -{ - const struct wiphy_wowlan_tcp_support *tcp = rdev->wiphy.wowlan.tcp; - struct nlattr *nl_tcp; - - if (!tcp) - return 0; - - nl_tcp = nla_nest_start(msg, NL80211_WOWLAN_TRIG_TCP_CONNECTION); - if (!nl_tcp) - return -ENOBUFS; - - if (nla_put_u32(msg, NL80211_WOWLAN_TCP_DATA_PAYLOAD, - tcp->data_payload_max)) - return -ENOBUFS; - - if (nla_put_u32(msg, NL80211_WOWLAN_TCP_DATA_PAYLOAD, - tcp->data_payload_max)) - return -ENOBUFS; - - if (tcp->seq && nla_put_flag(msg, NL80211_WOWLAN_TCP_DATA_PAYLOAD_SEQ)) - return -ENOBUFS; - - if (tcp->tok && nla_put(msg, NL80211_WOWLAN_TCP_DATA_PAYLOAD_TOKEN, - sizeof(*tcp->tok), tcp->tok)) - return -ENOBUFS; - - if (nla_put_u32(msg, NL80211_WOWLAN_TCP_DATA_INTERVAL, - tcp->data_interval_max)) - return -ENOBUFS; - - if (nla_put_u32(msg, NL80211_WOWLAN_TCP_WAKE_PAYLOAD, - tcp->wake_payload_max)) - return -ENOBUFS; - - nla_nest_end(msg, nl_tcp); - return 0; -} -#endif - static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *dev) { @@ -1330,9 +1266,6 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flag goto nla_put_failure; } - if (nl80211_send_wowlan_tcp_caps(dev, msg)) - goto nla_put_failure; - nla_nest_end(msg, nl_wowlan); } #endif @@ -1365,15 +1298,6 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flag dev->wiphy.max_acl_mac_addrs)) goto nla_put_failure; - if (dev->wiphy.extended_capabilities && - (nla_put(msg, NL80211_ATTR_EXT_CAPA, - dev->wiphy.extended_capabilities_len, - dev->wiphy.extended_capabilities) || - nla_put(msg, NL80211_ATTR_EXT_CAPA_MASK, - dev->wiphy.extended_capabilities_len, - dev->wiphy.extended_capabilities_mask))) - goto nla_put_failure; - return genlmsg_end(msg, hdr); nla_put_failure: @@ -1383,7 +1307,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flag static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) { - int idx = 0; + int idx = 0, ret; int start = cb->args[0]; struct cfg80211_registered_device *dev; @@ -1393,9 +1317,29 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) continue; if (++idx <= start) continue; - if (nl80211_send_wiphy(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - dev) < 0) { + ret = nl80211_send_wiphy(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + dev); + if (ret < 0) { + /* + * If sending the wiphy data didn't fit (ENOBUFS or + * EMSGSIZE returned), this SKB is still empty (so + * it's not too big because another wiphy dataset is + * already in the skb) and we've not tried to adjust + * the dump allocation yet ... then adjust the alloc + * size to be bigger, and return 1 but with the empty + * skb. This results in an empty message being RX'ed + * in userspace, but that is ignored. + * + * We can then retry with the larger buffer. + */ + if ((ret == -ENOBUFS || ret == -EMSGSIZE) && + !skb->len && + cb->min_dump_alloc < 4096) { + cb->min_dump_alloc = 4096; + mutex_unlock(&cfg80211_mutex); + return 1; + } idx--; break; } @@ -1412,7 +1356,7 @@ static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; struct cfg80211_registered_device *dev = info->user_ptr[0]; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + msg = nlmsg_new(4096, GFP_KERNEL); if (!msg) return -ENOMEM; @@ -4758,14 +4702,19 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->scan) return -EOPNOTSUPP; - if (rdev->scan_req) - return -EBUSY; + mutex_lock(&rdev->sched_scan_mtx); + if (rdev->scan_req) { + err = -EBUSY; + goto unlock; + } if (info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { n_channels = validate_scan_freqs( info->attrs[NL80211_ATTR_SCAN_FREQUENCIES]); - if (!n_channels) - return -EINVAL; + if (!n_channels) { + err = -EINVAL; + goto unlock; + } } else { enum ieee80211_band band; n_channels = 0; @@ -4779,23 +4728,29 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) n_ssids++; - if (n_ssids > wiphy->max_scan_ssids) - return -EINVAL; + if (n_ssids > wiphy->max_scan_ssids) { + err = -EINVAL; + goto unlock; + } if (info->attrs[NL80211_ATTR_IE]) ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); else ie_len = 0; - if (ie_len > wiphy->max_scan_ie_len) - return -EINVAL; + if (ie_len > wiphy->max_scan_ie_len) { + err = -EINVAL; + goto unlock; + } request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + sizeof(*request->channels) * n_channels + ie_len, GFP_KERNEL); - if (!request) - return -ENOMEM; + if (!request) { + err = -ENOMEM; + goto unlock; + } if (n_ssids) request->ssids = (void *)&request->channels[n_channels]; @@ -4932,6 +4887,8 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) kfree(request); } + unlock: + mutex_unlock(&rdev->sched_scan_mtx); return err; } @@ -7805,20 +7762,9 @@ static int nl80211_stop_p2p_device(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->stop_p2p_device) return -EOPNOTSUPP; - if (!wdev->p2p_started) - return 0; - - rdev_stop_p2p_device(rdev, wdev); - wdev->p2p_started = false; - - mutex_lock(&rdev->devlist_mtx); - rdev->opencount--; - mutex_unlock(&rdev->devlist_mtx); - - if (WARN_ON(rdev->scan_req && rdev->scan_req->wdev == wdev)) { - rdev->scan_req->aborted = true; - ___cfg80211_scan_done(rdev, true); - } + mutex_lock(&rdev->sched_scan_mtx); + cfg80211_stop_p2p_device(rdev, wdev); + mutex_unlock(&rdev->sched_scan_mtx); return 0; } @@ -8542,7 +8488,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg, struct nlattr *nest; int i; - ASSERT_RDEV_LOCK(rdev); + lockdep_assert_held(&rdev->sched_scan_mtx); if (WARN_ON(!req)) return 0; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 674aadca0079..fd99ea495b7e 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -169,7 +169,7 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev, bool leak) union iwreq_data wrqu; #endif - ASSERT_RDEV_LOCK(rdev); + lockdep_assert_held(&rdev->sched_scan_mtx); request = rdev->scan_req; @@ -230,9 +230,9 @@ void __cfg80211_scan_done(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, scan_done_wk); - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); ___cfg80211_scan_done(rdev, false); - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); } void cfg80211_scan_done(struct cfg80211_scan_request *request, bool aborted) @@ -698,11 +698,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, found = rb_find_bss(dev, tmp, BSS_CMP_REGULAR); if (found) { - found->pub.beacon_interval = tmp->pub.beacon_interval; - found->pub.signal = tmp->pub.signal; - found->pub.capability = tmp->pub.capability; - found->ts = tmp->ts; - /* Update IEs */ if (rcu_access_pointer(tmp->pub.proberesp_ies)) { const struct cfg80211_bss_ies *old; @@ -723,6 +718,8 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, if (found->pub.hidden_beacon_bss && !list_empty(&found->hidden_list)) { + const struct cfg80211_bss_ies *f; + /* * The found BSS struct is one of the probe * response members of a group, but we're @@ -732,6 +729,10 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, * SSID to showing it, which is confusing so * drop this information. */ + + f = rcu_access_pointer(tmp->pub.beacon_ies); + kfree_rcu((struct cfg80211_bss_ies *)f, + rcu_head); goto drop; } @@ -761,6 +762,11 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); } + + found->pub.beacon_interval = tmp->pub.beacon_interval; + found->pub.signal = tmp->pub.signal; + found->pub.capability = tmp->pub.capability; + found->ts = tmp->ts; } else { struct cfg80211_internal_bss *new; struct cfg80211_internal_bss *hidden; @@ -1056,6 +1062,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, if (IS_ERR(rdev)) return PTR_ERR(rdev); + mutex_lock(&rdev->sched_scan_mtx); if (rdev->scan_req) { err = -EBUSY; goto out; @@ -1162,6 +1169,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, dev_hold(dev); } out: + mutex_unlock(&rdev->sched_scan_mtx); kfree(creq); cfg80211_unlock_rdev(rdev); return err; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f432bd3755b1..482c70e70127 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -85,6 +85,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) ASSERT_RTNL(); ASSERT_RDEV_LOCK(rdev); ASSERT_WDEV_LOCK(wdev); + lockdep_assert_held(&rdev->sched_scan_mtx); if (rdev->scan_req) return -EBUSY; @@ -223,6 +224,7 @@ void cfg80211_conn_work(struct work_struct *work) rtnl_lock(); cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); + mutex_lock(&rdev->sched_scan_mtx); list_for_each_entry(wdev, &rdev->wdev_list, list) { wdev_lock(wdev); @@ -247,6 +249,7 @@ void cfg80211_conn_work(struct work_struct *work) wdev_unlock(wdev); } + mutex_unlock(&rdev->sched_scan_mtx); mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); rtnl_unlock(); @@ -320,11 +323,9 @@ void cfg80211_sme_scan_done(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; - mutex_lock(&wiphy_to_dev(wdev->wiphy)->devlist_mtx); wdev_lock(wdev); __cfg80211_sme_scan_done(dev); wdev_unlock(wdev); - mutex_unlock(&wiphy_to_dev(wdev->wiphy)->devlist_mtx); } void cfg80211_sme_rx_auth(struct net_device *dev, @@ -924,9 +925,12 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, int err; mutex_lock(&rdev->devlist_mtx); + /* might request scan - scan_mtx -> wdev_mtx dependency */ + mutex_lock(&rdev->sched_scan_mtx); wdev_lock(dev->ieee80211_ptr); err = __cfg80211_connect(rdev, dev, connect, connkeys, NULL); wdev_unlock(dev->ieee80211_ptr); + mutex_unlock(&rdev->sched_scan_mtx); mutex_unlock(&rdev->devlist_mtx); return err; diff --git a/net/wireless/trace.h b/net/wireless/trace.h index b7a531380e19..7586de77a2f8 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -27,7 +27,8 @@ #define WIPHY_PR_ARG __entry->wiphy_name #define WDEV_ENTRY __field(u32, id) -#define WDEV_ASSIGN (__entry->id) = (wdev ? wdev->identifier : 0) +#define WDEV_ASSIGN (__entry->id) = (!IS_ERR_OR_NULL(wdev) \ + ? wdev->identifier : 0) #define WDEV_PR_FMT "wdev(%u)" #define WDEV_PR_ARG (__entry->id) @@ -1778,7 +1779,7 @@ TRACE_EVENT(rdev_set_mac_acl, ), TP_fast_assign( WIPHY_ASSIGN; - WIPHY_ASSIGN; + NETDEV_ASSIGN; __entry->acl_policy = params->acl_policy; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", acl policy: %d", diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index fb9622f6d99c..e79cb5c0655a 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -89,6 +89,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); + mutex_lock(&rdev->sched_scan_mtx); wdev_lock(wdev); if (wdev->sme_state != CFG80211_SME_IDLE) { @@ -135,6 +136,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); + mutex_unlock(&rdev->sched_scan_mtx); mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); return err; @@ -190,6 +192,7 @@ int cfg80211_mgd_wext_siwessid(struct net_device *dev, cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); + mutex_lock(&rdev->sched_scan_mtx); wdev_lock(wdev); err = 0; @@ -223,6 +226,7 @@ int cfg80211_mgd_wext_siwessid(struct net_device *dev, err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); + mutex_unlock(&rdev->sched_scan_mtx); mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); return err; @@ -285,6 +289,7 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev, cfg80211_lock_rdev(rdev); mutex_lock(&rdev->devlist_mtx); + mutex_lock(&rdev->sched_scan_mtx); wdev_lock(wdev); if (wdev->sme_state != CFG80211_SME_IDLE) { @@ -313,6 +318,7 @@ int cfg80211_mgd_wext_siwap(struct net_device *dev, err = cfg80211_mgd_wext_connect(rdev, wdev); out: wdev_unlock(wdev); + mutex_unlock(&rdev->sched_scan_mtx); mutex_unlock(&rdev->devlist_mtx); cfg80211_unlock_rdev(rdev); return err; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index a306bc66000e..37ca9694aabe 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -208,11 +208,10 @@ static void x25_remove_socket(struct sock *sk) static void x25_kill_by_device(struct net_device *dev) { struct sock *s; - struct hlist_node *node; write_lock_bh(&x25_list_lock); - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if (x25_sk(s)->neighbour && x25_sk(s)->neighbour->dev == dev) x25_disconnect(s, ENETUNREACH, 0, 0); @@ -280,12 +279,11 @@ static struct sock *x25_find_listener(struct x25_address *addr, { struct sock *s; struct sock *next_best; - struct hlist_node *node; read_lock_bh(&x25_list_lock); next_best = NULL; - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if ((!strcmp(addr->x25_addr, x25_sk(s)->source_addr.x25_addr) || !strcmp(addr->x25_addr, @@ -323,9 +321,8 @@ found: static struct sock *__x25_find_socket(unsigned int lci, struct x25_neigh *nb) { struct sock *s; - struct hlist_node *node; - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if (x25_sk(s)->lci == lci && x25_sk(s)->neighbour == nb) { sock_hold(s); goto found; @@ -1782,11 +1779,10 @@ static struct notifier_block x25_dev_notifier = { void x25_kill_by_neigh(struct x25_neigh *nb) { struct sock *s; - struct hlist_node *node; write_lock_bh(&x25_list_lock); - sk_for_each(s, node, &x25_list) + sk_for_each(s, &x25_list) if (x25_sk(s)->neighbour == nb) x25_disconnect(s, ENETUNREACH, 0, 0); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5b47180986f8..167c67d46c6a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -379,27 +379,27 @@ static void xfrm_dst_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, unsigned int nhashmask) { - struct hlist_node *entry, *tmp, *entry0 = NULL; + struct hlist_node *tmp, *entry0 = NULL; struct xfrm_policy *pol; unsigned int h0 = 0; redo: - hlist_for_each_entry_safe(pol, entry, tmp, list, bydst) { + hlist_for_each_entry_safe(pol, tmp, list, bydst) { unsigned int h; h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask); if (!entry0) { - hlist_del(entry); + hlist_del(&pol->bydst); hlist_add_head(&pol->bydst, ndsttable+h); h0 = h; } else { if (h != h0) continue; - hlist_del(entry); + hlist_del(&pol->bydst); hlist_add_after(entry0, &pol->bydst); } - entry0 = entry; + entry0 = &pol->bydst; } if (!hlist_empty(list)) { entry0 = NULL; @@ -411,10 +411,10 @@ static void xfrm_idx_hash_transfer(struct hlist_head *list, struct hlist_head *nidxtable, unsigned int nhashmask) { - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; struct xfrm_policy *pol; - hlist_for_each_entry_safe(pol, entry, tmp, list, byidx) { + hlist_for_each_entry_safe(pol, tmp, list, byidx) { unsigned int h; h = __idx_hash(pol->index, nhashmask); @@ -544,7 +544,6 @@ static u32 xfrm_gen_index(struct net *net, int dir) static u32 idx_generator; for (;;) { - struct hlist_node *entry; struct hlist_head *list; struct xfrm_policy *p; u32 idx; @@ -556,7 +555,7 @@ static u32 xfrm_gen_index(struct net *net, int dir) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; - hlist_for_each_entry(p, entry, list, byidx) { + hlist_for_each_entry(p, list, byidx) { if (p->index == idx) { found = 1; break; @@ -628,13 +627,13 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *pol; struct xfrm_policy *delpol; struct hlist_head *chain; - struct hlist_node *entry, *newpos; + struct hlist_node *newpos; write_lock_bh(&xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); delpol = NULL; newpos = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(policy, pol) && @@ -691,13 +690,12 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, { struct xfrm_policy *pol, *ret; struct hlist_head *chain; - struct hlist_node *entry; *err = 0; write_lock_bh(&xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); ret = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && (mark & pol->mark.m) == pol->mark.v && !selector_cmp(sel, &pol->selector) && @@ -729,7 +727,6 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, { struct xfrm_policy *pol, *ret; struct hlist_head *chain; - struct hlist_node *entry; *err = -ENOENT; if (xfrm_policy_id2dir(id) != dir) @@ -739,7 +736,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, write_lock_bh(&xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; - hlist_for_each_entry(pol, entry, chain, byidx) { + hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && (mark & pol->mark.m) == pol->mark.v) { xfrm_pol_hold(pol); @@ -772,10 +769,9 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy *pol; - struct hlist_node *entry; int i; - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; @@ -789,7 +785,7 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audi } } for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) @@ -828,11 +824,10 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy *pol; - struct hlist_node *entry; int i; again1: - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; @@ -852,7 +847,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { again2: - hlist_for_each_entry(pol, entry, + hlist_for_each_entry(pol, net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) @@ -980,7 +975,6 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, int err; struct xfrm_policy *pol, *ret; const xfrm_address_t *daddr, *saddr; - struct hlist_node *entry; struct hlist_head *chain; u32 priority = ~0U; @@ -992,7 +986,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, read_lock_bh(&xfrm_policy_lock); chain = policy_hash_direct(net, daddr, saddr, family, dir); ret = NULL; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -1008,7 +1002,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } } chain = &net->xfrm.policy_inexact[dir]; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { if (err == -ESRCH) @@ -3041,13 +3035,12 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector u8 dir, u8 type) { struct xfrm_policy *pol, *ret = NULL; - struct hlist_node *entry; struct hlist_head *chain; u32 priority = ~0U; read_lock_bh(&xfrm_policy_lock); chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir); - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; @@ -3056,7 +3049,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector } } chain = &init_net.xfrm.policy_inexact[dir]; - hlist_for_each_entry(pol, entry, chain, bydst) { + hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type && pol->priority < priority) { diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 35754cc8a9e5..8dafe6d3c6e4 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -334,6 +334,70 @@ static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event) x->xflags &= ~XFRM_TIME_DEFER; } +static void xfrm_replay_notify_esn(struct xfrm_state *x, int event) +{ + u32 seq_diff, oseq_diff; + struct km_event c; + struct xfrm_replay_state_esn *replay_esn = x->replay_esn; + struct xfrm_replay_state_esn *preplay_esn = x->preplay_esn; + + /* we send notify messages in case + * 1. we updated on of the sequence numbers, and the seqno difference + * is at least x->replay_maxdiff, in this case we also update the + * timeout of our timer function + * 2. if x->replay_maxage has elapsed since last update, + * and there were changes + * + * The state structure must be locked! + */ + + switch (event) { + case XFRM_REPLAY_UPDATE: + if (!x->replay_maxdiff) + break; + + if (replay_esn->seq_hi == preplay_esn->seq_hi) + seq_diff = replay_esn->seq - preplay_esn->seq; + else + seq_diff = ~preplay_esn->seq + replay_esn->seq + 1; + + if (replay_esn->oseq_hi == preplay_esn->oseq_hi) + oseq_diff = replay_esn->oseq - preplay_esn->oseq; + else + oseq_diff = ~preplay_esn->oseq + replay_esn->oseq + 1; + + if (seq_diff < x->replay_maxdiff && + oseq_diff < x->replay_maxdiff) { + + if (x->xflags & XFRM_TIME_DEFER) + event = XFRM_REPLAY_TIMEOUT; + else + return; + } + + break; + + case XFRM_REPLAY_TIMEOUT: + if (memcmp(x->replay_esn, x->preplay_esn, + xfrm_replay_state_esn_len(replay_esn)) == 0) { + x->xflags |= XFRM_TIME_DEFER; + return; + } + + break; + } + + memcpy(x->preplay_esn, x->replay_esn, + xfrm_replay_state_esn_len(replay_esn)); + c.event = XFRM_MSG_NEWAE; + c.data.aevent = event; + km_state_notify(x, &c); + + if (x->replay_maxage && + !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) + x->xflags &= ~XFRM_TIME_DEFER; +} + static int xfrm_replay_overflow_esn(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; @@ -510,7 +574,7 @@ static struct xfrm_replay xfrm_replay_esn = { .advance = xfrm_replay_advance_esn, .check = xfrm_replay_check_esn, .recheck = xfrm_replay_recheck_esn, - .notify = xfrm_replay_notify_bmp, + .notify = xfrm_replay_notify_esn, .overflow = xfrm_replay_overflow_esn, }; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index ae01bdbcb294..2c341bdaf47c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -72,10 +72,10 @@ static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *nspitable, unsigned int nhashmask) { - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; struct xfrm_state *x; - hlist_for_each_entry_safe(x, entry, tmp, list, bydst) { + hlist_for_each_entry_safe(x, tmp, list, bydst) { unsigned int h; h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, @@ -368,14 +368,14 @@ static void xfrm_state_gc_task(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_gc_work); struct xfrm_state *x; - struct hlist_node *entry, *tmp; + struct hlist_node *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); hlist_move_list(&net->xfrm.state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); - hlist_for_each_entry_safe(x, entry, tmp, &gc_list, gclist) + hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); wake_up(&net->xfrm.km_waitq); @@ -577,10 +577,9 @@ xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audi int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct hlist_node *entry; struct xfrm_state *x; - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, @@ -613,10 +612,9 @@ int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info) err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct hlist_node *entry; struct xfrm_state *x; restart: - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); @@ -685,9 +683,8 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, { unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; - struct hlist_node *entry; - hlist_for_each_entry(x, entry, net->xfrm.state_byspi+h, byspi) { + hlist_for_each_entry(x, net->xfrm.state_byspi+h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || @@ -710,9 +707,8 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, { unsigned int h = xfrm_src_hash(net, daddr, saddr, family); struct xfrm_state *x; - struct hlist_node *entry; - hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || @@ -798,7 +794,6 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); unsigned int h, h_wildcard; - struct hlist_node *entry; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; int error = 0; @@ -810,7 +805,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, spin_lock_bh(&xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -826,7 +821,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, goto found; h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h_wildcard, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h_wildcard, bydst) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && @@ -906,11 +901,10 @@ xfrm_stateonly_find(struct net *net, u32 mark, { unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; - struct hlist_node *entry; spin_lock(&xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && @@ -972,12 +966,11 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) unsigned short family = xnew->props.family; u32 reqid = xnew->props.reqid; struct xfrm_state *x; - struct hlist_node *entry; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && @@ -1004,11 +997,10 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m, const xfrm_address_t *saddr, int create) { unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); - struct hlist_node *entry; struct xfrm_state *x; u32 mark = m->v & m->m; - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || @@ -1215,12 +1207,11 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) { unsigned int h; struct xfrm_state *x; - struct hlist_node *entry; if (m->reqid) { h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); - hlist_for_each_entry(x, entry, init_net.xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1237,7 +1228,7 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) } else { h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr, m->old_family); - hlist_for_each_entry(x, entry, init_net.xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1466,10 +1457,9 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s int i; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct hlist_node *entry; struct xfrm_state *x; - hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->km.state == XFRM_STATE_ACQ) { |