diff options
Diffstat (limited to 'net')
609 files changed, 10334 insertions, 17589 deletions
diff --git a/net/802/garp.c b/net/802/garp.c index 7f50d47470bd..8e19f51833d6 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -206,6 +206,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr kfree(attr); } +static void garp_attr_destroy_all(struct garp_applicant *app) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_destroy(app, attr); + } +} + static int garp_pdu_init(struct garp_applicant *app) { struct sk_buff *skb; @@ -612,6 +625,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl spin_lock_bh(&app->lock); garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_attr_destroy_all(app); garp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/802/mrp.c b/net/802/mrp.c index a808dd5bbb27..ce6e4774d333 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -295,6 +295,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) kfree(attr); } +static void mrp_attr_destroy_all(struct mrp_applicant *app) +{ + struct rb_node *node, *next; + struct mrp_attr *attr; + + for (node = rb_first(&app->mad); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct mrp_attr, node); + mrp_attr_destroy(app, attr); + } +} + static int mrp_pdu_init(struct mrp_applicant *app) { struct sk_buff *skb; @@ -596,7 +609,10 @@ static void mrp_join_timer(struct timer_list *t) spin_unlock(&app->lock); mrp_queue_xmit(app); - mrp_join_timer_arm(app); + spin_lock(&app->lock); + if (likely(app->active)) + mrp_join_timer_arm(app); + spin_unlock(&app->lock); } static void mrp_periodic_timer_arm(struct mrp_applicant *app) @@ -610,11 +626,12 @@ static void mrp_periodic_timer(struct timer_list *t) struct mrp_applicant *app = from_timer(app, t, periodic_timer); spin_lock(&app->lock); - mrp_mad_event(app, MRP_EVENT_PERIODIC); - mrp_pdu_queue(app); + if (likely(app->active)) { + mrp_mad_event(app, MRP_EVENT_PERIODIC); + mrp_pdu_queue(app); + mrp_periodic_timer_arm(app); + } spin_unlock(&app->lock); - - mrp_periodic_timer_arm(app); } static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) @@ -862,6 +879,7 @@ int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) app->dev = dev; app->app = appl; app->mad = RB_ROOT; + app->active = true; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); @@ -890,6 +908,9 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) RCU_INIT_POINTER(port->applicants[appl->type], NULL); + spin_lock_bh(&app->lock); + app->active = false; + spin_unlock_bh(&app->lock); /* Delete timer and generate a final TX event to flush out * all pending messages before the applicant is gone. */ @@ -898,6 +919,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) spin_lock_bh(&app->lock); mrp_mad_event(app, MRP_EVENT_TX); + mrp_attr_destroy_all(app); mrp_pdu_queue(app); spin_unlock_bh(&app->lock); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 5e9950453955..512ada90657b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -277,7 +277,8 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) return 0; out_free_newdev: - if (new_dev->reg_state == NETREG_UNINITIALIZED) + if (new_dev->reg_state == NETREG_UNINITIALIZED || + new_dev->reg_state == NETREG_UNREGISTERED) free_netdev(new_dev); return err; } diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 4f60e86f4b8d..e92c914316cb 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -380,6 +380,8 @@ int vlan_vids_add_by_dev(struct net_device *dev, return 0; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; err = vlan_vid_add(dev, vid_info->proto, vid_info->vid); if (err) goto unwind; @@ -390,6 +392,8 @@ unwind: list_for_each_entry_continue_reverse(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); } @@ -409,8 +413,11 @@ void vlan_vids_del_by_dev(struct net_device *dev, if (!vlan_info) return; - list_for_each_entry(vid_info, &vlan_info->vid_list, list) + list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); + } } EXPORT_SYMBOL(vlan_vids_del_by_dev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 84ef83772114..ba9b8980f100 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -115,8 +115,8 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, * NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs... */ - if (veth->h_vlan_proto != vlan->vlan_proto || - vlan->flags & VLAN_FLAG_REORDER_HDR) { + if (vlan->flags & VLAN_FLAG_REORDER_HDR || + veth->h_vlan_proto != vlan->vlan_proto) { u16 vlan_tci; vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb->priority); @@ -369,7 +369,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCSHWTSTAMP: - if (!net_eq(dev_net(dev), &init_net)) + if (!net_eq(dev_net(dev), dev_net(real_dev))) break; case SIOCGMIIPHY: case SIOCGMIIREG: diff --git a/net/9p/client.c b/net/9p/client.c index d62f83f93d7b..98301add20f4 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -553,6 +553,8 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) kfree(ename); } else { err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode); + if (err) + goto out_err; err = -ecode; p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode); @@ -906,16 +908,13 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt) struct p9_fid *fid; p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt); - fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL); + fid = kzalloc(sizeof(struct p9_fid), GFP_KERNEL); if (!fid) return NULL; - memset(&fid->qid, 0, sizeof(struct p9_qid)); fid->mode = -1; fid->uid = current_fsuid(); fid->clnt = clnt; - fid->rdir = NULL; - fid->fid = 0; idr_preload(GFP_KERNEL); spin_lock_irq(&clnt->lock); diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 462ba144cb39..9104a2fce015 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -243,6 +243,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, uint16_t *nwname = va_arg(ap, uint16_t *); char ***wnames = va_arg(ap, char ***); + *wnames = NULL; + errcode = p9pdu_readf(pdu, proto_version, "w", nwname); if (!errcode) { @@ -252,6 +254,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, GFP_NOFS); if (!*wnames) errcode = -ENOMEM; + else + (*wnames)[0] = NULL; } if (!errcode) { @@ -263,8 +267,10 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, proto_version, "s", &(*wnames)[i]); - if (errcode) + if (errcode) { + (*wnames)[i] = NULL; break; + } } } @@ -272,11 +278,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, if (*wnames) { int i; - for (i = 0; i < *nwname; i++) + for (i = 0; i < *nwname; i++) { + if (!(*wnames)[i]) + break; kfree((*wnames)[i]); + } + kfree(*wnames); + *wnames = NULL; } - kfree(*wnames); - *wnames = NULL; } } break; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index b6dcb40fa8a7..0ef3d2ede6e6 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -133,7 +133,7 @@ struct p9_conn { struct list_head unsent_req_list; struct p9_req_t *rreq; struct p9_req_t *wreq; - char tmp_buf[7]; + char tmp_buf[P9_HDRSZ]; struct p9_fcall rc; int wpos; int wsize; @@ -215,11 +215,15 @@ static void p9_conn_cancel(struct p9_conn *m, int err) list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) { list_move(&req->req_list, &cancel_list); + req->status = REQ_STATUS_ERROR; } + spin_unlock(&m->client->lock); + list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) { p9_debug(P9_DEBUG_ERROR, "call back req %p\n", req); list_del(&req->req_list); @@ -227,7 +231,6 @@ static void p9_conn_cancel(struct p9_conn *m, int err) req->t_err = err; p9_client_cb(m->client, req, REQ_STATUS_ERROR); } - spin_unlock(&m->client->lock); } static __poll_t @@ -303,7 +306,7 @@ static void p9_read_work(struct work_struct *work) if (!m->rc.sdata) { m->rc.sdata = m->tmp_buf; m->rc.offset = 0; - m->rc.capacity = 7; /* start by reading header */ + m->rc.capacity = P9_HDRSZ; /* start by reading header */ } clear_bit(Rpending, &m->wsched); @@ -326,7 +329,7 @@ static void p9_read_work(struct work_struct *work) p9_debug(P9_DEBUG_TRANS, "got new header\n"); /* Header size */ - m->rc.size = 7; + m->rc.size = P9_HDRSZ; err = p9_parse_header(&m->rc, &m->rc.size, NULL, NULL, 0); if (err) { p9_debug(P9_DEBUG_ERROR, @@ -835,11 +838,14 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) goto out_free_ts; if (!(ts->rd->f_mode & FMODE_READ)) goto out_put_rd; + /* prevent workers from hanging on IO when fd is a pipe */ + ts->rd->f_flags |= O_NONBLOCK; ts->wr = fget(wfd); if (!ts->wr) goto out_put_rd; if (!(ts->wr->f_mode & FMODE_WRITE)) goto out_put_wr; + ts->wr->f_flags |= O_NONBLOCK; client->trans = ts; client->status = Connected; @@ -861,8 +867,10 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket) struct file *file; p = kzalloc(sizeof(struct p9_trans_fd), GFP_KERNEL); - if (!p) + if (!p) { + sock_release(csocket); return -ENOMEM; + } csocket->sk->sk_allocation = GFP_NOIO; file = sock_alloc_file(csocket, 0, NULL); @@ -1038,7 +1046,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) csocket = NULL; - if (addr == NULL) + if (!addr || !strlen(addr)) return -EINVAL; if (strlen(addr) >= UNIX_PATH_MAX) { diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 119103bfa82e..4bbb8683d451 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -400,6 +400,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) struct p9_trans_rdma *rdma = client->trans; struct ib_recv_wr wr; struct ib_sge sge; + int ret; c->busa = ib_dma_map_single(rdma->cm_id->device, c->rc.sdata, client->msize, @@ -417,7 +418,12 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c) wr.wr_cqe = &c->cqe; wr.sg_list = &sge; wr.num_sge = 1; - return ib_post_recv(rdma->qp, &wr, NULL); + + ret = ib_post_recv(rdma->qp, &wr, NULL); + if (ret) + ib_dma_unmap_single(rdma->cm_id->device, c->busa, + client->msize, DMA_FROM_DEVICE); + return ret; error: p9_debug(P9_DEBUG_ERROR, "EIO\n"); @@ -514,7 +520,7 @@ dont_need_post_recv: if (down_interruptible(&rdma->sq_sem)) { err = -EINTR; - goto send_error; + goto dma_unmap; } /* Mark request as `sent' *before* we actually send it, @@ -524,11 +530,14 @@ dont_need_post_recv: req->status = REQ_STATUS_SENT; err = ib_post_send(rdma->qp, &wr, NULL); if (err) - goto send_error; + goto dma_unmap; /* Success */ return 0; +dma_unmap: + ib_dma_unmap_single(rdma->cm_id->device, c->busa, + c->req->tc.size, DMA_TO_DEVICE); /* Handle errors that happened during or while preparing the send: */ send_error: req->status = REQ_STATUS_ERROR; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 849336211c79..6b3357a77d99 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -409,7 +409,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req, struct page **in_pages = NULL, **out_pages = NULL; struct virtio_chan *chan = client->trans; struct scatterlist *sgs[4]; - size_t offs; + size_t offs = 0; int need_drop = 0; int kicked = 0; @@ -620,7 +620,7 @@ static int p9_virtio_probe(struct virtio_device *vdev) chan->vc_wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL); if (!chan->vc_wq) { err = -ENOMEM; - goto out_free_tag; + goto out_remove_file; } init_waitqueue_head(chan->vc_wq); chan->ring_bufs_avail = 1; @@ -638,6 +638,8 @@ static int p9_virtio_probe(struct virtio_device *vdev) return 0; +out_remove_file: + sysfs_remove_file(&vdev->dev.kobj, &dev_attr_mount_tag.attr); out_free_tag: kfree(tag); out_free_vq: diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 9daab0dd833b..c87146a49636 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -138,7 +138,7 @@ static bool p9_xen_write_todo(struct xen_9pfs_dataring *ring, RING_IDX size) static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req) { - struct xen_9pfs_front_priv *priv = NULL; + struct xen_9pfs_front_priv *priv; RING_IDX cons, prod, masked_cons, masked_prod; unsigned long flags; u32 size = p9_req->tc.size; @@ -151,7 +151,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req) break; } read_unlock(&xen_9pfs_lock); - if (!priv || priv->client != client) + if (list_entry_is_head(priv, &xen_9pfs_devs, list)) return -EINVAL; num = p9_req->tc.tag % priv->num_rings; @@ -230,6 +230,14 @@ static void p9_xen_response(struct work_struct *work) continue; } + if (h.size > req->rc.capacity) { + dev_warn(&priv->dev->dev, + "requested packet size too big: %d for tag %d with capacity %zd\n", + h.size, h.tag, req->rc.capacity); + req->status = REQ_STATUS_ERROR; + goto recv_error; + } + memcpy(&req->rc, &h, sizeof(h)); req->rc.offset = 0; @@ -239,6 +247,7 @@ static void p9_xen_response(struct work_struct *work) masked_prod, &masked_cons, XEN_9PFS_RING_SIZE); +recv_error: virt_mb(); cons += h.size; ring->intf->in_cons = cons; @@ -290,6 +299,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) @@ -301,9 +314,9 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) ref = priv->rings[i].intf->ref[j]; gnttab_end_foreign_access(ref, 0, 0); } - free_pages((unsigned long)priv->rings[i].data.in, - XEN_9PFS_RING_ORDER - - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + free_pages_exact(priv->rings[i].data.in, + 1UL << (XEN_9PFS_RING_ORDER + + XEN_PAGE_SHIFT)); } gnttab_end_foreign_access(priv->rings[i].ref, 0, 0); free_page((unsigned long)priv->rings[i].intf); @@ -341,8 +354,8 @@ static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, if (ret < 0) goto out; ring->ref = ret; - bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - XEN_9PFS_RING_ORDER - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + bytes = alloc_pages_exact(1UL << (XEN_9PFS_RING_ORDER + XEN_PAGE_SHIFT), + GFP_KERNEL | __GFP_ZERO); if (!bytes) { ret = -ENOMEM; goto out; @@ -373,28 +386,31 @@ out: if (bytes) { for (i--; i >= 0; i--) gnttab_end_foreign_access(ring->intf->ref[i], 0, 0); - free_pages((unsigned long)bytes, - XEN_9PFS_RING_ORDER - - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + free_pages_exact(bytes, 1UL << (XEN_9PFS_RING_ORDER + XEN_PAGE_SHIFT)); } gnttab_end_foreign_access(ring->ref, 0, 0); free_page((unsigned long)ring->intf); return ret; } -static int xen_9pfs_front_probe(struct xenbus_device *dev, - const struct xenbus_device_id *id) +static int xen_9pfs_front_init(struct xenbus_device *dev) { int ret, i; struct xenbus_transaction xbt; - struct xen_9pfs_front_priv *priv = NULL; - char *versions; + struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev); + char *versions, *v; unsigned int max_rings, max_ring_order, len = 0; versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len); if (IS_ERR(versions)) return PTR_ERR(versions); - if (strcmp(versions, "1")) { + for (v = versions; *v; v++) { + if (simple_strtoul(v, &v, 10) == 1) { + v = NULL; + break; + } + } + if (v) { kfree(versions); return -EINVAL; } @@ -407,11 +423,6 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, if (max_ring_order < XEN_9PFS_RING_ORDER) return -EINVAL; - priv = kzalloc(sizeof(*priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - - priv->dev = dev; priv->num_rings = XEN_9PFS_NUM_RINGS; priv->rings = kcalloc(priv->num_rings, sizeof(*priv->rings), GFP_KERNEL); @@ -469,23 +480,35 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, goto error; } - write_lock(&xen_9pfs_lock); - list_add_tail(&priv->list, &xen_9pfs_devs); - write_unlock(&xen_9pfs_lock); - dev_set_drvdata(&dev->dev, priv); - xenbus_switch_state(dev, XenbusStateInitialised); - return 0; error_xenbus: xenbus_transaction_end(xbt, 1); xenbus_dev_fatal(dev, ret, "writing xenstore"); error: - dev_set_drvdata(&dev->dev, NULL); xen_9pfs_front_free(priv); return ret; } +static int xen_9pfs_front_probe(struct xenbus_device *dev, + const struct xenbus_device_id *id) +{ + struct xen_9pfs_front_priv *priv = NULL; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + dev_set_drvdata(&dev->dev, priv); + + write_lock(&xen_9pfs_lock); + list_add_tail(&priv->list, &xen_9pfs_devs); + write_unlock(&xen_9pfs_lock); + + return 0; +} + static int xen_9pfs_front_resume(struct xenbus_device *dev) { dev_warn(&dev->dev, "suspend/resume unsupported\n"); @@ -504,6 +527,8 @@ static void xen_9pfs_front_changed(struct xenbus_device *dev, break; case XenbusStateInitWait: + if (!xen_9pfs_front_init(dev)) + xenbus_switch_state(dev, XenbusStateInitialised); break; case XenbusStateConnected: diff --git a/net/Kconfig b/net/Kconfig index 228dfa382eec..4bef62b4c806 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -197,7 +197,6 @@ config BRIDGE_NETFILTER source "net/netfilter/Kconfig" source "net/ipv4/netfilter/Kconfig" source "net/ipv6/netfilter/Kconfig" -source "net/decnet/netfilter/Kconfig" source "net/bridge/netfilter/Kconfig" endif @@ -214,7 +213,6 @@ source "net/802/Kconfig" source "net/bridge/Kconfig" source "net/dsa/Kconfig" source "net/8021q/Kconfig" -source "net/decnet/Kconfig" source "net/llc/Kconfig" source "drivers/net/appletalk/Kconfig" source "net/x25/Kconfig" diff --git a/net/Makefile b/net/Makefile index bdaf53925acd..177b6fbac29c 100644 --- a/net/Makefile +++ b/net/Makefile @@ -18,7 +18,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX) += unix/ +obj-$(CONFIG_UNIX_SCM) += unix/ obj-$(CONFIG_NET) += ipv6/ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ @@ -39,7 +39,6 @@ obj-$(CONFIG_AF_KCM) += kcm/ obj-$(CONFIG_STREAM_PARSER) += strparser/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_L2TP) += l2tp/ -obj-$(CONFIG_DECNET) += decnet/ obj-$(CONFIG_PHONET) += phonet/ ifneq ($(CONFIG_VLAN_8021Q),) obj-y += 8021q/ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 2880ac470379..c4f1bfe6e040 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1573,8 +1573,8 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sk_buff *skb; struct net_device *dev; struct ddpehdr *ddp; - int size; - struct atalk_route *rt; + int size, hard_header_len; + struct atalk_route *rt, *rt_lo = NULL; int err; if (flags & ~(MSG_DONTWAIT|MSG_CMSG_COMPAT)) @@ -1637,7 +1637,22 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) SOCK_DEBUG(sk, "SK %p: Size needed %d, device %s\n", sk, size, dev->name); - size += dev->hard_header_len; + hard_header_len = dev->hard_header_len; + /* Leave room for loopback hardware header if necessary */ + if (usat->sat_addr.s_node == ATADDR_BCAST && + (dev->flags & IFF_LOOPBACK || !(rt->flags & RTF_GATEWAY))) { + struct atalk_addr at_lo; + + at_lo.s_node = 0; + at_lo.s_net = 0; + + rt_lo = atrtr_find(&at_lo); + + if (rt_lo && rt_lo->dev->hard_header_len > hard_header_len) + hard_header_len = rt_lo->dev->hard_header_len; + } + + size += hard_header_len; release_sock(sk); skb = sock_alloc_send_skb(sk, size, (flags & MSG_DONTWAIT), &err); lock_sock(sk); @@ -1645,7 +1660,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; skb_reserve(skb, ddp_dl->header_length); - skb_reserve(skb, dev->hard_header_len); + skb_reserve(skb, hard_header_len); skb->dev = dev; SOCK_DEBUG(sk, "SK %p: Begin build.\n", sk); @@ -1696,18 +1711,12 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* loop back */ skb_orphan(skb); if (ddp->deh_dnode == ATADDR_BCAST) { - struct atalk_addr at_lo; - - at_lo.s_node = 0; - at_lo.s_net = 0; - - rt = atrtr_find(&at_lo); - if (!rt) { + if (!rt_lo) { kfree_skb(skb); err = -ENETUNREACH; goto out; } - dev = rt->dev; + dev = rt_lo->dev; skb->dev = dev; } ddp_dl->request(ddp_dl, skb, dev->dev_addr); @@ -1799,15 +1808,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } case TIOCINQ: { - /* - * These two are safe on a single CPU system as only - * user tasks fiddle here - */ - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + struct sk_buff *skb; long amount = 0; + spin_lock_irq(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len - sizeof(struct ddpehdr); + spin_unlock_irq(&sk->sk_receive_queue.lock); rc = put_user(amount, (int __user *)argp); break; } diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 2ff0e5e470e3..38f7f164e484 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -71,14 +71,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, case SIOCINQ: { struct sk_buff *skb; + int amount; if (sock->state != SS_CONNECTED) { error = -EINVAL; goto done; } + spin_lock_irq(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); - error = put_user(skb ? skb->len : 0, - (int __user *)argp) ? -EFAULT : 0; + amount = skb ? skb->len : 0; + spin_unlock_irq(&sk->sk_receive_queue.lock); + error = put_user(amount, (int __user *)argp) ? -EFAULT : 0; goto done; } case SIOCGSTAMP: /* borrowed from IP */ diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 46d6cd9a36ae..c4e9538ac144 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -222,11 +222,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, if (!page) return -ENOMEM; - for (p = page, len = 0; len < nbytes; p++, len++) { + for (p = page, len = 0; len < nbytes; p++) { if (get_user(*p, buff++)) { free_page((unsigned long)page); return -EFAULT; } + len += 1; if (*p == '\0' || *p == '\n') break; } diff --git a/net/atm/resources.c b/net/atm/resources.c index bada395ecdb1..9389080224f8 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -447,6 +447,7 @@ done: return error; } +#ifdef CONFIG_PROC_FS void *atm_dev_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&atm_dev_mutex); @@ -462,3 +463,4 @@ void *atm_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &atm_devs, pos); } +#endif diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index a45db78eaf00..7861f2747f84 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -80,6 +80,7 @@ static void ax25_kill_by_device(struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *s; + struct sock *sk; if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; @@ -88,11 +89,26 @@ static void ax25_kill_by_device(struct net_device *dev) again: ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { - s->ax25_dev = NULL; + sk = s->sk; + if (!sk) { + spin_unlock_bh(&ax25_list_lock); + ax25_disconnect(s, ENETUNREACH); + s->ax25_dev = NULL; + spin_lock_bh(&ax25_list_lock); + goto again; + } + sock_hold(sk); spin_unlock_bh(&ax25_list_lock); + lock_sock(sk); ax25_disconnect(s, ENETUNREACH); + s->ax25_dev = NULL; + if (sk->sk_socket) { + dev_put(ax25_dev->dev); + ax25_dev_put(ax25_dev); + } + release_sock(sk); spin_lock_bh(&ax25_list_lock); - + sock_put(sk); /* The entry could have been deleted from the * list meanwhile and thus the next pointer is * no longer valid. Play it safe and restart @@ -356,21 +372,25 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl))) return -EFAULT; - if ((ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr)) == NULL) - return -ENODEV; - if (ax25_ctl.digi_count > AX25_MAX_DIGIS) return -EINVAL; if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL) return -EINVAL; + ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr); + if (!ax25_dev) + return -ENODEV; + digi.ndigi = ax25_ctl.digi_count; for (k = 0; k < digi.ndigi; k++) digi.calls[k] = ax25_ctl.digi_addr[k]; - if ((ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev)) == NULL) + ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev); + if (!ax25) { + ax25_dev_put(ax25_dev); return -ENOTCONN; + } switch (ax25_ctl.cmd) { case AX25_KILL: @@ -437,6 +457,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) } out_put: + ax25_dev_put(ax25_dev); ax25_cb_put(ax25); return ret; @@ -962,14 +983,16 @@ static int ax25_release(struct socket *sock) { struct sock *sk = sock->sk; ax25_cb *ax25; + ax25_dev *ax25_dev; if (sk == NULL) return 0; sock_hold(sk); - sock_orphan(sk); lock_sock(sk); + sock_orphan(sk); ax25 = sk_to_ax25(sk); + ax25_dev = ax25->ax25_dev; if (sk->sk_type == SOCK_SEQPACKET) { switch (ax25->state) { @@ -1031,6 +1054,15 @@ static int ax25_release(struct socket *sock) sk->sk_state_change(sk); ax25_destroy_socket(ax25); } + if (ax25_dev) { + del_timer_sync(&ax25->timer); + del_timer_sync(&ax25->t1timer); + del_timer_sync(&ax25->t2timer); + del_timer_sync(&ax25->t3timer); + del_timer_sync(&ax25->idletimer); + dev_put(ax25_dev->dev); + ax25_dev_put(ax25_dev); + } sock->sk = NULL; release_sock(sk); @@ -1107,8 +1139,10 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } } - if (ax25_dev != NULL) + if (ax25_dev) { ax25_fillin_cb(ax25, ax25_dev); + dev_hold(ax25_dev->dev); + } done: ax25_cb_add(ax25); diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index d92195cd7834..55a611f7239b 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -40,6 +40,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr) for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) if (ax25cmp(addr, (ax25_address *)ax25_dev->dev->dev_addr) == 0) { res = ax25_dev; + ax25_dev_hold(ax25_dev); } spin_unlock_bh(&ax25_dev_lock); @@ -59,6 +60,7 @@ void ax25_dev_device_up(struct net_device *dev) return; } + refcount_set(&ax25_dev->refcount, 1); dev->ax25_ptr = ax25_dev; ax25_dev->dev = dev; dev_hold(dev); @@ -87,6 +89,7 @@ void ax25_dev_device_up(struct net_device *dev) ax25_dev->next = ax25_dev_list; ax25_dev_list = ax25_dev; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_hold(ax25_dev); ax25_register_dev_sysctl(ax25_dev); } @@ -116,9 +119,10 @@ void ax25_dev_device_down(struct net_device *dev) if ((s = ax25_dev_list) == ax25_dev) { ax25_dev_list = s->next; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; dev_put(dev); - kfree(ax25_dev); + ax25_dev_put(ax25_dev); return; } @@ -126,9 +130,10 @@ void ax25_dev_device_down(struct net_device *dev) if (s->next == ax25_dev) { s->next = ax25_dev->next; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; dev_put(dev); - kfree(ax25_dev); + ax25_dev_put(ax25_dev); return; } @@ -136,6 +141,7 @@ void ax25_dev_device_down(struct net_device *dev) } spin_unlock_bh(&ax25_dev_lock); dev->ax25_ptr = NULL; + ax25_dev_put(ax25_dev); } int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd) @@ -147,20 +153,32 @@ int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd) switch (cmd) { case SIOCAX25ADDFWD: - if ((fwd_dev = ax25_addr_ax25dev(&fwd->port_to)) == NULL) + fwd_dev = ax25_addr_ax25dev(&fwd->port_to); + if (!fwd_dev) { + ax25_dev_put(ax25_dev); return -EINVAL; - if (ax25_dev->forward != NULL) + } + if (ax25_dev->forward) { + ax25_dev_put(fwd_dev); + ax25_dev_put(ax25_dev); return -EINVAL; + } ax25_dev->forward = fwd_dev->dev; + ax25_dev_put(fwd_dev); + ax25_dev_put(ax25_dev); break; case SIOCAX25DELFWD: - if (ax25_dev->forward == NULL) + if (!ax25_dev->forward) { + ax25_dev_put(ax25_dev); return -EINVAL; + } ax25_dev->forward = NULL; + ax25_dev_put(ax25_dev); break; default: + ax25_dev_put(ax25_dev); return -EINVAL; } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index 66d54fc11831..8f81de88f006 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -78,11 +78,13 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) ax25_dev *ax25_dev; int i; - if ((ax25_dev = ax25_addr_ax25dev(&route->port_addr)) == NULL) - return -EINVAL; if (route->digi_count > AX25_MAX_DIGIS) return -EINVAL; + ax25_dev = ax25_addr_ax25dev(&route->port_addr); + if (!ax25_dev) + return -EINVAL; + write_lock_bh(&ax25_route_lock); ax25_rt = ax25_route_list; @@ -94,6 +96,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if (route->digi_count != 0) { if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return -ENOMEM; } ax25_rt->digipeat->lastrepeat = -1; @@ -104,6 +107,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) } } write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } ax25_rt = ax25_rt->next; @@ -111,6 +115,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if ((ax25_rt = kmalloc(sizeof(ax25_route), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return -ENOMEM; } @@ -123,6 +128,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); kfree(ax25_rt); + ax25_dev_put(ax25_dev); return -ENOMEM; } ax25_rt->digipeat->lastrepeat = -1; @@ -135,6 +141,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) ax25_rt->next = ax25_route_list; ax25_route_list = ax25_rt; write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } @@ -176,6 +183,7 @@ static int ax25_rt_del(struct ax25_routes_struct *route) } } write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } @@ -218,6 +226,7 @@ static int ax25_rt_opt(struct ax25_route_opt_struct *rt_option) out: write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return err; } diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index 038b109b2be7..c129865cad9f 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -264,12 +264,20 @@ void ax25_disconnect(ax25_cb *ax25, int reason) { ax25_clear_queues(ax25); - if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY)) - ax25_stop_heartbeat(ax25); - ax25_stop_t1timer(ax25); - ax25_stop_t2timer(ax25); - ax25_stop_t3timer(ax25); - ax25_stop_idletimer(ax25); + if (reason == ENETUNREACH) { + del_timer_sync(&ax25->timer); + del_timer_sync(&ax25->t1timer); + del_timer_sync(&ax25->t2timer); + del_timer_sync(&ax25->t3timer); + del_timer_sync(&ax25->idletimer); + } else { + if (!ax25->sk || !sock_flag(ax25->sk, SOCK_DESTROY)) + ax25_stop_heartbeat(ax25); + ax25_stop_t1timer(ax25); + ax25_stop_t2timer(ax25); + ax25_stop_t3timer(ax25); + ax25_stop_idletimer(ax25); + } ax25->state = AX25_STATE_0; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 0b052ff51bde..cede6826e5b3 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -594,8 +594,10 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) if (WARN_ON(!forw_packet->if_outgoing)) return; - if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) + if (forw_packet->if_outgoing->soft_iface != soft_iface) { + pr_warn("%s: soft interface switch for queued OGM\n", __func__); return; + } if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) return; diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index af3da6cdfc79..17100d9ceaf0 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -513,7 +513,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_elp_packet *elp_packet; struct batadv_hard_iface *primary_if; - struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header(skb); + struct ethhdr *ethhdr; bool res; int ret = NET_RX_DROP; @@ -521,6 +521,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb, if (!res) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 04a620fd1301..5d4232d8d651 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -119,8 +119,10 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - if (hard_iface->if_status != BATADV_IF_ACTIVE) + if (hard_iface->if_status != BATADV_IF_ACTIVE) { + kfree_skb(skb); return; + } batadv_inc_counter(bat_priv, BATADV_CNT_MGMT_TX); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES, @@ -832,7 +834,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, { struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct batadv_ogm2_packet *ogm_packet; - struct ethhdr *ethhdr = eth_hdr(skb); + struct ethhdr *ethhdr; int ogm_offset; u8 *packet_pos; int ret = NET_RX_DROP; @@ -846,6 +848,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, if (!batadv_check_management_packet(skb, if_incoming, BATADV_OGM2_HLEN)) goto free_skb; + ethhdr = eth_hdr(skb); if (batadv_is_my_mac(bat_priv, ethhdr->h_source)) goto free_skb; diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 1401031f4bb4..b9e61fc3928a 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1574,10 +1574,14 @@ int batadv_bla_init(struct batadv_priv *bat_priv) return 0; bat_priv->bla.claim_hash = batadv_hash_new(128); - bat_priv->bla.backbone_hash = batadv_hash_new(32); + if (!bat_priv->bla.claim_hash) + return -ENOMEM; - if (!bat_priv->bla.claim_hash || !bat_priv->bla.backbone_hash) + bat_priv->bla.backbone_hash = batadv_hash_new(32); + if (!bat_priv->bla.backbone_hash) { + batadv_hash_destroy(bat_priv->bla.claim_hash); return -ENOMEM; + } batadv_hash_set_lock_class(bat_priv->bla.claim_hash, &batadv_claim_hash_lock_class_key); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index f2dc7499d266..af380dc877e3 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -68,7 +68,6 @@ static void batadv_dat_purge(struct work_struct *work); */ static void batadv_dat_start_timer(struct batadv_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); queue_delayed_work(batadv_event_workqueue, &bat_priv->dat.work, msecs_to_jiffies(10000)); } @@ -783,6 +782,7 @@ int batadv_dat_init(struct batadv_priv *bat_priv) if (!bat_priv->dat.hash) return -ENOMEM; + INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); batadv_dat_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_dat_tvlv_ogm_handler_v1, diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 5b71a289d04f..a62eedf889eb 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -403,6 +403,7 @@ out: /** * batadv_frag_create() - create a fragment from skb + * @net_dev: outgoing device for fragment * @skb: skb to create fragment from * @frag_head: header to use in new fragment * @fragment_size: size of new fragment @@ -413,22 +414,25 @@ out: * * Return: the new fragment, NULL on error. */ -static struct sk_buff *batadv_frag_create(struct sk_buff *skb, +static struct sk_buff *batadv_frag_create(struct net_device *net_dev, + struct sk_buff *skb, struct batadv_frag_packet *frag_head, unsigned int fragment_size) { + unsigned int ll_reserved = LL_RESERVED_SPACE(net_dev); + unsigned int tailroom = net_dev->needed_tailroom; struct sk_buff *skb_fragment; unsigned int header_size = sizeof(*frag_head); unsigned int mtu = fragment_size + header_size; - skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN); + skb_fragment = dev_alloc_skb(ll_reserved + mtu + tailroom); if (!skb_fragment) goto err; skb_fragment->priority = skb->priority; /* Eat the last mtu-bytes of the skb */ - skb_reserve(skb_fragment, header_size + ETH_HLEN); + skb_reserve(skb_fragment, ll_reserved + header_size); skb_split(skb, skb_fragment, skb->len - fragment_size); /* Add the header */ @@ -451,11 +455,12 @@ int batadv_frag_send_packet(struct sk_buff *skb, struct batadv_orig_node *orig_node, struct batadv_neigh_node *neigh_node) { + struct net_device *net_dev = neigh_node->if_incoming->net_dev; struct batadv_priv *bat_priv; struct batadv_hard_iface *primary_if = NULL; struct batadv_frag_packet frag_header; struct sk_buff *skb_fragment; - unsigned int mtu = neigh_node->if_incoming->net_dev->mtu; + unsigned int mtu = net_dev->mtu; unsigned int header_size = sizeof(frag_header); unsigned int max_fragment_size, num_fragments; int ret; @@ -485,6 +490,17 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto free_skb; } + /* GRO might have added fragments to the fragment list instead of + * frags[]. But this is not handled by skb_split and must be + * linearized to avoid incorrect length information after all + * batman-adv fragments were created and submitted to the + * hard-interface + */ + if (skb_has_frag_list(skb) && __skb_linearize(skb)) { + ret = -ENOMEM; + goto free_skb; + } + /* Create one header to be copied to all fragments */ frag_header.packet_type = BATADV_UNICAST_FRAG; frag_header.version = BATADV_COMPAT_VERSION; @@ -515,7 +531,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, goto put_primary_if; } - skb_fragment = batadv_frag_create(skb, &frag_header, + skb_fragment = batadv_frag_create(net_dev, skb, &frag_header, max_fragment_size); if (!skb_fragment) { ret = -ENOMEM; @@ -534,13 +550,14 @@ int batadv_frag_send_packet(struct sk_buff *skb, frag_header.no++; } - /* Make room for the fragment header. */ - if (batadv_skb_head_push(skb, header_size) < 0 || - pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) { - ret = -ENOMEM; + /* make sure that there is at least enough head for the fragmentation + * and ethernet headers + */ + ret = skb_cow_head(skb, ETH_HLEN + header_size); + if (ret < 0) goto put_primary_if; - } + skb_push(skb, header_size); memcpy(skb->data, &frag_header, header_size); /* Send the last fragment */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index c4e0435c952d..0d5519fcb438 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -162,22 +162,25 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) struct net *net = dev_net(net_dev); struct net_device *parent_dev; struct net *parent_net; + int iflink; bool ret; /* check if this is a batman-adv mesh interface */ if (batadv_softif_is_valid(net_dev)) return true; - /* no more parents..stop recursion */ - if (dev_get_iflink(net_dev) == 0 || - dev_get_iflink(net_dev) == net_dev->ifindex) + iflink = dev_get_iflink(net_dev); + if (iflink == 0) return false; parent_net = batadv_getlink_net(net_dev, net); + /* iflink to itself, most likely physical device */ + if (net == parent_net && iflink == net_dev->ifindex) + return false; + /* recurse over the parent device */ - parent_dev = __dev_get_by_index((struct net *)parent_net, - dev_get_iflink(net_dev)); + parent_dev = __dev_get_by_index((struct net *)parent_net, iflink); /* if we got a NULL parent_dev there is something broken.. */ if (!parent_dev) { pr_err("Cannot find parent device\n"); @@ -227,14 +230,15 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) struct net_device *real_netdev = NULL; struct net *real_net; struct net *net; - int ifindex; + int iflink; ASSERT_RTNL(); if (!netdev) return NULL; - if (netdev->ifindex == dev_get_iflink(netdev)) { + iflink = dev_get_iflink(netdev); + if (iflink == 0) { dev_hold(netdev); return netdev; } @@ -244,9 +248,16 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) goto out; net = dev_net(hard_iface->soft_iface); - ifindex = dev_get_iflink(netdev); real_net = batadv_getlink_net(netdev, net); - real_netdev = dev_get_by_index(real_net, ifindex); + + /* iflink to itself, most likely physical device */ + if (net == real_net && netdev->ifindex == iflink) { + real_netdev = netdev; + dev_hold(real_netdev); + goto out; + } + + real_netdev = dev_get_by_index(real_net, iflink); out: if (hard_iface) @@ -565,6 +576,9 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface) needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN); needed_headroom += batadv_max_header_len(); + /* fragmentation headers don't strip the unicast/... header */ + needed_headroom += sizeof(struct batadv_frag_packet); + soft_iface->needed_headroom = needed_headroom; soft_iface->needed_tailroom = lower_tailroom; } @@ -629,7 +643,19 @@ out: */ void batadv_update_min_mtu(struct net_device *soft_iface) { - soft_iface->mtu = batadv_hardif_min_mtu(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + int limit_mtu; + int mtu; + + mtu = batadv_hardif_min_mtu(soft_iface); + + if (bat_priv->mtu_set_by_user) + limit_mtu = bat_priv->mtu_set_by_user; + else + limit_mtu = ETH_DATA_LEN; + + mtu = min(mtu, limit_mtu); + dev_set_mtu(soft_iface, mtu); /* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU. diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 853773e45f79..837f67c9fad3 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -205,6 +205,7 @@ static const struct file_operations batadv_log_fops = { .read = batadv_log_read, .poll = batadv_log_poll, .llseek = no_llseek, + .owner = THIS_MODULE, }; /** diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 79b8a2d8793e..bba64b9b3668 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -187,29 +187,41 @@ int batadv_mesh_init(struct net_device *soft_iface) INIT_HLIST_HEAD(&bat_priv->softif_vlan_list); INIT_HLIST_HEAD(&bat_priv->tp_list); - ret = batadv_v_mesh_init(bat_priv); - if (ret < 0) - goto err; - ret = batadv_originator_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_orig; + } ret = batadv_tt_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_tt; + } + + ret = batadv_v_mesh_init(bat_priv); + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_v; + } ret = batadv_bla_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_bla; + } ret = batadv_dat_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_dat; + } ret = batadv_nc_mesh_init(bat_priv); - if (ret < 0) - goto err; + if (ret < 0) { + atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); + goto err_nc; + } batadv_gw_init(bat_priv); batadv_mcast_init(bat_priv); @@ -219,8 +231,20 @@ int batadv_mesh_init(struct net_device *soft_iface) return 0; -err: - batadv_mesh_free(soft_iface); +err_nc: + batadv_dat_free(bat_priv); +err_dat: + batadv_bla_free(bat_priv); +err_bla: + batadv_v_mesh_free(bat_priv); +err_v: + batadv_tt_free(bat_priv); +err_tt: + batadv_originator_free(bat_priv); +err_orig: + batadv_purge_outstanding_packets(bat_priv, NULL); + atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE); + return ret; } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index b90fe25d6b0b..9b3311dae2e4 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -62,10 +62,12 @@ #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> +#include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "netlink.h" +#include "send.h" #include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" @@ -1025,6 +1027,35 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, } /** + * batadv_mcast_forw_send_orig() - send a multicast packet to an originator + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to send + * @vid: the vlan identifier + * @orig_node: the originator to send the packet to + * + * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. + */ +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + /* Avoid sending multicast-in-unicast packets to other BLA + * gateways - they already got the frame from the LAN side + * we share with them. + * TODO: Refactor to take BLA into account earlier, to avoid + * reducing the mcast_fanout count. + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) { + dev_kfree_skb(skb); + return NET_XMIT_SUCCESS; + } + + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, + orig_node, vid); +} + +/** * batadv_mcast_want_unsnoop_update() - update unsnoop counter and list * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node which multicast state might have changed of diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 3b04ab13f0eb..6f9f3813fc59 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -51,6 +51,11 @@ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node **mcast_single_orig); +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node); + void batadv_mcast_init(struct batadv_priv *bat_priv); int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset); @@ -79,6 +84,16 @@ static inline int batadv_mcast_init(struct batadv_priv *bat_priv) } static inline int +batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} + +static inline int batadv_mcast_mesh_info_put(struct sk_buff *msg, struct batadv_priv *bat_priv) { return 0; diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 7f1be5a28757..d6749fc22236 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -167,8 +167,10 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv) &batadv_nc_coding_hash_lock_class_key); bat_priv->nc.decoding_hash = batadv_hash_new(128); - if (!bat_priv->nc.decoding_hash) + if (!bat_priv->nc.decoding_hash) { + batadv_hash_destroy(bat_priv->nc.coding_hash); goto err; + } batadv_hash_set_lock_class(bat_priv->nc.decoding_hash, &batadv_nc_decoding_hash_lock_class_key); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6ff78080ec7f..7447dbd305fc 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -167,11 +167,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu) { + struct batadv_priv *bat_priv = netdev_priv(dev); + /* check ranges */ if (new_mtu < 68 || new_mtu > batadv_hardif_min_mtu(dev)) return -EINVAL; dev->mtu = new_mtu; + bat_priv->mtu_set_by_user = new_mtu; return 0; } @@ -367,9 +370,8 @@ send: goto dropped; ret = batadv_send_skb_via_gw(bat_priv, skb, vid); } else if (mcast_single_orig) { - ret = batadv_send_skb_unicast(bat_priv, skb, - BATADV_UNICAST, 0, - mcast_single_orig, vid); + ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid, + mcast_single_orig); } else { if (batadv_dat_snoop_outgoing_arp_request(bat_priv, skb)) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 9fa5389ea244..c64d58c1b724 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -793,7 +793,6 @@ check_roaming: if (roamed_back) { batadv_tt_global_free(bat_priv, tt_global, "Roaming canceled"); - tt_global = NULL; } else { /* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose @@ -904,6 +903,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, hlist_for_each_entry_rcu(vlan, &orig_node->vlan_list, list) { tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); + tt_vlan->reserved = 0; tt_vlan++; } @@ -987,6 +987,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); + tt_vlan->reserved = 0; tt_vlan++; } @@ -4411,8 +4412,10 @@ int batadv_tt_init(struct batadv_priv *bat_priv) return ret; ret = batadv_tt_global_init(bat_priv); - if (ret < 0) + if (ret < 0) { + batadv_tt_local_table_free(bat_priv); return ret; + } batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1, batadv_tt_tvlv_unicast_handler_v1, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 37598ae1d3f7..34c18f72a41b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1515,6 +1515,12 @@ struct batadv_priv { struct net_device *soft_iface; /** + * @mtu_set_by_user: MTU was set once by user + * protected by rtnl_lock + */ + int mtu_set_by_user; + + /** * @bat_counters: mesh internal traffic statistic counters (see * batadv_counters) */ diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 9a75f9b00b51..4530ffb2481a 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -1014,6 +1014,7 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_le(hdev, addr, *addr_type); hci_dev_unlock(hdev); + hci_dev_put(hdev); if (!hcon) return -ENOENT; diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 51c2cf2d8923..e09ea78356c3 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -233,6 +233,9 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_info_req req; found = true; + + memset(&req, 0, sizeof(req)); + req.id = cl->id; a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr), sizeof(req), &req); @@ -312,6 +315,8 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, if (!hdev || hdev->dev_type != HCI_AMP) { struct a2mp_info_rsp rsp; + memset(&rsp, 0, sizeof(rsp)); + rsp.id = req->id; rsp.status = A2MP_STATUS_INVALID_CTRL_ID; @@ -355,6 +360,8 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, if (!ctrl) return -ENOMEM; + memset(&req, 0, sizeof(req)); + req.id = rsp->id; a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req), &req); @@ -381,6 +388,8 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, hdev = hci_dev_get(req->id); if (!hdev || hdev->amp_type == AMP_TYPE_BREDR || tmp) { struct a2mp_amp_assoc_rsp rsp; + + memset(&rsp, 0, sizeof(rsp)); rsp.id = req->id; if (tmp) { @@ -471,7 +480,6 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; struct hci_dev *hdev; struct hci_conn *hcon; @@ -482,6 +490,8 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id); + memset(&rsp, 0, sizeof(rsp)); + rsp.local_id = req->remote_id; rsp.remote_id = req->local_id; @@ -509,6 +519,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, assoc = kmemdup(req->amp_assoc, assoc_len, GFP_KERNEL); if (!assoc) { amp_ctrl_put(ctrl); + hci_dev_put(hdev); return -ENOMEM; } @@ -560,6 +571,8 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id); + memset(&rsp, 0, sizeof(rsp)); + rsp.local_id = req->remote_id; rsp.remote_id = req->local_id; rsp.status = A2MP_STATUS_SUCCESS; @@ -682,6 +695,8 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) if (err) { struct a2mp_cmd_rej rej; + memset(&rej, 0, sizeof(rej)); + rej.reason = cpu_to_le16(0); hdr = (void *) skb->data; @@ -905,6 +920,8 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev) BT_DBG("%s mgr %p", hdev->name, mgr); + memset(&rsp, 0, sizeof(rsp)); + rsp.id = hdev->id; rsp.status = A2MP_STATUS_INVALID_CTRL_ID; @@ -1002,6 +1019,8 @@ void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status) if (!mgr) return; + memset(&rsp, 0, sizeof(rsp)); + hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT); if (!hs_hcon) { rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; @@ -1034,6 +1053,8 @@ void a2mp_discover_amp(struct l2cap_chan *chan) mgr->bredr_chan = chan; + memset(&req, 0, sizeof(req)); + req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); req.ext_feat = 0; a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req); diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index ee60c30f3be2..798f8f485e5a 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -743,7 +743,7 @@ static int __init bt_init(void) err = bt_sysfs_init(); if (err < 0) - return err; + goto cleanup_led; err = sock_register(&bt_sock_family_ops); if (err) @@ -779,6 +779,8 @@ unregister_socket: sock_unregister(PF_BLUETOOTH); cleanup_sysfs: bt_sysfs_cleanup(); +cleanup_led: + bt_leds_cleanup(); return err; } diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index 78bec8df8525..72ef967c5663 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -305,6 +305,9 @@ void amp_read_loc_assoc_final_data(struct hci_dev *hdev, struct hci_request req; int err; + if (!mgr) + return; + cp.phy_handle = hcon->handle; cp.len_so_far = cpu_to_le16(0); cp.max_len = cpu_to_le16(hdev->amp_assoc_size); diff --git a/net/bluetooth/cmtp/cmtp.h b/net/bluetooth/cmtp/cmtp.h index c32638dddbf9..f6b9dc4e408f 100644 --- a/net/bluetooth/cmtp/cmtp.h +++ b/net/bluetooth/cmtp/cmtp.h @@ -26,7 +26,7 @@ #include <linux/types.h> #include <net/bluetooth/bluetooth.h> -#define BTNAMSIZ 18 +#define BTNAMSIZ 21 /* CMTP ioctl defines */ #define CMTPCONNADD _IOW('C', 200, int) diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 7f26a5a19ff6..4764ed73f33b 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -391,6 +391,11 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) if (!(session->flags & BIT(CMTP_LOOPBACK))) { err = cmtp_attach_device(session); if (err < 0) { + /* Caller will call fput in case of failure, and so + * will cmtp_session kthread. + */ + get_file(session->sock->file); + atomic_inc(&session->terminate); wake_up_interruptible(sk_sleep(session->sock->sk)); up_write(&cmtp_session_sem); @@ -494,9 +499,7 @@ static int __init cmtp_init(void) { BT_INFO("CMTP (CAPI Emulation) ver %s", VERSION); - cmtp_init_sockets(); - - return 0; + return cmtp_init_sockets(); } static void __exit cmtp_exit(void) diff --git a/net/bluetooth/ecdh_helper.h b/net/bluetooth/ecdh_helper.h index a6f8d03d4aaf..830723971cf8 100644 --- a/net/bluetooth/ecdh_helper.h +++ b/net/bluetooth/ecdh_helper.h @@ -25,6 +25,6 @@ int compute_ecdh_secret(struct crypto_kpp *tfm, const u8 pair_public_key[64], u8 secret[32]); -int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 *private_key); +int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 private_key[32]); int generate_ecdh_public_key(struct crypto_kpp *tfm, u8 public_key[64]); int generate_ecdh_keys(struct crypto_kpp *tfm, u8 public_key[64]); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index db735d0d931e..b8730c5f1cac 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -125,13 +125,11 @@ static void hci_conn_cleanup(struct hci_conn *conn) if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); - hci_conn_del_sysfs(conn); - debugfs_remove_recursive(conn->debugfs); - hci_dev_put(hdev); + hci_conn_del_sysfs(conn); - hci_conn_put(conn); + hci_dev_put(hdev); } static void le_scan_cleanup(struct work_struct *work) @@ -1204,6 +1202,15 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-EOPNOTSUPP); } + /* Reject outgoing connection to device with same BD ADDR against + * CVE-2020-26555 + */ + if (!bacmp(&hdev->bdaddr, dst)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + dst); + return ERR_PTR(-ECONNREFUSED); + } + acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); @@ -1282,6 +1289,23 @@ int hci_conn_check_link_mode(struct hci_conn *conn) return 0; } + /* AES encryption is required for Level 4: + * + * BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 3, Part C + * page 1319: + * + * 128-bit equivalent strength for link and encryption keys + * required using FIPS approved algorithms (E0 not allowed, + * SAFER+ not allowed, and P-192 not allowed; encryption key + * not shortened) + */ + if (conn->sec_level == BT_SECURITY_FIPS && + !test_bit(HCI_CONN_AES_CCM, &conn->flags)) { + bt_dev_err(conn->hdev, + "Invalid security: Missing AES-CCM usage"); + return 0; + } + if (hci_conn_ssp_enabled(conn) && !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 0; @@ -1314,12 +1338,10 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); - /* If we're already encrypted set the REAUTH_PEND flag, - * otherwise set the ENCRYPT_PEND. + /* Set the ENCRYPT_PEND to trigger encryption after + * authentication. */ - if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) - set_bit(HCI_CONN_REAUTH_PEND, &conn->flags); - else + if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } @@ -1362,34 +1384,41 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, if (!test_bit(HCI_CONN_AUTH, &conn->flags)) goto auth; - /* An authenticated FIPS approved combination key has sufficient - * security for security level 4. */ - if (conn->key_type == HCI_LK_AUTH_COMBINATION_P256 && - sec_level == BT_SECURITY_FIPS) - goto encrypt; - - /* An authenticated combination key has sufficient security for - security level 3. */ - if ((conn->key_type == HCI_LK_AUTH_COMBINATION_P192 || - conn->key_type == HCI_LK_AUTH_COMBINATION_P256) && - sec_level == BT_SECURITY_HIGH) - goto encrypt; - - /* An unauthenticated combination key has sufficient security for - security level 1 and 2. */ - if ((conn->key_type == HCI_LK_UNAUTH_COMBINATION_P192 || - conn->key_type == HCI_LK_UNAUTH_COMBINATION_P256) && - (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW)) - goto encrypt; - - /* A combination key has always sufficient security for the security - levels 1 or 2. High security level requires the combination key - is generated using maximum PIN code length (16). - For pre 2.1 units. */ - if (conn->key_type == HCI_LK_COMBINATION && - (sec_level == BT_SECURITY_MEDIUM || sec_level == BT_SECURITY_LOW || - conn->pin_length == 16)) - goto encrypt; + switch (conn->key_type) { + case HCI_LK_AUTH_COMBINATION_P256: + /* An authenticated FIPS approved combination key has + * sufficient security for security level 4 or lower. + */ + if (sec_level <= BT_SECURITY_FIPS) + goto encrypt; + break; + case HCI_LK_AUTH_COMBINATION_P192: + /* An authenticated combination key has sufficient security for + * security level 3 or lower. + */ + if (sec_level <= BT_SECURITY_HIGH) + goto encrypt; + break; + case HCI_LK_UNAUTH_COMBINATION_P192: + case HCI_LK_UNAUTH_COMBINATION_P256: + /* An unauthenticated combination key has sufficient security + * for security level 2 or lower. + */ + if (sec_level <= BT_SECURITY_MEDIUM) + goto encrypt; + break; + case HCI_LK_COMBINATION: + /* A combination key has always sufficient security for the + * security levels 2 or lower. High security level requires the + * combination key is generated using maximum PIN code length + * (16). For pre 2.1 units. + */ + if (sec_level <= BT_SECURITY_MEDIUM || conn->pin_length == 16) + goto encrypt; + break; + default: + break; + } auth: if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e03faca84919..4d89e38dceec 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1296,6 +1296,12 @@ int hci_inquiry(void __user *arg) goto done; } + /* Restrict maximum inquiry length to 60 seconds */ + if (ir.length > 60) { + err = -EINVAL; + goto done; + } + hci_dev_lock(hdev); if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX || inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) { @@ -1316,8 +1322,10 @@ int hci_inquiry(void __user *arg) * cleared). If it is interrupted by a signal, return -EINTR. */ if (wait_on_bit(&hdev->flags, HCI_INQUIRY, - TASK_INTERRUPTIBLE)) - return -EINTR; + TASK_INTERRUPTIBLE)) { + err = -EINTR; + goto done; + } } /* for unlimited number of responses we will use buffer with @@ -1496,8 +1504,13 @@ static int hci_dev_do_open(struct hci_dev *hdev) } else { /* Init failed, cleanup */ flush_work(&hdev->tx_work); - flush_work(&hdev->cmd_work); + + /* Since hci_rx_work() is possible to awake new cmd_work + * it should be flushed first to avoid unexpected call of + * hci_cmd_work() + */ flush_work(&hdev->rx_work); + flush_work(&hdev->cmd_work); skb_queue_purge(&hdev->cmd_q); skb_queue_purge(&hdev->rx_q); @@ -1506,6 +1519,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) hdev->flush(hdev); if (hdev->sent_cmd) { + cancel_delayed_work_sync(&hdev->cmd_timer); kfree_skb(hdev->sent_cmd); hdev->sent_cmd = NULL; } @@ -1615,6 +1629,14 @@ int hci_dev_do_close(struct hci_dev *hdev) hci_request_cancel_all(hdev); hci_req_sync_lock(hdev); + if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + test_bit(HCI_UP, &hdev->flags)) { + /* Execute vendor specific shutdown routine */ + if (hdev->shutdown) + hdev->shutdown(hdev); + } + if (!test_and_clear_bit(HCI_UP, &hdev->flags)) { cancel_delayed_work_sync(&hdev->cmd_timer); hci_req_sync_unlock(hdev); @@ -2495,10 +2517,10 @@ int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { - struct smp_ltk *k; + struct smp_ltk *k, *tmp; int removed = 0; - list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; @@ -2514,9 +2536,9 @@ int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { - struct smp_irk *k; + struct smp_irk *k, *tmp; - list_for_each_entry_rcu(k, &hdev->identity_resolving_keys, list) { + list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) continue; @@ -3159,10 +3181,10 @@ int hci_register_dev(struct hci_dev *hdev) */ switch (hdev->dev_type) { case HCI_PRIMARY: - id = ida_simple_get(&hci_index_ida, 0, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); break; case HCI_AMP: - id = ida_simple_get(&hci_index_ida, 1, 0, GFP_KERNEL); + id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); break; default: return -EINVAL; @@ -3171,7 +3193,11 @@ int hci_register_dev(struct hci_dev *hdev) if (id < 0) return id; - sprintf(hdev->name, "hci%d", id); + error = dev_set_name(&hdev->dev, "hci%u", id); + if (error) + return error; + + hdev->name = dev_name(&hdev->dev); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); @@ -3193,8 +3219,6 @@ int hci_register_dev(struct hci_dev *hdev) if (!IS_ERR_OR_NULL(bt_debugfs)) hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs); - dev_set_name(&hdev->dev, "%s", hdev->name); - error = device_add(&hdev->dev); if (error < 0) goto err_wqueue; @@ -3242,6 +3266,7 @@ int hci_register_dev(struct hci_dev *hdev) return id; err_wqueue: + debugfs_remove_recursive(hdev->debugfs); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); err: @@ -3254,14 +3279,10 @@ EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { - int id; - BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); hci_dev_set_flag(hdev, HCI_UNREGISTER); - id = hdev->id; - write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); @@ -3290,7 +3311,14 @@ void hci_unregister_dev(struct hci_dev *hdev) } device_del(&hdev->dev); + /* Actual cleanup is deferred until hci_cleanup_dev(). */ + hci_dev_put(hdev); +} +EXPORT_SYMBOL(hci_unregister_dev); +/* Cleanup HCI device */ +void hci_cleanup_dev(struct hci_dev *hdev) +{ debugfs_remove_recursive(hdev->debugfs); kfree_const(hdev->hw_info); kfree_const(hdev->fw_info); @@ -3313,11 +3341,8 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_discovery_filter_clear(hdev); hci_dev_unlock(hdev); - hci_dev_put(hdev); - - ida_simple_remove(&hci_index_ida, id); + ida_simple_remove(&hci_index_ida, hdev->id); } -EXPORT_SYMBOL(hci_unregister_dev); /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) @@ -4309,7 +4334,7 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; else *req_complete = bt_cb(skb)->hci.req_complete; - kfree_skb(skb); + dev_kfree_skb_irq(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 310622086f74..9d01874e6b93 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -25,6 +25,8 @@ /* Bluetooth HCI event handling. */ #include <asm/unaligned.h> +#include <linux/crypto.h> +#include <crypto/algapi.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -1699,7 +1701,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) return; } - set_bit(HCI_INQUIRY, &hdev->flags); + if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) + set_bit(HCI_INQUIRY, &hdev->flags); } static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) @@ -2510,6 +2513,16 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s bdaddr %pMR type 0x%x", hdev->name, &ev->bdaddr, ev->link_type); + /* Reject incoming connection from device with same BD ADDR against + * CVE-2020-26555 + */ + if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + &ev->bdaddr); + hci_reject_conn(hdev, &ev->bdaddr); + return; + } + mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type, &flags); @@ -2709,14 +2722,8 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!ev->status) { clear_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); - - if (!hci_conn_ssp_enabled(conn) && - test_bit(HCI_CONN_REAUTH_PEND, &conn->flags)) { - bt_dev_info(hdev, "re-auth of legacy device is not possible."); - } else { - set_bit(HCI_CONN_AUTH, &conn->flags); - conn->sec_level = conn->pending_sec_level; - } + set_bit(HCI_CONN_AUTH, &conn->flags); + conn->sec_level = conn->pending_sec_level; } else { if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING) set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); @@ -2725,7 +2732,6 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) } clear_bit(HCI_CONN_AUTH_PEND, &conn->flags); - clear_bit(HCI_CONN_REAUTH_PEND, &conn->flags); if (conn->state == BT_CONFIG) { if (!ev->status && hci_conn_ssp_enabled(conn)) { @@ -2756,7 +2762,7 @@ static void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) &cp); } else { clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); - hci_encrypt_cfm(conn, ev->status, 0x00); + hci_encrypt_cfm(conn, ev->status); } } @@ -2841,22 +2847,7 @@ static void read_enc_key_size_complete(struct hci_dev *hdev, u8 status, conn->enc_key_size = rp->key_size; } - if (conn->state == BT_CONFIG) { - conn->state = BT_CONNECTED; - hci_connect_cfm(conn, 0); - hci_conn_drop(conn); - } else { - u8 encrypt; - - if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) - encrypt = 0x00; - else if (test_bit(HCI_CONN_AES_CCM, &conn->flags)) - encrypt = 0x02; - else - encrypt = 0x01; - - hci_encrypt_cfm(conn, 0, encrypt); - } + hci_encrypt_cfm(conn, 0); unlock: hci_dev_unlock(hdev); @@ -2905,27 +2896,23 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); + /* Check link security requirements are met */ + if (!hci_conn_check_link_mode(conn)) + ev->status = HCI_ERROR_AUTH_FAILURE; + if (ev->status && conn->state == BT_CONNECTED) { if (ev->status == HCI_ERROR_PIN_OR_KEY_MISSING) set_bit(HCI_CONN_AUTH_FAILURE, &conn->flags); + /* Notify upper layers so they can cleanup before + * disconnecting. + */ + hci_encrypt_cfm(conn, ev->status); hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); hci_conn_drop(conn); goto unlock; } - /* In Secure Connections Only mode, do not allow any connections - * that are not encrypted with AES-CCM using a P-256 authenticated - * combination key. - */ - if (hci_dev_test_flag(hdev, HCI_SC_ONLY) && - (!test_bit(HCI_CONN_AES_CCM, &conn->flags) || - conn->key_type != HCI_LK_AUTH_COMBINATION_P256)) { - hci_connect_cfm(conn, HCI_ERROR_AUTH_FAILURE); - hci_conn_drop(conn); - goto unlock; - } - /* Try reading the encryption key size for encrypted ACL links */ if (!ev->status && ev->encrypt && conn->type == ACL_LINK) { struct hci_cp_read_enc_key_size cp; @@ -2955,14 +2942,7 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb) } notify: - if (conn->state == BT_CONFIG) { - if (!ev->status) - conn->state = BT_CONNECTED; - - hci_connect_cfm(conn, ev->status); - hci_conn_drop(conn); - } else - hci_encrypt_cfm(conn, ev->status, ev->encrypt); + hci_encrypt_cfm(conn, ev->status); unlock: hci_dev_unlock(hdev); @@ -3842,6 +3822,15 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, struct sk_buff *skb) if (!conn) goto unlock; + /* Ignore NULL link key against CVE-2020-26555 */ + if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) { + bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR", + &ev->bdaddr); + hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_drop(conn); + goto unlock; + } + hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; hci_conn_drop(conn); @@ -4109,6 +4098,21 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, switch (ev->status) { case 0x00: + /* The synchronous connection complete event should only be + * sent once per new connection. Receiving a successful + * complete event when the connection status is already + * BT_CONNECTED means that the device is misbehaving and sent + * multiple complete event packets for the same new connection. + * + * Registering the device more than once can corrupt kernel + * memory, hence upon detecting this invalid event, we report + * an error and ignore the packet. + */ + if (conn->state == BT_CONNECTED) { + bt_dev_err(hdev, "Ignoring connect complete event for existing connection"); + goto unlock; + } + conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -4305,8 +4309,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * available, then do not declare that OOB data is * present. */ - if (!memcmp(data->rand256, ZERO_KEY, 16) || - !memcmp(data->hash256, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand256, ZERO_KEY, 16) || + !crypto_memneq(data->hash256, ZERO_KEY, 16)) return 0x00; return 0x02; @@ -4316,8 +4320,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * not supported by the hardware, then check that if * P-192 data values are present. */ - if (!memcmp(data->rand192, ZERO_KEY, 16) || - !memcmp(data->hash192, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand192, ZERO_KEY, 16) || + !crypto_memneq(data->hash192, ZERO_KEY, 16)) return 0x00; return 0x01; @@ -4333,7 +4337,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; hci_conn_hold(conn); @@ -4568,7 +4572,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; /* Reset the authentication requirement to unknown */ @@ -4698,6 +4702,11 @@ static void hci_phy_link_complete_evt(struct hci_dev *hdev, return; } + if (!hcon->amp_mgr) { + hci_dev_unlock(hdev); + return; + } + if (ev->status) { hci_conn_del(hcon); hci_dev_unlock(hdev); @@ -4742,6 +4751,7 @@ static void hci_loglink_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) return; hchan->handle = le16_to_cpu(ev->handle); + hchan->amp = true; BT_DBG("hcon %p mgr %p hchan %p", hcon, hcon->amp_mgr, hchan); @@ -4774,7 +4784,7 @@ static void hci_disconn_loglink_complete_evt(struct hci_dev *hdev, hci_dev_lock(hdev); hchan = hci_chan_lookup_handle(hdev, le16_to_cpu(ev->handle)); - if (!hchan) + if (!hchan || !hchan->amp) goto unlock; amp_destroy_logical_link(hchan, ev->reason); @@ -4797,8 +4807,9 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (hcon) { + if (hcon && hcon->type == AMP_LINK) { hcon->state = BT_CLOSED; + hci_disconn_cfm(hcon, ev->reason); hci_conn_del(hcon); } @@ -4806,9 +4817,64 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, } #endif +static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr, + u8 bdaddr_type, bdaddr_t *local_rpa) +{ + if (conn->out) { + conn->dst_type = bdaddr_type; + conn->resp_addr_type = bdaddr_type; + bacpy(&conn->resp_addr, bdaddr); + + /* Check if the controller has set a Local RPA then it must be + * used instead or hdev->rpa. + */ + if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) { + conn->init_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->init_addr, local_rpa); + } else if (hci_dev_test_flag(conn->hdev, HCI_PRIVACY)) { + conn->init_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->init_addr, &conn->hdev->rpa); + } else { + hci_copy_identity_address(conn->hdev, &conn->init_addr, + &conn->init_addr_type); + } + } else { + conn->resp_addr_type = conn->hdev->adv_addr_type; + /* Check if the controller has set a Local RPA then it must be + * used instead or hdev->rpa. + */ + if (local_rpa && bacmp(local_rpa, BDADDR_ANY)) { + conn->resp_addr_type = ADDR_LE_DEV_RANDOM; + bacpy(&conn->resp_addr, local_rpa); + } else if (conn->hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) { + /* In case of ext adv, resp_addr will be updated in + * Adv Terminated event. + */ + if (!ext_adv_capable(conn->hdev)) + bacpy(&conn->resp_addr, + &conn->hdev->random_addr); + } else { + bacpy(&conn->resp_addr, &conn->hdev->bdaddr); + } + + conn->init_addr_type = bdaddr_type; + bacpy(&conn->init_addr, bdaddr); + + /* For incoming connections, set the default minimum + * and maximum connection interval. They will be used + * to check if the parameters are in range and if not + * trigger the connection update procedure. + */ + conn->le_conn_min_interval = conn->hdev->le_conn_min_interval; + conn->le_conn_max_interval = conn->hdev->le_conn_max_interval; + } +} + static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, - bdaddr_t *bdaddr, u8 bdaddr_type, u8 role, u16 handle, - u16 interval, u16 latency, u16 supervision_timeout) + bdaddr_t *bdaddr, u8 bdaddr_type, + bdaddr_t *local_rpa, u8 role, u16 handle, + u16 interval, u16 latency, + u16 supervision_timeout) { struct hci_conn_params *params; struct hci_conn *conn; @@ -4856,32 +4922,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, cancel_delayed_work(&conn->le_conn_timeout); } - if (!conn->out) { - /* Set the responder (our side) address type based on - * the advertising address type. - */ - conn->resp_addr_type = hdev->adv_addr_type; - if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) { - /* In case of ext adv, resp_addr will be updated in - * Adv Terminated event. - */ - if (!ext_adv_capable(hdev)) - bacpy(&conn->resp_addr, &hdev->random_addr); - } else { - bacpy(&conn->resp_addr, &hdev->bdaddr); - } - - conn->init_addr_type = bdaddr_type; - bacpy(&conn->init_addr, bdaddr); - - /* For incoming connections, set the default minimum - * and maximum connection interval. They will be used - * to check if the parameters are in range and if not - * trigger the connection update procedure. - */ - conn->le_conn_min_interval = hdev->le_conn_min_interval; - conn->le_conn_max_interval = hdev->le_conn_max_interval; - } + le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa); /* Lookup the identity address from the stored connection * address and address type. @@ -4979,7 +5020,7 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, - ev->role, le16_to_cpu(ev->handle), + NULL, ev->role, le16_to_cpu(ev->handle), le16_to_cpu(ev->interval), le16_to_cpu(ev->latency), le16_to_cpu(ev->supervision_timeout)); @@ -4993,7 +5034,7 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev, BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type, - ev->role, le16_to_cpu(ev->handle), + &ev->local_rpa, ev->role, le16_to_cpu(ev->handle), le16_to_cpu(ev->interval), le16_to_cpu(ev->latency), le16_to_cpu(ev->supervision_timeout)); @@ -5006,14 +5047,26 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); - if (ev->status) + if (ev->status) { + struct adv_info *adv; + + adv = hci_find_adv_instance(hdev, ev->handle); + if (!adv) + return; + + /* Remove advertising as it has been terminated */ + hci_remove_adv_instance(hdev, ev->handle); + mgmt_advertising_removed(NULL, hdev, ev->handle); + return; + } conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle)); if (conn) { struct adv_info *adv_instance; - if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM) + if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM || + bacmp(&conn->resp_addr, BDADDR_ANY)) return; if (!hdev->cur_adv_instance) { @@ -5354,7 +5407,13 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) struct hci_ev_le_advertising_info *ev = ptr; s8 rssi; - if (ev->length <= HCI_MAX_AD_LENGTH) { + if (ptr > (void *)skb_tail_pointer(skb) - sizeof(*ev)) { + bt_dev_err(hdev, "Malicious advertising data."); + break; + } + + if (ev->length <= HCI_MAX_AD_LENGTH && + ev->data + ev->length <= skb_tail_pointer(skb)) { rssi = ev->data[ev->length]; process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, rssi, @@ -5622,21 +5681,19 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) { u8 num_reports = skb->data[0]; - void *ptr = &skb->data[1]; + struct hci_ev_le_direct_adv_info *ev = (void *)&skb->data[1]; - hci_dev_lock(hdev); + if (!num_reports || skb->len < num_reports * sizeof(*ev) + 1) + return; - while (num_reports--) { - struct hci_ev_le_direct_adv_info *ev = ptr; + hci_dev_lock(hdev); + for (; num_reports; num_reports--, ev++) process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, &ev->direct_addr, ev->direct_addr_type, ev->rssi, NULL, 0, false); - ptr += sizeof(*ev); - } - hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index a8ddd211e94c..76bd6b122724 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -271,12 +271,16 @@ int hci_req_sync(struct hci_dev *hdev, int (*req)(struct hci_request *req, { int ret; - if (!test_bit(HCI_UP, &hdev->flags)) - return -ENETDOWN; - /* Serialize all requests */ hci_req_sync_lock(hdev); - ret = __hci_req_sync(hdev, req, opt, timeout, hci_status); + /* check the state after obtaing the lock to protect the HCI_UP + * against any races from hci_dev_do_close when the controller + * gets removed. + */ + if (test_bit(HCI_UP, &hdev->flags)) + ret = __hci_req_sync(hdev, req, opt, timeout, hci_status); + else + ret = -ENETDOWN; hci_req_sync_unlock(hdev); return ret; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index e506c51ff765..a7e5bca9f7e4 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -59,6 +59,17 @@ struct hci_pinfo { char comm[TASK_COMM_LEN]; }; +static struct hci_dev *hci_hdev_from_sock(struct sock *sk) +{ + struct hci_dev *hdev = hci_pi(sk)->hdev; + + if (!hdev) + return ERR_PTR(-EBADFD); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return ERR_PTR(-EPIPE); + return hdev; +} + void hci_sock_set_flag(struct sock *sk, int nr) { set_bit(nr, &hci_pi(sk)->flags); @@ -419,7 +430,8 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) ni->type = hdev->dev_type; ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); - memcpy(ni->name, hdev->name, 8); + memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name, + strnlen(hdev->name, sizeof(ni->name)), '\0'); opcode = cpu_to_le16(HCI_MON_NEW_INDEX); break; @@ -752,19 +764,13 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event) if (event == HCI_DEV_UNREG) { struct sock *sk; - /* Detach sockets from device */ + /* Wake up sockets using this dead device */ read_lock(&hci_sk_list.lock); sk_for_each(sk, &hci_sk_list.head) { - bh_lock_sock_nested(sk); if (hci_pi(sk)->hdev == hdev) { - hci_pi(sk)->hdev = NULL; sk->sk_err = EPIPE; - sk->sk_state = BT_OPEN; sk->sk_state_change(sk); - - hci_dev_put(hdev); } - bh_unlock_sock(sk); } read_unlock(&hci_sk_list.lock); } @@ -876,10 +882,6 @@ static int hci_sock_release(struct socket *sock) } sock_orphan(sk); - - skb_queue_purge(&sk->sk_receive_queue); - skb_queue_purge(&sk->sk_write_queue); - release_sock(sk); sock_put(sk); return 0; @@ -923,10 +925,10 @@ static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { - struct hci_dev *hdev = hci_pi(sk)->hdev; + struct hci_dev *hdev = hci_hdev_from_sock(sk); - if (!hdev) - return -EBADFD; + if (IS_ERR(hdev)) + return PTR_ERR(hdev); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; @@ -972,6 +974,34 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, BT_DBG("cmd %x arg %lx", cmd, arg); + /* Make sure the cmd is valid before doing anything */ + switch (cmd) { + case HCIGETDEVLIST: + case HCIGETDEVINFO: + case HCIGETCONNLIST: + case HCIDEVUP: + case HCIDEVDOWN: + case HCIDEVRESET: + case HCIDEVRESTAT: + case HCISETSCAN: + case HCISETAUTH: + case HCISETENCRYPT: + case HCISETPTYPE: + case HCISETLINKPOL: + case HCISETLINKMODE: + case HCISETACLMTU: + case HCISETSCOMTU: + case HCIINQUIRY: + case HCISETRAW: + case HCIGETCONNINFO: + case HCIGETAUTHINFO: + case HCIBLOCKADDR: + case HCIUNBLOCKADDR: + break; + default: + return -ENOIOCTLCMD; + } + lock_sock(sk); if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) { @@ -988,7 +1018,14 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd, if (hci_sock_gen_cookie(sk)) { struct sk_buff *skb; - if (capable(CAP_NET_ADMIN)) + /* Perform careful checks before setting the HCI_SOCK_TRUSTED + * flag. Make sure that not only the current task but also + * the socket opener has the required capability, since + * privileged programs can be tricked into making ioctl calls + * on HCI sockets, and the socket should not be marked as + * trusted simply because the ioctl caller is privileged. + */ + if (sk_capable(sk, CAP_NET_ADMIN)) hci_sock_set_flag(sk, HCI_SOCK_TRUSTED); /* Send event to monitor */ @@ -1080,6 +1117,18 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, lock_sock(sk); + /* Allow detaching from dead device and attaching to alive device, if + * the caller wants to re-bind (instead of close) this socket in + * response to hci_sock_dev_event(HCI_DEV_UNREG) notification. + */ + hdev = hci_pi(sk)->hdev; + if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) { + hci_pi(sk)->hdev = NULL; + sk->sk_state = BT_OPEN; + hci_dev_put(hdev); + } + hdev = NULL; + if (sk->sk_state == BT_BOUND) { err = -EALREADY; goto done; @@ -1356,9 +1405,9 @@ static int hci_sock_getname(struct socket *sock, struct sockaddr *addr, lock_sock(sk); - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } @@ -1718,9 +1767,9 @@ static int hci_sock_sendmsg(struct socket *sock, struct msghdr *msg, goto done; } - hdev = hci_pi(sk)->hdev; - if (!hdev) { - err = -EBADFD; + hdev = hci_hdev_from_sock(sk); + if (IS_ERR(hdev)) { + err = PTR_ERR(hdev); goto done; } @@ -1968,6 +2017,12 @@ done: return err; } +static void hci_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); + skb_queue_purge(&sk->sk_write_queue); +} + static const struct proto_ops hci_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, @@ -2018,6 +2073,7 @@ static int hci_sock_create(struct net *net, struct socket *sock, int protocol, sock->state = SS_UNCONNECTED; sk->sk_state = BT_OPEN; + sk->sk_destruct = hci_sock_destruct; bt_sock_link(&hci_sk_list, sk); return 0; diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 9874844a95a9..266112c960ee 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -33,7 +33,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); conn->dev.type = &bt_link; conn->dev.class = bt_class; @@ -46,24 +46,30 @@ void hci_conn_add_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); + + if (device_is_registered(&conn->dev)) + return; dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); - if (device_add(&conn->dev) < 0) { + if (device_add(&conn->dev) < 0) bt_dev_err(hdev, "failed to register connection device"); - return; - } - - hci_dev_hold(hdev); } void hci_conn_del_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - if (!device_is_registered(&conn->dev)) + bt_dev_dbg(hdev, "conn %p", conn); + + if (!device_is_registered(&conn->dev)) { + /* If device_add() has *not* succeeded, use *only* put_device() + * to drop the reference count. + */ + put_device(&conn->dev); return; + } while (1) { struct device *dev; @@ -75,14 +81,15 @@ void hci_conn_del_sysfs(struct hci_conn *conn) put_device(dev); } - device_del(&conn->dev); - - hci_dev_put(hdev); + device_unregister(&conn->dev); } static void bt_host_release(struct device *dev) { struct hci_dev *hdev = to_hci_dev(dev); + + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + hci_cleanup_dev(hdev); kfree(hdev); module_put(THIS_MODULE); } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 253975cce943..00dae8e875a2 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -428,7 +428,7 @@ static void hidp_set_timer(struct hidp_session *session) static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) - del_timer(&session->timer); + del_timer_sync(&session->timer); } static void hidp_process_report(struct hidp_session *session, int type, @@ -1282,7 +1282,7 @@ static int hidp_session_thread(void *arg) /* cleanup runtime environment */ remove_wait_queue(sk_sleep(session->intr_sock->sk), &intr_wait); - remove_wait_queue(sk_sleep(session->intr_sock->sk), &ctrl_wait); + remove_wait_queue(sk_sleep(session->ctrl_sock->sk), &ctrl_wait); wake_up_interruptible(&session->report_queue); hidp_del_timer(session); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index c04107d44601..9346fae5d664 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -63,6 +63,9 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err); static void l2cap_tx(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff_head *skbs, u8 event); +static void l2cap_retrans_timeout(struct work_struct *work); +static void l2cap_monitor_timeout(struct work_struct *work); +static void l2cap_ack_timeout(struct work_struct *work); static inline u8 bdaddr_type(u8 link_type, u8 bdaddr_type) { @@ -113,7 +116,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn, } /* Find channel with given SCID. - * Returns locked channel. */ + * Returns a reference locked channel. + */ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, u16 cid) { @@ -121,15 +125,19 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_scid(conn, cid); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock); return c; } /* Find channel with given DCID. - * Returns locked channel. + * Returns a reference locked channel. */ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, u16 cid) @@ -138,8 +146,12 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_dcid(conn, cid); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock); return c; @@ -164,8 +176,12 @@ static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn, mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_ident(conn, ident); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock); return c; @@ -445,6 +461,8 @@ struct l2cap_chan *l2cap_chan_create(void) if (!chan) return NULL; + skb_queue_head_init(&chan->tx_q); + skb_queue_head_init(&chan->srej_q); mutex_init(&chan->lock); /* Set default lock nesting level */ @@ -455,6 +473,9 @@ struct l2cap_chan *l2cap_chan_create(void) write_unlock(&chan_list_lock); INIT_DELAYED_WORK(&chan->chan_timer, l2cap_chan_timeout); + INIT_DELAYED_WORK(&chan->retrans_timer, l2cap_retrans_timeout); + INIT_DELAYED_WORK(&chan->monitor_timer, l2cap_monitor_timeout); + INIT_DELAYED_WORK(&chan->ack_timer, l2cap_ack_timeout); chan->state = BT_OPEN; @@ -489,6 +510,16 @@ void l2cap_chan_hold(struct l2cap_chan *c) kref_get(&c->kref); } +struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c) +{ + BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref)); + + if (!kref_get_unless_zero(&c->kref)) + return NULL; + + return c; +} + void l2cap_chan_put(struct l2cap_chan *c) { BT_DBG("chan %p orig refcnt %d", c, kref_read(&c->kref)); @@ -510,7 +541,9 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; + chan->conf_state = 0; + set_bit(CONF_NOT_COMPLETE, &chan->conf_state); set_bit(FLAG_FORCE_ACTIVE, &chan->flags); } @@ -1777,11 +1810,11 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr_t *dst, u8 link_type) { - struct l2cap_chan *c, *c1 = NULL; + struct l2cap_chan *c, *tmp, *c1 = NULL; read_lock(&chan_list_lock); - list_for_each_entry(c, &chan_list, global_l) { + list_for_each_entry_safe(c, tmp, &chan_list, global_l) { if (state && c->state != state) continue; @@ -1791,7 +1824,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, if (link_type == LE_LINK && c->src_type == BDADDR_BREDR) continue; - if (c->psm == psm) { + if (c->chan_type != L2CAP_CHAN_FIXED && c->psm == psm) { int src_match, dst_match; int src_any, dst_any; @@ -1799,7 +1832,9 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, src_match = !bacmp(&c->src, src); dst_match = !bacmp(&c->dst, dst); if (src_match && dst_match) { - l2cap_chan_hold(c); + if (!l2cap_chan_hold_unless_zero(c)) + continue; + read_unlock(&chan_list_lock); return c; } @@ -1814,7 +1849,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, } if (c1) - l2cap_chan_hold(c1); + c1 = l2cap_chan_hold_unless_zero(c1); read_unlock(&chan_list_lock); @@ -2482,14 +2517,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) if (IS_ERR(skb)) return PTR_ERR(skb); - /* Channel lock is released before requesting new skb and then - * reacquired thus we need to recheck channel state. - */ - if (chan->state != BT_CONNECTED) { - kfree_skb(skb); - return -ENOTCONN; - } - l2cap_do_send(chan, skb); return len; } @@ -2533,14 +2560,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) if (IS_ERR(skb)) return PTR_ERR(skb); - /* Channel lock is released before requesting new skb and then - * reacquired thus we need to recheck channel state. - */ - if (chan->state != BT_CONNECTED) { - kfree_skb(skb); - return -ENOTCONN; - } - l2cap_do_send(chan, skb); err = len; break; @@ -2561,14 +2580,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) */ err = l2cap_segment_sdu(chan, &seg_queue, msg, len); - /* The channel could have been closed while segmenting, - * check that it is still connected. - */ - if (chan->state != BT_CONNECTED) { - __skb_queue_purge(&seg_queue); - err = -ENOTCONN; - } - if (err) break; @@ -3125,10 +3136,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan) chan->rx_state = L2CAP_RX_STATE_RECV; chan->tx_state = L2CAP_TX_STATE_XMIT; - INIT_DELAYED_WORK(&chan->retrans_timer, l2cap_retrans_timeout); - INIT_DELAYED_WORK(&chan->monitor_timer, l2cap_monitor_timeout); - INIT_DELAYED_WORK(&chan->ack_timer, l2cap_ack_timeout); - skb_queue_head_init(&chan->srej_q); err = l2cap_seq_list_init(&chan->srej_list, chan->tx_win); @@ -3520,7 +3527,8 @@ done: l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc, endptr - ptr); - if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { + if (remote_efs && + test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->remote_id = efs.id; chan->remote_stype = efs.stype; chan->remote_msdu = le16_to_cpu(efs.msdu); @@ -3999,6 +4007,10 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, result = __le16_to_cpu(rsp->result); status = __le16_to_cpu(rsp->status); + if (result == L2CAP_CR_SUCCESS && (dcid < L2CAP_CID_DYN_START || + dcid > L2CAP_CID_DYN_END)) + return -EPROTO; + BT_DBG("dcid 0x%4.4x scid 0x%4.4x result 0x%2.2x status 0x%2.2x", dcid, scid, result, status); @@ -4018,12 +4030,23 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, } } + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) { + err = -EBADSLT; + goto unlock; + } + err = 0; l2cap_chan_lock(chan); switch (result) { case L2CAP_CR_SUCCESS: + if (__l2cap_get_chan_by_dcid(conn, dcid)) { + err = -EBADSLT; + break; + } + l2cap_state_change(chan, BT_CONFIG); chan->ident = 0; chan->dcid = dcid; @@ -4047,6 +4070,7 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, } l2cap_chan_unlock(chan); + l2cap_chan_put(chan); unlock: mutex_unlock(&conn->chan_lock); @@ -4154,7 +4178,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, chan->ident = cmd->ident; l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, len, rsp); - chan->num_conf_rsp++; + if (chan->num_conf_rsp < L2CAP_CONF_MAX_CONF_RSP) + chan->num_conf_rsp++; /* Reset config buffer. */ chan->conf_len = 0; @@ -4200,6 +4225,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, unlock: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return err; } @@ -4312,6 +4338,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, done: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return err; } @@ -4332,33 +4359,29 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp); chan->ops->set_shutdown(chan); + l2cap_chan_unlock(chan); + mutex_lock(&conn->chan_lock); + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -4378,33 +4401,28 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { - mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; } + l2cap_chan_unlock(chan); + mutex_lock(&conn->chan_lock); + l2cap_chan_lock(chan); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -5040,6 +5058,7 @@ send_move_response: l2cap_send_move_chan_rsp(chan, result); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -5132,6 +5151,7 @@ static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result) } l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, @@ -5161,6 +5181,7 @@ static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static int l2cap_move_channel_rsp(struct l2cap_conn *conn, @@ -5224,6 +5245,7 @@ static int l2cap_move_channel_confirm(struct l2cap_conn *conn, l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -5259,6 +5281,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, } l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -5507,6 +5530,19 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm), scid, mtu, mps); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_BAD_PSM; + chan = NULL; + goto response; + } + /* Check if we have socket listening on psm */ pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, &conn->hcon->dst, LE_LINK); @@ -5631,12 +5667,11 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, if (credits > max_credits) { BT_ERR("LE credits overflow"); l2cap_send_disconn_req(chan, ECONNRESET); - l2cap_chan_unlock(chan); /* Return 0 so that we don't trigger an unnecessary * command reject packet. */ - return 0; + goto unlock; } chan->tx_credits += credits; @@ -5647,7 +5682,9 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, if (chan->tx_credits) chan->ops->resume(chan); +unlock: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -5668,9 +5705,14 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, if (!chan) goto done; + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) + goto done; + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNREFUSED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); done: mutex_unlock(&conn->chan_lock); @@ -6209,6 +6251,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb, u8 event) { + struct l2cap_ctrl local_control; int err = 0; bool skb_in_use = false; @@ -6233,15 +6276,32 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, chan->buffer_seq = chan->expected_tx_seq; skb_in_use = true; + /* l2cap_reassemble_sdu may free skb, hence invalidate + * control, so make a copy in advance to use it after + * l2cap_reassemble_sdu returns and to avoid the race + * condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but + * it was freed by skb_free_datagram. + */ + local_control = *control; err = l2cap_reassemble_sdu(chan, skb, control); if (err) break; - if (control->final) { + if (local_control.final) { if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) { - control->final = 0; - l2cap_retransmit_all(chan, control); + local_control.final = 0; + l2cap_retransmit_all(chan, &local_control); l2cap_ertm_send(chan); } } @@ -6621,11 +6681,27 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb) { + /* l2cap_reassemble_sdu may free skb, hence invalidate control, so store + * the txseq field in advance to use it after l2cap_reassemble_sdu + * returns and to avoid the race condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but it was freed by + * skb_free_datagram. + */ + u16 txseq = control->txseq; + BT_DBG("chan %p, control %p, skb %p, state %d", chan, control, skb, chan->rx_state); - if (l2cap_classify_txseq(chan, control->txseq) == - L2CAP_TXSEQ_EXPECTED) { + if (l2cap_classify_txseq(chan, txseq) == L2CAP_TXSEQ_EXPECTED) { l2cap_pass_to_tx(chan, control); BT_DBG("buffer_seq %d->%d", chan->buffer_seq, @@ -6648,8 +6724,8 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, } } - chan->last_acked_seq = control->txseq; - chan->expected_tx_seq = __next_seq(chan, control->txseq); + chan->last_acked_seq = txseq; + chan->expected_tx_seq = __next_seq(chan, txseq); return 0; } @@ -6683,9 +6759,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb) goto drop; } - if ((chan->mode == L2CAP_MODE_ERTM || - chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb)) - goto drop; + if (chan->ops->filter) { + if (chan->ops->filter(chan, skb)) + goto drop; + } if (!control->sframe) { int err; @@ -6886,6 +6963,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, return; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); } else { BT_DBG("unknown cid 0x%4.4x", cid); @@ -6944,6 +7022,7 @@ drop: done: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, @@ -7348,7 +7427,7 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c, if (src_type != c->src_type) continue; - l2cap_chan_hold(c); + c = l2cap_chan_hold_unless_zero(c); read_unlock(&chan_list_lock); return c; } diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 5572042f0453..b831e5fe3ebc 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -45,6 +45,7 @@ static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern); +static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) { @@ -179,9 +180,17 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct sockaddr_l2 la; int len, err = 0; + bool zapped; BT_DBG("sk %p", sk); + lock_sock(sk); + zapped = sock_flag(sk, SOCK_ZAPPED); + release_sock(sk); + + if (zapped) + return -EINVAL; + if (!addr || alen < offsetofend(struct sockaddr, sa_family) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; @@ -1197,6 +1206,7 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + l2cap_sock_cleanup_listen(sk); bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, 2); @@ -1320,6 +1330,9 @@ static void l2cap_sock_close_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; + if (!sk) + return; + l2cap_sock_kill(sk); } @@ -1328,6 +1341,9 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) struct sock *sk = chan->data; struct sock *parent; + if (!sk) + return; + BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); /* This callback can be called both for server (BT_LISTEN) @@ -1341,8 +1357,6 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) parent = bt_sk(sk)->parent; - sock_set_flag(sk, SOCK_ZAPPED); - switch (chan->state) { case BT_OPEN: case BT_BOUND: @@ -1369,8 +1383,11 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err) break; } - release_sock(sk); + + /* Only zap after cleanup to avoid use after free race */ + sock_set_flag(sk, SOCK_ZAPPED); + } static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state, @@ -1399,6 +1416,14 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, if (!skb) return ERR_PTR(err); + /* Channel lock is released before requesting new skb and then + * reacquired thus we need to recheck channel state. + */ + if (chan->state != BT_CONNECTED) { + kfree_skb(skb); + return ERR_PTR(-ENOTCONN); + } + skb->priority = sk->sk_priority; bt_cb(skb)->l2cap.chan = chan; @@ -1476,6 +1501,19 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan) sk->sk_state_change(sk); } +static int l2cap_sock_filter(struct l2cap_chan *chan, struct sk_buff *skb) +{ + struct sock *sk = chan->data; + + switch (chan->mode) { + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + return sk_filter(sk, skb); + } + + return 0; +} + static const struct l2cap_ops l2cap_chan_ops = { .name = "L2CAP Socket Interface", .new_connection = l2cap_sock_new_connection_cb, @@ -1490,14 +1528,17 @@ static const struct l2cap_ops l2cap_chan_ops = { .set_shutdown = l2cap_sock_set_shutdown_cb, .get_sndtimeo = l2cap_sock_get_sndtimeo_cb, .alloc_skb = l2cap_sock_alloc_skb_cb, + .filter = l2cap_sock_filter, }; static void l2cap_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); - if (l2cap_pi(sk)->chan) + if (l2cap_pi(sk)->chan) { + l2cap_pi(sk)->chan->data = NULL; l2cap_chan_put(l2cap_pi(sk)->chan); + } if (l2cap_pi(sk)->rx_busy_skb) { kfree_skb(l2cap_pi(sk)->rx_busy_skb); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ccce954f8146..d0ec0e336909 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -219,12 +219,15 @@ static u8 mgmt_status_table[] = { MGMT_STATUS_TIMEOUT, /* Instant Passed */ MGMT_STATUS_NOT_SUPPORTED, /* Pairing Not Supported */ MGMT_STATUS_FAILED, /* Transaction Collision */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_INVALID_PARAMS, /* Unacceptable Parameter */ MGMT_STATUS_REJECTED, /* QoS Rejected */ MGMT_STATUS_NOT_SUPPORTED, /* Classification Not Supported */ MGMT_STATUS_REJECTED, /* Insufficient Security */ MGMT_STATUS_INVALID_PARAMS, /* Parameter Out Of Range */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_BUSY, /* Role Switch Pending */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_FAILED, /* Slot Violation */ MGMT_STATUS_FAILED, /* Role Switch Failed */ MGMT_STATUS_INVALID_PARAMS, /* EIR Too Large */ @@ -756,7 +759,8 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { settings |= MGMT_SETTING_SSP; - settings |= MGMT_SETTING_HS; + if (IS_ENABLED(CONFIG_BT_HS)) + settings |= MGMT_SETTING_HS; } if (lmp_sc_capable(hdev)) @@ -1771,6 +1775,10 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) BT_DBG("request for %s", hdev->name); + if (!IS_ENABLED(CONFIG_BT_HS)) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + MGMT_STATUS_NOT_SUPPORTED); + status = mgmt_bredr_support(hdev); if (status) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); @@ -6463,6 +6471,9 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, for (i = 0, cur_len = 0; i < len; i += (cur_len + 1)) { cur_len = data[i]; + if (!cur_len) + continue; + if (data[i + 1] == EIR_FLAGS && (!is_adv_data || flags_managed(adv_flags))) return false; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index b98225d65e87..86edf512d497 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -552,22 +552,58 @@ struct rfcomm_dlc *rfcomm_dlc_exists(bdaddr_t *src, bdaddr_t *dst, u8 channel) return dlc; } +static int rfcomm_dlc_send_frag(struct rfcomm_dlc *d, struct sk_buff *frag) +{ + int len = frag->len; + + BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); + + if (len > d->mtu) + return -EINVAL; + + rfcomm_make_uih(frag, d->addr); + __skb_queue_tail(&d->tx_queue, frag); + + return len; +} + int rfcomm_dlc_send(struct rfcomm_dlc *d, struct sk_buff *skb) { - int len = skb->len; + unsigned long flags; + struct sk_buff *frag, *next; + int len; if (d->state != BT_CONNECTED) return -ENOTCONN; - BT_DBG("dlc %p mtu %d len %d", d, d->mtu, len); + frag = skb_shinfo(skb)->frag_list; + skb_shinfo(skb)->frag_list = NULL; - if (len > d->mtu) - return -EINVAL; + /* Queue all fragments atomically. */ + spin_lock_irqsave(&d->tx_queue.lock, flags); - rfcomm_make_uih(skb, d->addr); - skb_queue_tail(&d->tx_queue, skb); + len = rfcomm_dlc_send_frag(d, skb); + if (len < 0 || !frag) + goto unlock; + + for (; frag; frag = next) { + int ret; + + next = frag->next; + + ret = rfcomm_dlc_send_frag(d, frag); + if (ret < 0) { + dev_kfree_skb_irq(frag); + goto unlock; + } + + len += ret; + } + +unlock: + spin_unlock_irqrestore(&d->tx_queue.lock, flags); - if (!test_bit(RFCOMM_TX_THROTTLED, &d->flags)) + if (len > 0 && !test_bit(RFCOMM_TX_THROTTLED, &d->flags)) rfcomm_schedule(); return len; } diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index c044ff2f73e6..78830efe89d7 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -578,46 +578,20 @@ static int rfcomm_sock_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); sent = bt_sock_wait_ready(sk, msg->msg_flags); - if (sent) - goto done; - - while (len) { - size_t size = min_t(size_t, len, d->mtu); - int err; - - skb = sock_alloc_send_skb(sk, size + RFCOMM_SKB_RESERVE, - msg->msg_flags & MSG_DONTWAIT, &err); - if (!skb) { - if (sent == 0) - sent = err; - break; - } - skb_reserve(skb, RFCOMM_SKB_HEAD_RESERVE); - - err = memcpy_from_msg(skb_put(skb, size), msg, size); - if (err) { - kfree_skb(skb); - if (sent == 0) - sent = err; - break; - } - skb->priority = sk->sk_priority; + release_sock(sk); - err = rfcomm_dlc_send(d, skb); - if (err < 0) { - kfree_skb(skb); - if (sent == 0) - sent = err; - break; - } + if (sent) + return sent; - sent += size; - len -= size; - } + skb = bt_skb_sendmmsg(sk, msg, len, d->mtu, RFCOMM_SKB_HEAD_RESERVE, + RFCOMM_SKB_TAIL_RESERVE); + if (IS_ERR(skb)) + return PTR_ERR(skb); -done: - release_sock(sk); + sent = rfcomm_dlc_send(d, skb); + if (sent < 0) + kfree_skb(skb); return sent; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index a4ca55df7390..ee321d62b7d6 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -48,6 +48,8 @@ struct sco_conn { spinlock_t lock; struct sock *sk; + struct delayed_work timeout_work; + unsigned int mtu; }; @@ -73,9 +75,20 @@ struct sco_pinfo { #define SCO_CONN_TIMEOUT (HZ * 40) #define SCO_DISCONN_TIMEOUT (HZ * 2) -static void sco_sock_timeout(struct timer_list *t) +static void sco_sock_timeout(struct work_struct *work) { - struct sock *sk = from_timer(sk, t, sk_timer); + struct sco_conn *conn = container_of(work, struct sco_conn, + timeout_work.work); + struct sock *sk; + + sco_conn_lock(conn); + sk = conn->sk; + if (sk) + sock_hold(sk); + sco_conn_unlock(conn); + + if (!sk) + return; BT_DBG("sock %p state %d", sk, sk->sk_state); @@ -84,20 +97,26 @@ static void sco_sock_timeout(struct timer_list *t) sk->sk_state_change(sk); bh_unlock_sock(sk); - sco_sock_kill(sk); sock_put(sk); } static void sco_sock_set_timer(struct sock *sk, long timeout) { + if (!sco_pi(sk)->conn) + return; + BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); - sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout); + cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); + schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout); } static void sco_sock_clear_timer(struct sock *sk) { + if (!sco_pi(sk)->conn) + return; + BT_DBG("sock %p state %d", sk, sk->sk_state); - sk_stop_timer(sk, &sk->sk_timer); + cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); } /* ---- SCO connections ---- */ @@ -114,6 +133,7 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) return NULL; spin_lock_init(&conn->lock); + INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout); hcon->sco_data = conn; conn->hcon = hcon; @@ -176,10 +196,12 @@ static void sco_conn_del(struct hci_conn *hcon, int err) sco_sock_clear_timer(sk); sco_chan_del(sk, err); bh_unlock_sock(sk); - sco_sock_kill(sk); sock_put(sk); } + /* Ensure no more work items will run before freeing conn. */ + cancel_delayed_work_sync(&conn->timeout_work); + hcon->sco_data = NULL; kfree(conn); } @@ -211,44 +233,32 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, return err; } -static int sco_connect(struct sock *sk) +static int sco_connect(struct hci_dev *hdev, struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; - struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); - hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); - if (!hdev) - return -EHOSTUNREACH; - - hci_dev_lock(hdev); - if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { - err = -EOPNOTSUPP; - goto done; - } + (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) + return -EOPNOTSUPP; hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting); - if (IS_ERR(hcon)) { - err = PTR_ERR(hcon); - goto done; - } + if (IS_ERR(hcon)) + return PTR_ERR(hcon); conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); - err = -ENOMEM; - goto done; + return -ENOMEM; } /* Update source addr of the socket */ @@ -256,7 +266,7 @@ static int sco_connect(struct sock *sk) err = sco_chan_add(conn, sk, NULL); if (err) - goto done; + return err; if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); @@ -266,17 +276,13 @@ static int sco_connect(struct sock *sk) sco_sock_set_timer(sk, sk->sk_sndtimeo); } -done: - hci_dev_unlock(hdev); - hci_dev_put(hdev); return err; } -static int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) +static int sco_send_frame(struct sock *sk, struct sk_buff *skb) { struct sco_conn *conn = sco_pi(sk)->conn; - struct sk_buff *skb; - int err; + int len = skb->len; /* Check outgoing MTU */ if (len > conn->mtu) @@ -284,15 +290,6 @@ static int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) BT_DBG("sk %p len %d", sk, len); - skb = bt_skb_send_alloc(sk, len, msg->msg_flags & MSG_DONTWAIT, &err); - if (!skb) - return err; - - if (memcpy_from_msg(skb_put(skb, len), msg, len)) { - kfree_skb(skb); - return -EFAULT; - } - hci_send_sco(conn->hcon, skb); return len; @@ -393,8 +390,7 @@ static void sco_sock_cleanup_listen(struct sock *parent) */ static void sco_sock_kill(struct sock *sk) { - if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket || - sock_flag(sk, SOCK_DEAD)) + if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; BT_DBG("sk %p state %d", sk, sk->sk_state); @@ -446,7 +442,6 @@ static void sco_sock_close(struct sock *sk) lock_sock(sk); __sco_sock_close(sk); release_sock(sk); - sco_sock_kill(sk); } static void sco_sock_init(struct sock *sk, struct sock *parent) @@ -488,8 +483,6 @@ static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; - timer_setup(&sk->sk_timer, sco_sock_timeout, 0); - bt_sock_link(&sco_sk_list, sk); return sk; } @@ -554,6 +547,7 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; + struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); @@ -562,18 +556,30 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen addr->sa_family != AF_BLUETOOTH) return -EINVAL; - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) - return -EBADFD; + lock_sock(sk); + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { + err = -EBADFD; + goto done; + } - if (sk->sk_type != SOCK_SEQPACKET) - return -EINVAL; + if (sk->sk_type != SOCK_SEQPACKET) { + err = -EINVAL; + goto done; + } - lock_sock(sk); + hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); + if (!hdev) { + err = -EHOSTUNREACH; + goto done; + } + hci_dev_lock(hdev); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); - err = sco_connect(sk); + err = sco_connect(hdev, sk); + hci_dev_unlock(hdev); + hci_dev_put(hdev); if (err) goto done; @@ -702,6 +708,7 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; + struct sk_buff *skb; int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -713,14 +720,21 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; + skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0); + if (IS_ERR(skb)) + return PTR_ERR(skb); + lock_sock(sk); if (sk->sk_state == BT_CONNECTED) - err = sco_send_frame(sk, msg, len); + err = sco_send_frame(sk, skb); else err = -ENOTCONN; release_sock(sk); + + if (err < 0) + kfree_skb(skb); return err; } @@ -761,6 +775,11 @@ static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; + default: + /* use CVSD settings as fallback */ + cp.max_latency = cpu_to_le16(0xffff); + cp.retrans_effort = 0xff; + break; } hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index cc2f7ca91ccd..719ae1dff7b4 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2703,6 +2703,15 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*key)) return SMP_INVALID_PARAMS; + /* Check if remote and local public keys are the same and debug key is + * not in use. + */ + if (!test_bit(SMP_FLAG_DEBUG_KEY, &smp->flags) && + !crypto_memneq(key, smp->local_pk, 64)) { + bt_dev_err(hdev, "Remote and local public keys are identical"); + return SMP_UNSPECIFIED; + } + memcpy(smp->remote_pk, key, 64); if (test_bit(SMP_FLAG_REMOTE_OOB, &smp->flags)) { diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index f4078830ea50..e0c6dfae42d8 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -87,6 +87,7 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size, if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) return ERR_PTR(-EINVAL); + size = SKB_DATA_ALIGN(size); data = kzalloc(size + headroom + tailroom, GFP_USER); if (!data) return ERR_PTR(-ENOMEM); diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index eb44ae05abaa..b52e70362268 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -158,7 +158,9 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, if (br->neigh_suppress_enabled) { if (p && (p->flags & BR_NEIGH_SUPPRESS)) return; - if (ipv4_is_zeronet(sip) || sip == tip) { + if (parp->ar_op != htons(ARPOP_RREQUEST) && + parp->ar_op != htons(ARPOP_RREPLY) && + (ipv4_is_zeronet(sip) || sip == tip)) { /* prevent flooding to neigh suppress ports */ BR_INPUT_SKB_CB(skb)->proxyarp_replied = true; return; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 9ce661e2590d..9475e0443ff9 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -39,9 +39,10 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); const struct nf_br_ops *nf_ops; const unsigned char *dest; - struct ethhdr *eth; u16 vid = 0; + memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); + rcu_read_lock(); nf_ops = rcu_dereference(nf_br_ops); if (nf_ops && nf_ops->br_dev_xmit_hook(skb)) { @@ -58,15 +59,14 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); - eth = eth_hdr(skb); skb_pull(skb, ETH_HLEN); if (!br_allowed_ingress(br, br_vlan_group_rcu(br), skb, &vid)) goto out; if (IS_ENABLED(CONFIG_INET) && - (eth->h_proto == htons(ETH_P_ARP) || - eth->h_proto == htons(ETH_P_RARP)) && + (eth_hdr(skb)->h_proto == htons(ETH_P_ARP) || + eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br->neigh_suppress_enabled) { br_do_proxy_suppress_arp(skb, br, vid, NULL); } else if (IS_ENABLED(CONFIG_IPV6) && @@ -215,6 +215,7 @@ static void br_get_stats64(struct net_device *dev, sum.rx_packets += tmp.rx_packets; } + netdev_stats_to_stats64(stats, &dev->stats); stats->tx_bytes = sum.tx_bytes; stats->tx_packets = sum.tx_packets; stats->rx_bytes = sum.rx_bytes; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 48ddc60b4fbd..c07a47d65c39 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -122,7 +122,7 @@ static int deliver_clone(const struct net_bridge_port *prev, skb = skb_clone(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return -ENOMEM; } @@ -261,7 +261,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, skb = skb_copy(skb, GFP_ATOMIC); if (!skb) { - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return; } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index ed2b6002ae53..ab539551b7d3 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -161,8 +161,9 @@ void br_manage_promisc(struct net_bridge *br) * This lets us disable promiscuous mode and write * this config to hw. */ - if (br->auto_cnt == 0 || - (br->auto_cnt == 1 && br_auto_port(p))) + if ((p->dev->priv_flags & IFF_UNICAST_FLT) && + (br->auto_cnt == 0 || + (br->auto_cnt == 1 && br_auto_port(p)))) br_port_clear_promisc(p); else br_port_set_promisc(p); @@ -564,7 +565,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, struct net_bridge_port *p; int err = 0; unsigned br_hr, dev_hr; - bool changed_addr; + bool changed_addr, fdb_synced = false; /* Don't allow bridging non-ethernet like devices, or DSA-enabled * master network devices since the bridge layer rx_handler prevents @@ -604,6 +605,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, err = dev_set_allmulti(dev, 1); if (err) { + br_multicast_del_port(p); kfree(p); /* kobject not yet init'd, manually free */ goto err1; } @@ -640,6 +642,19 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, list_add_rcu(&p->list, &br->port_list); nbp_update_port_count(br); + if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) { + /* When updating the port count we also update all ports' + * promiscuous mode. + * A port leaving promiscuous mode normally gets the bridge's + * fdb synced to the unicast filter (if supported), however, + * `br_port_clear_promisc` does not distinguish between + * non-promiscuous ports and *new* ports, so we need to + * sync explicitly here. + */ + fdb_synced = br_fdb_sync_static(br, p) == 0; + if (!fdb_synced) + netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n"); + } netdev_update_features(br->dev); @@ -680,6 +695,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, return 0; err7: + if (fdb_synced) + br_fdb_unsync_static(br, p); list_del_rcu(&p->list); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); @@ -693,6 +710,7 @@ err4: err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: + br_multicast_del_port(p); kobject_put(&p->kobj); dev_set_allmulti(dev, -1); err1: diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 2532c1a19645..f3938337ff87 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -47,6 +47,13 @@ static int br_pass_frame_up(struct sk_buff *skb) u64_stats_update_end(&brstats->syncp); vg = br_vlan_group_rcu(br); + + /* Reset the offload_fwd_mark because there could be a stacked + * bridge above, and it should not think this bridge it doing + * that bridge's work forwarding out its ports. + */ + br_switchdev_frame_unmark(skb); + /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc modue when someone * may be running packet capture. @@ -139,12 +146,12 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if ((mdst && mdst->host_joined) || br_multicast_is_router(br)) { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } mcast_hit = true; } else { local_rcv = true; - br->dev->stats.multicast++; + DEV_STATS_INC(br->dev, multicast); } break; case BR_PKT_UNICAST: diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 6a362da211e1..3504c3acd38f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1791,7 +1791,9 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; + spin_lock(&br->multicast_lock); br_multicast_mark_router(br, port); + spin_unlock(&br->multicast_lock); } static int br_multicast_ipv4_rcv(struct net_bridge *br, diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index ccab290c14d4..35642dc96852 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -385,6 +385,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ /* - Bridged-and-DNAT'ed traffic doesn't * require ip_forwarding. */ if (rt->dst.dev == dev) { + skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); goto bridged_dnat; } @@ -414,6 +415,7 @@ bridged_dnat: kfree_skb(skb); return 0; } + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); } @@ -719,9 +721,17 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu; + if (nf_bridge->pkt_otherhost) { + skb->pkt_type = PACKET_OTHERHOST; + nf_bridge->pkt_otherhost = false; + } + if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) mtu = nf_bridge->frag_max_size; + nf_bridge_update_protocol(skb); + nf_bridge_push_encap_header(skb); + if (skb_is_gso(skb) || skb->len + mtu_reserved <= mtu) { nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); @@ -739,8 +749,6 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; - nf_bridge_update_protocol(skb); - data = this_cpu_ptr(&brnf_frag_data_storage); data->vlan_tci = skb->vlan_tci; @@ -763,8 +771,6 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; - nf_bridge_update_protocol(skb); - data = this_cpu_ptr(&brnf_frag_data_storage); data->encap_size = nf_bridge_encap_header_len(skb); data->size = ETH_HLEN + data->encap_size; @@ -812,8 +818,6 @@ static unsigned int br_nf_post_routing(void *priv, else return NF_ACCEPT; - /* We assume any code from br_dev_queue_push_xmit onwards doesn't care - * about the value of skb->pkt_type. */ if (skb->pkt_type == PACKET_OTHERHOST) { skb->pkt_type = PACKET_HOST; nf_bridge->pkt_otherhost = true; @@ -999,9 +1003,24 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net, return okfn(net, sk, skb); ops = nf_hook_entries_get_hook_ops(e); - for (i = 0; i < e->num_hook_entries && - ops[i]->priority <= NF_BR_PRI_BRNF; i++) - ; + for (i = 0; i < e->num_hook_entries; i++) { + /* These hooks have already been called */ + if (ops[i]->priority < NF_BR_PRI_BRNF) + continue; + + /* These hooks have not been called yet, run them. */ + if (ops[i]->priority > NF_BR_PRI_BRNF) + break; + + /* take a closer look at NF_BR_PRI_BRNF. */ + if (ops[i]->hook == br_nf_pre_routing) { + /* This hook diverted the skb to this function, + * hooks after this have not been run yet. + */ + i++; + break; + } + } nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev, sk, net, okfn); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 09d5e0c7b3ba..995d86777e7c 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -201,6 +201,7 @@ static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struc kfree_skb(skb); return 0; } + skb_dst_drop(skb); skb_dst_set_noref(skb, &rt->dst); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index ec2b58a09f76..c00cb376263a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1511,7 +1511,7 @@ static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) } return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) + - nla_total_size(sizeof(struct br_mcast_stats)) + + nla_total_size_64bit(sizeof(struct br_mcast_stats)) + nla_total_size(0); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 33b8222db75c..7ca3b469242e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -100,8 +100,8 @@ struct br_vlan_stats { }; struct br_tunnel_info { - __be64 tunnel_id; - struct metadata_dst *tunnel_dst; + __be64 tunnel_id; + struct metadata_dst __rcu *tunnel_dst; }; /** diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 7c87a2fe5248..e9e2a3b1f477 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -59,9 +59,8 @@ static BRPORT_ATTR(_name, 0644, \ static int store_flag(struct net_bridge_port *p, unsigned long v, unsigned long mask) { - unsigned long flags; - - flags = p->flags; + unsigned long flags = p->flags; + int err; if (v) flags |= mask; @@ -69,6 +68,10 @@ static int store_flag(struct net_bridge_port *p, unsigned long v, flags &= ~mask; if (flags != p->flags) { + err = br_switchdev_set_port_flag(p, flags, mask); + if (err) + return err; + p->flags = flags; br_port_flags_change(p, mask); } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 5f3950f00f73..a82d0021d461 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -242,8 +242,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags) } masterv = br_vlan_get_master(br, v->vid); - if (!masterv) + if (!masterv) { + err = -ENOMEM; goto out_filt; + } v->brvlan = masterv; v->stats = masterv->stats; } else { diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 6d2c4eed2dc8..adb6845ceba4 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -46,26 +46,33 @@ static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, br_vlan_tunnel_rht_params); } +static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan) +{ + struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst); + + WRITE_ONCE(vlan->tinfo.tunnel_id, 0); + RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL); + dst_release(&tdst->dst); +} + void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan) { - if (!vlan->tinfo.tunnel_dst) + if (!rcu_access_pointer(vlan->tinfo.tunnel_dst)) return; rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); - vlan->tinfo.tunnel_id = 0; - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; + vlan_tunnel_info_release(vlan); } static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u32 tun_id) { - struct metadata_dst *metadata = NULL; + struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); int err; - if (vlan->tinfo.tunnel_dst) + if (metadata) return -EEXIST; metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, @@ -74,8 +81,8 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return -EINVAL; metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; - vlan->tinfo.tunnel_dst = metadata; - vlan->tinfo.tunnel_id = key; + rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata); + WRITE_ONCE(vlan->tinfo.tunnel_id, key); err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); @@ -84,9 +91,7 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return 0; out: - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; - vlan->tinfo.tunnel_id = 0; + vlan_tunnel_info_release(vlan); return err; } @@ -186,12 +191,15 @@ int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + struct metadata_dst *tunnel_dst; + __be64 tunnel_id; int err; - if (!vlan || !vlan->tinfo.tunnel_id) + if (!vlan) return 0; - if (unlikely(!skb_vlan_tag_present(skb))) + tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id); + if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb))) return 0; skb_dst_drop(skb); @@ -199,7 +207,9 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, if (err) return err; - skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst)); + tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); + if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst)) + skb_dst_set(skb, &tunnel_dst->dst); return 0; } diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 276b60262981..b21c8a317be7 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -33,18 +33,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)&initial_chain, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~(1 << NF_BR_BROUTING)) - return -EINVAL; - return 0; -} - static const struct ebt_table broute_table = { .name = "broute", .table = &initial_table, .valid_hooks = 1 << NF_BR_BROUTING, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 550324c516ee..c71795e4c18c 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -42,18 +42,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~FILTER_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_filter = { .name = "filter", .table = &initial_table, .valid_hooks = FILTER_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index c0fb3ca518af..44dde9e635e2 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -42,18 +42,10 @@ static struct ebt_replace_kernel initial_table = { .entries = (char *)initial_chains, }; -static int check(const struct ebt_table_info *info, unsigned int valid_hooks) -{ - if (valid_hooks & ~NAT_VALID_HOOKS) - return -EINVAL; - return 0; -} - static const struct ebt_table frame_nat = { .name = "nat", .table = &initial_table, .valid_hooks = NAT_VALID_HOOKS, - .check = check, .me = THIS_MODULE, }; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f59230e4fc29..59d8974ee92b 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1003,9 +1003,10 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, goto free_iterate; } - /* the table doesn't like it */ - if (t->check && (ret = t->check(newinfo, repl->valid_hooks))) + if (repl->valid_hooks != t->valid_hooks) { + ret = -EINVAL; goto free_unlock; + } if (repl->num_counters && repl->num_counters != t->private->nentries) { ret = -EINVAL; @@ -1197,11 +1198,6 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, if (ret != 0) goto free_chainstack; - if (table->check && table->check(newinfo, table->valid_hooks)) { - ret = -EINVAL; - goto free_chainstack; - } - table->private = newinfo; rwlock_init(&table->lock); mutex_lock(&ebt_mutex); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 711d7156efd8..cc305d84168f 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -303,7 +303,7 @@ static void dev_flowctrl(struct net_device *dev, int on) caifd_put(caifd); } -void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, +int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)(struct sk_buff *, struct net_device *, @@ -314,11 +314,12 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, enum cfcnfg_phy_preference pref; struct cfcnfg *cfg = get_cfcnfg(dev_net(dev)); struct caif_device_entry_list *caifdevs; + int res; caifdevs = caif_device_list(dev_net(dev)); caifd = caif_device_alloc(dev); if (!caifd) - return; + return -ENOMEM; *layer = &caifd->layer; spin_lock_init(&caifd->flow_lock); @@ -339,7 +340,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, strlcpy(caifd->layer.name, dev->name, sizeof(caifd->layer.name)); caifd->layer.transmit = transmit; - cfcnfg_add_phy_layer(cfg, + res = cfcnfg_add_phy_layer(cfg, dev, &caifd->layer, pref, @@ -349,6 +350,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, mutex_unlock(&caifdevs->lock); if (rcv_func) *rcv_func = receive; + return res; } EXPORT_SYMBOL(caif_enroll_dev); @@ -363,6 +365,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, struct cflayer *layer, *link_support; int head_room = 0; struct caif_device_entry_list *caifdevs; + int res; cfg = get_cfcnfg(dev_net(dev)); caifdevs = caif_device_list(dev_net(dev)); @@ -388,8 +391,10 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what, break; } } - caif_enroll_dev(dev, caifdev, link_support, head_room, + res = caif_enroll_dev(dev, caifdev, link_support, head_room, &layer, NULL); + if (res) + cfserl_release(link_support); caifdev->flowctrl = dev_flowctrl; break; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 4b31f0aaa96d..cab0b239f96a 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -539,7 +539,8 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg, goto err; ret = -EINVAL; - if (unlikely(msg->msg_iter.iov->iov_base == NULL)) + if (unlikely(msg->msg_iter.nr_segs == 0) || + unlikely(msg->msg_iter.iov->iov_base == NULL)) goto err; noblock = msg->msg_flags & MSG_DONTWAIT; @@ -1021,6 +1022,7 @@ static void caif_sock_destructor(struct sock *sk) return; } sk_stream_kill_queues(&cf_sk->sk); + WARN_ON(sk->sk_forward_alloc); caif_free_client(&cf_sk->layer); } diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c index 1a082a946045..609c5793f45a 100644 --- a/net/caif/caif_usb.c +++ b/net/caif/caif_usb.c @@ -116,6 +116,11 @@ static struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN], return (struct cflayer *) this; } +static void cfusbl_release(struct cflayer *layer) +{ + kfree(layer); +} + static struct packet_type caif_usb_type __read_mostly = { .type = cpu_to_be16(ETH_P_802_EX1), }; @@ -128,6 +133,10 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, struct cflayer *layer, *link_support; struct usbnet *usbnet; struct usb_device *usbdev; + int res; + + if (what == NETDEV_UNREGISTER && dev->reg_state >= NETREG_UNREGISTERED) + return 0; /* Check whether we have a NCM device, and find its VID/PID. */ if (!(dev->dev.parent && dev->dev.parent->driver && @@ -170,8 +179,11 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, if (dev->num_tx_queues > 1) pr_warn("USB device uses more than one tx queue\n"); - caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN, + res = caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN, &layer, &caif_usb_type.func); + if (res) + goto err; + if (!pack_added) dev_add_pack(&caif_usb_type); pack_added = true; @@ -179,6 +191,9 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what, strlcpy(layer->name, dev->name, sizeof(layer->name)); return 0; +err: + cfusbl_release(link_support); + return res; } static struct notifier_block caif_device_notifier = { diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index 8f00bea093b9..b456b79abd3b 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -450,7 +450,7 @@ unlock: rcu_read_unlock(); } -void +int cfcnfg_add_phy_layer(struct cfcnfg *cnfg, struct net_device *dev, struct cflayer *phy_layer, enum cfcnfg_phy_preference pref, @@ -459,7 +459,7 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, { struct cflayer *frml; struct cfcnfg_phyinfo *phyinfo = NULL; - int i; + int i, res = 0; u8 phyid; mutex_lock(&cnfg->lock); @@ -473,12 +473,15 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, goto got_phyid; } pr_warn("Too many CAIF Link Layers (max 6)\n"); + res = -EEXIST; goto out; got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); - if (!phyinfo) + if (!phyinfo) { + res = -ENOMEM; goto out_err; + } phy_layer->id = phyid; phyinfo->pref = pref; @@ -492,8 +495,10 @@ got_phyid: frml = cffrml_create(phyid, fcs); - if (!frml) + if (!frml) { + res = -ENOMEM; goto out_err; + } phyinfo->frm_layer = frml; layer_set_up(frml, cnfg->mux); @@ -511,11 +516,12 @@ got_phyid: list_add_rcu(&phyinfo->node, &cnfg->phys); out: mutex_unlock(&cnfg->lock); - return; + return res; out_err: kfree(phyinfo); mutex_unlock(&cnfg->lock); + return res; } EXPORT_SYMBOL(cfcnfg_add_phy_layer); diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index a1e85f032108..330cb2b087bb 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -269,11 +269,15 @@ int cfctrl_linkup_request(struct cflayer *layer, default: pr_warn("Request setup of bad link type = %d\n", param->linktype); + cfpkt_destroy(pkt); return -EINVAL; } req = kzalloc(sizeof(*req), GFP_KERNEL); - if (!req) + if (!req) { + cfpkt_destroy(pkt); return -ENOMEM; + } + req->client_layer = user_layer; req->cmd = CFCTRL_CMD_LINK_SETUP; req->param = *param; diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c index ce60f06d76de..af1e1e36dc90 100644 --- a/net/caif/cfserl.c +++ b/net/caif/cfserl.c @@ -31,6 +31,11 @@ static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt); static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, int phyid); +void cfserl_release(struct cflayer *layer) +{ + kfree(layer); +} + struct cflayer *cfserl_create(int instance, bool use_stx) { struct cfserl *this = kzalloc(sizeof(struct cfserl), GFP_ATOMIC); diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 13e2ae6be620..ece140ad0ac1 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -53,20 +53,6 @@ struct chnl_net { enum caif_states state; }; -static void robust_list_del(struct list_head *delete_node) -{ - struct list_head *list_node; - struct list_head *n; - ASSERT_RTNL(); - list_for_each_safe(list_node, n, &chnl_net_list) { - if (list_node == delete_node) { - list_del(list_node); - return; - } - } - WARN_ON(1); -} - static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) { struct sk_buff *skb; @@ -328,9 +314,6 @@ static int chnl_net_open(struct net_device *dev) if (result == 0) { pr_debug("connect timeout\n"); - caif_disconnect_client(dev_net(dev), &priv->chnl); - priv->state = CAIF_DISCONNECTED; - pr_debug("state disconnected\n"); result = -ETIMEDOUT; goto error; } @@ -368,6 +351,7 @@ static int chnl_net_init(struct net_device *dev) ASSERT_RTNL(); priv = netdev_priv(dev); strncpy(priv->name, dev->name, sizeof(priv->name)); + INIT_LIST_HEAD(&priv->list_field); return 0; } @@ -376,7 +360,7 @@ static void chnl_net_uninit(struct net_device *dev) struct chnl_net *priv; ASSERT_RTNL(); priv = netdev_priv(dev); - robust_list_del(&priv->list_field); + list_del_init(&priv->list_field); } static const struct net_device_ops netdev_ops = { @@ -541,7 +525,7 @@ static void __exit chnl_exit_module(void) rtnl_lock(); list_for_each_safe(list_node, _tmp, &chnl_net_list) { dev = list_entry(list_node, struct chnl_net, list_field); - list_del(list_node); + list_del_init(list_node); delete_device(dev); } rtnl_unlock(); diff --git a/net/can/af_can.c b/net/can/af_can.c index 04132b0b5d36..b3edb8092124 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -722,16 +722,25 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU || - cfd->len > CAN_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CAN_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, @@ -739,16 +748,25 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; - if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU || - cfd->len > CANFD_MAX_DLEN)) { - pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n", + if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n", + dev->type, skb->len); + goto free_skb; + } + + /* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */ + if (unlikely(cfd->len > CANFD_MAX_DLEN)) { + pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d, datalen %d\n", dev->type, skb->len, cfd->len); - kfree_skb(skb); - return NET_RX_DROP; + goto free_skb; } can_receive(skb, dev); return NET_RX_SUCCESS; + +free_skb: + kfree_skb(skb); + return NET_RX_DROP; } /* diff --git a/net/can/bcm.c b/net/can/bcm.c index 79bb8afa9c0c..1c9953c68f09 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -99,13 +99,13 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset) struct bcm_op { struct list_head list; + struct rcu_head rcu; int ifindex; canid_t can_id; u32 flags; unsigned long frames_abs, frames_filtered; struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; - struct tasklet_struct tsklet, thrtsklet; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; int rx_ifindex; int cfsiz; @@ -125,7 +125,7 @@ struct bcm_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; @@ -133,6 +133,10 @@ struct bcm_sock { char procname [32]; /* inode number in decimal with \0 */ }; +static LIST_HEAD(bcm_notifier_list); +static DEFINE_SPINLOCK(bcm_notifier_lock); +static struct bcm_sock *bcm_busy_notifier; + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -269,6 +273,7 @@ static void bcm_can_tx(struct bcm_op *op) struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; + int err; /* no target device? => exit */ if (!op->ifindex) @@ -293,11 +298,11 @@ static void bcm_can_tx(struct bcm_op *op) /* send with loopback */ skb->dev = dev; can_skb_set_owner(skb, op->sk); - can_send(skb, 1); + err = can_send(skb, 1); + if (!err) + op->frames_abs++; - /* update statistics */ op->currframe++; - op->frames_abs++; /* reached last frame? */ if (op->currframe >= op->nframes) @@ -370,29 +375,39 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, } } -static void bcm_tx_start_timer(struct bcm_op *op) +static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt) { + ktime_t ival; + if (op->kt_ival1 && op->count) - hrtimer_start(&op->timer, - ktime_add(ktime_get(), op->kt_ival1), - HRTIMER_MODE_ABS); + ival = op->kt_ival1; else if (op->kt_ival2) - hrtimer_start(&op->timer, - ktime_add(ktime_get(), op->kt_ival2), - HRTIMER_MODE_ABS); + ival = op->kt_ival2; + else + return false; + + hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival)); + return true; } -static void bcm_tx_timeout_tsklet(unsigned long data) +static void bcm_tx_start_timer(struct bcm_op *op) { - struct bcm_op *op = (struct bcm_op *)data; + if (bcm_tx_set_expiry(op, &op->timer)) + hrtimer_start_expires(&op->timer, HRTIMER_MODE_ABS_SOFT); +} + +/* bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */ +static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) +{ + struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { - op->count--; if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; @@ -405,22 +420,12 @@ static void bcm_tx_timeout_tsklet(unsigned long data) } bcm_can_tx(op); - } else if (op->kt_ival2) + } else if (op->kt_ival2) { bcm_can_tx(op); + } - bcm_tx_start_timer(op); -} - -/* - * bcm_tx_timeout_handler - performs cyclic CAN frame transmissions - */ -static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) -{ - struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); - - tasklet_schedule(&op->tsklet); - - return HRTIMER_NORESTART; + return bcm_tx_set_expiry(op, &op->timer) ? + HRTIMER_RESTART : HRTIMER_NORESTART; } /* @@ -440,6 +445,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) /* this element is not throttled anymore */ data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV); + memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; @@ -486,7 +492,7 @@ static void bcm_rx_update_and_send(struct bcm_op *op, /* do not send the saved data - only start throttle timer */ hrtimer_start(&op->thrtimer, ktime_add(op->kt_lastmsg, op->kt_ival2), - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_SOFT); return; } @@ -545,15 +551,23 @@ static void bcm_rx_starttimer(struct bcm_op *op) return; if (op->kt_ival1) - hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL); + hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } -static void bcm_rx_timeout_tsklet(unsigned long data) +/* bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out */ +static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) { - struct bcm_op *op = (struct bcm_op *)data; + struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; + /* if user wants to be informed, when cyclic CAN-Messages come back */ + if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { + /* clear received CAN frames to indicate 'nothing received' */ + memset(op->last_frames, 0, op->nframes * op->cfsiz); + } + /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; @@ -563,25 +577,6 @@ static void bcm_rx_timeout_tsklet(unsigned long data) msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); -} - -/* - * bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out - */ -static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) -{ - struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); - - /* schedule before NET_RX_SOFTIRQ */ - tasklet_hi_schedule(&op->tsklet); - - /* no restart of the timer is done here! */ - - /* if user wants to be informed, when cyclic CAN-Messages come back */ - if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { - /* clear received CAN frames to indicate 'nothing received' */ - memset(op->last_frames, 0, op->nframes * op->cfsiz); - } return HRTIMER_NORESTART; } @@ -589,14 +584,12 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) /* * bcm_rx_do_flush - helper for bcm_rx_thr_flush */ -static inline int bcm_rx_do_flush(struct bcm_op *op, int update, - unsigned int index) +static inline int bcm_rx_do_flush(struct bcm_op *op, unsigned int index) { struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; if ((op->last_frames) && (lcf->flags & RX_THR)) { - if (update) - bcm_rx_changed(op, lcf); + bcm_rx_changed(op, lcf); return 1; } return 0; @@ -604,11 +597,8 @@ static inline int bcm_rx_do_flush(struct bcm_op *op, int update, /* * bcm_rx_thr_flush - Check for throttled data and send it to the userspace - * - * update == 0 : just check if throttled data is available (any irq context) - * update == 1 : check and send throttled data to userspace (soft_irq context) */ -static int bcm_rx_thr_flush(struct bcm_op *op, int update) +static int bcm_rx_thr_flush(struct bcm_op *op) { int updated = 0; @@ -617,24 +607,16 @@ static int bcm_rx_thr_flush(struct bcm_op *op, int update) /* for MUX filter we start at index 1 */ for (i = 1; i < op->nframes; i++) - updated += bcm_rx_do_flush(op, update, i); + updated += bcm_rx_do_flush(op, i); } else { /* for RX_FILTER_ID and simple filter */ - updated += bcm_rx_do_flush(op, update, 0); + updated += bcm_rx_do_flush(op, 0); } return updated; } -static void bcm_rx_thr_tsklet(unsigned long data) -{ - struct bcm_op *op = (struct bcm_op *)data; - - /* push the changed data to the userspace */ - bcm_rx_thr_flush(op, 1); -} - /* * bcm_rx_thr_handler - the time for blocked content updates is over now: * Check for throttled data and send it to the userspace @@ -643,9 +625,7 @@ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer); - tasklet_schedule(&op->thrtsklet); - - if (bcm_rx_thr_flush(op, 0)) { + if (bcm_rx_thr_flush(op)) { hrtimer_forward(hrtimer, ktime_get(), op->kt_ival2); return HRTIMER_RESTART; } else { @@ -739,25 +719,9 @@ static struct bcm_op *bcm_find_op(struct list_head *ops, return NULL; } -static void bcm_remove_op(struct bcm_op *op) +static void bcm_free_op_rcu(struct rcu_head *rcu_head) { - if (op->tsklet.func) { - while (test_bit(TASKLET_STATE_SCHED, &op->tsklet.state) || - test_bit(TASKLET_STATE_RUN, &op->tsklet.state) || - hrtimer_active(&op->timer)) { - hrtimer_cancel(&op->timer); - tasklet_kill(&op->tsklet); - } - } - - if (op->thrtsklet.func) { - while (test_bit(TASKLET_STATE_SCHED, &op->thrtsklet.state) || - test_bit(TASKLET_STATE_RUN, &op->thrtsklet.state) || - hrtimer_active(&op->thrtimer)) { - hrtimer_cancel(&op->thrtimer); - tasklet_kill(&op->thrtsklet); - } - } + struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); @@ -768,6 +732,14 @@ static void bcm_remove_op(struct bcm_op *op) kfree(op); } +static void bcm_remove_op(struct bcm_op *op) +{ + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); + + call_rcu(&op->rcu, bcm_free_op_rcu); +} + static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) { if (op->rx_reg_dev == dev) { @@ -793,6 +765,9 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { + /* disable automatic timer on frame reception */ + op->flags |= RX_NO_AUTOTIMER; + /* * Don't care if we're bound or not (due to netdev * problems) can_rx_unregister() is always a save @@ -960,6 +935,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); + if (err < 0) + goto free_op; if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) @@ -969,12 +946,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, err = -EINVAL; } - if (err < 0) { - if (op->frames != &op->sframe) - kfree(op->frames); - kfree(op); - return err; - } + if (err < 0) + goto free_op; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ @@ -990,15 +963,13 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ - hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_tx_timeout_handler; - /* initialize tasklet for tx countevent notification */ - tasklet_init(&op->tsklet, bcm_tx_timeout_tsklet, - (unsigned long) op); - /* currently unused in tx_ops */ - hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); /* add this bcm_op to the list of the tx_ops */ list_add(&op->list, &bo->tx_ops); @@ -1047,6 +1018,12 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_tx_start_timer(op); return msg_head->nframes * op->cfsiz + MHSIZ; + +free_op: + if (op->frames != &op->sframe) + kfree(op->frames); + kfree(op); + return err; } /* @@ -1167,20 +1144,14 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->rx_ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ - hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_rx_timeout_handler; - /* initialize tasklet for rx timeout notification */ - tasklet_init(&op->tsklet, bcm_rx_timeout_tsklet, - (unsigned long) op); - - hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_SOFT); op->thrtimer.function = bcm_rx_thr_handler; - /* initialize tasklet for rx throttle handling */ - tasklet_init(&op->thrtsklet, bcm_rx_thr_tsklet, - (unsigned long) op); - /* add this bcm_op to the list of the rx_ops */ list_add(&op->list, &bo->rx_ops); @@ -1226,12 +1197,12 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, */ op->kt_lastmsg = 0; hrtimer_cancel(&op->thrtimer); - bcm_rx_thr_flush(op, 1); + bcm_rx_thr_flush(op); } if ((op->flags & STARTTIMER) && op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, - HRTIMER_MODE_REL); + HRTIMER_MODE_REL_SOFT); } /* now we can register for can_ids, if we added a new bcm_op */ @@ -1429,20 +1400,15 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* * notification handler for netdevice status changes */ -static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void bcm_notify(struct bcm_sock *bo, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; switch (msg) { @@ -1477,7 +1443,28 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); } } +} + +static int bcm_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + spin_lock(&bcm_notifier_lock); + list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { + spin_unlock(&bcm_notifier_lock); + bcm_notify(bcm_busy_notifier, msg, dev); + spin_lock(&bcm_notifier_lock); + } + bcm_busy_notifier = NULL; + spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } @@ -1497,9 +1484,9 @@ static int bcm_init(struct sock *sk) INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ - bo->notifier.notifier_call = bcm_notifier; - - register_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + list_add_tail(&bo->notifier, &bcm_notifier_list); + spin_unlock(&bcm_notifier_lock); return 0; } @@ -1522,10 +1509,23 @@ static int bcm_release(struct socket *sock) /* remove bcm_ops, timer, rx_unregister(), etc. */ - unregister_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + while (bcm_busy_notifier == bo) { + spin_unlock(&bcm_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&bcm_notifier_lock); + } + list_del(&bo->notifier); + spin_unlock(&bcm_notifier_lock); lock_sock(sk); +#if IS_ENABLED(CONFIG_PROC_FS) + /* remove procfs entry */ + if (net->can.bcmproc_dir && bo->bcm_proc_read) + remove_proc_entry(bo->procname, net->can.bcmproc_dir); +#endif /* CONFIG_PROC_FS */ + list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); @@ -1554,14 +1554,12 @@ static int bcm_release(struct socket *sock) REGMASK(op->can_id), bcm_rx_handler, op); - bcm_remove_op(op); } -#if IS_ENABLED(CONFIG_PROC_FS) - /* remove procfs entry */ - if (net->can.bcmproc_dir && bo->bcm_proc_read) - remove_proc_entry(bo->procname, net->can.bcmproc_dir); -#endif /* CONFIG_PROC_FS */ + synchronize_rcu(); + + list_for_each_entry_safe(op, next, &bo->rx_ops, list) + bcm_remove_op(op); /* remove device reference */ if (bo->bound) { @@ -1737,6 +1735,10 @@ static struct pernet_operations canbcm_pernet_ops __read_mostly = { .exit = canbcm_pernet_exit, }; +static struct notifier_block canbcm_notifier = { + .notifier_call = bcm_notifier +}; + static int __init bcm_module_init(void) { int err; @@ -1750,12 +1752,14 @@ static int __init bcm_module_init(void) } register_pernet_subsys(&canbcm_pernet_ops); + register_netdevice_notifier(&canbcm_notifier); return 0; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); + unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } diff --git a/net/can/gw.c b/net/can/gw.c index bd2161470e45..9c2066323529 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -494,6 +494,7 @@ static int cgw_notifier(struct notifier_block *nb, if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -941,6 +942,7 @@ static void cgw_remove_all_jobs(struct net *net) hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -1010,6 +1012,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); err = 0; break; diff --git a/net/can/proc.c b/net/can/proc.c index 70fea17bb04c..a3071f43acd7 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -467,6 +467,9 @@ void can_init_proc(struct net *net) */ void can_remove_proc(struct net *net) { + if (!net->can.proc_dir) + return; + if (net->can.pde_version) remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir); @@ -494,6 +497,5 @@ void can_remove_proc(struct net *net) if (net->can.pde_rcvlist_sff) remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir); - if (net->can.proc_dir) - remove_proc_entry("can", net->proc_net); + remove_proc_entry("can", net->proc_net); } diff --git a/net/can/raw.c b/net/can/raw.c index 3aab7664933f..2a6db8752b61 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,7 +84,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; @@ -96,6 +96,10 @@ struct raw_sock { struct uniqframe __percpu *uniq; }; +static LIST_HEAD(raw_notifier_list); +static DEFINE_SPINLOCK(raw_notifier_lock); +static struct raw_sock *raw_busy_notifier; + /* * Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' @@ -266,21 +270,16 @@ static int raw_enable_allfilters(struct net *net, struct net_device *dev, return err; } -static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *ptr) +static void raw_notify(struct raw_sock *ro, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (ro->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { @@ -309,7 +308,28 @@ static int raw_notifier(struct notifier_block *nb, sk->sk_error_report(sk); break; } +} + +static int raw_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + spin_lock(&raw_notifier_lock); + list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { + spin_unlock(&raw_notifier_lock); + raw_notify(raw_busy_notifier, msg, dev); + spin_lock(&raw_notifier_lock); + } + raw_busy_notifier = NULL; + spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } @@ -338,9 +358,9 @@ static int raw_init(struct sock *sk) return -ENOMEM; /* set notifier */ - ro->notifier.notifier_call = raw_notifier; - - register_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + list_add_tail(&ro->notifier, &raw_notifier_list); + spin_unlock(&raw_notifier_lock); return 0; } @@ -355,7 +375,14 @@ static int raw_release(struct socket *sock) ro = raw_sk(sk); - unregister_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + while (raw_busy_notifier == ro) { + spin_unlock(&raw_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&raw_notifier_lock); + } + list_del(&ro->notifier); + spin_unlock(&raw_notifier_lock); lock_sock(sk); @@ -522,10 +549,18 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; } + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + if (count > 1) + kfree(filter); + err = -ENODEV; + goto out_fil; + } + } if (ro->bound) { /* (try to) register the new filters */ @@ -564,6 +599,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; @@ -576,10 +612,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, err_mask &= CAN_ERR_MASK; + rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) + if (ro->bound && ro->ifindex) { dev = dev_get_by_index(sock_net(sk), ro->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + } /* remove current error mask */ if (ro->bound) { @@ -603,6 +645,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, dev_put(dev); release_sock(sk); + rtnl_unlock(); break; @@ -771,7 +814,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err < 0) goto free_skb; - sock_tx_timestamp(sk, sk->sk_tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sk->sk_tsflags); skb->dev = dev; skb->sk = sk; @@ -870,6 +913,10 @@ static const struct can_proto raw_can_proto = { .prot = &raw_proto, }; +static struct notifier_block canraw_notifier = { + .notifier_call = raw_notifier +}; + static __init int raw_module_init(void) { int err; @@ -879,6 +926,8 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) printk(KERN_ERR "can: registration of raw protocol failed\n"); + else + register_netdevice_notifier(&canraw_notifier); return err; } @@ -886,6 +935,7 @@ static __init int raw_module_init(void) static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); + unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index f7d7f32ac673..7fd18e10755e 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -462,7 +462,7 @@ static void set_sock_callbacks(struct socket *sock, */ static int ceph_tcp_connect(struct ceph_connection *con) { - struct sockaddr_storage *paddr = &con->peer_addr.in_addr; + struct sockaddr_storage ss = con->peer_addr.in_addr; /* align */ struct socket *sock; unsigned int noio_flag; int ret; @@ -471,7 +471,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) /* sock_create_kern() allocates with GFP_KERNEL */ noio_flag = memalloc_noio_save(); - ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family, + ret = sock_create_kern(read_pnet(&con->msgr->net), ss.ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); memalloc_noio_restore(noio_flag); if (ret) @@ -487,8 +487,8 @@ static int ceph_tcp_connect(struct ceph_connection *con) dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr)); con_sock_state_connecting(con); - ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr), - O_NONBLOCK); + ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss), + O_NONBLOCK); if (ret == -EINPROGRESS) { dout("connect %s EINPROGRESS sk_state = %u\n", ceph_pr_addr(&con->peer_addr.in_addr), @@ -1824,14 +1824,15 @@ static int verify_hello(struct ceph_connection *con) return 0; } -static bool addr_is_blank(struct sockaddr_storage *ss) +static bool addr_is_blank(struct ceph_entity_addr *addr) { - struct in_addr *addr = &((struct sockaddr_in *)ss)->sin_addr; - struct in6_addr *addr6 = &((struct sockaddr_in6 *)ss)->sin6_addr; + struct sockaddr_storage ss = addr->in_addr; /* align */ + struct in_addr *addr4 = &((struct sockaddr_in *)&ss)->sin_addr; + struct in6_addr *addr6 = &((struct sockaddr_in6 *)&ss)->sin6_addr; - switch (ss->ss_family) { + switch (ss.ss_family) { case AF_INET: - return addr->s_addr == htonl(INADDR_ANY); + return addr4->s_addr == htonl(INADDR_ANY); case AF_INET6: return ipv6_addr_any(addr6); default: @@ -1839,25 +1840,25 @@ static bool addr_is_blank(struct sockaddr_storage *ss) } } -static int addr_port(struct sockaddr_storage *ss) +static int addr_port(struct ceph_entity_addr *addr) { - switch (ss->ss_family) { + switch (get_unaligned(&addr->in_addr.ss_family)) { case AF_INET: - return ntohs(((struct sockaddr_in *)ss)->sin_port); + return ntohs(get_unaligned(&((struct sockaddr_in *)&addr->in_addr)->sin_port)); case AF_INET6: - return ntohs(((struct sockaddr_in6 *)ss)->sin6_port); + return ntohs(get_unaligned(&((struct sockaddr_in6 *)&addr->in_addr)->sin6_port)); } return 0; } -static void addr_set_port(struct sockaddr_storage *ss, int p) +static void addr_set_port(struct ceph_entity_addr *addr, int p) { - switch (ss->ss_family) { + switch (get_unaligned(&addr->in_addr.ss_family)) { case AF_INET: - ((struct sockaddr_in *)ss)->sin_port = htons(p); + put_unaligned(htons(p), &((struct sockaddr_in *)&addr->in_addr)->sin_port); break; case AF_INET6: - ((struct sockaddr_in6 *)ss)->sin6_port = htons(p); + put_unaligned(htons(p), &((struct sockaddr_in6 *)&addr->in_addr)->sin6_port); break; } } @@ -1865,21 +1866,18 @@ static void addr_set_port(struct sockaddr_storage *ss, int p) /* * Unlike other *_pton function semantics, zero indicates success. */ -static int ceph_pton(const char *str, size_t len, struct sockaddr_storage *ss, +static int ceph_pton(const char *str, size_t len, struct ceph_entity_addr *addr, char delim, const char **ipend) { - struct sockaddr_in *in4 = (struct sockaddr_in *) ss; - struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) ss; - - memset(ss, 0, sizeof(*ss)); + memset(&addr->in_addr, 0, sizeof(addr->in_addr)); - if (in4_pton(str, len, (u8 *)&in4->sin_addr.s_addr, delim, ipend)) { - ss->ss_family = AF_INET; + if (in4_pton(str, len, (u8 *)&((struct sockaddr_in *)&addr->in_addr)->sin_addr.s_addr, delim, ipend)) { + put_unaligned(AF_INET, &addr->in_addr.ss_family); return 0; } - if (in6_pton(str, len, (u8 *)&in6->sin6_addr.s6_addr, delim, ipend)) { - ss->ss_family = AF_INET6; + if (in6_pton(str, len, (u8 *)&((struct sockaddr_in6 *)&addr->in_addr)->sin6_addr.s6_addr, delim, ipend)) { + put_unaligned(AF_INET6, &addr->in_addr.ss_family); return 0; } @@ -1891,7 +1889,7 @@ static int ceph_pton(const char *str, size_t len, struct sockaddr_storage *ss, */ #ifdef CONFIG_CEPH_LIB_USE_DNS_RESOLVER static int ceph_dns_resolve_name(const char *name, size_t namelen, - struct sockaddr_storage *ss, char delim, const char **ipend) + struct ceph_entity_addr *addr, char delim, const char **ipend) { const char *end, *delim_p; char *colon_p, *ip_addr = NULL; @@ -1920,7 +1918,7 @@ static int ceph_dns_resolve_name(const char *name, size_t namelen, /* do dns_resolve upcall */ ip_len = dns_query(NULL, name, end - name, NULL, &ip_addr, NULL); if (ip_len > 0) - ret = ceph_pton(ip_addr, ip_len, ss, -1, NULL); + ret = ceph_pton(ip_addr, ip_len, addr, -1, NULL); else ret = -ESRCH; @@ -1929,13 +1927,13 @@ static int ceph_dns_resolve_name(const char *name, size_t namelen, *ipend = end; pr_info("resolve '%.*s' (ret=%d): %s\n", (int)(end - name), name, - ret, ret ? "failed" : ceph_pr_addr(ss)); + ret, ret ? "failed" : ceph_pr_addr(&addr->in_addr)); return ret; } #else static inline int ceph_dns_resolve_name(const char *name, size_t namelen, - struct sockaddr_storage *ss, char delim, const char **ipend) + struct ceph_entity_addr *addr, char delim, const char **ipend) { return -EINVAL; } @@ -1946,13 +1944,13 @@ static inline int ceph_dns_resolve_name(const char *name, size_t namelen, * then try to extract a hostname to resolve using userspace DNS upcall. */ static int ceph_parse_server_name(const char *name, size_t namelen, - struct sockaddr_storage *ss, char delim, const char **ipend) + struct ceph_entity_addr *addr, char delim, const char **ipend) { int ret; - ret = ceph_pton(name, namelen, ss, delim, ipend); + ret = ceph_pton(name, namelen, addr, delim, ipend); if (ret) - ret = ceph_dns_resolve_name(name, namelen, ss, delim, ipend); + ret = ceph_dns_resolve_name(name, namelen, addr, delim, ipend); return ret; } @@ -1971,7 +1969,6 @@ int ceph_parse_ips(const char *c, const char *end, dout("parse_ips on '%.*s'\n", (int)(end-c), c); for (i = 0; i < max_count; i++) { const char *ipend; - struct sockaddr_storage *ss = &addr[i].in_addr; int port; char delim = ','; @@ -1980,7 +1977,7 @@ int ceph_parse_ips(const char *c, const char *end, p++; } - ret = ceph_parse_server_name(p, end - p, ss, delim, &ipend); + ret = ceph_parse_server_name(p, end - p, &addr[i], delim, &ipend); if (ret) goto bad; ret = -EINVAL; @@ -2011,9 +2008,9 @@ int ceph_parse_ips(const char *c, const char *end, port = CEPH_MON_PORT; } - addr_set_port(ss, port); + addr_set_port(&addr[i], port); - dout("parse_ips got %s\n", ceph_pr_addr(ss)); + dout("parse_ips got %s\n", ceph_pr_addr(&addr[i].in_addr)); if (p == end) break; @@ -2052,7 +2049,7 @@ static int process_banner(struct ceph_connection *con) */ if (memcmp(&con->peer_addr, &con->actual_peer_addr, sizeof(con->peer_addr)) != 0 && - !(addr_is_blank(&con->actual_peer_addr.in_addr) && + !(addr_is_blank(&con->actual_peer_addr) && con->actual_peer_addr.nonce == con->peer_addr.nonce)) { pr_warn("wrong peer, want %s/%d, got %s/%d\n", ceph_pr_addr(&con->peer_addr.in_addr), @@ -2066,13 +2063,13 @@ static int process_banner(struct ceph_connection *con) /* * did we learn our address? */ - if (addr_is_blank(&con->msgr->inst.addr.in_addr)) { - int port = addr_port(&con->msgr->inst.addr.in_addr); + if (addr_is_blank(&con->msgr->inst.addr)) { + int port = addr_port(&con->msgr->inst.addr); memcpy(&con->msgr->inst.addr.in_addr, &con->peer_addr_for_me.in_addr, sizeof(con->peer_addr_for_me.in_addr)); - addr_set_port(&con->msgr->inst.addr.in_addr, port); + addr_set_port(&con->msgr->inst.addr, port); encode_my_addr(con->msgr); dout("process_banner learned my addr is %s\n", ceph_pr_addr(&con->msgr->inst.addr.in_addr)); @@ -3037,6 +3034,11 @@ static void con_fault(struct ceph_connection *con) ceph_msg_put(con->in_msg); con->in_msg = NULL; } + if (con->out_msg) { + BUG_ON(con->out_msg->con != con); + ceph_msg_put(con->out_msg); + con->out_msg = NULL; + } /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 713fe1fbcb18..90ebb0ba927c 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -3137,17 +3137,24 @@ static int linger_reg_commit_wait(struct ceph_osd_linger_request *lreq) int ret; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->reg_commit_wait); + ret = wait_for_completion_killable(&lreq->reg_commit_wait); return ret ?: lreq->reg_commit_error; } -static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq) +static int linger_notify_finish_wait(struct ceph_osd_linger_request *lreq, + unsigned long timeout) { - int ret; + long left; dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - ret = wait_for_completion_interruptible(&lreq->notify_finish_wait); - return ret ?: lreq->notify_finish_error; + left = wait_for_completion_killable_timeout(&lreq->notify_finish_wait, + ceph_timeout_jiffies(timeout)); + if (left <= 0) + left = left ?: -ETIMEDOUT; + else + left = lreq->notify_finish_error; /* completed */ + + return left; } /* @@ -4760,7 +4767,8 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, ret = linger_reg_commit_wait(lreq); if (!ret) - ret = linger_notify_finish_wait(lreq); + ret = linger_notify_finish_wait(lreq, + msecs_to_jiffies(2 * timeout * MSEC_PER_SEC)); else dout("lreq %p failed to initiate notify %d\n", lreq, ret); diff --git a/net/compat.c b/net/compat.c index 2a8c7cb5f06a..2778a236e091 100644 --- a/net/compat.c +++ b/net/compat.c @@ -158,7 +158,7 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, if (kcmlen > stackbuf_size) kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL); if (kcmsg == NULL) - return -ENOBUFS; + return -ENOMEM; /* Now copy them over neatly. */ memset(kcmsg, 0, kcmlen); diff --git a/net/core/datagram.c b/net/core/datagram.c index 865a8cb7b0bd..6ba82eb14b46 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -837,18 +837,21 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) + if (READ_ONCE(sk->sk_err) || + !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ @@ -857,10 +860,12 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, /* Connection-based need to check for termination and startup */ if (connection_based(sk)) { - if (sk->sk_state == TCP_CLOSE) + int state = READ_ONCE(sk->sk_state); + + if (state == TCP_CLOSE) mask |= EPOLLHUP; /* connection hasn't started yet? */ - if (sk->sk_state == TCP_SYN_SENT) + if (state == TCP_SYN_SENT) return mask; } diff --git a/net/core/dev.c b/net/core/dev.c index c77d12a35f92..b5c9648c2192 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2303,6 +2303,8 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, bool active = false; unsigned int nr_ids; + WARN_ON_ONCE(index >= dev->num_tx_queues); + if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; @@ -2648,6 +2650,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); + dev_qdisc_change_real_num_tx(dev, txq); + dev->real_num_tx_queues = txq; if (disabling) { @@ -2792,8 +2796,10 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_irq() || irqs_disabled()) __dev_kfree_skb_irq(skb, reason); + else if (unlikely(reason == SKB_REASON_DROPPED)) + kfree_skb(skb); else - dev_kfree_skb(skb); + consume_skb(skb); } EXPORT_SYMBOL(__dev_kfree_skb_any); @@ -2846,6 +2852,12 @@ static u16 skb_tx_hash(const struct net_device *dev, qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; + if (unlikely(!qcount)) { + net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", + sb_dev->name, qoffset, tc); + qoffset = 0; + qcount = dev->real_num_tx_queues; + } } if (skb_rx_queue_recorded(skb)) { @@ -3188,6 +3200,14 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, if (gso_segs > dev->gso_max_segs) return features & ~NETIF_F_GSO_MASK; + if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size))) + return features & ~NETIF_F_GSO_MASK; + + if (!skb_shinfo(skb)->gso_type) { + skb_warn_bad_offload(skb); + return features & ~NETIF_F_GSO_MASK; + } + /* Support for GSO partial features requires software * intervention before we can actually process the packets * so we need to strip support for any partial features now @@ -3823,7 +3843,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - if (txq->xmit_lock_owner != cpu) { + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; @@ -4049,8 +4072,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, u32 next_cpu; u32 ident; - /* First check into global flow table if there is a match */ - ident = sock_flow_table->ents[hash & sock_flow_table->mask]; + /* First check into global flow table if there is a match. + * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). + */ + ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~rps_cpu_mask) goto try_rps; @@ -4463,7 +4488,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_rx(skb); @@ -4783,7 +4808,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!netdev_tstamp_prequeue, skb); + net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5135,7 +5160,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5165,7 +5190,7 @@ static void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(netdev_tstamp_prequeue, skb); + net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5400,7 +5425,8 @@ static void skb_gro_reset_offset(struct sk_buff *skb) if (skb_mac_header(skb) == skb_tail_pointer(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0))) { + !PageHighMem(skb_frag_page(frag0)) && + (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, skb_frag_size(frag0), @@ -5839,7 +5865,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = dev_rx_weight; + napi->weight = READ_ONCE(dev_rx_weight); while (again) { struct sk_buff *skb; @@ -5931,11 +5957,18 @@ EXPORT_SYMBOL(napi_schedule_prep); * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * - * Variant of __napi_schedule() assuming hard irqs are masked + * Variant of __napi_schedule() assuming hard irqs are masked. + * + * On PREEMPT_RT enabled kernels this maps to __napi_schedule() + * because the interrupt disabled assumption might not be true + * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { - ____napi_schedule(this_cpu_ptr(&softnet_data), n); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + else + __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); @@ -6316,8 +6349,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(netdev_budget_usecs); - int budget = netdev_budget; + usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); + int budget = READ_ONCE(netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -8351,6 +8384,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, } } + if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { + netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_RX; + } + return features; } @@ -8980,9 +9018,7 @@ void netdev_run_todo(void) BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); -#if IS_ENABLED(CONFIG_DECNET) - WARN_ON(dev->dn_ptr); -#endif + if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) @@ -9007,24 +9043,16 @@ void netdev_run_todo(void) void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { -#if BITS_PER_LONG == 64 - BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); - memcpy(stats64, netdev_stats, sizeof(*netdev_stats)); - /* zero out counters that only exist in rtnl_link_stats64 */ - memset((char *)stats64 + sizeof(*netdev_stats), 0, - sizeof(*stats64) - sizeof(*netdev_stats)); -#else - size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long); - const unsigned long *src = (const unsigned long *)netdev_stats; + size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); + const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = src[i]; + dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); -#endif } EXPORT_SYMBOL(netdev_stats_to_stats64); @@ -9703,7 +9731,7 @@ static void __net_exit default_device_exit(struct net *net) continue; /* Leave virtual devices for the generic cleanup */ - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ diff --git a/net/core/devlink.c b/net/core/devlink.c index a77e3777c8dd..6ad095264896 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1113,7 +1113,7 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, pool_index, &cur, &max); if (err && err != -EOPNOTSUPP) - return err; + goto sb_occ_get_failure; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; @@ -1126,8 +1126,10 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, return 0; nla_put_failure: + err = -EMSGSIZE; +sb_occ_get_failure: genlmsg_cancel(msg, hdr); - return -EMSGSIZE; + return err; } static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 3978a5e8d261..52e559252a9e 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -122,7 +122,7 @@ out: } static const struct genl_multicast_group dropmon_mcgrps[] = { - { .name = "events", }, + { .name = "events", .cap_sys_admin = 1 }, }; static void send_dm_alert(struct work_struct *work) @@ -219,13 +219,17 @@ static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi, rcu_read_lock(); list_for_each_entry_rcu(new_stat, &hw_stats_list, list) { + struct net_device *dev; + /* * only add a note to our monitor buffer if: * 1) this is the dev we received on * 2) its after the last_rx delta * 3) our rx_dropped count has gone up */ - if ((new_stat->dev == napi->dev) && + /* Paired with WRITE_ONCE() in dropmon_net_event() */ + dev = READ_ONCE(new_stat->dev); + if ((dev == napi->dev) && (time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) && (napi->dev->stats.rx_dropped != new_stat->last_drop_val)) { trace_drop_common(NULL, NULL); @@ -340,7 +344,10 @@ static int dropmon_net_event(struct notifier_block *ev_block, mutex_lock(&trace_state_mutex); list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) { if (new_stat->dev == dev) { - new_stat->dev = NULL; + + /* Paired with READ_ONCE() in trace_napi_poll_hit() */ + WRITE_ONCE(new_stat->dev, NULL); + if (trace_state == TRACE_OFF) { list_del_rcu(&new_stat->list); kfree_rcu(new_stat, rcu); @@ -363,10 +370,12 @@ static const struct genl_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_START, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, }; diff --git a/net/core/dst.c b/net/core/dst.c index 81ccf20e2826..1b1677683b97 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -97,10 +97,10 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, { struct dst_entry *dst; - if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) - return NULL; - } + if (ops->gc && + !(flags & DST_NOCOUNT) && + dst_entries_get_fast(ops) > ops->gc_thresh) + ops->gc(ops); dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 1011625a0ca4..d007f1cca64c 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -618,7 +618,7 @@ store_link_ksettings_for_user(void __user *to, { struct ethtool_link_usettings link_usettings; - memcpy(&link_usettings.base, &from->base, sizeof(link_usettings)); + memcpy(&link_usettings, from, sizeof(link_usettings)); bitmap_to_arr32(link_usettings.link_modes.supported, from->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -1594,7 +1594,7 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, if (eeprom.offset + eeprom.len > total_len) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1659,7 +1659,7 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1840,7 +1840,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) return -EFAULT; test.len = test_len; - data = kmalloc_array(test_len, sizeof(u64), GFP_USER); + data = kcalloc(test_len, sizeof(u64), GFP_USER); if (!data) return -ENOMEM; @@ -2023,7 +2023,8 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) return n_stats; if (n_stats > S32_MAX / sizeof(u64)) return -ENOMEM; - WARN_ON_ONCE(!n_stats); + if (WARN_ON_ONCE(!n_stats)) + return -EOPNOTSUPP; if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; @@ -2372,7 +2373,7 @@ static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; ret = ops->get_tunable(dev, &tuna, data); @@ -2552,7 +2553,7 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; mutex_lock(&phydev->lock); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 8916c5d9b3b3..46a13ed15c4e 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -1105,7 +1105,7 @@ static void notify_rule_change(int event, struct fib_rule *rule, { struct net *net; struct sk_buff *skb; - int err = -ENOBUFS; + int err = -ENOMEM; net = ops->fro_net; skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); diff --git a/net/core/filter.c b/net/core/filter.c index 557bd5cc8f94..dea7132f3813 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1666,7 +1666,7 @@ BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; - if (unlikely(offset > 0xffff)) + if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; @@ -1701,7 +1701,7 @@ BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, { void *ptr; - if (unlikely(offset > 0xffff)) + if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); @@ -2025,6 +2025,10 @@ static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, if (mlen) { __skb_pull(skb, mlen); + if (unlikely(!skb->len)) { + kfree_skb(skb); + return -ERANGE; + } /* At ingress, the mac header has already been pulled once. * At egress, skb_pospull_rcsum has to be done in case that @@ -2561,15 +2565,18 @@ static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) { + void *old_data; + /* skb_ensure_writable() is not needed here, as we're * already working on an uncloned skb. */ if (unlikely(!pskb_may_pull(skb, off + len))) return -ENOMEM; - skb_postpull_rcsum(skb, skb->data + off, len); - memmove(skb->data + len, skb->data, off); + old_data = skb->data; __skb_pull(skb, len); + skb_postpull_rcsum(skb, old_data + off, len); + memmove(skb->data, old_data, off); return 0; } @@ -2639,8 +2646,6 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) shinfo->gso_type |= SKB_GSO_TCPV6; } - /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_decrease_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; @@ -2680,8 +2685,6 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) shinfo->gso_type |= SKB_GSO_TCPV4; } - /* Due to IPv4 header, MSS can be upgraded. */ - skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; @@ -2836,18 +2839,14 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) return 0; } -static u32 __bpf_skb_max_len(const struct sk_buff *skb) -{ - return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : - SKB_MAX_ALLOC; -} +#define BPF_SKB_MAX_LEN SKB_MAX_ALLOC static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) { bool trans_same = skb->transport_header == skb->network_header; u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); - u32 len_max = __bpf_skb_max_len(skb); + u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb_protocol(skb, true); bool shrink = len_diff < 0; int ret; @@ -2926,7 +2925,7 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; @@ -3002,7 +3001,7 @@ static const struct bpf_func_proto sk_skb_change_tail_proto = { static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { - u32 max_len = __bpf_skb_max_len(skb); + u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; @@ -3024,6 +3023,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); + skb_reset_mac_len(skb); } return ret; @@ -4235,7 +4235,6 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; - params->ifindex = dev->ifindex; return 0; } @@ -4333,6 +4332,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->ipv4_dst = nh->nh_gw; params->rt_metric = res.fi->fib_priority; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here @@ -4447,6 +4447,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, dev = f6i->fib6_nh.nh_dev; params->rt_metric = f6i->fib6_metric; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. Can not use __ipv6_neigh_lookup_noref here @@ -4500,6 +4501,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, { struct net *net = dev_net(skb->dev); int rc = -EAFNOSUPPORT; + bool check_mtu = false; if (plen < sizeof(*params)) return -EINVAL; @@ -4507,22 +4509,28 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, if (flags & ~(BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT)) return -EINVAL; + if (params->tot_len) + check_mtu = true; + switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: - rc = bpf_ipv4_fib_lookup(net, params, flags, false); + rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - rc = bpf_ipv6_fib_lookup(net, params, flags, false); + rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu); break; #endif } - if (!rc) { + if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) { struct net_device *dev; + /* When tot_len isn't provided by user, check skb + * against MTU of FIB lookup resulting net_device + */ dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; @@ -4570,7 +4578,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len if (err) return err; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); @@ -5534,9 +5541,9 @@ void bpf_warn_invalid_xdp_action(u32 act) { const u32 act_max = XDP_REDIRECT; - WARN_ONCE(1, "%s XDP return value %u, expect packet loss!\n", - act > act_max ? "Illegal" : "Driver unsupported", - act); + pr_warn_once("%s XDP return value %u, expect packet loss!\n", + act > act_max ? "Illegal" : "Driver unsupported", + act); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 994dd1520f07..da860a680256 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -694,8 +694,10 @@ proto_again: FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container); - memcpy(&key_addrs->v4addrs, &iph->saddr, - sizeof(key_addrs->v4addrs)); + memcpy(&key_addrs->v4addrs.src, &iph->saddr, + sizeof(key_addrs->v4addrs.src)); + memcpy(&key_addrs->v4addrs.dst, &iph->daddr, + sizeof(key_addrs->v4addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } @@ -744,8 +746,10 @@ proto_again: FLOW_DISSECTOR_KEY_IPV6_ADDRS, target_container); - memcpy(&key_addrs->v6addrs, &iph->saddr, - sizeof(key_addrs->v6addrs)); + memcpy(&key_addrs->v6addrs.src, &iph->saddr, + sizeof(key_addrs->v6addrs.src)); + memcpy(&key_addrs->v6addrs.dst, &iph->daddr, + sizeof(key_addrs->v6addrs.dst)); key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } @@ -823,6 +827,7 @@ proto_again: VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } key_vlan->vlan_tpid = saved_vlan_tpid; + key_vlan->vlan_eth_type = proto; } fdret = FLOW_DISSECT_RET_PROTO_AGAIN; diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index e4e442d70c2d..752744db11ff 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -84,11 +84,11 @@ static void est_timer(struct timer_list *t) u64 rate, brate; est_fetch_counters(est, &b); - brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log); - brate -= (est->avbps >> est->ewma_log); + brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); + brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); - rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log); - rate -= (est->avpps >> est->ewma_log); + rate = (u64)(b.packets - est->last_packets) << (10 - est->intvl_log); + rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); est->avbps += brate; @@ -147,6 +147,9 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, if (parm->interval < -2 || parm->interval > 3) return -EINVAL; + if (parm->ewma_log == 0 || parm->ewma_log >= 31) + return -EINVAL; + est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS; diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index a648568c5e8f..4a5f4fbffd83 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -44,12 +44,11 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, { int ret; - /* Preempt disable is needed to protect per-cpu redirect_info between - * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and - * access to maps strictly require a rcu_read_lock() for protection, - * mixing with BH RCU lock doesn't work. + /* Preempt disable and BH disable are needed to protect per-cpu + * redirect_info between BPF prog and skb_do_redirect(). */ preempt_disable(); + local_bh_disable(); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -82,6 +81,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, break; } + local_bh_enable(); preempt_enable(); return ret; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6e890f51b7d8..5b6f3175d55b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -224,11 +224,26 @@ static int neigh_del_timer(struct neighbour *n) return 0; } -static void pneigh_queue_purge(struct sk_buff_head *list) +static void pneigh_queue_purge(struct sk_buff_head *list, struct net *net) { + struct sk_buff_head tmp; + unsigned long flags; struct sk_buff *skb; - while ((skb = skb_dequeue(list)) != NULL) { + skb_queue_head_init(&tmp); + spin_lock_irqsave(&list->lock, flags); + skb = skb_peek(list); + while (skb != NULL) { + struct sk_buff *skb_next = skb_peek_next(skb, list); + if (net == NULL || net_eq(dev_net(skb->dev), net)) { + __skb_unlink(skb, list); + __skb_queue_tail(&tmp, skb); + } + skb = skb_next; + } + spin_unlock_irqrestore(&list->lock, flags); + + while ((skb = __skb_dequeue(&tmp))) { dev_put(skb->dev); kfree_skb(skb); } @@ -297,9 +312,9 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev); pneigh_ifdown_and_unlock(tbl, dev); - - del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); + if (skb_queue_empty_lockless(&tbl->proxy_queue)) + del_timer_sync(&tbl->proxy_timer); return 0; } EXPORT_SYMBOL(neigh_ifdown); @@ -461,37 +476,6 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, } EXPORT_SYMBOL(neigh_lookup); -struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, - const void *pkey) -{ - struct neighbour *n; - unsigned int key_len = tbl->key_len; - u32 hash_val; - struct neigh_hash_table *nht; - - NEIGH_CACHE_STAT_INC(tbl, lookups); - - rcu_read_lock_bh(); - nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift); - - for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); - n != NULL; - n = rcu_dereference_bh(n->next)) { - if (!memcmp(n->primary_key, pkey, key_len) && - net_eq(dev_net(n->dev), net)) { - if (!refcount_inc_not_zero(&n->refcnt)) - n = NULL; - NEIGH_CACHE_STAT_INC(tbl, hits); - break; - } - } - - rcu_read_unlock_bh(); - return n; -} -EXPORT_SYMBOL(neigh_lookup_nodev); - struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { @@ -635,7 +619,7 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, ASSERT_RTNL(); - n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL); + n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; @@ -1271,7 +1255,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, * we can reinject the packet there. */ n2 = NULL; - if (dst) { + if (dst && dst->obsolete != DST_OBSOLETE_DEAD) { n2 = dst_neigh_lookup_skb(dst, skb); if (n2) n1 = n2; @@ -1614,7 +1598,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) /* It is not clean... Fix it to unload IPv6 module safely */ cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); - pneigh_queue_purge(&tbl->proxy_queue); + pneigh_queue_purge(&tbl->proxy_queue, NULL); neigh_ifdown(tbl, NULL); if (atomic_read(&tbl->entries)) pr_crit("neighbour leakage\n"); @@ -1646,9 +1630,6 @@ static struct neigh_table *neigh_find_table(int family) case AF_INET6: tbl = neigh_tables[NEIGH_ND_TABLE]; break; - case AF_DECnet: - tbl = neigh_tables[NEIGH_DN_TABLE]; - break; } return tbl; diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 63881f72ef71..2808c5f9c1f0 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -182,12 +182,23 @@ static const struct seq_operations softnet_seq_ops = { .show = softnet_seq_show, }; -static void *ptype_get_idx(loff_t pos) +static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { + struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; + struct net_device *dev; loff_t i = 0; int t; + for_each_netdev_rcu(seq_file_net(seq), dev) { + ptype_list = &dev->ptype_all; + list_for_each_entry_rcu(pt, ptype_list, list) { + if (i == pos) + return pt; + ++i; + } + } + list_for_each_entry_rcu(pt, &ptype_all, list) { if (i == pos) return pt; @@ -208,22 +219,40 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); - return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; + return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash; ++*pos; if (v == SEQ_START_TOKEN) - return ptype_get_idx(0); + return ptype_get_idx(seq, 0); pt = v; nxt = pt->list.next; + if (pt->dev) { + if (nxt != &pt->dev->ptype_all) + goto found; + + dev = pt->dev; + for_each_netdev_continue_rcu(seq_file_net(seq), dev) { + if (!list_empty(&dev->ptype_all)) { + nxt = dev->ptype_all.next; + goto found; + } + } + + nxt = ptype_all.next; + goto ptype_all; + } + if (pt->type == htons(ETH_P_ALL)) { +ptype_all: if (nxt != &ptype_all) goto found; hash = 0; @@ -252,7 +281,8 @@ static int ptype_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { + else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && + (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 001d7f07e780..7a11b2d90975 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -203,7 +203,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev)) { + if (netif_running(netdev) && netif_device_present(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) @@ -1244,8 +1244,8 @@ static const struct attribute_group dql_group = { static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) { + int cpu, len, ret, num_tc = 1, tc = 0; struct net_device *dev = queue->dev; - int cpu, len, num_tc = 1, tc = 0; struct xps_dev_maps *dev_maps; cpumask_var_t mask; unsigned long index; @@ -1255,22 +1255,31 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, index = get_netdev_queue_index(queue); + if (!rtnl_trylock()) + return restart_syscall(); + if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; - if (num_tc < 0) - return -EINVAL; + if (num_tc < 0) { + ret = -EINVAL; + goto err_rtnl_unlock; + } /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); - if (tc < 0) - return -EINVAL; + if (tc < 0) { + ret = -EINVAL; + goto err_rtnl_unlock; + } } - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { + ret = -ENOMEM; + goto err_rtnl_unlock; + } rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_cpus_map); @@ -1293,9 +1302,15 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, } rcu_read_unlock(); + rtnl_unlock(); + len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; + +err_rtnl_unlock: + rtnl_unlock(); + return ret; } static ssize_t xps_cpus_store(struct netdev_queue *queue, @@ -1323,7 +1338,13 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue, return err; } + if (!rtnl_trylock()) { + free_cpumask_var(mask); + return restart_syscall(); + } + err = netif_set_xps_queue(dev, mask, index); + rtnl_unlock(); free_cpumask_var(mask); @@ -1335,23 +1356,30 @@ static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) { + int j, len, ret, num_tc = 1, tc = 0; struct net_device *dev = queue->dev; struct xps_dev_maps *dev_maps; unsigned long *mask, index; - int j, len, num_tc = 1, tc = 0; index = get_netdev_queue_index(queue); + if (!rtnl_trylock()) + return restart_syscall(); + if (dev->num_tc) { num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); - if (tc < 0) - return -EINVAL; + if (tc < 0) { + ret = -EINVAL; + goto err_rtnl_unlock; + } } mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long), GFP_KERNEL); - if (!mask) - return -ENOMEM; + if (!mask) { + ret = -ENOMEM; + goto err_rtnl_unlock; + } rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_rxqs_map); @@ -1377,10 +1405,16 @@ static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) out_no_maps: rcu_read_unlock(); + rtnl_unlock(); + len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues); kfree(mask); return len < PAGE_SIZE ? len : -EINVAL; + +err_rtnl_unlock: + rtnl_unlock(); + return ret; } static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, @@ -1407,10 +1441,17 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, return err; } + if (!rtnl_trylock()) { + bitmap_free(mask); + return restart_syscall(); + } + cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, true); cpus_read_unlock(); + rtnl_unlock(); + kfree(mask); return err ? : len; } @@ -1575,6 +1616,9 @@ static void remove_queue_kobjects(struct net_device *dev) net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); + + dev->real_num_rx_queues = 0; + dev->real_num_tx_queues = 0; #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index c60123dff803..a87774424829 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -112,6 +112,7 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data) static int ops_init(const struct pernet_operations *ops, struct net *net) { + struct net_generic *ng; int err = -ENOMEM; void *data = NULL; @@ -130,6 +131,12 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) if (!err) return 0; + if (ops->id && ops->size) { + ng = rcu_dereference_protected(net->gen, + lockdep_is_held(&pernet_ops_rwsem)); + ng->ptr[*ops->id] = NULL; + } + cleanup: kfree(data); @@ -149,8 +156,10 @@ static void ops_exit_list(const struct pernet_operations *ops, { struct net *net; if (ops->exit) { - list_for_each_entry(net, net_exit_list, exit_list) + list_for_each_entry(net, net_exit_list, exit_list) { ops->exit(net); + cond_resched(); + } } if (ops->exit_batch) ops->exit_batch(net_exit_list); @@ -192,9 +201,9 @@ static int net_eq_idr(int id, void *net, void *peer) return 0; } -/* Should be called with nsid_lock held. If a new id is assigned, the bool alloc - * is set to true, thus the caller knows that the new id must be notified via - * rtnl. +/* Must be called from RCU-critical section or with nsid_lock held. If + * a new id is assigned, the bool alloc is set to true, thus the + * caller knows that the new id must be notified via rtnl. */ static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) { @@ -218,7 +227,7 @@ static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) return NETNSA_NSID_NOT_ASSIGNED; } -/* should be called with nsid_lock held */ +/* Must be called from RCU-critical section or with nsid_lock held */ static int __peernet2id(struct net *net, struct net *peer) { bool no = false; @@ -261,9 +270,10 @@ int peernet2id(struct net *net, struct net *peer) { int id; - spin_lock_bh(&net->nsid_lock); + rcu_read_lock(); id = __peernet2id(net, peer); - spin_unlock_bh(&net->nsid_lock); + rcu_read_unlock(); + return id; } EXPORT_SYMBOL(peernet2id); @@ -598,6 +608,18 @@ void __put_net(struct net *net) } EXPORT_SYMBOL_GPL(__put_net); +/** + * get_net_ns - increment the refcount of the network namespace + * @ns: common namespace (net) + * + * Returns the net's common namespace. + */ +struct ns_common *get_net_ns(struct ns_common *ns) +{ + return &get_net(container_of(ns, struct net, ns))->ns; +} +EXPORT_SYMBOL_GPL(get_net_ns); + struct net *get_net_ns_by_fd(int fd) { struct file *file; @@ -825,6 +847,7 @@ struct rtnl_net_dump_cb { int s_idx; }; +/* Runs in RCU-critical section. */ static int rtnl_net_dumpid_one(int id, void *peer, void *data) { struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; @@ -855,9 +878,9 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) .s_idx = cb->args[0], }; - spin_lock_bh(&net->nsid_lock); + rcu_read_lock(); idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb); - spin_unlock_bh(&net->nsid_lock); + rcu_read_unlock(); cb->args[0] = net_cb.idx; return skb->len; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 023ce0fbb496..08f0da9e6a80 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -28,6 +28,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/if_vlan.h> +#include <net/dsa.h> #include <net/tcp.h> #include <net/udp.h> #include <net/addrconf.h> @@ -135,6 +136,20 @@ static void queue_process(struct work_struct *work) } } +static int netif_local_xmit_active(struct net_device *dev) +{ + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + return 1; + } + + return 0; +} + static void poll_one_napi(struct napi_struct *napi) { int work; @@ -181,7 +196,10 @@ void netpoll_poll_dev(struct net_device *dev) if (!ni || down_trylock(&ni->dev_lock)) return; - if (!netif_running(dev)) { + /* Some drivers will take the same locks in poll and xmit, + * we can't poll if local CPU is already in xmit. + */ + if (!netif_running(dev) || netif_local_xmit_active(dev)) { up(&ni->dev_lock); return; } @@ -638,15 +656,15 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { - struct net_device *ndev = NULL; + struct net_device *ndev = NULL, *dev = NULL; + struct net *net = current->nsproxy->net_ns; struct in_device *in_dev; int err; rtnl_lock(); - if (np->dev_name[0]) { - struct net *net = current->nsproxy->net_ns; + if (np->dev_name[0]) ndev = __dev_get_by_name(net, np->dev_name); - } + if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); err = -ENODEV; @@ -654,6 +672,19 @@ int netpoll_setup(struct netpoll *np) } dev_hold(ndev); + /* bring up DSA management network devices up first */ + for_each_netdev(net, dev) { + if (!netdev_uses_dsa(dev)) + continue; + + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + np_err(np, "%s failed to open %s\n", + np->dev_name, dev->name); + goto put; + } + } + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 092fa3d75b32..3ade60ec4512 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -651,19 +651,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_puts(seq, " Flags: "); for (i = 0; i < NR_PKT_FLAGS; i++) { - if (i == F_FLOW_SEQ) + if (i == FLOW_SEQ_SHIFT) if (!pkt_dev->cflows) continue; - if (pkt_dev->flags & (1 << i)) + if (pkt_dev->flags & (1 << i)) { seq_printf(seq, "%s ", pkt_flag_names[i]); - else if (i == F_FLOW_SEQ) - seq_puts(seq, "FLOW_RND "); - #ifdef CONFIG_XFRM - if (i == F_IPSEC && pkt_dev->spi) - seq_printf(seq, "spi:%u", pkt_dev->spi); + if (i == IPSEC_SHIFT && pkt_dev->spi) + seq_printf(seq, "spi:%u ", pkt_dev->spi); #endif + } else if (i == FLOW_SEQ_SHIFT) { + seq_puts(seq, "FLOW_RND "); + } } seq_puts(seq, "\n"); @@ -3471,7 +3471,7 @@ static int pktgen_thread_worker(void *arg) struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - BUG_ON(smp_processor_id() != cpu); + WARN_ON(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); complete(&t->start_done); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 935053ee7765..0d3f724da78b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -130,6 +130,12 @@ int rtnl_is_locked(void) } EXPORT_SYMBOL(rtnl_is_locked); +bool refcount_dec_and_rtnl_lock(refcount_t *r) +{ + return refcount_dec_and_mutex_lock(r, &rtnl_mutex); +} +EXPORT_SYMBOL(refcount_dec_and_rtnl_lock); + #ifdef CONFIG_PROVE_LOCKING bool lockdep_rtnl_is_held(void) { @@ -2936,9 +2942,9 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; - const struct rtnl_link_ops *m_ops = NULL; + const struct rtnl_link_ops *m_ops; struct net_device *dev; - struct net_device *master_dev = NULL; + struct net_device *master_dev; struct ifinfomsg *ifm; char kind[MODULE_NAME_LEN]; char ifname[IFNAMSIZ]; @@ -2964,15 +2970,20 @@ replay: ifname[0] = '\0'; ifm = nlmsg_data(nlh); - if (ifm->ifi_index > 0) + if (ifm->ifi_index > 0) { dev = __dev_get_by_index(net, ifm->ifi_index); - else { + } else if (ifm->ifi_index < 0) { + NL_SET_ERR_MSG(extack, "ifindex can't be negative"); + return -EINVAL; + } else { if (ifname[0]) dev = __dev_get_by_name(net, ifname); else dev = NULL; } + master_dev = NULL; + m_ops = NULL; if (dev) { master_dev = netdev_master_upper_dev_get(dev); if (master_dev) @@ -3428,7 +3439,7 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, ndm->ndm_ifindex = dev->ifindex; ndm->ndm_state = ndm_state; - if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) + if (nla_put(skb, NDA_LLADDR, dev->addr_len, addr)) goto nla_put_failure; if (vid) if (nla_put(skb, NDA_VLAN, sizeof(u16), &vid)) @@ -3442,10 +3453,10 @@ nla_put_failure: return -EMSGSIZE; } -static inline size_t rtnl_fdb_nlmsg_size(void) +static inline size_t rtnl_fdb_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + - nla_total_size(ETH_ALEN) + /* NDA_LLADDR */ + nla_total_size(dev->addr_len) + /* NDA_LLADDR */ nla_total_size(sizeof(u16)) + /* NDA_VLAN */ 0; } @@ -3457,7 +3468,7 @@ static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, u16 vid, int type, struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC); + skb = nlmsg_new(rtnl_fdb_nlmsg_size(dev), GFP_ATOMIC); if (!skb) goto errout; @@ -4102,6 +4113,10 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout; + /* Notification info is only filled for bridge ports, not the bridge + * device itself. Therefore, a zero notification length is valid and + * should not result in an error. + */ if (!skb->len) goto errout; @@ -4508,7 +4523,7 @@ nla_put_failure: static size_t if_nlmsg_stats_size(const struct net_device *dev, u32 filter_mask) { - size_t size = 0; + size_t size = NLMSG_ALIGN(sizeof(struct if_stats_msg)); if (stats_attr_valid(filter_mask, IFLA_STATS_LINK_64, 0)) size += nla_total_size_64bit(sizeof(struct rtnl_link_stats64)); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index af6ad467ed61..6fd25279bee9 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -22,6 +22,8 @@ static siphash_key_t net_secret __read_mostly; static siphash_key_t ts_secret __read_mostly; +#define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) + static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); @@ -94,17 +96,19 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, } EXPORT_SYMBOL(secure_tcpv6_seq); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) { const struct { struct in6_addr saddr; struct in6_addr daddr; + unsigned int timeseed; __be16 dport; } __aligned(SIPHASH_ALIGNMENT) combined = { .saddr = *(struct in6_addr *)saddr, .daddr = *(struct in6_addr *)daddr, - .dport = dport + .timeseed = jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + .dport = dport, }; net_secret_init(); return siphash(&combined, offsetofend(typeof(combined), dport), @@ -142,11 +146,13 @@ u32 secure_tcp_seq(__be32 saddr, __be32 daddr, } EXPORT_SYMBOL_GPL(secure_tcp_seq); -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { net_secret_init(); - return siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u16)dport, &net_secret); + return siphash_4u32((__force u32)saddr, (__force u32)daddr, + (__force u16)dport, + jiffies / EPHEMERAL_PORT_SHUFFLE_PERIOD, + &net_secret); } EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); #endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index be4bc833c28a..e03cd719b86b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -398,7 +398,11 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, len += NET_SKB_PAD; - if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || + /* If requested length is either too small or too big, + * we use kmalloc() for skb->head allocation. + */ + if (len <= SKB_WITH_OVERHEAD(1024) || + len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) @@ -459,13 +463,17 @@ EXPORT_SYMBOL(__netdev_alloc_skb); struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, gfp_t gfp_mask) { - struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + struct napi_alloc_cache *nc; struct sk_buff *skb; void *data; len += NET_SKB_PAD + NET_IP_ALIGN; - if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) || + /* If requested length is either too small or too big, + * we use kmalloc() for skb->head allocation. + */ + if (len <= SKB_WITH_OVERHEAD(1024) || + len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); if (!skb) @@ -473,6 +481,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, goto skb_success; } + nc = this_cpu_ptr(&napi_alloc_cache); len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); len = SKB_DATA_ALIGN(len); @@ -1853,6 +1862,12 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) skb->csum = csum_block_sub(skb->csum, skb_checksum(skb, len, delta, 0), len); + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len; + int offset = skb_checksum_start_offset(skb) + skb->csum_offset; + + if (offset + sizeof(__sum16) > hdlen) + return -EINVAL; } return __pskb_trim(skb, len); } @@ -1938,6 +1953,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) insp = list; } else { /* Eaten partially. */ + if (skb_is_gso(skb) && !list->head_frag && + skb_headlen(list)) + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; if (skb_shared(list)) { /* Sucks! We need to fork list. :-( */ @@ -1962,7 +1980,7 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) /* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) { skb_shinfo(skb)->frag_list = list->next; - kfree_skb(list); + consume_skb(list); } /* And insert new clone at head. */ if (clone) { @@ -2690,8 +2708,11 @@ skb_zerocopy_headlen(const struct sk_buff *from) if (!from->head_frag || skb_headlen(from) < L1_CACHE_BYTES || - skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) + skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) { hlen = skb_headlen(from); + if (!hlen) + hlen = from->len; + } if (skb_has_frag_list(from)) hlen = from->len; @@ -3077,7 +3098,19 @@ EXPORT_SYMBOL(skb_split); */ static int skb_prepare_for_shift(struct sk_buff *skb) { - return skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + int ret = 0; + + if (skb_cloned(skb)) { + /* Save and restore truesize: pskb_expand_head() may reallocate + * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we + * cannot change truesize at this point. + */ + unsigned int save_truesize = skb->truesize; + + ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + skb->truesize = save_truesize; + } + return ret; } /** @@ -3513,40 +3546,41 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list; - skb_frag_t *frag = skb_shinfo(head_skb)->frags; unsigned int mss = skb_shinfo(head_skb)->gso_size; unsigned int doffset = head_skb->data - skb_mac_header(head_skb); - struct sk_buff *frag_skb = head_skb; unsigned int offset = doffset; unsigned int tnl_hlen = skb_tnl_header_len(head_skb); unsigned int partial_segs = 0; unsigned int headroom; unsigned int len = head_skb->len; + struct sk_buff *frag_skb; + skb_frag_t *frag; __be16 proto; bool csum, sg; - int nfrags = skb_shinfo(head_skb)->nr_frags; int err = -ENOMEM; int i = 0; - int pos; + int nfrags, pos; int dummy; - if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) && - (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) { - /* gso_size is untrusted, and we have a frag_list with a linear - * non head_frag head. - * - * (we assume checking the first list_skb member suffices; - * i.e if either of the list_skb members have non head_frag - * head, then the first one has too). - * - * If head_skb's headlen does not fit requested gso_size, it - * means that the frag_list members do NOT terminate on exact - * gso_size boundaries. Hence we cannot perform skb_frag_t page - * sharing. Therefore we must fallback to copying the frag_list - * skbs; we do so by disabling SG. - */ - if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) - features &= ~NETIF_F_SG; + if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && + mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { + struct sk_buff *check_skb; + + for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { + if (skb_headlen(check_skb) && !check_skb->head_frag) { + /* gso_size is untrusted, and we have a frag_list with + * a linear non head_frag item. + * + * If head_skb's headlen does not fit requested gso_size, + * it means that the frag_list members do NOT terminate + * on exact gso_size boundaries. Hence we cannot perform + * skb_frag_t page sharing. Therefore we must fallback to + * copying the frag_list skbs; we do so by disabling SG. + */ + features &= ~NETIF_F_SG; + break; + } + } } __skb_push(head_skb, doffset); @@ -3603,6 +3637,13 @@ normal: headroom = skb_headroom(head_skb); pos = skb_headlen(head_skb); + if (skb_orphan_frags(head_skb, GFP_ATOMIC)) + return ERR_PTR(-ENOMEM); + + nfrags = skb_shinfo(head_skb)->nr_frags; + frag = skb_shinfo(head_skb)->frags; + frag_skb = head_skb; + do { struct sk_buff *nskb; skb_frag_t *nskb_frag; @@ -3627,6 +3668,10 @@ normal: (skb_headlen(list_skb) == len || sg)) { BUG_ON(skb_headlen(list_skb) > len); + nskb = skb_clone(list_skb, GFP_ATOMIC); + if (unlikely(!nskb)) + goto err; + i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; @@ -3645,12 +3690,8 @@ normal: frag++; } - nskb = skb_clone(list_skb, GFP_ATOMIC); list_skb = list_skb->next; - if (unlikely(!nskb)) - goto err; - if (unlikely(pskb_trim(nskb, len))) { kfree_skb(nskb); goto err; @@ -3715,12 +3756,16 @@ normal: skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & SKBTX_SHARED_FRAG; - if (skb_orphan_frags(frag_skb, GFP_ATOMIC) || - skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) + if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) goto err; while (pos < offset + len) { if (i >= nfrags) { + if (skb_orphan_frags(list_skb, GFP_ATOMIC) || + skb_zerocopy_clone(nskb, list_skb, + GFP_ATOMIC)) + goto err; + i = 0; nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; @@ -3734,10 +3779,6 @@ normal: i--; frag--; } - if (skb_orphan_frags(frag_skb, GFP_ATOMIC) || - skb_zerocopy_clone(nskb, frag_skb, - GFP_ATOMIC)) - goto err; list_skb = list_skb->next; } @@ -4265,7 +4306,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) if (skb && (skb_next = skb_peek(q))) { icmp_next = is_icmp_err_skb(skb_next); if (icmp_next) - sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin; + sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno; } spin_unlock_irqrestore(&q->lock, flags); @@ -4347,7 +4388,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly) { bool ret; - if (likely(sysctl_tstamp_allow_data || tsonly)) + if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly)) return true; read_lock_bh(&sk->sk_callback_lock); @@ -4410,6 +4451,11 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, skb = alloc_skb(0, GFP_ATOMIC); } else { skb = skb_clone(orig_skb, GFP_ATOMIC); + + if (skb_orphan_frags_rx(skb, GFP_ATOMIC)) { + kfree_skb(skb); + return; + } } if (!skb) return; @@ -5452,7 +5498,7 @@ static int pskb_carve_frag_list(struct sk_buff *skb, /* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) { shinfo->frag_list = list->next; - kfree_skb(list); + consume_skb(list); } /* And insert new clone at head. */ if (clone) { diff --git a/net/core/sock.c b/net/core/sock.c index e6cbe137cb6f..62d169bcfcfa 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -496,7 +496,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; @@ -632,7 +632,8 @@ bool sk_mc_loop(struct sock *sk) return false; if (!sk) return true; - switch (sk->sk_family) { + /* IPV6_ADDRFORM can change sk->sk_family under us. */ + switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_sk(sk)->mc_loop; #if IS_ENABLED(CONFIG_IPV6) @@ -989,7 +990,7 @@ set_rcvbuf: if (val < 0) ret = -EINVAL; else - sk->sk_ll_usec = val; + WRITE_ONCE(sk->sk_ll_usec, val); } break; #endif @@ -1057,6 +1058,16 @@ set_rcvbuf: } EXPORT_SYMBOL(sock_setsockopt); +static const struct cred *sk_get_peer_cred(struct sock *sk) +{ + const struct cred *cred; + + spin_lock(&sk->sk_peer_lock); + cred = get_cred(sk->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + return cred; +} static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) @@ -1231,7 +1242,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); + + spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + spin_unlock(&sk->sk_peer_lock); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; @@ -1239,20 +1254,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_PEERGROUPS: { + const struct cred *cred; int ret, n; - if (!sk->sk_peer_cred) + cred = sk_get_peer_cred(sk); + if (!cred) return -ENODATA; - n = sk->sk_peer_cred->group_info->ngroups; + n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); + put_cred(cred); return put_user(len, optlen) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, - sk->sk_peer_cred->group_info); + ret = groups_to_user((gid_t __user *)optval, cred->group_info); + put_cred(cred); if (ret) return ret; goto lenout; @@ -1302,7 +1320,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (!sock->ops->set_peek_off) return -EOPNOTSUPP; - v.val = sk->sk_peek_off; + v.val = READ_ONCE(sk->sk_peek_off); break; case SO_NOFCS: v.val = sock_flag(sk, SOCK_NOFCS); @@ -1332,7 +1350,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, #ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: - v.val = sk->sk_ll_usec; + v.val = READ_ONCE(sk->sk_ll_usec); break; #endif @@ -1576,9 +1594,10 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_frag.page = NULL; } - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ + put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); + if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); @@ -1777,7 +1796,6 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { u32 max_segs = 1; - sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features | sk->sk_route_forced_caps; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; @@ -1792,6 +1810,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } } sk->sk_gso_max_segs = max_segs; + sk_dst_set(sk, dst); } EXPORT_SYMBOL_GPL(sk_setup_caps); @@ -1921,13 +1940,24 @@ kuid_t sock_i_uid(struct sock *sk) } EXPORT_SYMBOL(sock_i_uid); -unsigned long sock_i_ino(struct sock *sk) +unsigned long __sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock_bh(&sk->sk_callback_lock); + read_lock(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock_bh(&sk->sk_callback_lock); + read_unlock(&sk->sk_callback_lock); + return ino; +} +EXPORT_SYMBOL(__sock_i_ino); + +unsigned long sock_i_ino(struct sock *sk) +{ + unsigned long ino; + + local_bh_disable(); + ino = __sock_i_ino(sk); + local_bh_enable(); return ino; } EXPORT_SYMBOL(sock_i_ino); @@ -2042,9 +2072,9 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) break; - if (sk->sk_shutdown & SEND_SHUTDOWN) + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) break; - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) break; timeo = schedule_timeout(timeo); } @@ -2072,7 +2102,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, goto failure; err = -EPIPE; - if (sk->sk_shutdown & SEND_SHUTDOWN) + if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) goto failure; if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf) @@ -2189,9 +2219,6 @@ static void sk_leave_memory_pressure(struct sock *sk) } } -/* On 32bit arches, an skb frag is limited to 2^15 */ -#define SKB_FRAG_PAGE_ORDER get_order(32768) - /** * skb_page_frag_refill - check that a page_frag contains enough room * @sz: minimum size of the fragment we want to get @@ -2512,7 +2539,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount) if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); - if (sk_under_memory_pressure(sk) && + if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } @@ -2533,7 +2560,7 @@ EXPORT_SYMBOL(__sk_mem_reclaim); int sk_set_peek_off(struct sock *sk, int val) { - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); return 0; } EXPORT_SYMBOL_GPL(sk_set_peek_off); @@ -2826,6 +2853,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; + spin_lock_init(&sk->sk_peer_lock); + sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; @@ -2839,7 +2868,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_busy_read; + sk->sk_ll_usec = READ_ONCE(sysctl_net_busy_read); #endif sk->sk_max_pacing_rate = ~0U; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 9c85ef2b7e1d..375a3bbe6485 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -299,7 +299,7 @@ select_by_hash: i = j = reciprocal_scale(hash, socks); while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { i++; - if (i >= reuse->num_socks) + if (i >= socks) i = 0; if (i == j) goto out; diff --git a/net/core/stream.c b/net/core/stream.c index 7f5eaa95a675..cd60746877b1 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -32,7 +32,7 @@ void sk_stream_write_space(struct sock *sk) struct socket *sock = sk->sk_socket; struct socket_wq *wq; - if (sk_stream_is_writeable(sk) && sock) { + if (__sk_stream_is_writeable(sk, 1) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); @@ -159,7 +159,8 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) *timeo_p = current_timeo; } out: - remove_wait_queue(sk_sleep(sk), &wait); + if (!sock_flag(sk, SOCK_DEAD)) + remove_wait_queue(sk_sleep(sk), &wait); return err; do_error: @@ -195,8 +196,11 @@ void sk_stream_kill_queues(struct sock *sk) /* First the read buffer. */ __skb_queue_purge(&sk->sk_receive_queue); - /* Next, the error queue. */ - __skb_queue_purge(&sk->sk_error_queue); + /* Next, the error queue. + * We need to use queue lock, because other threads might + * add packets to the queue without socket lock being held. + */ + skb_queue_purge(&sk->sk_error_queue); /* Next, the write queue. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); @@ -205,7 +209,6 @@ void sk_stream_kill_queues(struct sock *sk) sk_mem_reclaim(sk); WARN_ON(sk->sk_wmem_queued); - WARN_ON(sk->sk_forward_alloc); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 2597449ae9b4..d7e39167ceca 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -231,14 +231,17 @@ static int set_default_qdisc(struct ctl_table *table, int write, static int proc_do_dev_weight(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret; + static DEFINE_MUTEX(dev_weight_mutex); + int ret, weight; + mutex_lock(&dev_weight_mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret != 0) - return ret; - - dev_rx_weight = weight_p * dev_weight_rx_bias; - dev_tx_weight = weight_p * dev_weight_tx_bias; + if (!ret && write) { + weight = READ_ONCE(weight_p); + WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + } + mutex_unlock(&dev_weight_mutex); return ret; } @@ -417,7 +420,7 @@ static struct ctl_table net_core_table[] = { .mode = 0600, .proc_handler = proc_dolongvec_minmax_bpf_restricted, .extra1 = &long_one, - .extra2 = &long_max, + .extra2 = &bpf_jit_limit_max, }, #endif { diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 5ee6b94131b2..1ceeba2429f7 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1756,6 +1756,8 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, fn = &reply_funcs[dcb->cmd]; if (!fn->cb) return -EOPNOTSUPP; + if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; if (!tb[DCB_ATTR_IFNAME]) return -EINVAL; @@ -2052,10 +2054,54 @@ u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev) } EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); +static void dcbnl_flush_dev(struct net_device *dev) +{ + struct dcb_app_type *itr, *tmp; + + spin_lock_bh(&dcb_lock); + + list_for_each_entry_safe(itr, tmp, &dcb_app_list, list) { + if (itr->ifindex == dev->ifindex) { + list_del(&itr->list); + kfree(itr); + } + } + + spin_unlock_bh(&dcb_lock); +} + +static int dcbnl_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_UNREGISTER: + if (!dev->dcbnl_ops) + return NOTIFY_DONE; + + dcbnl_flush_dev(dev); + + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block dcbnl_nb __read_mostly = { + .notifier_call = dcbnl_netdevice_event, +}; + static int __init dcbnl_init(void) { + int err; + INIT_LIST_HEAD(&dcb_app_list); + err = register_netdevice_notifier(&dcbnl_nb); + if (err) + return err; + rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0); rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index f91e3816806b..579f39e0d02e 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -44,9 +44,9 @@ extern bool dccp_debug; #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) #define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else -#define dccp_pr_debug(format, a...) -#define dccp_pr_debug_cat(format, a...) -#define dccp_debug(format, a...) +#define dccp_pr_debug(format, a...) do {} while (0) +#define dccp_pr_debug_cat(format, a...) do {} while (0) +#define dccp_debug(format, a...) do {} while (0) #endif extern struct inet_hashinfo dccp_hashinfo; @@ -291,6 +291,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned int len); +void dccp_destruct_common(struct sock *sk); int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); void dccp_destroy_sock(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 176bddacc16e..5281ac3260f6 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -134,6 +134,8 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; @@ -245,12 +247,12 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) int err; struct net *net = dev_net(skb->dev); - /* Only need dccph_dport & dccph_sport which are the first - * 4 bytes in dccp header. - * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. - */ - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return; + dh = (struct dccp_hdr *)(skb->data + offset); + if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) + return; + iph = (struct iphdr *)skb->data; dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet_lookup_established(net, &dccp_hashinfo, @@ -428,7 +430,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); if (*own_req) ireq->ireq_opt = NULL; else @@ -610,9 +612,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_parse_options(sk, dreq, skb)) goto drop_and_free; - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_free; - ireq = inet_rsk(req); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); @@ -620,6 +619,9 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq->ireq_family = AF_INET; ireq->ir_iif = sk->sk_bound_dev_if; + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + /* * Step 3: Process LISTEN state * diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index b438bed6749d..72ceefbf2312 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -71,7 +71,7 @@ static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { - const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; + const struct ipv6hdr *hdr; const struct dccp_hdr *dh; struct dccp_sock *dp; struct ipv6_pinfo *np; @@ -80,12 +80,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, __u64 seq; struct net *net = dev_net(skb->dev); - /* Only need dccph_dport & dccph_sport which are the first - * 4 bytes in dccp header. - * Our caller (icmpv6_notify()) already pulled 8 bytes for us. - */ - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_sport) > 8); - BUILD_BUG_ON(offsetofend(struct dccp_hdr, dccph_dport) > 8); + if (!pskb_may_pull(skb, offset + sizeof(*dh))) + return; + dh = (struct dccp_hdr *)(skb->data + offset); + if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) + return; + hdr = (const struct ipv6hdr *)skb->data; dh = (struct dccp_hdr *)(skb->data + offset); sk = __inet6_lookup_established(net, &dccp_hashinfo, @@ -319,6 +319,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) return 0; /* discard, don't send a reset here */ + if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { + __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); + return 0; + } + if (dccp_bad_service_code(sk, service)) { dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; @@ -344,15 +349,15 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_parse_options(sk, dreq, skb)) goto drop_and_free; - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_free; - ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; ireq->ireq_family = AF_INET6; ireq->ir_mark = inet_request_mark(sk, skb); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { @@ -533,14 +538,12 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, dccp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL); /* Clone pktoptions received with SYN, if we own the req */ if (*own_req && ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) - skb_set_owner_r(newnp->pktoptions, newsk); } return newsk; @@ -600,7 +603,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, GFP_ATOMIC); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == DCCP_OPEN) { /* Fast path */ if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) @@ -664,7 +667,6 @@ ipv6_pktoptions: np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &DCCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); memmove(IP6CB(opt_skb), &DCCP_SKB_CB(opt_skb)->header.h6, sizeof(struct inet6_skb_parm)); @@ -952,6 +954,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; @@ -996,6 +1000,12 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { #endif }; +static void dccp_v6_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); + inet6_sock_destruct(sk); +} + /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ @@ -1008,17 +1018,12 @@ static int dccp_v6_init_sock(struct sock *sk) if (unlikely(!dccp_v6_ctl_sock_initialized)) dccp_v6_ctl_sock_initialized = 1; inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + sk->sk_destruct = dccp_v6_sk_destruct; } return err; } -static void dccp_v6_destroy_sock(struct sock *sk) -{ - dccp_destroy_sock(sk); - inet6_destroy_sock(sk); -} - static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; @@ -1041,7 +1046,7 @@ static struct proto dccp_v6_prot = { .accept = inet_csk_accept, .get_port = inet_csk_get_port, .shutdown = dccp_shutdown, - .destroy = dccp_v6_destroy_sock, + .destroy = dccp_destroy_sock, .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index ba6fc3c1186b..e91838a7b849 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -98,6 +98,8 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; newdp->dccps_service_list = NULL; + newdp->dccps_hc_rx_ccid = NULL; + newdp->dccps_hc_tx_ccid = NULL; newdp->dccps_service = dreq->dreq_service; newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo; newdp->dccps_timestamp_time = dreq->dreq_timestamp_time; diff --git a/net/dccp/options.c b/net/dccp/options.c index 4e40db017e19..3c464d63b0bb 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -60,7 +60,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, (dh->dccph_doff * 4); struct dccp_options_received *opt_recv = &dp->dccps_options_received; unsigned char opt, len; - unsigned char *uninitialized_var(value); + unsigned char *value; u32 elapsed_time; __be32 opt_val; int rc; diff --git a/net/dccp/output.c b/net/dccp/output.c index 91a15b3c4915..d872dd1cfb5e 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -189,7 +189,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 43733accf58e..c4ea0159ce2e 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -174,12 +174,18 @@ const char *dccp_packet_name(const int type) EXPORT_SYMBOL_GPL(dccp_packet_name); -static void dccp_sk_destruct(struct sock *sk) +void dccp_destruct_common(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = NULL; +} +EXPORT_SYMBOL_GPL(dccp_destruct_common); + +static void dccp_sk_destruct(struct sock *sk) +{ + dccp_destruct_common(sk); inet_sock_destruct(sk); } @@ -322,11 +328,15 @@ EXPORT_SYMBOL_GPL(dccp_disconnect); __poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { - __poll_t mask; struct sock *sk = sock->sk; + __poll_t mask; + u8 shutdown; + int state; sock_poll_wait(file, sock, wait); - if (sk->sk_state == DCCP_LISTEN) + + state = inet_sk_state_load(sk); + if (state == DCCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events @@ -335,20 +345,21 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, */ mask = 0; - if (sk->sk_err) + if (READ_ONCE(sk->sk_err)) mask = EPOLLERR; + shutdown = READ_ONCE(sk->sk_shutdown); - if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED) + if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected? */ - if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { + if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) { if (atomic_read(&sk->sk_rmem_alloc) > 0) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + if (!(shutdown & SEND_SHUTDOWN)) { if (sk_stream_is_writeable(sk)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ @@ -366,7 +377,6 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, } return mask; } - EXPORT_SYMBOL_GPL(dccp_poll); int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) @@ -642,7 +652,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -764,16 +774,11 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); - if (dccp_qpolicy_full(sk)) { - rc = -EAGAIN; - goto out_release; - } - timeo = sock_sndtimeo(sk, noblock); /* @@ -792,11 +797,22 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (skb == NULL) goto out_release; + if (dccp_qpolicy_full(sk)) { + rc = -EAGAIN; + goto out_discard; + } + if (sk->sk_state == DCCP_CLOSED) { rc = -ENOTCONN; goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/decnet/Kconfig b/net/decnet/Kconfig deleted file mode 100644 index dcc74956badd..000000000000 --- a/net/decnet/Kconfig +++ /dev/null @@ -1,42 +0,0 @@ -# -# DECnet configuration -# -config DECNET - tristate "DECnet Support" - ---help--- - The DECnet networking protocol was used in many products made by - Digital (now Compaq). It provides reliable stream and sequenced - packet communications over which run a variety of services similar - to those which run over TCP/IP. - - To find some tools to use with the kernel layer support, please - look at Patrick Caulfield's web site: - <http://linux-decnet.sourceforge.net/>. - - More detailed documentation is available in - <file:Documentation/networking/decnet.txt>. - - Be sure to say Y to "/proc file system support" and "Sysctl support" - below when using DECnet, since you will need sysctl support to aid - in configuration at run time. - - The DECnet code is also available as a module ( = code which can be - inserted in and removed from the running kernel whenever you want). - The module is called decnet. - -config DECNET_ROUTER - bool "DECnet: router support" - depends on DECNET - select FIB_RULES - ---help--- - Add support for turning your DECnet Endnode into a level 1 or 2 - router. This is an experimental, but functional option. If you - do say Y here, then make sure that you also say Y to "Kernel/User - network link driver", "Routing messages" and "Network packet - filtering". The first two are required to allow configuration via - rtnetlink (you will need Alexey Kuznetsov's iproute2 package - from <ftp://ftp.tux.org/pub/net/ip-routing/>). The "Network packet - filtering" option will be required for the forthcoming routing daemon - to work. - - See <file:Documentation/networking/decnet.txt> for more information. diff --git a/net/decnet/Makefile b/net/decnet/Makefile deleted file mode 100644 index 07b38e441b2d..000000000000 --- a/net/decnet/Makefile +++ /dev/null @@ -1,10 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -obj-$(CONFIG_DECNET) += decnet.o - -decnet-y := af_decnet.o dn_nsp_in.o dn_nsp_out.o \ - dn_route.o dn_dev.o dn_neigh.o dn_timer.o -decnet-$(CONFIG_DECNET_ROUTER) += dn_fib.o dn_rules.o dn_table.o -decnet-y += sysctl_net_decnet.o - -obj-$(CONFIG_NETFILTER) += netfilter/ diff --git a/net/decnet/README b/net/decnet/README deleted file mode 100644 index 60e7ec88c81f..000000000000 --- a/net/decnet/README +++ /dev/null @@ -1,8 +0,0 @@ - Linux DECnet Project - ====================== - -The documentation for this kernel subsystem is available in the -Documentation/networking subdirectory of this distribution and also -on line at http://www.chygwyn.com/DECnet/ - -Steve Whitehouse <SteveW@ACM.org> diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c deleted file mode 100644 index 0e6f32defd67..000000000000 --- a/net/decnet/af_decnet.c +++ /dev/null @@ -1,2411 +0,0 @@ - -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Socket Layer Interface - * - * Authors: Eduardo Marcelo Serrat <emserrat@geocities.com> - * Patrick Caulfield <patrick@pandh.demon.co.uk> - * - * Changes: - * Steve Whitehouse: Copied from Eduardo Serrat and Patrick Caulfield's - * version of the code. Original copyright preserved - * below. - * Steve Whitehouse: Some bug fixes, cleaning up some code to make it - * compatible with my routing layer. - * Steve Whitehouse: Merging changes from Eduardo Serrat and Patrick - * Caulfield. - * Steve Whitehouse: Further bug fixes, checking module code still works - * with new routing layer. - * Steve Whitehouse: Additional set/get_sockopt() calls. - * Steve Whitehouse: Fixed TIOCINQ ioctl to be same as Eduardo's new - * code. - * Steve Whitehouse: recvmsg() changed to try and behave in a POSIX like - * way. Didn't manage it entirely, but its better. - * Steve Whitehouse: ditto for sendmsg(). - * Steve Whitehouse: A selection of bug fixes to various things. - * Steve Whitehouse: Added TIOCOUTQ ioctl. - * Steve Whitehouse: Fixes to username2sockaddr & sockaddr2username. - * Steve Whitehouse: Fixes to connect() error returns. - * Patrick Caulfield: Fixes to delayed acceptance logic. - * David S. Miller: New socket locking - * Steve Whitehouse: Socket list hashing/locking - * Arnaldo C. Melo: use capable, not suser - * Steve Whitehouse: Removed unused code. Fix to use sk->allocation - * when required. - * Patrick Caulfield: /proc/net/decnet now has object name/number - * Steve Whitehouse: Fixed local port allocation, hashed sk list - * Matthew Wilcox: Fixes for dn_ioctl() - * Steve Whitehouse: New connect/accept logic to allow timeouts and - * prepare for sendpage etc. - */ - - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - -HISTORY: - -Version Kernel Date Author/Comments -------- ------ ---- --------------- -Version 0.0.1 2.0.30 01-dic-97 Eduardo Marcelo Serrat - (emserrat@geocities.com) - - First Development of DECnet Socket La- - yer for Linux. Only supports outgoing - connections. - -Version 0.0.2 2.1.105 20-jun-98 Patrick J. Caulfield - (patrick@pandh.demon.co.uk) - - Port to new kernel development version. - -Version 0.0.3 2.1.106 25-jun-98 Eduardo Marcelo Serrat - (emserrat@geocities.com) - _ - Added support for incoming connections - so we can start developing server apps - on Linux. - - - Module Support -Version 0.0.4 2.1.109 21-jul-98 Eduardo Marcelo Serrat - (emserrat@geocities.com) - _ - Added support for X11R6.4. Now we can - use DECnet transport for X on Linux!!! - - -Version 0.0.5 2.1.110 01-aug-98 Eduardo Marcelo Serrat - (emserrat@geocities.com) - Removed bugs on flow control - Removed bugs on incoming accessdata - order - - -Version 0.0.6 2.1.110 07-aug-98 Eduardo Marcelo Serrat - dn_recvmsg fixes - - Patrick J. Caulfield - dn_bind fixes -*******************************************************************************/ - -#include <linux/module.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/kernel.h> -#include <linux/sched/signal.h> -#include <linux/timer.h> -#include <linux/string.h> -#include <linux/sockios.h> -#include <linux/net.h> -#include <linux/netdevice.h> -#include <linux/inet.h> -#include <linux/route.h> -#include <linux/netfilter.h> -#include <linux/seq_file.h> -#include <net/sock.h> -#include <net/tcp_states.h> -#include <net/flow.h> -#include <asm/ioctls.h> -#include <linux/capability.h> -#include <linux/mm.h> -#include <linux/interrupt.h> -#include <linux/proc_fs.h> -#include <linux/stat.h> -#include <linux/init.h> -#include <linux/poll.h> -#include <linux/jiffies.h> -#include <net/net_namespace.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/fib_rules.h> -#include <net/tcp.h> -#include <net/dn.h> -#include <net/dn_nsp.h> -#include <net/dn_dev.h> -#include <net/dn_route.h> -#include <net/dn_fib.h> -#include <net/dn_neigh.h> - -struct dn_sock { - struct sock sk; - struct dn_scp scp; -}; - -static void dn_keepalive(struct sock *sk); - -#define DN_SK_HASH_SHIFT 8 -#define DN_SK_HASH_SIZE (1 << DN_SK_HASH_SHIFT) -#define DN_SK_HASH_MASK (DN_SK_HASH_SIZE - 1) - - -static const struct proto_ops dn_proto_ops; -static DEFINE_RWLOCK(dn_hash_lock); -static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE]; -static struct hlist_head dn_wild_sk; -static atomic_long_t decnet_memory_allocated; - -static int __dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen, int flags); -static int __dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen, int flags); - -static struct hlist_head *dn_find_list(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->addr.sdn_flags & SDF_WILD) - return hlist_empty(&dn_wild_sk) ? &dn_wild_sk : NULL; - - return &dn_sk_hash[le16_to_cpu(scp->addrloc) & DN_SK_HASH_MASK]; -} - -/* - * Valid ports are those greater than zero and not already in use. - */ -static int check_port(__le16 port) -{ - struct sock *sk; - - if (port == 0) - return -1; - - 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; - } - return 0; -} - -static unsigned short port_alloc(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); -static unsigned short port = 0x2000; - unsigned short i_port = port; - - while(check_port(cpu_to_le16(++port)) != 0) { - if (port == i_port) - return 0; - } - - scp->addrloc = cpu_to_le16(port); - - return 1; -} - -/* - * Since this is only ever called from user - * level, we don't need a write_lock() version - * of this. - */ -static int dn_hash_sock(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - struct hlist_head *list; - int rv = -EUSERS; - - BUG_ON(sk_hashed(sk)); - - write_lock_bh(&dn_hash_lock); - - if (!scp->addrloc && !port_alloc(sk)) - goto out; - - rv = -EADDRINUSE; - if ((list = dn_find_list(sk)) == NULL) - goto out; - - sk_add_node(sk, list); - rv = 0; -out: - write_unlock_bh(&dn_hash_lock); - return rv; -} - -static void dn_unhash_sock(struct sock *sk) -{ - write_lock(&dn_hash_lock); - sk_del_node_init(sk); - write_unlock(&dn_hash_lock); -} - -static void dn_unhash_sock_bh(struct sock *sk) -{ - write_lock_bh(&dn_hash_lock); - sk_del_node_init(sk); - write_unlock_bh(&dn_hash_lock); -} - -static struct hlist_head *listen_hash(struct sockaddr_dn *addr) -{ - int i; - unsigned int hash = addr->sdn_objnum; - - if (hash == 0) { - hash = addr->sdn_objnamel; - for(i = 0; i < le16_to_cpu(addr->sdn_objnamel); i++) { - hash ^= addr->sdn_objname[i]; - hash ^= (hash << 3); - } - } - - return &dn_sk_hash[hash & DN_SK_HASH_MASK]; -} - -/* - * Called to transform a socket from bound (i.e. with a local address) - * into a listening socket (doesn't need a local port number) and rehashes - * based upon the object name/number. - */ -static void dn_rehash_sock(struct sock *sk) -{ - struct hlist_head *list; - struct dn_scp *scp = DN_SK(sk); - - if (scp->addr.sdn_flags & SDF_WILD) - return; - - write_lock_bh(&dn_hash_lock); - sk_del_node_init(sk); - DN_SK(sk)->addrloc = 0; - list = listen_hash(&DN_SK(sk)->addr); - sk_add_node(sk, list); - write_unlock_bh(&dn_hash_lock); -} - -int dn_sockaddr2username(struct sockaddr_dn *sdn, unsigned char *buf, unsigned char type) -{ - int len = 2; - - *buf++ = type; - - switch (type) { - case 0: - *buf++ = sdn->sdn_objnum; - break; - case 1: - *buf++ = 0; - *buf++ = le16_to_cpu(sdn->sdn_objnamel); - memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); - len = 3 + le16_to_cpu(sdn->sdn_objnamel); - break; - case 2: - memset(buf, 0, 5); - buf += 5; - *buf++ = le16_to_cpu(sdn->sdn_objnamel); - memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); - len = 7 + le16_to_cpu(sdn->sdn_objnamel); - break; - } - - return len; -} - -/* - * On reception of usernames, we handle types 1 and 0 for destination - * addresses only. Types 2 and 4 are used for source addresses, but the - * UIC, GIC are ignored and they are both treated the same way. Type 3 - * is never used as I've no idea what its purpose might be or what its - * format is. - */ -int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *sdn, unsigned char *fmt) -{ - unsigned char type; - int size = len; - int namel = 12; - - sdn->sdn_objnum = 0; - sdn->sdn_objnamel = cpu_to_le16(0); - memset(sdn->sdn_objname, 0, DN_MAXOBJL); - - if (len < 2) - return -1; - - len -= 2; - *fmt = *data++; - type = *data++; - - switch (*fmt) { - case 0: - sdn->sdn_objnum = type; - return 2; - case 1: - namel = 16; - break; - case 2: - len -= 4; - data += 4; - break; - case 4: - len -= 8; - data += 8; - break; - default: - return -1; - } - - len -= 1; - - if (len < 0) - return -1; - - sdn->sdn_objnamel = cpu_to_le16(*data++); - len -= le16_to_cpu(sdn->sdn_objnamel); - - if ((len < 0) || (le16_to_cpu(sdn->sdn_objnamel) > namel)) - return -1; - - memcpy(sdn->sdn_objname, data, le16_to_cpu(sdn->sdn_objnamel)); - - return size - len; -} - -struct sock *dn_sklist_find_listener(struct sockaddr_dn *addr) -{ - struct hlist_head *list = listen_hash(addr); - struct sock *sk; - - read_lock(&dn_hash_lock); - sk_for_each(sk, list) { - struct dn_scp *scp = DN_SK(sk); - if (sk->sk_state != TCP_LISTEN) - continue; - if (scp->addr.sdn_objnum) { - if (scp->addr.sdn_objnum != addr->sdn_objnum) - continue; - } else { - if (addr->sdn_objnum) - continue; - if (scp->addr.sdn_objnamel != addr->sdn_objnamel) - continue; - if (memcmp(scp->addr.sdn_objname, addr->sdn_objname, le16_to_cpu(addr->sdn_objnamel)) != 0) - continue; - } - sock_hold(sk); - read_unlock(&dn_hash_lock); - return sk; - } - - sk = sk_head(&dn_wild_sk); - if (sk) { - if (sk->sk_state == TCP_LISTEN) - sock_hold(sk); - else - sk = NULL; - } - - read_unlock(&dn_hash_lock); - return sk; -} - -struct sock *dn_find_by_skb(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct sock *sk; - struct dn_scp *scp; - - read_lock(&dn_hash_lock); - 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; - if (cb->dst_port != scp->addrloc) - continue; - if (scp->addrrem && (cb->src_port != scp->addrrem)) - continue; - sock_hold(sk); - goto found; - } - sk = NULL; -found: - read_unlock(&dn_hash_lock); - return sk; -} - - - -static void dn_destruct(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - skb_queue_purge(&scp->data_xmit_queue); - skb_queue_purge(&scp->other_xmit_queue); - skb_queue_purge(&scp->other_receive_queue); - - dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); -} - -static unsigned long dn_memory_pressure; - -static void dn_enter_memory_pressure(struct sock *sk) -{ - if (!dn_memory_pressure) { - dn_memory_pressure = 1; - } -} - -static struct proto dn_proto = { - .name = "NSP", - .owner = THIS_MODULE, - .enter_memory_pressure = dn_enter_memory_pressure, - .memory_pressure = &dn_memory_pressure, - .memory_allocated = &decnet_memory_allocated, - .sysctl_mem = sysctl_decnet_mem, - .sysctl_wmem = sysctl_decnet_wmem, - .sysctl_rmem = sysctl_decnet_rmem, - .max_header = DN_MAX_NSP_DATA_HEADER + 64, - .obj_size = sizeof(struct dn_sock), -}; - -static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gfp, int kern) -{ - struct dn_scp *scp; - struct sock *sk = sk_alloc(net, PF_DECnet, gfp, &dn_proto, kern); - - if (!sk) - goto out; - - if (sock) - sock->ops = &dn_proto_ops; - sock_init_data(sock, sk); - - sk->sk_backlog_rcv = dn_nsp_backlog_rcv; - sk->sk_destruct = dn_destruct; - sk->sk_no_check_tx = 1; - sk->sk_family = PF_DECnet; - sk->sk_protocol = 0; - sk->sk_allocation = gfp; - sk->sk_sndbuf = sysctl_decnet_wmem[1]; - sk->sk_rcvbuf = sysctl_decnet_rmem[1]; - - /* Initialization of DECnet Session Control Port */ - scp = DN_SK(sk); - scp->state = DN_O; /* Open */ - scp->numdat = 1; /* Next data seg to tx */ - scp->numoth = 1; /* Next oth data to tx */ - scp->ackxmt_dat = 0; /* Last data seg ack'ed */ - scp->ackxmt_oth = 0; /* Last oth data ack'ed */ - scp->ackrcv_dat = 0; /* Highest data ack recv*/ - scp->ackrcv_oth = 0; /* Last oth data ack rec*/ - scp->flowrem_sw = DN_SEND; - scp->flowloc_sw = DN_SEND; - scp->flowrem_dat = 0; - scp->flowrem_oth = 1; - scp->flowloc_dat = 0; - scp->flowloc_oth = 1; - scp->services_rem = 0; - scp->services_loc = 1 | NSP_FC_NONE; - scp->info_rem = 0; - scp->info_loc = 0x03; /* NSP version 4.1 */ - scp->segsize_rem = 230 - DN_MAX_NSP_DATA_HEADER; /* Default: Updated by remote segsize */ - scp->nonagle = 0; - scp->multi_ireq = 1; - scp->accept_mode = ACC_IMMED; - scp->addr.sdn_family = AF_DECnet; - scp->peer.sdn_family = AF_DECnet; - scp->accessdata.acc_accl = 5; - memcpy(scp->accessdata.acc_acc, "LINUX", 5); - - scp->max_window = NSP_MAX_WINDOW; - scp->snd_window = NSP_MIN_WINDOW; - scp->nsp_srtt = NSP_INITIAL_SRTT; - scp->nsp_rttvar = NSP_INITIAL_RTTVAR; - scp->nsp_rxtshift = 0; - - skb_queue_head_init(&scp->data_xmit_queue); - skb_queue_head_init(&scp->other_xmit_queue); - skb_queue_head_init(&scp->other_receive_queue); - - scp->persist = 0; - scp->persist_fxn = NULL; - scp->keepalive = 10 * HZ; - scp->keepalive_fxn = dn_keepalive; - - dn_start_slow_timer(sk); -out: - return sk; -} - -/* - * Keepalive timer. - * FIXME: Should respond to SO_KEEPALIVE etc. - */ -static void dn_keepalive(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - /* - * By checking the other_data transmit queue is empty - * we are double checking that we are not sending too - * many of these keepalive frames. - */ - if (skb_queue_empty(&scp->other_xmit_queue)) - dn_nsp_send_link(sk, DN_NOCHANGE, 0); -} - - -/* - * Timer for shutdown/destroyed sockets. - * When socket is dead & no packets have been sent for a - * certain amount of time, they are removed by this - * routine. Also takes care of sending out DI & DC - * frames at correct times. - */ -int dn_destroy_timer(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - scp->persist = dn_nsp_persist(sk); - - switch (scp->state) { - case DN_DI: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); - if (scp->nsp_rxtshift >= decnet_di_count) - scp->state = DN_CN; - return 0; - - case DN_DR: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); - if (scp->nsp_rxtshift >= decnet_dr_count) - scp->state = DN_DRC; - return 0; - - case DN_DN: - if (scp->nsp_rxtshift < decnet_dn_count) { - /* printk(KERN_DEBUG "dn_destroy_timer: DN\n"); */ - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, - GFP_ATOMIC); - return 0; - } - } - - scp->persist = (HZ * decnet_time_wait); - - if (sk->sk_socket) - return 0; - - if (time_after_eq(jiffies, scp->stamp + HZ * decnet_time_wait)) { - dn_unhash_sock(sk); - sock_put(sk); - return 1; - } - - return 0; -} - -static void dn_destroy_sock(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - scp->nsp_rxtshift = 0; /* reset back off */ - - if (sk->sk_socket) { - if (sk->sk_socket->state != SS_UNCONNECTED) - sk->sk_socket->state = SS_DISCONNECTING; - } - - sk->sk_state = TCP_CLOSE; - - switch (scp->state) { - case DN_DN: - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, - sk->sk_allocation); - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - break; - case DN_CR: - scp->state = DN_DR; - goto disc_reject; - case DN_RUN: - scp->state = DN_DI; - /* fall through */ - case DN_DI: - case DN_DR: -disc_reject: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); - /* fall through */ - case DN_NC: - case DN_NR: - case DN_RJ: - case DN_DIC: - case DN_CN: - case DN_DRC: - case DN_CI: - case DN_CD: - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - break; - default: - printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); - /* fall through */ - case DN_O: - dn_stop_slow_timer(sk); - - dn_unhash_sock_bh(sk); - sock_put(sk); - - break; - } -} - -char *dn_addr2asc(__u16 addr, char *buf) -{ - unsigned short node, area; - - node = addr & 0x03ff; - area = addr >> 10; - sprintf(buf, "%hd.%hd", area, node); - - return buf; -} - - - -static int dn_create(struct net *net, struct socket *sock, int protocol, - int kern) -{ - struct sock *sk; - - if (protocol < 0 || protocol > SK_PROTOCOL_MAX) - return -EINVAL; - - if (!net_eq(net, &init_net)) - return -EAFNOSUPPORT; - - switch (sock->type) { - case SOCK_SEQPACKET: - if (protocol != DNPROTO_NSP) - return -EPROTONOSUPPORT; - break; - case SOCK_STREAM: - break; - default: - return -ESOCKTNOSUPPORT; - } - - - if ((sk = dn_alloc_sock(net, sock, GFP_KERNEL, kern)) == NULL) - return -ENOBUFS; - - sk->sk_protocol = protocol; - - return 0; -} - - -static int -dn_release(struct socket *sock) -{ - struct sock *sk = sock->sk; - - if (sk) { - sock_orphan(sk); - sock_hold(sk); - lock_sock(sk); - dn_destroy_sock(sk); - release_sock(sk); - sock_put(sk); - } - - return 0; -} - -static int dn_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - struct sockaddr_dn *saddr = (struct sockaddr_dn *)uaddr; - struct net_device *dev, *ldev; - int rv; - - if (addr_len != sizeof(struct sockaddr_dn)) - return -EINVAL; - - if (saddr->sdn_family != AF_DECnet) - return -EINVAL; - - if (le16_to_cpu(saddr->sdn_nodeaddrl) && (le16_to_cpu(saddr->sdn_nodeaddrl) != 2)) - return -EINVAL; - - if (le16_to_cpu(saddr->sdn_objnamel) > DN_MAXOBJL) - return -EINVAL; - - if (saddr->sdn_flags & ~SDF_WILD) - return -EINVAL; - - if (!capable(CAP_NET_BIND_SERVICE) && (saddr->sdn_objnum || - (saddr->sdn_flags & SDF_WILD))) - return -EACCES; - - if (!(saddr->sdn_flags & SDF_WILD)) { - if (le16_to_cpu(saddr->sdn_nodeaddrl)) { - rcu_read_lock(); - ldev = NULL; - for_each_netdev_rcu(&init_net, dev) { - if (!dev->dn_ptr) - continue; - if (dn_dev_islocal(dev, dn_saddr2dn(saddr))) { - ldev = dev; - break; - } - } - rcu_read_unlock(); - if (ldev == NULL) - return -EADDRNOTAVAIL; - } - } - - rv = -EINVAL; - lock_sock(sk); - if (sock_flag(sk, SOCK_ZAPPED)) { - memcpy(&scp->addr, saddr, addr_len); - sock_reset_flag(sk, SOCK_ZAPPED); - - rv = dn_hash_sock(sk); - if (rv) - sock_set_flag(sk, SOCK_ZAPPED); - } - release_sock(sk); - - return rv; -} - - -static int dn_auto_bind(struct socket *sock) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - int rv; - - sock_reset_flag(sk, SOCK_ZAPPED); - - scp->addr.sdn_flags = 0; - scp->addr.sdn_objnum = 0; - - /* - * This stuff is to keep compatibility with Eduardo's - * patch. I hope I can dispense with it shortly... - */ - if ((scp->accessdata.acc_accl != 0) && - (scp->accessdata.acc_accl <= 12)) { - - scp->addr.sdn_objnamel = cpu_to_le16(scp->accessdata.acc_accl); - memcpy(scp->addr.sdn_objname, scp->accessdata.acc_acc, le16_to_cpu(scp->addr.sdn_objnamel)); - - scp->accessdata.acc_accl = 0; - memset(scp->accessdata.acc_acc, 0, 40); - } - /* End of compatibility stuff */ - - scp->addr.sdn_add.a_len = cpu_to_le16(2); - rv = dn_dev_bind_default((__le16 *)scp->addr.sdn_add.a_addr); - if (rv == 0) { - rv = dn_hash_sock(sk); - if (rv) - sock_set_flag(sk, SOCK_ZAPPED); - } - - return rv; -} - -static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) -{ - struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); - int err; - - if (scp->state != DN_CR) - return -EINVAL; - - scp->state = DN_CC; - scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk)); - dn_send_conn_conf(sk, allocation); - - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - for(;;) { - release_sock(sk); - if (scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); - lock_sock(sk); - err = 0; - if (scp->state == DN_RUN) - break; - err = sock_error(sk); - if (err) - break; - err = sock_intr_errno(*timeo); - if (signal_pending(current)) - break; - err = -EAGAIN; - if (!*timeo) - break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - } - finish_wait(sk_sleep(sk), &wait); - if (err == 0) { - sk->sk_socket->state = SS_CONNECTED; - } else if (scp->state != DN_CC) { - sk->sk_socket->state = SS_UNCONNECTED; - } - return err; -} - -static int dn_wait_run(struct sock *sk, long *timeo) -{ - struct dn_scp *scp = DN_SK(sk); - DEFINE_WAIT(wait); - int err = 0; - - if (scp->state == DN_RUN) - goto out; - - if (!*timeo) - return -EALREADY; - - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - for(;;) { - release_sock(sk); - if (scp->state == DN_CI || scp->state == DN_CC) - *timeo = schedule_timeout(*timeo); - lock_sock(sk); - err = 0; - if (scp->state == DN_RUN) - break; - err = sock_error(sk); - if (err) - break; - err = sock_intr_errno(*timeo); - if (signal_pending(current)) - break; - err = -ETIMEDOUT; - if (!*timeo) - break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - } - finish_wait(sk_sleep(sk), &wait); -out: - if (err == 0) { - sk->sk_socket->state = SS_CONNECTED; - } else if (scp->state != DN_CI && scp->state != DN_CC) { - sk->sk_socket->state = SS_UNCONNECTED; - } - return err; -} - -static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen, long *timeo, int flags) -{ - struct socket *sock = sk->sk_socket; - struct dn_scp *scp = DN_SK(sk); - int err = -EISCONN; - struct flowidn fld; - struct dst_entry *dst; - - if (sock->state == SS_CONNECTED) - goto out; - - if (sock->state == SS_CONNECTING) { - err = 0; - if (scp->state == DN_RUN) { - sock->state = SS_CONNECTED; - goto out; - } - err = -ECONNREFUSED; - if (scp->state != DN_CI && scp->state != DN_CC) { - sock->state = SS_UNCONNECTED; - goto out; - } - return dn_wait_run(sk, timeo); - } - - err = -EINVAL; - if (scp->state != DN_O) - goto out; - - if (addr == NULL || addrlen != sizeof(struct sockaddr_dn)) - goto out; - if (addr->sdn_family != AF_DECnet) - goto out; - if (addr->sdn_flags & SDF_WILD) - goto out; - - if (sock_flag(sk, SOCK_ZAPPED)) { - err = dn_auto_bind(sk->sk_socket); - if (err) - goto out; - } - - memcpy(&scp->peer, addr, sizeof(struct sockaddr_dn)); - - err = -EHOSTUNREACH; - memset(&fld, 0, sizeof(fld)); - fld.flowidn_oif = sk->sk_bound_dev_if; - fld.daddr = dn_saddr2dn(&scp->peer); - fld.saddr = dn_saddr2dn(&scp->addr); - dn_sk_ports_copy(&fld, scp); - fld.flowidn_proto = DNPROTO_NSP; - if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, flags) < 0) - goto out; - dst = __sk_dst_get(sk); - sk->sk_route_caps = dst->dev->features; - sock->state = SS_CONNECTING; - scp->state = DN_CI; - scp->segsize_loc = dst_metric_advmss(dst); - - dn_nsp_send_conninit(sk, NSP_CI); - err = -EINPROGRESS; - if (*timeo) { - err = dn_wait_run(sk, timeo); - } -out: - return err; -} - -static int dn_connect(struct socket *sock, struct sockaddr *uaddr, int addrlen, int flags) -{ - struct sockaddr_dn *addr = (struct sockaddr_dn *)uaddr; - struct sock *sk = sock->sk; - int err; - long timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); - - lock_sock(sk); - err = __dn_connect(sk, addr, addrlen, &timeo, 0); - release_sock(sk); - - return err; -} - -static inline int dn_check_state(struct sock *sk, struct sockaddr_dn *addr, int addrlen, long *timeo, int flags) -{ - struct dn_scp *scp = DN_SK(sk); - - switch (scp->state) { - case DN_RUN: - return 0; - case DN_CR: - return dn_confirm_accept(sk, timeo, sk->sk_allocation); - case DN_CI: - case DN_CC: - return dn_wait_run(sk, timeo); - case DN_O: - return __dn_connect(sk, addr, addrlen, timeo, flags); - } - - return -EINVAL; -} - - -static void dn_access_copy(struct sk_buff *skb, struct accessdata_dn *acc) -{ - unsigned char *ptr = skb->data; - - acc->acc_userl = *ptr++; - memcpy(&acc->acc_user, ptr, acc->acc_userl); - ptr += acc->acc_userl; - - acc->acc_passl = *ptr++; - memcpy(&acc->acc_pass, ptr, acc->acc_passl); - ptr += acc->acc_passl; - - acc->acc_accl = *ptr++; - memcpy(&acc->acc_acc, ptr, acc->acc_accl); - - skb_pull(skb, acc->acc_accl + acc->acc_passl + acc->acc_userl + 3); - -} - -static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt) -{ - unsigned char *ptr = skb->data; - u16 len = *ptr++; /* yes, it's 8bit on the wire */ - - BUG_ON(len > 16); /* we've checked the contents earlier */ - opt->opt_optl = cpu_to_le16(len); - opt->opt_status = 0; - memcpy(opt->opt_data, ptr, len); - skb_pull(skb, len + 1); -} - -static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) -{ - DEFINE_WAIT(wait); - struct sk_buff *skb = NULL; - int err = 0; - - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - for(;;) { - release_sock(sk); - skb = skb_dequeue(&sk->sk_receive_queue); - if (skb == NULL) { - *timeo = schedule_timeout(*timeo); - skb = skb_dequeue(&sk->sk_receive_queue); - } - lock_sock(sk); - if (skb != NULL) - break; - err = -EINVAL; - if (sk->sk_state != TCP_LISTEN) - break; - err = sock_intr_errno(*timeo); - if (signal_pending(current)) - break; - err = -EAGAIN; - if (!*timeo) - break; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - } - finish_wait(sk_sleep(sk), &wait); - - return skb == NULL ? ERR_PTR(err) : skb; -} - -static int dn_accept(struct socket *sock, struct socket *newsock, int flags, - bool kern) -{ - struct sock *sk = sock->sk, *newsk; - struct sk_buff *skb = NULL; - struct dn_skb_cb *cb; - unsigned char menuver; - int err = 0; - unsigned char type; - long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); - struct dst_entry *dst; - - lock_sock(sk); - - if (sk->sk_state != TCP_LISTEN || DN_SK(sk)->state != DN_O) { - release_sock(sk); - return -EINVAL; - } - - skb = skb_dequeue(&sk->sk_receive_queue); - if (skb == NULL) { - skb = dn_wait_for_connect(sk, &timeo); - if (IS_ERR(skb)) { - release_sock(sk); - return PTR_ERR(skb); - } - } - - cb = DN_SKB_CB(skb); - sk->sk_ack_backlog--; - newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern); - if (newsk == NULL) { - release_sock(sk); - kfree_skb(skb); - return -ENOBUFS; - } - release_sock(sk); - - dst = skb_dst(skb); - sk_dst_set(newsk, dst); - skb_dst_set(skb, NULL); - - DN_SK(newsk)->state = DN_CR; - DN_SK(newsk)->addrrem = cb->src_port; - DN_SK(newsk)->services_rem = cb->services; - DN_SK(newsk)->info_rem = cb->info; - DN_SK(newsk)->segsize_rem = cb->segsize; - DN_SK(newsk)->accept_mode = DN_SK(sk)->accept_mode; - - if (DN_SK(newsk)->segsize_rem < 230) - DN_SK(newsk)->segsize_rem = 230; - - if ((DN_SK(newsk)->services_rem & NSP_FC_MASK) == NSP_FC_NONE) - DN_SK(newsk)->max_window = decnet_no_fc_max_cwnd; - - newsk->sk_state = TCP_LISTEN; - memcpy(&(DN_SK(newsk)->addr), &(DN_SK(sk)->addr), sizeof(struct sockaddr_dn)); - - /* - * If we are listening on a wild socket, we don't want - * the newly created socket on the wrong hash queue. - */ - DN_SK(newsk)->addr.sdn_flags &= ~SDF_WILD; - - skb_pull(skb, dn_username2sockaddr(skb->data, skb->len, &(DN_SK(newsk)->addr), &type)); - skb_pull(skb, dn_username2sockaddr(skb->data, skb->len, &(DN_SK(newsk)->peer), &type)); - *(__le16 *)(DN_SK(newsk)->peer.sdn_add.a_addr) = cb->src; - *(__le16 *)(DN_SK(newsk)->addr.sdn_add.a_addr) = cb->dst; - - menuver = *skb->data; - skb_pull(skb, 1); - - if (menuver & DN_MENUVER_ACC) - dn_access_copy(skb, &(DN_SK(newsk)->accessdata)); - - if (menuver & DN_MENUVER_USR) - dn_user_copy(skb, &(DN_SK(newsk)->conndata_in)); - - if (menuver & DN_MENUVER_PRX) - DN_SK(newsk)->peer.sdn_flags |= SDF_PROXY; - - if (menuver & DN_MENUVER_UIC) - DN_SK(newsk)->peer.sdn_flags |= SDF_UICPROXY; - - kfree_skb(skb); - - memcpy(&(DN_SK(newsk)->conndata_out), &(DN_SK(sk)->conndata_out), - sizeof(struct optdata_dn)); - memcpy(&(DN_SK(newsk)->discdata_out), &(DN_SK(sk)->discdata_out), - sizeof(struct optdata_dn)); - - lock_sock(newsk); - err = dn_hash_sock(newsk); - if (err == 0) { - sock_reset_flag(newsk, SOCK_ZAPPED); - dn_send_conn_ack(newsk); - - /* - * Here we use sk->sk_allocation since although the conn conf is - * for the newsk, the context is the old socket. - */ - if (DN_SK(newsk)->accept_mode == ACC_IMMED) - err = dn_confirm_accept(newsk, &timeo, - sk->sk_allocation); - } - release_sock(newsk); - return err; -} - - -static int dn_getname(struct socket *sock, struct sockaddr *uaddr,int peer) -{ - struct sockaddr_dn *sa = (struct sockaddr_dn *)uaddr; - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - - lock_sock(sk); - - if (peer) { - if ((sock->state != SS_CONNECTED && - sock->state != SS_CONNECTING) && - scp->accept_mode == ACC_IMMED) { - release_sock(sk); - return -ENOTCONN; - } - - memcpy(sa, &scp->peer, sizeof(struct sockaddr_dn)); - } else { - memcpy(sa, &scp->addr, sizeof(struct sockaddr_dn)); - } - - release_sock(sk); - - return sizeof(struct sockaddr_dn); -} - - -static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wait) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - __poll_t mask = datagram_poll(file, sock, wait); - - if (!skb_queue_empty_lockless(&scp->other_receive_queue)) - mask |= EPOLLRDBAND; - - return mask; -} - -static int dn_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - int err = -EOPNOTSUPP; - long amount = 0; - struct sk_buff *skb; - int val; - - switch(cmd) - { - case SIOCGIFADDR: - case SIOCSIFADDR: - return dn_dev_ioctl(cmd, (void __user *)arg); - - case SIOCATMARK: - lock_sock(sk); - val = !skb_queue_empty(&scp->other_receive_queue); - if (scp->state != DN_RUN) - val = -ENOTCONN; - release_sock(sk); - return val; - - case TIOCOUTQ: - amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); - if (amount < 0) - amount = 0; - err = put_user(amount, (int __user *)arg); - break; - - case TIOCINQ: - lock_sock(sk); - skb = skb_peek(&scp->other_receive_queue); - if (skb) { - amount = skb->len; - } else { - skb_queue_walk(&sk->sk_receive_queue, skb) - amount += skb->len; - } - release_sock(sk); - err = put_user(amount, (int __user *)arg); - break; - - default: - err = -ENOIOCTLCMD; - break; - } - - return err; -} - -static int dn_listen(struct socket *sock, int backlog) -{ - struct sock *sk = sock->sk; - int err = -EINVAL; - - lock_sock(sk); - - if (sock_flag(sk, SOCK_ZAPPED)) - goto out; - - if ((DN_SK(sk)->state != DN_O) || (sk->sk_state == TCP_LISTEN)) - goto out; - - sk->sk_max_ack_backlog = backlog; - sk->sk_ack_backlog = 0; - sk->sk_state = TCP_LISTEN; - err = 0; - dn_rehash_sock(sk); - -out: - release_sock(sk); - - return err; -} - - -static int dn_shutdown(struct socket *sock, int how) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - int err = -ENOTCONN; - - lock_sock(sk); - - if (sock->state == SS_UNCONNECTED) - goto out; - - err = 0; - if (sock->state == SS_DISCONNECTING) - goto out; - - err = -EINVAL; - if (scp->state == DN_O) - goto out; - - if (how != SHUT_RDWR) - goto out; - - sk->sk_shutdown = SHUTDOWN_MASK; - dn_destroy_sock(sk); - err = 0; - -out: - release_sock(sk); - - return err; -} - -static int dn_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) -{ - struct sock *sk = sock->sk; - int err; - - lock_sock(sk); - err = __dn_setsockopt(sock, level, optname, optval, optlen, 0); - release_sock(sk); -#ifdef CONFIG_NETFILTER - /* we need to exclude all possible ENOPROTOOPTs except default case */ - if (err == -ENOPROTOOPT && optname != DSO_LINKINFO && - optname != DSO_STREAM && optname != DSO_SEQPACKET) - err = nf_setsockopt(sk, PF_DECnet, optname, optval, optlen); -#endif - - return err; -} - -static int __dn_setsockopt(struct socket *sock, int level,int optname, char __user *optval, unsigned int optlen, int flags) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - long timeo; - union { - struct optdata_dn opt; - struct accessdata_dn acc; - int mode; - unsigned long win; - int val; - unsigned char services; - unsigned char info; - } u; - int err; - - if (optlen && !optval) - return -EINVAL; - - if (optlen > sizeof(u)) - return -EINVAL; - - if (copy_from_user(&u, optval, optlen)) - return -EFAULT; - - switch (optname) { - case DSO_CONDATA: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if ((scp->state != DN_O) && (scp->state != DN_CR)) - return -EINVAL; - - if (optlen != sizeof(struct optdata_dn)) - return -EINVAL; - - if (le16_to_cpu(u.opt.opt_optl) > 16) - return -EINVAL; - - memcpy(&scp->conndata_out, &u.opt, optlen); - break; - - case DSO_DISDATA: - if (sock->state != SS_CONNECTED && - scp->accept_mode == ACC_IMMED) - return -ENOTCONN; - - if (optlen != sizeof(struct optdata_dn)) - return -EINVAL; - - if (le16_to_cpu(u.opt.opt_optl) > 16) - return -EINVAL; - - memcpy(&scp->discdata_out, &u.opt, optlen); - break; - - case DSO_CONACCESS: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if (scp->state != DN_O) - return -EINVAL; - - if (optlen != sizeof(struct accessdata_dn)) - return -EINVAL; - - if ((u.acc.acc_accl > DN_MAXACCL) || - (u.acc.acc_passl > DN_MAXACCL) || - (u.acc.acc_userl > DN_MAXACCL)) - return -EINVAL; - - memcpy(&scp->accessdata, &u.acc, optlen); - break; - - case DSO_ACCEPTMODE: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if (scp->state != DN_O) - return -EINVAL; - - if (optlen != sizeof(int)) - return -EINVAL; - - if ((u.mode != ACC_IMMED) && (u.mode != ACC_DEFER)) - return -EINVAL; - - scp->accept_mode = (unsigned char)u.mode; - break; - - case DSO_CONACCEPT: - if (scp->state != DN_CR) - return -EINVAL; - timeo = sock_rcvtimeo(sk, 0); - err = dn_confirm_accept(sk, &timeo, sk->sk_allocation); - return err; - - case DSO_CONREJECT: - if (scp->state != DN_CR) - return -EINVAL; - - scp->state = DN_DR; - sk->sk_shutdown = SHUTDOWN_MASK; - dn_nsp_send_disc(sk, 0x38, 0, sk->sk_allocation); - break; - - case DSO_MAXWINDOW: - if (optlen != sizeof(unsigned long)) - return -EINVAL; - if (u.win > NSP_MAX_WINDOW) - u.win = NSP_MAX_WINDOW; - if (u.win == 0) - return -EINVAL; - scp->max_window = u.win; - if (scp->snd_window > u.win) - scp->snd_window = u.win; - break; - - case DSO_NODELAY: - if (optlen != sizeof(int)) - return -EINVAL; - if (scp->nonagle == TCP_NAGLE_CORK) - return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_OFF; - /* if (scp->nonagle == 1) { Push pending frames } */ - break; - - case DSO_CORK: - if (optlen != sizeof(int)) - return -EINVAL; - if (scp->nonagle == TCP_NAGLE_OFF) - return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : TCP_NAGLE_CORK; - /* if (scp->nonagle == 0) { Push pending frames } */ - break; - - case DSO_SERVICES: - if (optlen != sizeof(unsigned char)) - return -EINVAL; - if ((u.services & ~NSP_FC_MASK) != 0x01) - return -EINVAL; - if ((u.services & NSP_FC_MASK) == NSP_FC_MASK) - return -EINVAL; - scp->services_loc = u.services; - break; - - case DSO_INFO: - if (optlen != sizeof(unsigned char)) - return -EINVAL; - if (u.info & 0xfc) - return -EINVAL; - scp->info_loc = u.info; - break; - - case DSO_LINKINFO: - case DSO_STREAM: - case DSO_SEQPACKET: - default: - return -ENOPROTOOPT; - } - - return 0; -} - -static int dn_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) -{ - struct sock *sk = sock->sk; - int err; - - lock_sock(sk); - err = __dn_getsockopt(sock, level, optname, optval, optlen, 0); - release_sock(sk); -#ifdef CONFIG_NETFILTER - if (err == -ENOPROTOOPT && optname != DSO_STREAM && - optname != DSO_SEQPACKET && optname != DSO_CONACCEPT && - optname != DSO_CONREJECT) { - int len; - - if (get_user(len, optlen)) - return -EFAULT; - - err = nf_getsockopt(sk, PF_DECnet, optname, optval, &len); - if (err >= 0) - err = put_user(len, optlen); - } -#endif - - return err; -} - -static int __dn_getsockopt(struct socket *sock, int level,int optname, char __user *optval,int __user *optlen, int flags) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - struct linkinfo_dn link; - unsigned int r_len; - void *r_data = NULL; - unsigned int val; - - if(get_user(r_len , optlen)) - return -EFAULT; - - switch (optname) { - case DSO_CONDATA: - if (r_len > sizeof(struct optdata_dn)) - r_len = sizeof(struct optdata_dn); - r_data = &scp->conndata_in; - break; - - case DSO_DISDATA: - if (r_len > sizeof(struct optdata_dn)) - r_len = sizeof(struct optdata_dn); - r_data = &scp->discdata_in; - break; - - case DSO_CONACCESS: - if (r_len > sizeof(struct accessdata_dn)) - r_len = sizeof(struct accessdata_dn); - r_data = &scp->accessdata; - break; - - case DSO_ACCEPTMODE: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->accept_mode; - break; - - case DSO_LINKINFO: - if (r_len > sizeof(struct linkinfo_dn)) - r_len = sizeof(struct linkinfo_dn); - - memset(&link, 0, sizeof(link)); - - switch (sock->state) { - case SS_CONNECTING: - link.idn_linkstate = LL_CONNECTING; - break; - case SS_DISCONNECTING: - link.idn_linkstate = LL_DISCONNECTING; - break; - case SS_CONNECTED: - link.idn_linkstate = LL_RUNNING; - break; - default: - link.idn_linkstate = LL_INACTIVE; - } - - link.idn_segsize = scp->segsize_rem; - r_data = &link; - break; - - case DSO_MAXWINDOW: - if (r_len > sizeof(unsigned long)) - r_len = sizeof(unsigned long); - r_data = &scp->max_window; - break; - - case DSO_NODELAY: - if (r_len > sizeof(int)) - r_len = sizeof(int); - val = (scp->nonagle == TCP_NAGLE_OFF); - r_data = &val; - break; - - case DSO_CORK: - if (r_len > sizeof(int)) - r_len = sizeof(int); - val = (scp->nonagle == TCP_NAGLE_CORK); - r_data = &val; - break; - - case DSO_SERVICES: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->services_rem; - break; - - case DSO_INFO: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->info_rem; - break; - - case DSO_STREAM: - case DSO_SEQPACKET: - case DSO_CONACCEPT: - case DSO_CONREJECT: - default: - return -ENOPROTOOPT; - } - - if (r_data) { - if (copy_to_user(optval, r_data, r_len)) - return -EFAULT; - if (put_user(r_len, optlen)) - return -EFAULT; - } - - return 0; -} - - -static int dn_data_ready(struct sock *sk, struct sk_buff_head *q, int flags, int target) -{ - struct sk_buff *skb; - int len = 0; - - if (flags & MSG_OOB) - return !skb_queue_empty(q) ? 1 : 0; - - skb_queue_walk(q, skb) { - struct dn_skb_cb *cb = DN_SKB_CB(skb); - len += skb->len; - - if (cb->nsp_flags & 0x40) { - /* SOCK_SEQPACKET reads to EOM */ - if (sk->sk_type == SOCK_SEQPACKET) - return 1; - /* so does SOCK_STREAM unless WAITALL is specified */ - if (!(flags & MSG_WAITALL)) - return 1; - } - - /* minimum data length for read exceeded */ - if (len >= target) - return 1; - } - - return 0; -} - - -static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, - int flags) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - struct sk_buff_head *queue = &sk->sk_receive_queue; - size_t target = size > 1 ? 1 : 0; - size_t copied = 0; - int rv = 0; - struct sk_buff *skb, *n; - struct dn_skb_cb *cb = NULL; - unsigned char eor = 0; - long timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - if (sock_flag(sk, SOCK_ZAPPED)) { - rv = -EADDRNOTAVAIL; - goto out; - } - - if (sk->sk_shutdown & RCV_SHUTDOWN) { - rv = 0; - goto out; - } - - rv = dn_check_state(sk, NULL, 0, &timeo, flags); - if (rv) - goto out; - - if (flags & ~(MSG_CMSG_COMPAT|MSG_PEEK|MSG_OOB|MSG_WAITALL|MSG_DONTWAIT|MSG_NOSIGNAL)) { - rv = -EOPNOTSUPP; - goto out; - } - - if (flags & MSG_OOB) - queue = &scp->other_receive_queue; - - if (flags & MSG_WAITALL) - target = size; - - - /* - * See if there is data ready to read, sleep if there isn't - */ - for(;;) { - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - if (sk->sk_err) - goto out; - - if (!skb_queue_empty(&scp->other_receive_queue)) { - if (!(flags & MSG_OOB)) { - msg->msg_flags |= MSG_OOB; - if (!scp->other_report) { - scp->other_report = 1; - goto out; - } - } - } - - if (scp->state != DN_RUN) - goto out; - - if (signal_pending(current)) { - rv = sock_intr_errno(timeo); - goto out; - } - - if (dn_data_ready(sk, queue, flags, target)) - break; - - if (flags & MSG_DONTWAIT) { - rv = -EWOULDBLOCK; - goto out; - } - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - } - - skb_queue_walk_safe(queue, skb, n) { - unsigned int chunk = skb->len; - cb = DN_SKB_CB(skb); - - if ((chunk + copied) > size) - chunk = size - copied; - - if (memcpy_to_msg(msg, skb->data, chunk)) { - rv = -EFAULT; - break; - } - copied += chunk; - - if (!(flags & MSG_PEEK)) - skb_pull(skb, chunk); - - eor = cb->nsp_flags & 0x40; - - if (skb->len == 0) { - skb_unlink(skb, queue); - kfree_skb(skb); - /* - * N.B. Don't refer to skb or cb after this point - * in loop. - */ - if ((scp->flowloc_sw == DN_DONTSEND) && !dn_congested(sk)) { - scp->flowloc_sw = DN_SEND; - dn_nsp_send_link(sk, DN_SEND, 0); - } - } - - if (eor) { - if (sk->sk_type == SOCK_SEQPACKET) - break; - if (!(flags & MSG_WAITALL)) - break; - } - - if (flags & MSG_OOB) - break; - - if (copied >= target) - break; - } - - rv = copied; - - - if (eor && (sk->sk_type == SOCK_SEQPACKET)) - msg->msg_flags |= MSG_EOR; - -out: - if (rv == 0) - rv = (flags & MSG_PEEK) ? -sk->sk_err : sock_error(sk); - - if ((rv >= 0) && msg->msg_name) { - __sockaddr_check_size(sizeof(struct sockaddr_dn)); - memcpy(msg->msg_name, &scp->peer, sizeof(struct sockaddr_dn)); - msg->msg_namelen = sizeof(struct sockaddr_dn); - } - - release_sock(sk); - - return rv; -} - - -static inline int dn_queue_too_long(struct dn_scp *scp, struct sk_buff_head *queue, int flags) -{ - unsigned char fctype = scp->services_rem & NSP_FC_MASK; - if (skb_queue_len(queue) >= scp->snd_window) - return 1; - if (fctype != NSP_FC_NONE) { - if (flags & MSG_OOB) { - if (scp->flowrem_oth == 0) - return 1; - } else { - if (scp->flowrem_dat == 0) - return 1; - } - } - return 0; -} - -/* - * The DECnet spec requires that the "routing layer" accepts packets which - * are at least 230 bytes in size. This excludes any headers which the NSP - * layer might add, so we always assume that we'll be using the maximal - * length header on data packets. The variation in length is due to the - * inclusion (or not) of the two 16 bit acknowledgement fields so it doesn't - * make much practical difference. - */ -unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu) -{ - unsigned int mss = 230 - DN_MAX_NSP_DATA_HEADER; - if (dev) { - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - mtu -= LL_RESERVED_SPACE(dev); - if (dn_db->use_long) - mtu -= 21; - else - mtu -= 6; - mtu -= DN_MAX_NSP_DATA_HEADER; - } else { - /* - * 21 = long header, 16 = guess at MAC header length - */ - mtu -= (21 + DN_MAX_NSP_DATA_HEADER + 16); - } - if (mtu > mss) - mss = mtu; - return mss; -} - -static inline unsigned int dn_current_mss(struct sock *sk, int flags) -{ - struct dst_entry *dst = __sk_dst_get(sk); - struct dn_scp *scp = DN_SK(sk); - int mss_now = min_t(int, scp->segsize_loc, scp->segsize_rem); - - /* Other data messages are limited to 16 bytes per packet */ - if (flags & MSG_OOB) - return 16; - - /* This works out the maximum size of segment we can send out */ - if (dst) { - u32 mtu = dst_mtu(dst); - mss_now = min_t(int, dn_mss_from_pmtu(dst->dev, mtu), mss_now); - } - - return mss_now; -} - -/* - * N.B. We get the timeout wrong here, but then we always did get it - * wrong before and this is another step along the road to correcting - * it. It ought to get updated each time we pass through the routine, - * but in practise it probably doesn't matter too much for now. - */ -static inline struct sk_buff *dn_alloc_send_pskb(struct sock *sk, - unsigned long datalen, int noblock, - int *errcode) -{ - struct sk_buff *skb = sock_alloc_send_skb(sk, datalen, - noblock, errcode); - if (skb) { - skb->protocol = htons(ETH_P_DNA_RT); - skb->pkt_type = PACKET_OUTGOING; - } - return skb; -} - -static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) -{ - struct sock *sk = sock->sk; - struct dn_scp *scp = DN_SK(sk); - size_t mss; - struct sk_buff_head *queue = &scp->data_xmit_queue; - int flags = msg->msg_flags; - int err = 0; - size_t sent = 0; - int addr_len = msg->msg_namelen; - DECLARE_SOCKADDR(struct sockaddr_dn *, addr, msg->msg_name); - struct sk_buff *skb = NULL; - struct dn_skb_cb *cb; - size_t len; - unsigned char fctype; - long timeo; - - if (flags & ~(MSG_TRYHARD|MSG_OOB|MSG_DONTWAIT|MSG_EOR|MSG_NOSIGNAL|MSG_MORE|MSG_CMSG_COMPAT)) - return -EOPNOTSUPP; - - if (addr_len && (addr_len != sizeof(struct sockaddr_dn))) - return -EINVAL; - - lock_sock(sk); - timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* - * The only difference between stream sockets and sequenced packet - * sockets is that the stream sockets always behave as if MSG_EOR - * has been set. - */ - if (sock->type == SOCK_STREAM) { - if (flags & MSG_EOR) { - err = -EINVAL; - goto out; - } - flags |= MSG_EOR; - } - - - err = dn_check_state(sk, addr, addr_len, &timeo, flags); - if (err) - goto out_err; - - if (sk->sk_shutdown & SEND_SHUTDOWN) { - err = -EPIPE; - if (!(flags & MSG_NOSIGNAL)) - send_sig(SIGPIPE, current, 0); - goto out_err; - } - - if ((flags & MSG_TRYHARD) && sk->sk_dst_cache) - dst_negative_advice(sk); - - mss = scp->segsize_rem; - fctype = scp->services_rem & NSP_FC_MASK; - - mss = dn_current_mss(sk, flags); - - if (flags & MSG_OOB) { - queue = &scp->other_xmit_queue; - if (size > mss) { - err = -EMSGSIZE; - goto out; - } - } - - scp->persist_fxn = dn_nsp_xmit_timeout; - - while(sent < size) { - err = sock_error(sk); - if (err) - goto out; - - if (signal_pending(current)) { - err = sock_intr_errno(timeo); - goto out; - } - - /* - * Calculate size that we wish to send. - */ - len = size - sent; - - if (len > mss) - len = mss; - - /* - * Wait for queue size to go down below the window - * size. - */ - if (dn_queue_too_long(scp, queue, flags)) { - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - if (flags & MSG_DONTWAIT) { - err = -EWOULDBLOCK; - goto out; - } - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, - !dn_queue_too_long(scp, queue, flags), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - continue; - } - - /* - * Get a suitably sized skb. - * 64 is a bit of a hack really, but its larger than any - * link-layer headers and has served us well as a good - * guess as to their real length. - */ - skb = dn_alloc_send_pskb(sk, len + 64 + DN_MAX_NSP_DATA_HEADER, - flags & MSG_DONTWAIT, &err); - - if (err) - break; - - if (!skb) - continue; - - cb = DN_SKB_CB(skb); - - skb_reserve(skb, 64 + DN_MAX_NSP_DATA_HEADER); - - if (memcpy_from_msg(skb_put(skb, len), msg, len)) { - err = -EFAULT; - goto out; - } - - if (flags & MSG_OOB) { - cb->nsp_flags = 0x30; - if (fctype != NSP_FC_NONE) - scp->flowrem_oth--; - } else { - cb->nsp_flags = 0x00; - if (scp->seg_total == 0) - cb->nsp_flags |= 0x20; - - scp->seg_total += len; - - if (((sent + len) == size) && (flags & MSG_EOR)) { - cb->nsp_flags |= 0x40; - scp->seg_total = 0; - if (fctype == NSP_FC_SCMC) - scp->flowrem_dat--; - } - if (fctype == NSP_FC_SRC) - scp->flowrem_dat--; - } - - sent += len; - dn_nsp_queue_xmit(sk, skb, sk->sk_allocation, flags & MSG_OOB); - skb = NULL; - - scp->persist = dn_nsp_persist(sk); - - } -out: - - kfree_skb(skb); - - release_sock(sk); - - return sent ? sent : err; - -out_err: - err = sk_stream_error(sk, flags, err); - release_sock(sk); - return err; -} - -static int dn_device_event(struct notifier_block *this, unsigned long event, - void *ptr) -{ - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - switch (event) { - case NETDEV_UP: - dn_dev_up(dev); - break; - case NETDEV_DOWN: - dn_dev_down(dev); - break; - default: - break; - } - - return NOTIFY_DONE; -} - -static struct notifier_block dn_dev_notifier = { - .notifier_call = dn_device_event, -}; - -static struct packet_type dn_dix_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_DNA_RT), - .func = dn_route_rcv, -}; - -#ifdef CONFIG_PROC_FS -struct dn_iter_state { - int bucket; -}; - -static struct sock *dn_socket_get_first(struct seq_file *seq) -{ - struct dn_iter_state *state = seq->private; - struct sock *n = NULL; - - for(state->bucket = 0; - state->bucket < DN_SK_HASH_SIZE; - ++state->bucket) { - n = sk_head(&dn_sk_hash[state->bucket]); - if (n) - break; - } - - return n; -} - -static struct sock *dn_socket_get_next(struct seq_file *seq, - struct sock *n) -{ - struct dn_iter_state *state = seq->private; - - n = sk_next(n); -try_again: - if (n) - goto out; - if (++state->bucket >= DN_SK_HASH_SIZE) - goto out; - n = sk_head(&dn_sk_hash[state->bucket]); - goto try_again; -out: - return n; -} - -static struct sock *socket_get_idx(struct seq_file *seq, loff_t *pos) -{ - struct sock *sk = dn_socket_get_first(seq); - - if (sk) { - while(*pos && (sk = dn_socket_get_next(seq, sk))) - --*pos; - } - return *pos ? NULL : sk; -} - -static void *dn_socket_get_idx(struct seq_file *seq, loff_t pos) -{ - void *rc; - read_lock_bh(&dn_hash_lock); - rc = socket_get_idx(seq, &pos); - if (!rc) { - read_unlock_bh(&dn_hash_lock); - } - return rc; -} - -static void *dn_socket_seq_start(struct seq_file *seq, loff_t *pos) -{ - return *pos ? dn_socket_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; -} - -static void *dn_socket_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - void *rc; - - if (v == SEQ_START_TOKEN) { - rc = dn_socket_get_idx(seq, 0); - goto out; - } - - rc = dn_socket_get_next(seq, v); - if (rc) - goto out; - read_unlock_bh(&dn_hash_lock); -out: - ++*pos; - return rc; -} - -static void dn_socket_seq_stop(struct seq_file *seq, void *v) -{ - if (v && v != SEQ_START_TOKEN) - read_unlock_bh(&dn_hash_lock); -} - -#define IS_NOT_PRINTABLE(x) ((x) < 32 || (x) > 126) - -static void dn_printable_object(struct sockaddr_dn *dn, unsigned char *buf) -{ - int i; - - switch (le16_to_cpu(dn->sdn_objnamel)) { - case 0: - sprintf(buf, "%d", dn->sdn_objnum); - break; - default: - for (i = 0; i < le16_to_cpu(dn->sdn_objnamel); i++) { - buf[i] = dn->sdn_objname[i]; - if (IS_NOT_PRINTABLE(buf[i])) - buf[i] = '.'; - } - buf[i] = 0; - } -} - -static char *dn_state2asc(unsigned char state) -{ - switch (state) { - case DN_O: - return "OPEN"; - case DN_CR: - return " CR"; - case DN_DR: - return " DR"; - case DN_DRC: - return " DRC"; - case DN_CC: - return " CC"; - case DN_CI: - return " CI"; - case DN_NR: - return " NR"; - case DN_NC: - return " NC"; - case DN_CD: - return " CD"; - case DN_RJ: - return " RJ"; - case DN_RUN: - return " RUN"; - case DN_DI: - return " DI"; - case DN_DIC: - return " DIC"; - case DN_DN: - return " DN"; - case DN_CL: - return " CL"; - case DN_CN: - return " CN"; - } - - return "????"; -} - -static inline void dn_socket_format_entry(struct seq_file *seq, struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - char buf1[DN_ASCBUF_LEN]; - char buf2[DN_ASCBUF_LEN]; - char local_object[DN_MAXOBJL+3]; - char remote_object[DN_MAXOBJL+3]; - - dn_printable_object(&scp->addr, local_object); - dn_printable_object(&scp->peer, remote_object); - - seq_printf(seq, - "%6s/%04X %04d:%04d %04d:%04d %01d %-16s " - "%6s/%04X %04d:%04d %04d:%04d %01d %-16s %4s %s\n", - dn_addr2asc(le16_to_cpu(dn_saddr2dn(&scp->addr)), buf1), - scp->addrloc, - scp->numdat, - scp->numoth, - scp->ackxmt_dat, - scp->ackxmt_oth, - scp->flowloc_sw, - local_object, - dn_addr2asc(le16_to_cpu(dn_saddr2dn(&scp->peer)), buf2), - scp->addrrem, - scp->numdat_rcv, - scp->numoth_rcv, - scp->ackrcv_dat, - scp->ackrcv_oth, - scp->flowrem_sw, - remote_object, - dn_state2asc(scp->state), - ((scp->accept_mode == ACC_IMMED) ? "IMMED" : "DEFER")); -} - -static int dn_socket_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) { - seq_puts(seq, "Local Remote\n"); - } else { - dn_socket_format_entry(seq, v); - } - return 0; -} - -static const struct seq_operations dn_socket_seq_ops = { - .start = dn_socket_seq_start, - .next = dn_socket_seq_next, - .stop = dn_socket_seq_stop, - .show = dn_socket_seq_show, -}; -#endif - -static const struct net_proto_family dn_family_ops = { - .family = AF_DECnet, - .create = dn_create, - .owner = THIS_MODULE, -}; - -static const struct proto_ops dn_proto_ops = { - .family = AF_DECnet, - .owner = THIS_MODULE, - .release = dn_release, - .bind = dn_bind, - .connect = dn_connect, - .socketpair = sock_no_socketpair, - .accept = dn_accept, - .getname = dn_getname, - .poll = dn_poll, - .ioctl = dn_ioctl, - .listen = dn_listen, - .shutdown = dn_shutdown, - .setsockopt = dn_setsockopt, - .getsockopt = dn_getsockopt, - .sendmsg = dn_sendmsg, - .recvmsg = dn_recvmsg, - .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, -}; - -MODULE_DESCRIPTION("The Linux DECnet Network Protocol"); -MODULE_AUTHOR("Linux DECnet Project Team"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NETPROTO(PF_DECnet); - -static const char banner[] __initconst = KERN_INFO -"NET4: DECnet for Linux: V.2.5.68s (C) 1995-2003 Linux DECnet Project Team\n"; - -static int __init decnet_init(void) -{ - int rc; - - printk(banner); - - rc = proto_register(&dn_proto, 1); - if (rc != 0) - goto out; - - dn_neigh_init(); - dn_dev_init(); - dn_route_init(); - dn_fib_init(); - - sock_register(&dn_family_ops); - dev_add_pack(&dn_dix_packet_type); - register_netdevice_notifier(&dn_dev_notifier); - - proc_create_seq_private("decnet", 0444, init_net.proc_net, - &dn_socket_seq_ops, sizeof(struct dn_iter_state), - NULL); - dn_register_sysctl(); -out: - return rc; - -} -module_init(decnet_init); - -/* - * Prevent DECnet module unloading until its fixed properly. - * Requires an audit of the code to check for memory leaks and - * initialisation problems etc. - */ -#if 0 -static void __exit decnet_exit(void) -{ - sock_unregister(AF_DECnet); - rtnl_unregister_all(PF_DECnet); - dev_remove_pack(&dn_dix_packet_type); - - dn_unregister_sysctl(); - - unregister_netdevice_notifier(&dn_dev_notifier); - - dn_route_cleanup(); - dn_dev_cleanup(); - dn_neigh_cleanup(); - dn_fib_cleanup(); - - remove_proc_entry("decnet", init_net.proc_net); - - proto_unregister(&dn_proto); - - rcu_barrier_bh(); /* Wait for completion of call_rcu_bh()'s */ -} -module_exit(decnet_exit); -#endif diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c deleted file mode 100644 index 3235540f6adf..000000000000 --- a/net/decnet/dn_dev.c +++ /dev/null @@ -1,1438 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Device Layer - * - * Authors: Steve Whitehouse <SteveW@ACM.org> - * Eduardo Marcelo Serrat <emserrat@geocities.com> - * - * Changes: - * Steve Whitehouse : Devices now see incoming frames so they - * can mark on who it came from. - * Steve Whitehouse : Fixed bug in creating neighbours. Each neighbour - * can now have a device specific setup func. - * Steve Whitehouse : Added /proc/sys/net/decnet/conf/<dev>/ - * Steve Whitehouse : Fixed bug which sometimes killed timer - * Steve Whitehouse : Multiple ifaddr support - * Steve Whitehouse : SIOCGIFCONF is now a compile time option - * Steve Whitehouse : /proc/sys/net/decnet/conf/<sys>/forwarding - * Steve Whitehouse : Removed timer1 - it's a user space issue now - * Patrick Caulfield : Fixed router hello message format - * Steve Whitehouse : Got rid of constant sizes for blksize for - * devices. All mtu based now. - */ - -#include <linux/capability.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/init.h> -#include <linux/net.h> -#include <linux/netdevice.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/timer.h> -#include <linux/string.h> -#include <linux/if_addr.h> -#include <linux/if_arp.h> -#include <linux/if_ether.h> -#include <linux/skbuff.h> -#include <linux/sysctl.h> -#include <linux/notifier.h> -#include <linux/slab.h> -#include <linux/jiffies.h> -#include <linux/uaccess.h> -#include <net/net_namespace.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/flow.h> -#include <net/fib_rules.h> -#include <net/netlink.h> -#include <net/dn.h> -#include <net/dn_dev.h> -#include <net/dn_route.h> -#include <net/dn_neigh.h> -#include <net/dn_fib.h> - -#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn)) - -static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00}; -static char dn_rt_all_rt_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x03,0x00,0x00}; -static char dn_hiord[ETH_ALEN] = {0xAA,0x00,0x04,0x00,0x00,0x00}; -static unsigned char dn_eco_version[3] = {0x02,0x00,0x00}; - -extern struct neigh_table dn_neigh_table; - -/* - * decnet_address is kept in network order. - */ -__le16 decnet_address = 0; - -static DEFINE_SPINLOCK(dndev_lock); -static struct net_device *decnet_default_device; -static BLOCKING_NOTIFIER_HEAD(dnaddr_chain); - -static struct dn_dev *dn_dev_create(struct net_device *dev, int *err); -static void dn_dev_delete(struct net_device *dev); -static void dn_ifaddr_notify(int event, struct dn_ifaddr *ifa); - -static int dn_eth_up(struct net_device *); -static void dn_eth_down(struct net_device *); -static void dn_send_brd_hello(struct net_device *dev, struct dn_ifaddr *ifa); -static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa); - -static struct dn_dev_parms dn_dev_list[] = { -{ - .type = ARPHRD_ETHER, /* Ethernet */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "ethernet", - .up = dn_eth_up, - .down = dn_eth_down, - .timer3 = dn_send_brd_hello, -}, -{ - .type = ARPHRD_IPGRE, /* DECnet tunneled over GRE in IP */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "ipgre", - .timer3 = dn_send_brd_hello, -}, -#if 0 -{ - .type = ARPHRD_X25, /* Bog standard X.25 */ - .mode = DN_DEV_UCAST, - .state = DN_DEV_S_DS, - .t2 = 1, - .t3 = 120, - .name = "x25", - .timer3 = dn_send_ptp_hello, -}, -#endif -#if 0 -{ - .type = ARPHRD_PPP, /* DECnet over PPP */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "ppp", - .timer3 = dn_send_brd_hello, -}, -#endif -{ - .type = ARPHRD_DDCMP, /* DECnet over DDCMP */ - .mode = DN_DEV_UCAST, - .state = DN_DEV_S_DS, - .t2 = 1, - .t3 = 120, - .name = "ddcmp", - .timer3 = dn_send_ptp_hello, -}, -{ - .type = ARPHRD_LOOPBACK, /* Loopback interface - always last */ - .mode = DN_DEV_BCAST, - .state = DN_DEV_S_RU, - .t2 = 1, - .t3 = 10, - .name = "loopback", - .timer3 = dn_send_brd_hello, -} -}; - -#define DN_DEV_LIST_SIZE ARRAY_SIZE(dn_dev_list) - -#define DN_DEV_PARMS_OFFSET(x) offsetof(struct dn_dev_parms, x) - -#ifdef CONFIG_SYSCTL - -static int min_t2[] = { 1 }; -static int max_t2[] = { 60 }; /* No max specified, but this seems sensible */ -static int min_t3[] = { 1 }; -static int max_t3[] = { 8191 }; /* Must fit in 16 bits when multiplied by BCT3MULT or T3MULT */ - -static int min_priority[1]; -static int max_priority[] = { 127 }; /* From DECnet spec */ - -static int dn_forwarding_proc(struct ctl_table *, int, - void __user *, size_t *, loff_t *); -static struct dn_dev_sysctl_table { - struct ctl_table_header *sysctl_header; - struct ctl_table dn_dev_vars[5]; -} dn_dev_sysctl = { - NULL, - { - { - .procname = "forwarding", - .data = (void *)DN_DEV_PARMS_OFFSET(forwarding), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = dn_forwarding_proc, - }, - { - .procname = "priority", - .data = (void *)DN_DEV_PARMS_OFFSET(priority), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_priority, - .extra2 = &max_priority - }, - { - .procname = "t2", - .data = (void *)DN_DEV_PARMS_OFFSET(t2), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_t2, - .extra2 = &max_t2 - }, - { - .procname = "t3", - .data = (void *)DN_DEV_PARMS_OFFSET(t3), - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_t3, - .extra2 = &max_t3 - }, - { } - }, -}; - -static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms *parms) -{ - struct dn_dev_sysctl_table *t; - int i; - - char path[sizeof("net/decnet/conf/") + IFNAMSIZ]; - - t = kmemdup(&dn_dev_sysctl, sizeof(*t), GFP_KERNEL); - if (t == NULL) - return; - - for(i = 0; i < ARRAY_SIZE(t->dn_dev_vars) - 1; i++) { - long offset = (long)t->dn_dev_vars[i].data; - t->dn_dev_vars[i].data = ((char *)parms) + offset; - } - - snprintf(path, sizeof(path), "net/decnet/conf/%s", - dev? dev->name : parms->name); - - t->dn_dev_vars[0].extra1 = (void *)dev; - - t->sysctl_header = register_net_sysctl(&init_net, path, t->dn_dev_vars); - if (t->sysctl_header == NULL) - kfree(t); - else - parms->sysctl = t; -} - -static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) -{ - if (parms->sysctl) { - struct dn_dev_sysctl_table *t = parms->sysctl; - parms->sysctl = NULL; - unregister_net_sysctl_table(t->sysctl_header); - kfree(t); - } -} - -static int dn_forwarding_proc(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ -#ifdef CONFIG_DECNET_ROUTER - struct net_device *dev = table->extra1; - struct dn_dev *dn_db; - int err; - int tmp, old; - - if (table->extra1 == NULL) - return -EINVAL; - - dn_db = rcu_dereference_raw(dev->dn_ptr); - old = dn_db->parms.forwarding; - - err = proc_dointvec(table, write, buffer, lenp, ppos); - - if ((err >= 0) && write) { - if (dn_db->parms.forwarding < 0) - dn_db->parms.forwarding = 0; - if (dn_db->parms.forwarding > 2) - dn_db->parms.forwarding = 2; - /* - * What an ugly hack this is... its works, just. It - * would be nice if sysctl/proc were just that little - * bit more flexible so I don't have to write a special - * routine, or suffer hacks like this - SJW - */ - tmp = dn_db->parms.forwarding; - dn_db->parms.forwarding = old; - if (dn_db->parms.down) - dn_db->parms.down(dev); - dn_db->parms.forwarding = tmp; - if (dn_db->parms.up) - dn_db->parms.up(dev); - } - - return err; -#else - return -EINVAL; -#endif -} - -#else /* CONFIG_SYSCTL */ -static void dn_dev_sysctl_unregister(struct dn_dev_parms *parms) -{ -} -static void dn_dev_sysctl_register(struct net_device *dev, struct dn_dev_parms *parms) -{ -} - -#endif /* CONFIG_SYSCTL */ - -static inline __u16 mtu2blksize(struct net_device *dev) -{ - u32 blksize = dev->mtu; - if (blksize > 0xffff) - blksize = 0xffff; - - if (dev->type == ARPHRD_ETHER || - dev->type == ARPHRD_PPP || - dev->type == ARPHRD_IPGRE || - dev->type == ARPHRD_LOOPBACK) - blksize -= 2; - - return (__u16)blksize; -} - -static struct dn_ifaddr *dn_dev_alloc_ifa(void) -{ - struct dn_ifaddr *ifa; - - ifa = kzalloc(sizeof(*ifa), GFP_KERNEL); - - return ifa; -} - -static void dn_dev_free_ifa(struct dn_ifaddr *ifa) -{ - kfree_rcu(ifa, rcu); -} - -static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr __rcu **ifap, int destroy) -{ - struct dn_ifaddr *ifa1 = rtnl_dereference(*ifap); - unsigned char mac_addr[6]; - struct net_device *dev = dn_db->dev; - - ASSERT_RTNL(); - - *ifap = ifa1->ifa_next; - - if (dn_db->dev->type == ARPHRD_ETHER) { - if (ifa1->ifa_local != dn_eth2dn(dev->dev_addr)) { - dn_dn2eth(mac_addr, ifa1->ifa_local); - dev_mc_del(dev, mac_addr); - } - } - - dn_ifaddr_notify(RTM_DELADDR, ifa1); - blocking_notifier_call_chain(&dnaddr_chain, NETDEV_DOWN, ifa1); - if (destroy) { - dn_dev_free_ifa(ifa1); - - if (dn_db->ifa_list == NULL) - dn_dev_delete(dn_db->dev); - } -} - -static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) -{ - struct net_device *dev = dn_db->dev; - struct dn_ifaddr *ifa1; - unsigned char mac_addr[6]; - - ASSERT_RTNL(); - - /* Check for duplicates */ - for (ifa1 = rtnl_dereference(dn_db->ifa_list); - ifa1 != NULL; - ifa1 = rtnl_dereference(ifa1->ifa_next)) { - if (ifa1->ifa_local == ifa->ifa_local) - return -EEXIST; - } - - if (dev->type == ARPHRD_ETHER) { - if (ifa->ifa_local != dn_eth2dn(dev->dev_addr)) { - dn_dn2eth(mac_addr, ifa->ifa_local); - dev_mc_add(dev, mac_addr); - } - } - - ifa->ifa_next = dn_db->ifa_list; - rcu_assign_pointer(dn_db->ifa_list, ifa); - - dn_ifaddr_notify(RTM_NEWADDR, ifa); - blocking_notifier_call_chain(&dnaddr_chain, NETDEV_UP, ifa); - - return 0; -} - -static int dn_dev_set_ifa(struct net_device *dev, struct dn_ifaddr *ifa) -{ - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - int rv; - - if (dn_db == NULL) { - int err; - dn_db = dn_dev_create(dev, &err); - if (dn_db == NULL) - return err; - } - - ifa->ifa_dev = dn_db; - - if (dev->flags & IFF_LOOPBACK) - ifa->ifa_scope = RT_SCOPE_HOST; - - rv = dn_dev_insert_ifa(dn_db, ifa); - if (rv) - dn_dev_free_ifa(ifa); - return rv; -} - - -int dn_dev_ioctl(unsigned int cmd, void __user *arg) -{ - char buffer[DN_IFREQ_SIZE]; - struct ifreq *ifr = (struct ifreq *)buffer; - struct sockaddr_dn *sdn = (struct sockaddr_dn *)&ifr->ifr_addr; - struct dn_dev *dn_db; - struct net_device *dev; - struct dn_ifaddr *ifa = NULL; - struct dn_ifaddr __rcu **ifap = NULL; - int ret = 0; - - if (copy_from_user(ifr, arg, DN_IFREQ_SIZE)) - return -EFAULT; - ifr->ifr_name[IFNAMSIZ-1] = 0; - - dev_load(&init_net, ifr->ifr_name); - - switch (cmd) { - case SIOCGIFADDR: - break; - case SIOCSIFADDR: - if (!capable(CAP_NET_ADMIN)) - return -EACCES; - if (sdn->sdn_family != AF_DECnet) - return -EINVAL; - break; - default: - return -EINVAL; - } - - rtnl_lock(); - - if ((dev = __dev_get_by_name(&init_net, ifr->ifr_name)) == NULL) { - ret = -ENODEV; - goto done; - } - - if ((dn_db = rtnl_dereference(dev->dn_ptr)) != NULL) { - for (ifap = &dn_db->ifa_list; - (ifa = rtnl_dereference(*ifap)) != NULL; - ifap = &ifa->ifa_next) - if (strcmp(ifr->ifr_name, ifa->ifa_label) == 0) - break; - } - - if (ifa == NULL && cmd != SIOCSIFADDR) { - ret = -EADDRNOTAVAIL; - goto done; - } - - switch (cmd) { - case SIOCGIFADDR: - *((__le16 *)sdn->sdn_nodeaddr) = ifa->ifa_local; - goto rarok; - - case SIOCSIFADDR: - if (!ifa) { - if ((ifa = dn_dev_alloc_ifa()) == NULL) { - ret = -ENOBUFS; - break; - } - memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); - } else { - if (ifa->ifa_local == dn_saddr2dn(sdn)) - break; - dn_dev_del_ifa(dn_db, ifap, 0); - } - - ifa->ifa_local = ifa->ifa_address = dn_saddr2dn(sdn); - - ret = dn_dev_set_ifa(dev, ifa); - } -done: - rtnl_unlock(); - - return ret; -rarok: - if (copy_to_user(arg, ifr, DN_IFREQ_SIZE)) - ret = -EFAULT; - goto done; -} - -struct net_device *dn_dev_get_default(void) -{ - struct net_device *dev; - - spin_lock(&dndev_lock); - dev = decnet_default_device; - if (dev) { - if (dev->dn_ptr) - dev_hold(dev); - else - dev = NULL; - } - spin_unlock(&dndev_lock); - - return dev; -} - -int dn_dev_set_default(struct net_device *dev, int force) -{ - struct net_device *old = NULL; - int rv = -EBUSY; - if (!dev->dn_ptr) - return -ENODEV; - - spin_lock(&dndev_lock); - if (force || decnet_default_device == NULL) { - old = decnet_default_device; - decnet_default_device = dev; - rv = 0; - } - spin_unlock(&dndev_lock); - - if (old) - dev_put(old); - return rv; -} - -static void dn_dev_check_default(struct net_device *dev) -{ - spin_lock(&dndev_lock); - if (dev == decnet_default_device) { - decnet_default_device = NULL; - } else { - dev = NULL; - } - spin_unlock(&dndev_lock); - - if (dev) - dev_put(dev); -} - -/* - * Called with RTNL - */ -static struct dn_dev *dn_dev_by_index(int ifindex) -{ - struct net_device *dev; - struct dn_dev *dn_dev = NULL; - - dev = __dev_get_by_index(&init_net, ifindex); - if (dev) - dn_dev = rtnl_dereference(dev->dn_ptr); - - return dn_dev; -} - -static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = { - [IFA_ADDRESS] = { .type = NLA_U16 }, - [IFA_LOCAL] = { .type = NLA_U16 }, - [IFA_LABEL] = { .type = NLA_STRING, - .len = IFNAMSIZ - 1 }, - [IFA_FLAGS] = { .type = NLA_U32 }, -}; - -static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct nlattr *tb[IFA_MAX+1]; - struct dn_dev *dn_db; - struct ifaddrmsg *ifm; - struct dn_ifaddr *ifa; - struct dn_ifaddr __rcu **ifap; - int err = -EINVAL; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - goto errout; - - err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy, - extack); - if (err < 0) - goto errout; - - err = -ENODEV; - ifm = nlmsg_data(nlh); - if ((dn_db = dn_dev_by_index(ifm->ifa_index)) == NULL) - goto errout; - - err = -EADDRNOTAVAIL; - for (ifap = &dn_db->ifa_list; - (ifa = rtnl_dereference(*ifap)) != NULL; - ifap = &ifa->ifa_next) { - if (tb[IFA_LOCAL] && - nla_memcmp(tb[IFA_LOCAL], &ifa->ifa_local, 2)) - continue; - - if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) - continue; - - dn_dev_del_ifa(dn_db, ifap, 1); - return 0; - } - -errout: - return err; -} - -static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct nlattr *tb[IFA_MAX+1]; - struct net_device *dev; - struct dn_dev *dn_db; - struct ifaddrmsg *ifm; - struct dn_ifaddr *ifa; - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, dn_ifa_policy, - extack); - if (err < 0) - return err; - - if (tb[IFA_LOCAL] == NULL) - return -EINVAL; - - ifm = nlmsg_data(nlh); - if ((dev = __dev_get_by_index(&init_net, ifm->ifa_index)) == NULL) - return -ENODEV; - - if ((dn_db = rtnl_dereference(dev->dn_ptr)) == NULL) { - dn_db = dn_dev_create(dev, &err); - if (!dn_db) - return err; - } - - if ((ifa = dn_dev_alloc_ifa()) == NULL) - return -ENOBUFS; - - if (tb[IFA_ADDRESS] == NULL) - tb[IFA_ADDRESS] = tb[IFA_LOCAL]; - - ifa->ifa_local = nla_get_le16(tb[IFA_LOCAL]); - ifa->ifa_address = nla_get_le16(tb[IFA_ADDRESS]); - ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : - ifm->ifa_flags; - ifa->ifa_scope = ifm->ifa_scope; - ifa->ifa_dev = dn_db; - - if (tb[IFA_LABEL]) - nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); - else - memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); - - err = dn_dev_insert_ifa(dn_db, ifa); - if (err) - dn_dev_free_ifa(ifa); - - return err; -} - -static inline size_t dn_ifaddr_nlmsg_size(void) -{ - return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) - + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ - + nla_total_size(2) /* IFA_ADDRESS */ - + nla_total_size(2) /* IFA_LOCAL */ - + nla_total_size(4); /* IFA_FLAGS */ -} - -static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) -{ - struct ifaddrmsg *ifm; - struct nlmsghdr *nlh; - u32 ifa_flags = ifa->ifa_flags | IFA_F_PERMANENT; - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); - if (nlh == NULL) - return -EMSGSIZE; - - ifm = nlmsg_data(nlh); - ifm->ifa_family = AF_DECnet; - ifm->ifa_prefixlen = 16; - ifm->ifa_flags = ifa_flags; - ifm->ifa_scope = ifa->ifa_scope; - ifm->ifa_index = ifa->ifa_dev->dev->ifindex; - - if ((ifa->ifa_address && - nla_put_le16(skb, IFA_ADDRESS, ifa->ifa_address)) || - (ifa->ifa_local && - nla_put_le16(skb, IFA_LOCAL, ifa->ifa_local)) || - (ifa->ifa_label[0] && - nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || - nla_put_u32(skb, IFA_FLAGS, ifa_flags)) - goto nla_put_failure; - nlmsg_end(skb, nlh); - return 0; - -nla_put_failure: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - -static void dn_ifaddr_notify(int event, struct dn_ifaddr *ifa) -{ - struct sk_buff *skb; - int err = -ENOBUFS; - - skb = alloc_skb(dn_ifaddr_nlmsg_size(), GFP_KERNEL); - if (skb == NULL) - goto errout; - - err = dn_nl_fill_ifaddr(skb, ifa, 0, 0, event, 0); - if (err < 0) { - /* -EMSGSIZE implies BUG in dn_ifaddr_nlmsg_size() */ - WARN_ON(err == -EMSGSIZE); - kfree_skb(skb); - goto errout; - } - rtnl_notify(skb, &init_net, 0, RTNLGRP_DECnet_IFADDR, NULL, GFP_KERNEL); - return; -errout: - if (err < 0) - rtnl_set_sk_err(&init_net, RTNLGRP_DECnet_IFADDR, err); -} - -static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - int idx, dn_idx = 0, skip_ndevs, skip_naddr; - struct net_device *dev; - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - - if (!net_eq(net, &init_net)) - return 0; - - skip_ndevs = cb->args[0]; - skip_naddr = cb->args[1]; - - idx = 0; - rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - if (idx < skip_ndevs) - goto cont; - else if (idx > skip_ndevs) { - /* Only skip over addresses for first dev dumped - * in this iteration (idx == skip_ndevs) */ - skip_naddr = 0; - } - - if ((dn_db = rcu_dereference(dev->dn_ptr)) == NULL) - goto cont; - - for (ifa = rcu_dereference(dn_db->ifa_list), dn_idx = 0; ifa; - ifa = rcu_dereference(ifa->ifa_next), dn_idx++) { - if (dn_idx < skip_naddr) - continue; - - if (dn_nl_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWADDR, - NLM_F_MULTI) < 0) - goto done; - } -cont: - idx++; - } -done: - rcu_read_unlock(); - cb->args[0] = idx; - cb->args[1] = dn_idx; - - return skb->len; -} - -static int dn_dev_get_first(struct net_device *dev, __le16 *addr) -{ - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - int rv = -ENODEV; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) - goto out; - - ifa = rcu_dereference(dn_db->ifa_list); - if (ifa != NULL) { - *addr = ifa->ifa_local; - rv = 0; - } -out: - rcu_read_unlock(); - return rv; -} - -/* - * Find a default address to bind to. - * - * This is one of those areas where the initial VMS concepts don't really - * map onto the Linux concepts, and since we introduced multiple addresses - * per interface we have to cope with slightly odd ways of finding out what - * "our address" really is. Mostly it's not a problem; for this we just guess - * a sensible default. Eventually the routing code will take care of all the - * nasties for us I hope. - */ -int dn_dev_bind_default(__le16 *addr) -{ - struct net_device *dev; - int rv; - dev = dn_dev_get_default(); -last_chance: - if (dev) { - rv = dn_dev_get_first(dev, addr); - dev_put(dev); - if (rv == 0 || dev == init_net.loopback_dev) - return rv; - } - dev = init_net.loopback_dev; - dev_hold(dev); - goto last_chance; -} - -static void dn_send_endnode_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - struct endnode_hello_message *msg; - struct sk_buff *skb = NULL; - __le16 *pktlen; - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if ((skb = dn_alloc_skb(NULL, sizeof(*msg), GFP_ATOMIC)) == NULL) - return; - - skb->dev = dev; - - msg = skb_put(skb, sizeof(*msg)); - - msg->msgflg = 0x0D; - memcpy(msg->tiver, dn_eco_version, 3); - dn_dn2eth(msg->id, ifa->ifa_local); - msg->iinfo = DN_RT_INFO_ENDN; - msg->blksize = cpu_to_le16(mtu2blksize(dev)); - msg->area = 0x00; - memset(msg->seed, 0, 8); - memcpy(msg->neighbor, dn_hiord, ETH_ALEN); - - if (dn_db->router) { - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; - dn_dn2eth(msg->neighbor, dn->addr); - } - - msg->timer = cpu_to_le16((unsigned short)dn_db->parms.t3); - msg->mpd = 0x00; - msg->datalen = 0x02; - memset(msg->data, 0xAA, 2); - - pktlen = skb_push(skb, 2); - *pktlen = cpu_to_le16(skb->len - 2); - - skb_reset_network_header(skb); - - dn_rt_finish_output(skb, dn_rt_all_rt_mcast, msg->id); -} - - -#define DRDELAY (5 * HZ) - -static int dn_am_i_a_router(struct dn_neigh *dn, struct dn_dev *dn_db, struct dn_ifaddr *ifa) -{ - /* First check time since device went up */ - if (time_before(jiffies, dn_db->uptime + DRDELAY)) - return 0; - - /* If there is no router, then yes... */ - if (!dn_db->router) - return 1; - - /* otherwise only if we have a higher priority or.. */ - if (dn->priority < dn_db->parms.priority) - return 1; - - /* if we have equal priority and a higher node number */ - if (dn->priority != dn_db->parms.priority) - return 0; - - if (le16_to_cpu(dn->addr) < le16_to_cpu(ifa->ifa_local)) - return 1; - - return 0; -} - -static void dn_send_router_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - int n; - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - struct dn_neigh *dn = (struct dn_neigh *)dn_db->router; - struct sk_buff *skb; - size_t size; - unsigned char *ptr; - unsigned char *i1, *i2; - __le16 *pktlen; - char *src; - - if (mtu2blksize(dev) < (26 + 7)) - return; - - n = mtu2blksize(dev) - 26; - n /= 7; - - if (n > 32) - n = 32; - - size = 2 + 26 + 7 * n; - - if ((skb = dn_alloc_skb(NULL, size, GFP_ATOMIC)) == NULL) - return; - - skb->dev = dev; - ptr = skb_put(skb, size); - - *ptr++ = DN_RT_PKT_CNTL | DN_RT_PKT_ERTH; - *ptr++ = 2; /* ECO */ - *ptr++ = 0; - *ptr++ = 0; - dn_dn2eth(ptr, ifa->ifa_local); - src = ptr; - ptr += ETH_ALEN; - *ptr++ = dn_db->parms.forwarding == 1 ? - DN_RT_INFO_L1RT : DN_RT_INFO_L2RT; - *((__le16 *)ptr) = cpu_to_le16(mtu2blksize(dev)); - ptr += 2; - *ptr++ = dn_db->parms.priority; /* Priority */ - *ptr++ = 0; /* Area: Reserved */ - *((__le16 *)ptr) = cpu_to_le16((unsigned short)dn_db->parms.t3); - ptr += 2; - *ptr++ = 0; /* MPD: Reserved */ - i1 = ptr++; - memset(ptr, 0, 7); /* Name: Reserved */ - ptr += 7; - i2 = ptr++; - - n = dn_neigh_elist(dev, ptr, n); - - *i2 = 7 * n; - *i1 = 8 + *i2; - - skb_trim(skb, (27 + *i2)); - - pktlen = skb_push(skb, 2); - *pktlen = cpu_to_le16(skb->len - 2); - - skb_reset_network_header(skb); - - if (dn_am_i_a_router(dn, dn_db, ifa)) { - struct sk_buff *skb2 = skb_copy(skb, GFP_ATOMIC); - if (skb2) { - dn_rt_finish_output(skb2, dn_rt_all_end_mcast, src); - } - } - - dn_rt_finish_output(skb, dn_rt_all_rt_mcast, src); -} - -static void dn_send_brd_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.forwarding == 0) - dn_send_endnode_hello(dev, ifa); - else - dn_send_router_hello(dev, ifa); -} - -static void dn_send_ptp_hello(struct net_device *dev, struct dn_ifaddr *ifa) -{ - int tdlen = 16; - int size = dev->hard_header_len + 2 + 4 + tdlen; - struct sk_buff *skb = dn_alloc_skb(NULL, size, GFP_ATOMIC); - int i; - unsigned char *ptr; - char src[ETH_ALEN]; - - if (skb == NULL) - return ; - - skb->dev = dev; - skb_push(skb, dev->hard_header_len); - ptr = skb_put(skb, 2 + 4 + tdlen); - - *ptr++ = DN_RT_PKT_HELO; - *((__le16 *)ptr) = ifa->ifa_local; - ptr += 2; - *ptr++ = tdlen; - - for(i = 0; i < tdlen; i++) - *ptr++ = 0252; - - dn_dn2eth(src, ifa->ifa_local); - dn_rt_finish_output(skb, dn_rt_all_rt_mcast, src); -} - -static int dn_eth_up(struct net_device *dev) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.forwarding == 0) - dev_mc_add(dev, dn_rt_all_end_mcast); - else - dev_mc_add(dev, dn_rt_all_rt_mcast); - - dn_db->use_long = 1; - - return 0; -} - -static void dn_eth_down(struct net_device *dev) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.forwarding == 0) - dev_mc_del(dev, dn_rt_all_end_mcast); - else - dev_mc_del(dev, dn_rt_all_rt_mcast); -} - -static void dn_dev_set_timer(struct net_device *dev); - -static void dn_dev_timer_func(struct timer_list *t) -{ - struct dn_dev *dn_db = from_timer(dn_db, t, timer); - struct net_device *dev; - struct dn_ifaddr *ifa; - - rcu_read_lock(); - dev = dn_db->dev; - if (dn_db->t3 <= dn_db->parms.t2) { - if (dn_db->parms.timer3) { - for (ifa = rcu_dereference(dn_db->ifa_list); - ifa; - ifa = rcu_dereference(ifa->ifa_next)) { - if (!(ifa->ifa_flags & IFA_F_SECONDARY)) - dn_db->parms.timer3(dev, ifa); - } - } - dn_db->t3 = dn_db->parms.t3; - } else { - dn_db->t3 -= dn_db->parms.t2; - } - rcu_read_unlock(); - dn_dev_set_timer(dev); -} - -static void dn_dev_set_timer(struct net_device *dev) -{ - struct dn_dev *dn_db = rcu_dereference_raw(dev->dn_ptr); - - if (dn_db->parms.t2 > dn_db->parms.t3) - dn_db->parms.t2 = dn_db->parms.t3; - - dn_db->timer.expires = jiffies + (dn_db->parms.t2 * HZ); - - add_timer(&dn_db->timer); -} - -static struct dn_dev *dn_dev_create(struct net_device *dev, int *err) -{ - int i; - struct dn_dev_parms *p = dn_dev_list; - struct dn_dev *dn_db; - - for(i = 0; i < DN_DEV_LIST_SIZE; i++, p++) { - if (p->type == dev->type) - break; - } - - *err = -ENODEV; - if (i == DN_DEV_LIST_SIZE) - return NULL; - - *err = -ENOBUFS; - if ((dn_db = kzalloc(sizeof(struct dn_dev), GFP_ATOMIC)) == NULL) - return NULL; - - memcpy(&dn_db->parms, p, sizeof(struct dn_dev_parms)); - - rcu_assign_pointer(dev->dn_ptr, dn_db); - dn_db->dev = dev; - timer_setup(&dn_db->timer, dn_dev_timer_func, 0); - - dn_db->uptime = jiffies; - - dn_db->neigh_parms = neigh_parms_alloc(dev, &dn_neigh_table); - if (!dn_db->neigh_parms) { - RCU_INIT_POINTER(dev->dn_ptr, NULL); - kfree(dn_db); - return NULL; - } - - if (dn_db->parms.up) { - if (dn_db->parms.up(dev) < 0) { - neigh_parms_release(&dn_neigh_table, dn_db->neigh_parms); - dev->dn_ptr = NULL; - kfree(dn_db); - return NULL; - } - } - - dn_dev_sysctl_register(dev, &dn_db->parms); - - dn_dev_set_timer(dev); - - *err = 0; - return dn_db; -} - - -/* - * This processes a device up event. We only start up - * the loopback device & ethernet devices with correct - * MAC addresses automatically. Others must be started - * specifically. - * - * FIXME: How should we configure the loopback address ? If we could dispense - * with using decnet_address here and for autobind, it will be one less thing - * for users to worry about setting up. - */ - -void dn_dev_up(struct net_device *dev) -{ - struct dn_ifaddr *ifa; - __le16 addr = decnet_address; - int maybe_default = 0; - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - - if ((dev->type != ARPHRD_ETHER) && (dev->type != ARPHRD_LOOPBACK)) - return; - - /* - * Need to ensure that loopback device has a dn_db attached to it - * to allow creation of neighbours against it, even though it might - * not have a local address of its own. Might as well do the same for - * all autoconfigured interfaces. - */ - if (dn_db == NULL) { - int err; - dn_db = dn_dev_create(dev, &err); - if (dn_db == NULL) - return; - } - - if (dev->type == ARPHRD_ETHER) { - if (memcmp(dev->dev_addr, dn_hiord, 4) != 0) - return; - addr = dn_eth2dn(dev->dev_addr); - maybe_default = 1; - } - - if (addr == 0) - return; - - if ((ifa = dn_dev_alloc_ifa()) == NULL) - return; - - ifa->ifa_local = ifa->ifa_address = addr; - ifa->ifa_flags = 0; - ifa->ifa_scope = RT_SCOPE_UNIVERSE; - strcpy(ifa->ifa_label, dev->name); - - dn_dev_set_ifa(dev, ifa); - - /* - * Automagically set the default device to the first automatically - * configured ethernet card in the system. - */ - if (maybe_default) { - dev_hold(dev); - if (dn_dev_set_default(dev, 0)) - dev_put(dev); - } -} - -static void dn_dev_delete(struct net_device *dev) -{ - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - - if (dn_db == NULL) - return; - - del_timer_sync(&dn_db->timer); - dn_dev_sysctl_unregister(&dn_db->parms); - dn_dev_check_default(dev); - neigh_ifdown(&dn_neigh_table, dev); - - if (dn_db->parms.down) - dn_db->parms.down(dev); - - dev->dn_ptr = NULL; - - neigh_parms_release(&dn_neigh_table, dn_db->neigh_parms); - neigh_ifdown(&dn_neigh_table, dev); - - if (dn_db->router) - neigh_release(dn_db->router); - if (dn_db->peer) - neigh_release(dn_db->peer); - - kfree(dn_db); -} - -void dn_dev_down(struct net_device *dev) -{ - struct dn_dev *dn_db = rtnl_dereference(dev->dn_ptr); - struct dn_ifaddr *ifa; - - if (dn_db == NULL) - return; - - while ((ifa = rtnl_dereference(dn_db->ifa_list)) != NULL) { - dn_dev_del_ifa(dn_db, &dn_db->ifa_list, 0); - dn_dev_free_ifa(ifa); - } - - dn_dev_delete(dev); -} - -void dn_dev_init_pkt(struct sk_buff *skb) -{ -} - -void dn_dev_veri_pkt(struct sk_buff *skb) -{ -} - -void dn_dev_hello(struct sk_buff *skb) -{ -} - -void dn_dev_devices_off(void) -{ - struct net_device *dev; - - rtnl_lock(); - for_each_netdev(&init_net, dev) - dn_dev_down(dev); - rtnl_unlock(); - -} - -void dn_dev_devices_on(void) -{ - struct net_device *dev; - - rtnl_lock(); - for_each_netdev(&init_net, dev) { - if (dev->flags & IFF_UP) - dn_dev_up(dev); - } - rtnl_unlock(); -} - -int register_dnaddr_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&dnaddr_chain, nb); -} - -int unregister_dnaddr_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&dnaddr_chain, nb); -} - -#ifdef CONFIG_PROC_FS -static inline int is_dn_dev(struct net_device *dev) -{ - return dev->dn_ptr != NULL; -} - -static void *dn_dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) -{ - int i; - struct net_device *dev; - - rcu_read_lock(); - - if (*pos == 0) - return SEQ_START_TOKEN; - - i = 1; - for_each_netdev_rcu(&init_net, dev) { - if (!is_dn_dev(dev)) - continue; - - if (i++ == *pos) - return dev; - } - - return NULL; -} - -static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct net_device *dev; - - ++*pos; - - dev = v; - if (v == SEQ_START_TOKEN) - dev = net_device_entry(&init_net.dev_base_head); - - for_each_netdev_continue_rcu(&init_net, dev) { - if (!is_dn_dev(dev)) - continue; - - return dev; - } - - return NULL; -} - -static void dn_dev_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) -{ - rcu_read_unlock(); -} - -static char *dn_type2asc(char type) -{ - switch (type) { - case DN_DEV_BCAST: - return "B"; - case DN_DEV_UCAST: - return "U"; - case DN_DEV_MPOINT: - return "M"; - } - - return "?"; -} - -static int dn_dev_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Name Flags T1 Timer1 T3 Timer3 BlkSize Pri State DevType Router Peer\n"); - else { - struct net_device *dev = v; - char peer_buf[DN_ASCBUF_LEN]; - char router_buf[DN_ASCBUF_LEN]; - struct dn_dev *dn_db = rcu_dereference(dev->dn_ptr); - - seq_printf(seq, "%-8s %1s %04u %04u %04lu %04lu" - " %04hu %03d %02x %-10s %-7s %-7s\n", - dev->name ? dev->name : "???", - dn_type2asc(dn_db->parms.mode), - 0, 0, - dn_db->t3, dn_db->parms.t3, - mtu2blksize(dev), - dn_db->parms.priority, - dn_db->parms.state, dn_db->parms.name, - dn_db->router ? dn_addr2asc(le16_to_cpu(*(__le16 *)dn_db->router->primary_key), router_buf) : "", - dn_db->peer ? dn_addr2asc(le16_to_cpu(*(__le16 *)dn_db->peer->primary_key), peer_buf) : ""); - } - return 0; -} - -static const struct seq_operations dn_dev_seq_ops = { - .start = dn_dev_seq_start, - .next = dn_dev_seq_next, - .stop = dn_dev_seq_stop, - .show = dn_dev_seq_show, -}; -#endif /* CONFIG_PROC_FS */ - -static int addr[2]; -module_param_array(addr, int, NULL, 0444); -MODULE_PARM_DESC(addr, "The DECnet address of this machine: area,node"); - -void __init dn_dev_init(void) -{ - if (addr[0] > 63 || addr[0] < 0) { - printk(KERN_ERR "DECnet: Area must be between 0 and 63"); - return; - } - - if (addr[1] > 1023 || addr[1] < 0) { - printk(KERN_ERR "DECnet: Node must be between 0 and 1023"); - return; - } - - decnet_address = cpu_to_le16((addr[0] << 10) | addr[1]); - - dn_dev_devices_on(); - - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_NEWADDR, - dn_nl_newaddr, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELADDR, - dn_nl_deladdr, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETADDR, - NULL, dn_nl_dump_ifaddr, 0); - - proc_create_seq("decnet_dev", 0444, init_net.proc_net, &dn_dev_seq_ops); - -#ifdef CONFIG_SYSCTL - { - int i; - for(i = 0; i < DN_DEV_LIST_SIZE; i++) - dn_dev_sysctl_register(NULL, &dn_dev_list[i]); - } -#endif /* CONFIG_SYSCTL */ -} - -void __exit dn_dev_cleanup(void) -{ -#ifdef CONFIG_SYSCTL - { - int i; - for(i = 0; i < DN_DEV_LIST_SIZE; i++) - dn_dev_sysctl_unregister(&dn_dev_list[i]); - } -#endif /* CONFIG_SYSCTL */ - - remove_proc_entry("decnet_dev", init_net.proc_net); - - dn_dev_devices_off(); -} diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c deleted file mode 100644 index f78fe58eafc8..000000000000 --- a/net/decnet/dn_fib.c +++ /dev/null @@ -1,799 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Forwarding Information Base (Glue/Info List) - * - * Author: Steve Whitehouse <SteveW@ACM.org> - * - * - * Changes: - * Alexey Kuznetsov : SMP locking changes - * Steve Whitehouse : Rewrote it... Well to be more correct, I - * copied most of it from the ipv4 fib code. - * Steve Whitehouse : Updated it in style and fixed a few bugs - * which were fixed in the ipv4 code since - * this code was copied from it. - * - */ -#include <linux/string.h> -#include <linux/net.h> -#include <linux/socket.h> -#include <linux/slab.h> -#include <linux/sockios.h> -#include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/netlink.h> -#include <linux/rtnetlink.h> -#include <linux/proc_fs.h> -#include <linux/netdevice.h> -#include <linux/timer.h> -#include <linux/spinlock.h> -#include <linux/atomic.h> -#include <linux/uaccess.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/flow.h> -#include <net/fib_rules.h> -#include <net/dn.h> -#include <net/dn_route.h> -#include <net/dn_fib.h> -#include <net/dn_neigh.h> -#include <net/dn_dev.h> -#include <net/nexthop.h> - -#define RT_MIN_TABLE 1 - -#define for_fib_info() { struct dn_fib_info *fi;\ - for(fi = dn_fib_info_list; fi; fi = fi->fib_next) -#define endfor_fib_info() } - -#define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\ - for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define change_nexthops(fi) { int nhsel; struct dn_fib_nh *nh;\ - for(nhsel = 0, nh = (struct dn_fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define endfor_nexthops(fi) } - -static DEFINE_SPINLOCK(dn_fib_multipath_lock); -static struct dn_fib_info *dn_fib_info_list; -static DEFINE_SPINLOCK(dn_fib_info_lock); - -static struct -{ - int error; - u8 scope; -} dn_fib_props[RTN_MAX+1] = { - [RTN_UNSPEC] = { .error = 0, .scope = RT_SCOPE_NOWHERE }, - [RTN_UNICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE }, - [RTN_LOCAL] = { .error = 0, .scope = RT_SCOPE_HOST }, - [RTN_BROADCAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, - [RTN_ANYCAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, - [RTN_MULTICAST] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, - [RTN_BLACKHOLE] = { .error = -EINVAL, .scope = RT_SCOPE_UNIVERSE }, - [RTN_UNREACHABLE] = { .error = -EHOSTUNREACH, .scope = RT_SCOPE_UNIVERSE }, - [RTN_PROHIBIT] = { .error = -EACCES, .scope = RT_SCOPE_UNIVERSE }, - [RTN_THROW] = { .error = -EAGAIN, .scope = RT_SCOPE_UNIVERSE }, - [RTN_NAT] = { .error = 0, .scope = RT_SCOPE_NOWHERE }, - [RTN_XRESOLVE] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE }, -}; - -static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force); -static int dn_fib_sync_up(struct net_device *dev); - -void dn_fib_free_info(struct dn_fib_info *fi) -{ - if (fi->fib_dead == 0) { - printk(KERN_DEBUG "DECnet: BUG! Attempt to free alive dn_fib_info\n"); - return; - } - - change_nexthops(fi) { - if (nh->nh_dev) - dev_put(nh->nh_dev); - nh->nh_dev = NULL; - } endfor_nexthops(fi); - kfree(fi); -} - -void dn_fib_release_info(struct dn_fib_info *fi) -{ - spin_lock(&dn_fib_info_lock); - if (fi && --fi->fib_treeref == 0) { - if (fi->fib_next) - fi->fib_next->fib_prev = fi->fib_prev; - if (fi->fib_prev) - fi->fib_prev->fib_next = fi->fib_next; - if (fi == dn_fib_info_list) - dn_fib_info_list = fi->fib_next; - fi->fib_dead = 1; - dn_fib_info_put(fi); - } - spin_unlock(&dn_fib_info_lock); -} - -static inline int dn_fib_nh_comp(const struct dn_fib_info *fi, const struct dn_fib_info *ofi) -{ - const struct dn_fib_nh *onh = ofi->fib_nh; - - for_nexthops(fi) { - if (nh->nh_oif != onh->nh_oif || - nh->nh_gw != onh->nh_gw || - nh->nh_scope != onh->nh_scope || - nh->nh_weight != onh->nh_weight || - ((nh->nh_flags^onh->nh_flags)&~RTNH_F_DEAD)) - return -1; - onh++; - } endfor_nexthops(fi); - return 0; -} - -static inline struct dn_fib_info *dn_fib_find_info(const struct dn_fib_info *nfi) -{ - for_fib_info() { - if (fi->fib_nhs != nfi->fib_nhs) - continue; - if (nfi->fib_protocol == fi->fib_protocol && - nfi->fib_prefsrc == fi->fib_prefsrc && - nfi->fib_priority == fi->fib_priority && - memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(fi->fib_metrics)) == 0 && - ((nfi->fib_flags^fi->fib_flags)&~RTNH_F_DEAD) == 0 && - (nfi->fib_nhs == 0 || dn_fib_nh_comp(fi, nfi) == 0)) - return fi; - } endfor_fib_info(); - return NULL; -} - -static int dn_fib_count_nhs(const struct nlattr *attr) -{ - struct rtnexthop *nhp = nla_data(attr); - int nhs = 0, nhlen = nla_len(attr); - - while (rtnh_ok(nhp, nhlen)) { - nhs++; - nhp = rtnh_next(nhp, &nhlen); - } - - /* leftover implies invalid nexthop configuration, discard it */ - return nhlen > 0 ? 0 : nhs; -} - -static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr, - const struct rtmsg *r) -{ - struct rtnexthop *nhp = nla_data(attr); - int nhlen = nla_len(attr); - - change_nexthops(fi) { - int attrlen; - - if (!rtnh_ok(nhp, nhlen)) - return -EINVAL; - - nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags; - nh->nh_oif = nhp->rtnh_ifindex; - nh->nh_weight = nhp->rtnh_hops + 1; - - attrlen = rtnh_attrlen(nhp); - if (attrlen > 0) { - struct nlattr *gw_attr; - - gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY); - nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0; - } - - nhp = rtnh_next(nhp, &nhlen); - } endfor_nexthops(fi); - - return 0; -} - - -static int dn_fib_check_nh(const struct rtmsg *r, struct dn_fib_info *fi, struct dn_fib_nh *nh) -{ - int err; - - if (nh->nh_gw) { - struct flowidn fld; - struct dn_fib_res res; - - if (nh->nh_flags&RTNH_F_ONLINK) { - struct net_device *dev; - - if (r->rtm_scope >= RT_SCOPE_LINK) - return -EINVAL; - if (dnet_addr_type(nh->nh_gw) != RTN_UNICAST) - return -EINVAL; - if ((dev = __dev_get_by_index(&init_net, nh->nh_oif)) == NULL) - return -ENODEV; - if (!(dev->flags&IFF_UP)) - return -ENETDOWN; - nh->nh_dev = dev; - dev_hold(dev); - nh->nh_scope = RT_SCOPE_LINK; - return 0; - } - - memset(&fld, 0, sizeof(fld)); - fld.daddr = nh->nh_gw; - fld.flowidn_oif = nh->nh_oif; - fld.flowidn_scope = r->rtm_scope + 1; - - if (fld.flowidn_scope < RT_SCOPE_LINK) - fld.flowidn_scope = RT_SCOPE_LINK; - - if ((err = dn_fib_lookup(&fld, &res)) != 0) - return err; - - err = -EINVAL; - if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) - goto out; - nh->nh_scope = res.scope; - nh->nh_oif = DN_FIB_RES_OIF(res); - nh->nh_dev = DN_FIB_RES_DEV(res); - if (nh->nh_dev == NULL) - goto out; - dev_hold(nh->nh_dev); - err = -ENETDOWN; - if (!(nh->nh_dev->flags & IFF_UP)) - goto out; - err = 0; -out: - dn_fib_res_put(&res); - return err; - } else { - struct net_device *dev; - - if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK)) - return -EINVAL; - - dev = __dev_get_by_index(&init_net, nh->nh_oif); - if (dev == NULL || dev->dn_ptr == NULL) - return -ENODEV; - if (!(dev->flags&IFF_UP)) - return -ENETDOWN; - nh->nh_dev = dev; - dev_hold(nh->nh_dev); - nh->nh_scope = RT_SCOPE_HOST; - } - - return 0; -} - - -struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *attrs[], - const struct nlmsghdr *nlh, int *errp) -{ - int err; - struct dn_fib_info *fi = NULL; - struct dn_fib_info *ofi; - int nhs = 1; - - if (r->rtm_type > RTN_MAX) - goto err_inval; - - if (dn_fib_props[r->rtm_type].scope > r->rtm_scope) - goto err_inval; - - if (attrs[RTA_MULTIPATH] && - (nhs = dn_fib_count_nhs(attrs[RTA_MULTIPATH])) == 0) - goto err_inval; - - fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct dn_fib_nh), GFP_KERNEL); - err = -ENOBUFS; - if (fi == NULL) - goto failure; - - fi->fib_protocol = r->rtm_protocol; - fi->fib_nhs = nhs; - fi->fib_flags = r->rtm_flags; - - if (attrs[RTA_PRIORITY]) - fi->fib_priority = nla_get_u32(attrs[RTA_PRIORITY]); - - if (attrs[RTA_METRICS]) { - struct nlattr *attr; - int rem; - - nla_for_each_nested(attr, attrs[RTA_METRICS], rem) { - int type = nla_type(attr); - - if (type) { - if (type > RTAX_MAX || type == RTAX_CC_ALGO || - nla_len(attr) < 4) - goto err_inval; - - fi->fib_metrics[type-1] = nla_get_u32(attr); - } - } - } - - if (attrs[RTA_PREFSRC]) - fi->fib_prefsrc = nla_get_le16(attrs[RTA_PREFSRC]); - - if (attrs[RTA_MULTIPATH]) { - if ((err = dn_fib_get_nhs(fi, attrs[RTA_MULTIPATH], r)) != 0) - goto failure; - - if (attrs[RTA_OIF] && - fi->fib_nh->nh_oif != nla_get_u32(attrs[RTA_OIF])) - goto err_inval; - - if (attrs[RTA_GATEWAY] && - fi->fib_nh->nh_gw != nla_get_le16(attrs[RTA_GATEWAY])) - goto err_inval; - } else { - struct dn_fib_nh *nh = fi->fib_nh; - - if (attrs[RTA_OIF]) - nh->nh_oif = nla_get_u32(attrs[RTA_OIF]); - - if (attrs[RTA_GATEWAY]) - nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]); - - nh->nh_flags = r->rtm_flags; - nh->nh_weight = 1; - } - - if (r->rtm_type == RTN_NAT) { - if (!attrs[RTA_GATEWAY] || nhs != 1 || attrs[RTA_OIF]) - goto err_inval; - - fi->fib_nh->nh_gw = nla_get_le16(attrs[RTA_GATEWAY]); - goto link_it; - } - - if (dn_fib_props[r->rtm_type].error) { - if (attrs[RTA_GATEWAY] || attrs[RTA_OIF] || attrs[RTA_MULTIPATH]) - goto err_inval; - - goto link_it; - } - - if (r->rtm_scope > RT_SCOPE_HOST) - goto err_inval; - - if (r->rtm_scope == RT_SCOPE_HOST) { - struct dn_fib_nh *nh = fi->fib_nh; - - /* Local address is added */ - if (nhs != 1 || nh->nh_gw) - goto err_inval; - nh->nh_scope = RT_SCOPE_NOWHERE; - nh->nh_dev = dev_get_by_index(&init_net, fi->fib_nh->nh_oif); - err = -ENODEV; - if (nh->nh_dev == NULL) - goto failure; - } else { - change_nexthops(fi) { - if ((err = dn_fib_check_nh(r, fi, nh)) != 0) - goto failure; - } endfor_nexthops(fi) - } - - if (fi->fib_prefsrc) { - if (r->rtm_type != RTN_LOCAL || !attrs[RTA_DST] || - fi->fib_prefsrc != nla_get_le16(attrs[RTA_DST])) - if (dnet_addr_type(fi->fib_prefsrc) != RTN_LOCAL) - goto err_inval; - } - -link_it: - if ((ofi = dn_fib_find_info(fi)) != NULL) { - fi->fib_dead = 1; - dn_fib_free_info(fi); - ofi->fib_treeref++; - return ofi; - } - - fi->fib_treeref++; - refcount_set(&fi->fib_clntref, 1); - spin_lock(&dn_fib_info_lock); - fi->fib_next = dn_fib_info_list; - fi->fib_prev = NULL; - if (dn_fib_info_list) - dn_fib_info_list->fib_prev = fi; - dn_fib_info_list = fi; - spin_unlock(&dn_fib_info_lock); - return fi; - -err_inval: - err = -EINVAL; - -failure: - *errp = err; - if (fi) { - fi->fib_dead = 1; - dn_fib_free_info(fi); - } - - return NULL; -} - -int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn *fld, struct dn_fib_res *res) -{ - int err = dn_fib_props[type].error; - - if (err == 0) { - if (fi->fib_flags & RTNH_F_DEAD) - return 1; - - res->fi = fi; - - switch (type) { - case RTN_NAT: - DN_FIB_RES_RESET(*res); - refcount_inc(&fi->fib_clntref); - return 0; - case RTN_UNICAST: - case RTN_LOCAL: - for_nexthops(fi) { - if (nh->nh_flags & RTNH_F_DEAD) - continue; - if (!fld->flowidn_oif || - fld->flowidn_oif == nh->nh_oif) - break; - } - if (nhsel < fi->fib_nhs) { - res->nh_sel = nhsel; - refcount_inc(&fi->fib_clntref); - return 0; - } - endfor_nexthops(fi); - res->fi = NULL; - return 1; - default: - net_err_ratelimited("DECnet: impossible routing event : dn_fib_semantic_match type=%d\n", - type); - res->fi = NULL; - return -EINVAL; - } - } - return err; -} - -void dn_fib_select_multipath(const struct flowidn *fld, struct dn_fib_res *res) -{ - struct dn_fib_info *fi = res->fi; - int w; - - spin_lock_bh(&dn_fib_multipath_lock); - if (fi->fib_power <= 0) { - int power = 0; - change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { - power += nh->nh_weight; - nh->nh_power = nh->nh_weight; - } - } endfor_nexthops(fi); - fi->fib_power = power; - if (power < 0) { - spin_unlock_bh(&dn_fib_multipath_lock); - res->nh_sel = 0; - return; - } - } - - w = jiffies % fi->fib_power; - - change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) { - if ((w -= nh->nh_power) <= 0) { - nh->nh_power--; - fi->fib_power--; - res->nh_sel = nhsel; - spin_unlock_bh(&dn_fib_multipath_lock); - return; - } - } - } endfor_nexthops(fi); - res->nh_sel = 0; - spin_unlock_bh(&dn_fib_multipath_lock); -} - -static inline u32 rtm_get_table(struct nlattr *attrs[], u8 table) -{ - if (attrs[RTA_TABLE]) - table = nla_get_u32(attrs[RTA_TABLE]); - - return table; -} - -static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct dn_fib_table *tb; - struct rtmsg *r = nlmsg_data(nlh); - struct nlattr *attrs[RTA_MAX+1]; - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy, - extack); - if (err < 0) - return err; - - tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 0); - if (!tb) - return -ESRCH; - - return tb->delete(tb, r, attrs, nlh, &NETLINK_CB(skb)); -} - -static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(skb->sk); - struct dn_fib_table *tb; - struct rtmsg *r = nlmsg_data(nlh); - struct nlattr *attrs[RTA_MAX+1]; - int err; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse(nlh, sizeof(*r), attrs, RTA_MAX, rtm_dn_policy, - extack); - if (err < 0) - return err; - - tb = dn_fib_get_table(rtm_get_table(attrs, r->rtm_table), 1); - if (!tb) - return -ENOBUFS; - - return tb->insert(tb, r, attrs, nlh, &NETLINK_CB(skb)); -} - -static void fib_magic(int cmd, int type, __le16 dst, int dst_len, struct dn_ifaddr *ifa) -{ - struct dn_fib_table *tb; - struct { - struct nlmsghdr nlh; - struct rtmsg rtm; - } req; - struct { - struct nlattr hdr; - __le16 dst; - } dst_attr = { - .dst = dst, - }; - struct { - struct nlattr hdr; - __le16 prefsrc; - } prefsrc_attr = { - .prefsrc = ifa->ifa_local, - }; - struct { - struct nlattr hdr; - u32 oif; - } oif_attr = { - .oif = ifa->ifa_dev->dev->ifindex, - }; - struct nlattr *attrs[RTA_MAX+1] = { - [RTA_DST] = (struct nlattr *) &dst_attr, - [RTA_PREFSRC] = (struct nlattr * ) &prefsrc_attr, - [RTA_OIF] = (struct nlattr *) &oif_attr, - }; - - memset(&req.rtm, 0, sizeof(req.rtm)); - - if (type == RTN_UNICAST) - tb = dn_fib_get_table(RT_MIN_TABLE, 1); - else - tb = dn_fib_get_table(RT_TABLE_LOCAL, 1); - - if (tb == NULL) - return; - - req.nlh.nlmsg_len = sizeof(req); - req.nlh.nlmsg_type = cmd; - req.nlh.nlmsg_flags = NLM_F_REQUEST|NLM_F_CREATE|NLM_F_APPEND; - req.nlh.nlmsg_pid = 0; - req.nlh.nlmsg_seq = 0; - - req.rtm.rtm_dst_len = dst_len; - req.rtm.rtm_table = tb->n; - req.rtm.rtm_protocol = RTPROT_KERNEL; - req.rtm.rtm_scope = (type != RTN_LOCAL ? RT_SCOPE_LINK : RT_SCOPE_HOST); - req.rtm.rtm_type = type; - - if (cmd == RTM_NEWROUTE) - tb->insert(tb, &req.rtm, attrs, &req.nlh, NULL); - else - tb->delete(tb, &req.rtm, attrs, &req.nlh, NULL); -} - -static void dn_fib_add_ifaddr(struct dn_ifaddr *ifa) -{ - - fib_magic(RTM_NEWROUTE, RTN_LOCAL, ifa->ifa_local, 16, ifa); - -#if 0 - if (!(dev->flags&IFF_UP)) - return; - /* In the future, we will want to add default routes here */ - -#endif -} - -static void dn_fib_del_ifaddr(struct dn_ifaddr *ifa) -{ - int found_it = 0; - struct net_device *dev; - struct dn_dev *dn_db; - struct dn_ifaddr *ifa2; - - ASSERT_RTNL(); - - /* Scan device list */ - rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) - continue; - for (ifa2 = rcu_dereference(dn_db->ifa_list); - ifa2 != NULL; - ifa2 = rcu_dereference(ifa2->ifa_next)) { - if (ifa2->ifa_local == ifa->ifa_local) { - found_it = 1; - break; - } - } - } - rcu_read_unlock(); - - if (found_it == 0) { - fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 16, ifa); - - if (dnet_addr_type(ifa->ifa_local) != RTN_LOCAL) { - if (dn_fib_sync_down(ifa->ifa_local, NULL, 0)) - dn_fib_flush(); - } - } -} - -static void dn_fib_disable_addr(struct net_device *dev, int force) -{ - if (dn_fib_sync_down(0, dev, force)) - dn_fib_flush(); - dn_rt_cache_flush(0); - neigh_ifdown(&dn_neigh_table, dev); -} - -static int dn_fib_dnaddr_event(struct notifier_block *this, unsigned long event, void *ptr) -{ - struct dn_ifaddr *ifa = (struct dn_ifaddr *)ptr; - - switch (event) { - case NETDEV_UP: - dn_fib_add_ifaddr(ifa); - dn_fib_sync_up(ifa->ifa_dev->dev); - dn_rt_cache_flush(-1); - break; - case NETDEV_DOWN: - dn_fib_del_ifaddr(ifa); - if (ifa->ifa_dev && ifa->ifa_dev->ifa_list == NULL) { - dn_fib_disable_addr(ifa->ifa_dev->dev, 1); - } else { - dn_rt_cache_flush(-1); - } - break; - } - return NOTIFY_DONE; -} - -static int dn_fib_sync_down(__le16 local, struct net_device *dev, int force) -{ - int ret = 0; - int scope = RT_SCOPE_NOWHERE; - - if (force) - scope = -1; - - for_fib_info() { - /* - * This makes no sense for DECnet.... we will almost - * certainly have more than one local address the same - * over all our interfaces. It needs thinking about - * some more. - */ - if (local && fi->fib_prefsrc == local) { - fi->fib_flags |= RTNH_F_DEAD; - ret++; - } else if (dev && fi->fib_nhs) { - int dead = 0; - - change_nexthops(fi) { - if (nh->nh_flags&RTNH_F_DEAD) - dead++; - else if (nh->nh_dev == dev && - nh->nh_scope != scope) { - spin_lock_bh(&dn_fib_multipath_lock); - nh->nh_flags |= RTNH_F_DEAD; - fi->fib_power -= nh->nh_power; - nh->nh_power = 0; - spin_unlock_bh(&dn_fib_multipath_lock); - dead++; - } - } endfor_nexthops(fi) - if (dead == fi->fib_nhs) { - fi->fib_flags |= RTNH_F_DEAD; - ret++; - } - } - } endfor_fib_info(); - return ret; -} - - -static int dn_fib_sync_up(struct net_device *dev) -{ - int ret = 0; - - if (!(dev->flags&IFF_UP)) - return 0; - - for_fib_info() { - int alive = 0; - - change_nexthops(fi) { - if (!(nh->nh_flags&RTNH_F_DEAD)) { - alive++; - continue; - } - if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP)) - continue; - if (nh->nh_dev != dev || dev->dn_ptr == NULL) - continue; - alive++; - spin_lock_bh(&dn_fib_multipath_lock); - nh->nh_power = 0; - nh->nh_flags &= ~RTNH_F_DEAD; - spin_unlock_bh(&dn_fib_multipath_lock); - } endfor_nexthops(fi); - - if (alive > 0) { - fi->fib_flags &= ~RTNH_F_DEAD; - ret++; - } - } endfor_fib_info(); - return ret; -} - -static struct notifier_block dn_fib_dnaddr_notifier = { - .notifier_call = dn_fib_dnaddr_event, -}; - -void __exit dn_fib_cleanup(void) -{ - dn_fib_table_cleanup(); - dn_fib_rules_cleanup(); - - unregister_dnaddr_notifier(&dn_fib_dnaddr_notifier); -} - - -void __init dn_fib_init(void) -{ - dn_fib_table_init(); - dn_fib_rules_init(); - - register_dnaddr_notifier(&dn_fib_dnaddr_notifier); - - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_NEWROUTE, - dn_fib_rtm_newroute, NULL, 0); - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELROUTE, - dn_fib_rtm_delroute, NULL, 0); -} diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c deleted file mode 100644 index 94b306f6d551..000000000000 --- a/net/decnet/dn_neigh.c +++ /dev/null @@ -1,605 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Neighbour Functions (Adjacency Database and - * On-Ethernet Cache) - * - * Author: Steve Whitehouse <SteveW@ACM.org> - * - * - * Changes: - * Steve Whitehouse : Fixed router listing routine - * Steve Whitehouse : Added error_report functions - * Steve Whitehouse : Added default router detection - * Steve Whitehouse : Hop counts in outgoing messages - * Steve Whitehouse : Fixed src/dst in outgoing messages so - * forwarding now stands a good chance of - * working. - * Steve Whitehouse : Fixed neighbour states (for now anyway). - * Steve Whitehouse : Made error_report functions dummies. This - * is not the right place to return skbs. - * Steve Whitehouse : Convert to seq_file - * - */ - -#include <linux/net.h> -#include <linux/module.h> -#include <linux/socket.h> -#include <linux/if_arp.h> -#include <linux/slab.h> -#include <linux/if_ether.h> -#include <linux/init.h> -#include <linux/proc_fs.h> -#include <linux/string.h> -#include <linux/netfilter_decnet.h> -#include <linux/spinlock.h> -#include <linux/seq_file.h> -#include <linux/rcupdate.h> -#include <linux/jhash.h> -#include <linux/atomic.h> -#include <net/net_namespace.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/flow.h> -#include <net/dn.h> -#include <net/dn_dev.h> -#include <net/dn_neigh.h> -#include <net/dn_route.h> - -static int dn_neigh_construct(struct neighbour *); -static void dn_neigh_error_report(struct neighbour *, struct sk_buff *); -static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb); - -/* - * Operations for adding the link layer header. - */ -static const struct neigh_ops dn_neigh_ops = { - .family = AF_DECnet, - .error_report = dn_neigh_error_report, - .output = dn_neigh_output, - .connected_output = dn_neigh_output, -}; - -static u32 dn_neigh_hash(const void *pkey, - const struct net_device *dev, - __u32 *hash_rnd) -{ - return jhash_2words(*(__u16 *)pkey, 0, hash_rnd[0]); -} - -static bool dn_key_eq(const struct neighbour *neigh, const void *pkey) -{ - return neigh_key_eq16(neigh, pkey); -} - -struct neigh_table dn_neigh_table = { - .family = PF_DECnet, - .entry_size = NEIGH_ENTRY_SIZE(sizeof(struct dn_neigh)), - .key_len = sizeof(__le16), - .protocol = cpu_to_be16(ETH_P_DNA_RT), - .hash = dn_neigh_hash, - .key_eq = dn_key_eq, - .constructor = dn_neigh_construct, - .id = "dn_neigh_cache", - .parms ={ - .tbl = &dn_neigh_table, - .reachable_time = 30 * HZ, - .data = { - [NEIGH_VAR_MCAST_PROBES] = 0, - [NEIGH_VAR_UCAST_PROBES] = 0, - [NEIGH_VAR_APP_PROBES] = 0, - [NEIGH_VAR_RETRANS_TIME] = 1 * HZ, - [NEIGH_VAR_BASE_REACHABLE_TIME] = 30 * HZ, - [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, - [NEIGH_VAR_GC_STALETIME] = 60 * HZ, - [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, - [NEIGH_VAR_PROXY_QLEN] = 0, - [NEIGH_VAR_ANYCAST_DELAY] = 0, - [NEIGH_VAR_PROXY_DELAY] = 0, - [NEIGH_VAR_LOCKTIME] = 1 * HZ, - }, - }, - .gc_interval = 30 * HZ, - .gc_thresh1 = 128, - .gc_thresh2 = 512, - .gc_thresh3 = 1024, -}; - -static int dn_neigh_construct(struct neighbour *neigh) -{ - struct net_device *dev = neigh->dev; - struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n); - struct dn_dev *dn_db; - struct neigh_parms *parms; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - if (dn_db == NULL) { - rcu_read_unlock(); - return -EINVAL; - } - - parms = dn_db->neigh_parms; - if (!parms) { - rcu_read_unlock(); - return -EINVAL; - } - - __neigh_parms_put(neigh->parms); - neigh->parms = neigh_parms_clone(parms); - rcu_read_unlock(); - - neigh->ops = &dn_neigh_ops; - neigh->nud_state = NUD_NOARP; - neigh->output = neigh->ops->connected_output; - - if ((dev->type == ARPHRD_IPGRE) || (dev->flags & IFF_POINTOPOINT)) - memcpy(neigh->ha, dev->broadcast, dev->addr_len); - else if ((dev->type == ARPHRD_ETHER) || (dev->type == ARPHRD_LOOPBACK)) - dn_dn2eth(neigh->ha, dn->addr); - else { - net_dbg_ratelimited("Trying to create neigh for hw %d\n", - dev->type); - return -EINVAL; - } - - /* - * Make an estimate of the remote block size by assuming that its - * two less then the device mtu, which it true for ethernet (and - * other things which support long format headers) since there is - * an extra length field (of 16 bits) which isn't part of the - * ethernet headers and which the DECnet specs won't admit is part - * of the DECnet routing headers either. - * - * If we over estimate here its no big deal, the NSP negotiations - * will prevent us from sending packets which are too large for the - * remote node to handle. In any case this figure is normally updated - * by a hello message in most cases. - */ - dn->blksize = dev->mtu - 2; - - return 0; -} - -static void dn_neigh_error_report(struct neighbour *neigh, struct sk_buff *skb) -{ - printk(KERN_DEBUG "dn_neigh_error_report: called\n"); - kfree_skb(skb); -} - -static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *)dst; - struct net_device *dev = neigh->dev; - char mac_addr[ETH_ALEN]; - unsigned int seq; - int err; - - dn_dn2eth(mac_addr, rt->rt_local_src); - do { - seq = read_seqbegin(&neigh->ha_lock); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, mac_addr, skb->len); - } while (read_seqretry(&neigh->ha_lock, seq)); - - if (err >= 0) - err = dev_queue_xmit(skb); - else { - kfree_skb(skb); - err = -EINVAL; - } - return err; -} - -static int dn_neigh_output_packet(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *)dst; - struct neighbour *neigh = rt->n; - - return neigh->output(neigh, skb); -} - -/* - * For talking to broadcast devices: Ethernet & PPP - */ -static int dn_long_output(struct neighbour *neigh, struct sock *sk, - struct sk_buff *skb) -{ - struct net_device *dev = neigh->dev; - int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3; - unsigned char *data; - struct dn_long_packet *lp; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - - if (skb_headroom(skb) < headroom) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); - if (skb2 == NULL) { - net_crit_ratelimited("dn_long_output: no memory\n"); - kfree_skb(skb); - return -ENOBUFS; - } - consume_skb(skb); - skb = skb2; - net_info_ratelimited("dn_long_output: Increasing headroom\n"); - } - - data = skb_push(skb, sizeof(struct dn_long_packet) + 3); - lp = (struct dn_long_packet *)(data+3); - - *((__le16 *)data) = cpu_to_le16(skb->len - 2); - *(data + 2) = 1 | DN_RT_F_PF; /* Padding */ - - lp->msgflg = DN_RT_PKT_LONG|(cb->rt_flags&(DN_RT_F_IE|DN_RT_F_RQR|DN_RT_F_RTS)); - lp->d_area = lp->d_subarea = 0; - dn_dn2eth(lp->d_id, cb->dst); - lp->s_area = lp->s_subarea = 0; - dn_dn2eth(lp->s_id, cb->src); - lp->nl2 = 0; - lp->visit_ct = cb->hops & 0x3f; - lp->s_class = 0; - lp->pt = 0; - - skb_reset_network_header(skb); - - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, - &init_net, sk, skb, NULL, neigh->dev, - dn_neigh_output_packet); -} - -/* - * For talking to pointopoint and multidrop devices: DDCMP and X.25 - */ -static int dn_short_output(struct neighbour *neigh, struct sock *sk, - struct sk_buff *skb) -{ - struct net_device *dev = neigh->dev; - int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; - struct dn_short_packet *sp; - unsigned char *data; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - - if (skb_headroom(skb) < headroom) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); - if (skb2 == NULL) { - net_crit_ratelimited("dn_short_output: no memory\n"); - kfree_skb(skb); - return -ENOBUFS; - } - consume_skb(skb); - skb = skb2; - net_info_ratelimited("dn_short_output: Increasing headroom\n"); - } - - data = skb_push(skb, sizeof(struct dn_short_packet) + 2); - *((__le16 *)data) = cpu_to_le16(skb->len - 2); - sp = (struct dn_short_packet *)(data+2); - - sp->msgflg = DN_RT_PKT_SHORT|(cb->rt_flags&(DN_RT_F_RQR|DN_RT_F_RTS)); - sp->dstnode = cb->dst; - sp->srcnode = cb->src; - sp->forward = cb->hops & 0x3f; - - skb_reset_network_header(skb); - - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, - &init_net, sk, skb, NULL, neigh->dev, - dn_neigh_output_packet); -} - -/* - * For talking to DECnet phase III nodes - * Phase 3 output is the same as short output, execpt that - * it clears the area bits before transmission. - */ -static int dn_phase3_output(struct neighbour *neigh, struct sock *sk, - struct sk_buff *skb) -{ - struct net_device *dev = neigh->dev; - int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; - struct dn_short_packet *sp; - unsigned char *data; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - if (skb_headroom(skb) < headroom) { - struct sk_buff *skb2 = skb_realloc_headroom(skb, headroom); - if (skb2 == NULL) { - net_crit_ratelimited("dn_phase3_output: no memory\n"); - kfree_skb(skb); - return -ENOBUFS; - } - consume_skb(skb); - skb = skb2; - net_info_ratelimited("dn_phase3_output: Increasing headroom\n"); - } - - data = skb_push(skb, sizeof(struct dn_short_packet) + 2); - *((__le16 *)data) = cpu_to_le16(skb->len - 2); - sp = (struct dn_short_packet *)(data + 2); - - sp->msgflg = DN_RT_PKT_SHORT|(cb->rt_flags&(DN_RT_F_RQR|DN_RT_F_RTS)); - sp->dstnode = cb->dst & cpu_to_le16(0x03ff); - sp->srcnode = cb->src & cpu_to_le16(0x03ff); - sp->forward = cb->hops & 0x3f; - - skb_reset_network_header(skb); - - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, - &init_net, sk, skb, NULL, neigh->dev, - dn_neigh_output_packet); -} - -int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *) dst; - struct neighbour *neigh = rt->n; - struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n); - struct dn_dev *dn_db; - bool use_long; - - rcu_read_lock(); - dn_db = rcu_dereference(neigh->dev->dn_ptr); - if (dn_db == NULL) { - rcu_read_unlock(); - return -EINVAL; - } - use_long = dn_db->use_long; - rcu_read_unlock(); - - if (dn->flags & DN_NDFLAG_P3) - return dn_phase3_output(neigh, sk, skb); - if (use_long) - return dn_long_output(neigh, sk, skb); - else - return dn_short_output(neigh, sk, skb); -} - -/* - * Unfortunately, the neighbour code uses the device in its hash - * function, so we don't get any advantage from it. This function - * basically does a neigh_lookup(), but without comparing the device - * field. This is required for the On-Ethernet cache - */ - -/* - * Pointopoint link receives a hello message - */ -void dn_neigh_pointopoint_hello(struct sk_buff *skb) -{ - kfree_skb(skb); -} - -/* - * Ethernet router hello message received - */ -int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct rtnode_hello_message *msg = (struct rtnode_hello_message *)skb->data; - - struct neighbour *neigh; - struct dn_neigh *dn; - struct dn_dev *dn_db; - __le16 src; - - src = dn_eth2dn(msg->id); - - neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); - - dn = container_of(neigh, struct dn_neigh, n); - - if (neigh) { - write_lock(&neigh->lock); - - neigh->used = jiffies; - dn_db = rcu_dereference(neigh->dev->dn_ptr); - - if (!(neigh->nud_state & NUD_PERMANENT)) { - neigh->updated = jiffies; - - if (neigh->dev->type == ARPHRD_ETHER) - memcpy(neigh->ha, ð_hdr(skb)->h_source, ETH_ALEN); - - dn->blksize = le16_to_cpu(msg->blksize); - dn->priority = msg->priority; - - dn->flags &= ~DN_NDFLAG_P3; - - switch (msg->iinfo & DN_RT_INFO_TYPE) { - case DN_RT_INFO_L1RT: - dn->flags &=~DN_NDFLAG_R2; - dn->flags |= DN_NDFLAG_R1; - break; - case DN_RT_INFO_L2RT: - dn->flags |= DN_NDFLAG_R2; - } - } - - /* Only use routers in our area */ - if ((le16_to_cpu(src)>>10) == (le16_to_cpu((decnet_address))>>10)) { - if (!dn_db->router) { - dn_db->router = neigh_clone(neigh); - } else { - if (msg->priority > ((struct dn_neigh *)dn_db->router)->priority) - neigh_release(xchg(&dn_db->router, neigh_clone(neigh))); - } - } - write_unlock(&neigh->lock); - neigh_release(neigh); - } - - kfree_skb(skb); - return 0; -} - -/* - * Endnode hello message received - */ -int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data; - struct neighbour *neigh; - struct dn_neigh *dn; - __le16 src; - - src = dn_eth2dn(msg->id); - - neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1); - - dn = container_of(neigh, struct dn_neigh, n); - - if (neigh) { - write_lock(&neigh->lock); - - neigh->used = jiffies; - - if (!(neigh->nud_state & NUD_PERMANENT)) { - neigh->updated = jiffies; - - if (neigh->dev->type == ARPHRD_ETHER) - memcpy(neigh->ha, ð_hdr(skb)->h_source, ETH_ALEN); - dn->flags &= ~(DN_NDFLAG_R1 | DN_NDFLAG_R2); - dn->blksize = le16_to_cpu(msg->blksize); - dn->priority = 0; - } - - write_unlock(&neigh->lock); - neigh_release(neigh); - } - - kfree_skb(skb); - return 0; -} - -static char *dn_find_slot(char *base, int max, int priority) -{ - int i; - unsigned char *min = NULL; - - base += 6; /* skip first id */ - - for(i = 0; i < max; i++) { - if (!min || (*base < *min)) - min = base; - base += 7; /* find next priority */ - } - - if (!min) - return NULL; - - return (*min < priority) ? (min - 6) : NULL; -} - -struct elist_cb_state { - struct net_device *dev; - unsigned char *ptr; - unsigned char *rs; - int t, n; -}; - -static void neigh_elist_cb(struct neighbour *neigh, void *_info) -{ - struct elist_cb_state *s = _info; - struct dn_neigh *dn; - - if (neigh->dev != s->dev) - return; - - dn = container_of(neigh, struct dn_neigh, n); - if (!(dn->flags & (DN_NDFLAG_R1|DN_NDFLAG_R2))) - return; - - if (s->t == s->n) - s->rs = dn_find_slot(s->ptr, s->n, dn->priority); - else - s->t++; - if (s->rs == NULL) - return; - - dn_dn2eth(s->rs, dn->addr); - s->rs += 6; - *(s->rs) = neigh->nud_state & NUD_CONNECTED ? 0x80 : 0x0; - *(s->rs) |= dn->priority; - s->rs++; -} - -int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n) -{ - struct elist_cb_state state; - - state.dev = dev; - state.t = 0; - state.n = n; - state.ptr = ptr; - state.rs = ptr; - - neigh_for_each(&dn_neigh_table, neigh_elist_cb, &state); - - return state.t; -} - - -#ifdef CONFIG_PROC_FS - -static inline void dn_neigh_format_entry(struct seq_file *seq, - struct neighbour *n) -{ - struct dn_neigh *dn = container_of(n, struct dn_neigh, n); - char buf[DN_ASCBUF_LEN]; - - read_lock(&n->lock); - seq_printf(seq, "%-7s %s%s%s %02x %02d %07ld %-8s\n", - dn_addr2asc(le16_to_cpu(dn->addr), buf), - (dn->flags&DN_NDFLAG_R1) ? "1" : "-", - (dn->flags&DN_NDFLAG_R2) ? "2" : "-", - (dn->flags&DN_NDFLAG_P3) ? "3" : "-", - dn->n.nud_state, - refcount_read(&dn->n.refcnt), - dn->blksize, - (dn->n.dev) ? dn->n.dev->name : "?"); - read_unlock(&n->lock); -} - -static int dn_neigh_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) { - seq_puts(seq, "Addr Flags State Use Blksize Dev\n"); - } else { - dn_neigh_format_entry(seq, v); - } - - return 0; -} - -static void *dn_neigh_seq_start(struct seq_file *seq, loff_t *pos) -{ - return neigh_seq_start(seq, pos, &dn_neigh_table, - NEIGH_SEQ_NEIGH_ONLY); -} - -static const struct seq_operations dn_neigh_seq_ops = { - .start = dn_neigh_seq_start, - .next = neigh_seq_next, - .stop = neigh_seq_stop, - .show = dn_neigh_seq_show, -}; -#endif - -void __init dn_neigh_init(void) -{ - neigh_table_init(NEIGH_DN_TABLE, &dn_neigh_table); - proc_create_net("decnet_neigh", 0444, init_net.proc_net, - &dn_neigh_seq_ops, sizeof(struct neigh_seq_state)); -} - -void __exit dn_neigh_cleanup(void) -{ - remove_proc_entry("decnet_neigh", init_net.proc_net); - neigh_table_clear(NEIGH_DN_TABLE, &dn_neigh_table); -} diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c deleted file mode 100644 index 2fb5e055ba25..000000000000 --- a/net/decnet/dn_nsp_in.c +++ /dev/null @@ -1,914 +0,0 @@ -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Network Services Protocol (Input) - * - * Author: Eduardo Marcelo Serrat <emserrat@geocities.com> - * - * Changes: - * - * Steve Whitehouse: Split into dn_nsp_in.c and dn_nsp_out.c from - * original dn_nsp.c. - * Steve Whitehouse: Updated to work with my new routing architecture. - * Steve Whitehouse: Add changes from Eduardo Serrat's patches. - * Steve Whitehouse: Put all ack handling code in a common routine. - * Steve Whitehouse: Put other common bits into dn_nsp_rx() - * Steve Whitehouse: More checks on skb->len to catch bogus packets - * Fixed various race conditions and possible nasties. - * Steve Whitehouse: Now handles returned conninit frames. - * David S. Miller: New socket locking - * Steve Whitehouse: Fixed lockup when socket filtering was enabled. - * Paul Koning: Fix to push CC sockets into RUN when acks are - * received. - * Steve Whitehouse: - * Patrick Caulfield: Checking conninits for correctness & sending of error - * responses. - * Steve Whitehouse: Added backlog congestion level return codes. - * Patrick Caulfield: - * Steve Whitehouse: Added flow control support (outbound) - * Steve Whitehouse: Prepare for nonlinear skbs - */ - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. -*******************************************************************************/ - -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/kernel.h> -#include <linux/timer.h> -#include <linux/string.h> -#include <linux/sockios.h> -#include <linux/net.h> -#include <linux/netdevice.h> -#include <linux/inet.h> -#include <linux/route.h> -#include <linux/slab.h> -#include <net/sock.h> -#include <net/tcp_states.h> -#include <linux/fcntl.h> -#include <linux/mm.h> -#include <linux/termios.h> -#include <linux/interrupt.h> -#include <linux/proc_fs.h> -#include <linux/stat.h> -#include <linux/init.h> -#include <linux/poll.h> -#include <linux/netfilter_decnet.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/dn.h> -#include <net/dn_nsp.h> -#include <net/dn_dev.h> -#include <net/dn_route.h> - -extern int decnet_log_martians; - -static void dn_log_martian(struct sk_buff *skb, const char *msg) -{ - if (decnet_log_martians) { - char *devname = skb->dev ? skb->dev->name : "???"; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - net_info_ratelimited("DECnet: Martian packet (%s) dev=%s src=0x%04hx dst=0x%04hx srcport=0x%04hx dstport=0x%04hx\n", - msg, devname, - le16_to_cpu(cb->src), - le16_to_cpu(cb->dst), - le16_to_cpu(cb->src_port), - le16_to_cpu(cb->dst_port)); - } -} - -/* - * For this function we've flipped the cross-subchannel bit - * if the message is an otherdata or linkservice message. Thus - * we can use it to work out what to update. - */ -static void dn_ack(struct sock *sk, struct sk_buff *skb, unsigned short ack) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short type = ((ack >> 12) & 0x0003); - int wakeup = 0; - - switch (type) { - case 0: /* ACK - Data */ - if (dn_after(ack, scp->ackrcv_dat)) { - scp->ackrcv_dat = ack & 0x0fff; - wakeup |= dn_nsp_check_xmit_queue(sk, skb, - &scp->data_xmit_queue, - ack); - } - break; - case 1: /* NAK - Data */ - break; - case 2: /* ACK - OtherData */ - if (dn_after(ack, scp->ackrcv_oth)) { - scp->ackrcv_oth = ack & 0x0fff; - wakeup |= dn_nsp_check_xmit_queue(sk, skb, - &scp->other_xmit_queue, - ack); - } - break; - case 3: /* NAK - OtherData */ - break; - } - - if (wakeup && !sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); -} - -/* - * This function is a universal ack processor. - */ -static int dn_process_ack(struct sock *sk, struct sk_buff *skb, int oth) -{ - __le16 *ptr = (__le16 *)skb->data; - int len = 0; - unsigned short ack; - - if (skb->len < 2) - return len; - - if ((ack = le16_to_cpu(*ptr)) & 0x8000) { - skb_pull(skb, 2); - ptr++; - len += 2; - if ((ack & 0x4000) == 0) { - if (oth) - ack ^= 0x2000; - dn_ack(sk, skb, ack); - } - } - - if (skb->len < 2) - return len; - - if ((ack = le16_to_cpu(*ptr)) & 0x8000) { - skb_pull(skb, 2); - len += 2; - if ((ack & 0x4000) == 0) { - if (oth) - ack ^= 0x2000; - dn_ack(sk, skb, ack); - } - } - - return len; -} - - -/** - * dn_check_idf - Check an image data field format is correct. - * @pptr: Pointer to pointer to image data - * @len: Pointer to length of image data - * @max: The maximum allowed length of the data in the image data field - * @follow_on: Check that this many bytes exist beyond the end of the image data - * - * Returns: 0 if ok, -1 on error - */ -static inline int dn_check_idf(unsigned char **pptr, int *len, unsigned char max, unsigned char follow_on) -{ - unsigned char *ptr = *pptr; - unsigned char flen = *ptr++; - - (*len)--; - if (flen > max) - return -1; - if ((flen + follow_on) > *len) - return -1; - - *len -= flen; - *pptr = ptr + flen; - return 0; -} - -/* - * Table of reason codes to pass back to node which sent us a badly - * formed message, plus text messages for the log. A zero entry in - * the reason field means "don't reply" otherwise a disc init is sent with - * the specified reason code. - */ -static struct { - unsigned short reason; - const char *text; -} ci_err_table[] = { - { 0, "CI: Truncated message" }, - { NSP_REASON_ID, "CI: Destination username error" }, - { NSP_REASON_ID, "CI: Destination username type" }, - { NSP_REASON_US, "CI: Source username error" }, - { 0, "CI: Truncated at menuver" }, - { 0, "CI: Truncated before access or user data" }, - { NSP_REASON_IO, "CI: Access data format error" }, - { NSP_REASON_IO, "CI: User data format error" } -}; - -/* - * This function uses a slightly different lookup method - * to find its sockets, since it searches on object name/number - * rather than port numbers. Various tests are done to ensure that - * the incoming data is in the correct format before it is queued to - * a socket. - */ -static struct sock *dn_find_listener(struct sk_buff *skb, unsigned short *reason) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct nsp_conn_init_msg *msg = (struct nsp_conn_init_msg *)skb->data; - struct sockaddr_dn dstaddr; - struct sockaddr_dn srcaddr; - unsigned char type = 0; - int dstlen; - int srclen; - unsigned char *ptr; - int len; - int err = 0; - unsigned char menuver; - - memset(&dstaddr, 0, sizeof(struct sockaddr_dn)); - memset(&srcaddr, 0, sizeof(struct sockaddr_dn)); - - /* - * 1. Decode & remove message header - */ - cb->src_port = msg->srcaddr; - cb->dst_port = msg->dstaddr; - cb->services = msg->services; - cb->info = msg->info; - cb->segsize = le16_to_cpu(msg->segsize); - - if (!pskb_may_pull(skb, sizeof(*msg))) - goto err_out; - - skb_pull(skb, sizeof(*msg)); - - len = skb->len; - ptr = skb->data; - - /* - * 2. Check destination end username format - */ - dstlen = dn_username2sockaddr(ptr, len, &dstaddr, &type); - err++; - if (dstlen < 0) - goto err_out; - - err++; - if (type > 1) - goto err_out; - - len -= dstlen; - ptr += dstlen; - - /* - * 3. Check source end username format - */ - srclen = dn_username2sockaddr(ptr, len, &srcaddr, &type); - err++; - if (srclen < 0) - goto err_out; - - len -= srclen; - ptr += srclen; - err++; - if (len < 1) - goto err_out; - - menuver = *ptr; - ptr++; - len--; - - /* - * 4. Check that optional data actually exists if menuver says it does - */ - err++; - if ((menuver & (DN_MENUVER_ACC | DN_MENUVER_USR)) && (len < 1)) - goto err_out; - - /* - * 5. Check optional access data format - */ - err++; - if (menuver & DN_MENUVER_ACC) { - if (dn_check_idf(&ptr, &len, 39, 1)) - goto err_out; - if (dn_check_idf(&ptr, &len, 39, 1)) - goto err_out; - if (dn_check_idf(&ptr, &len, 39, (menuver & DN_MENUVER_USR) ? 1 : 0)) - goto err_out; - } - - /* - * 6. Check optional user data format - */ - err++; - if (menuver & DN_MENUVER_USR) { - if (dn_check_idf(&ptr, &len, 16, 0)) - goto err_out; - } - - /* - * 7. Look up socket based on destination end username - */ - return dn_sklist_find_listener(&dstaddr); -err_out: - dn_log_martian(skb, ci_err_table[err].text); - *reason = ci_err_table[err].reason; - return NULL; -} - - -static void dn_nsp_conn_init(struct sock *sk, struct sk_buff *skb) -{ - if (sk_acceptq_is_full(sk)) { - kfree_skb(skb); - return; - } - - sk->sk_ack_backlog++; - skb_queue_tail(&sk->sk_receive_queue, skb); - sk->sk_state_change(sk); -} - -static void dn_nsp_conn_conf(struct sock *sk, struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dn_scp *scp = DN_SK(sk); - unsigned char *ptr; - - if (skb->len < 4) - goto out; - - ptr = skb->data; - cb->services = *ptr++; - cb->info = *ptr++; - cb->segsize = le16_to_cpu(*(__le16 *)ptr); - - if ((scp->state == DN_CI) || (scp->state == DN_CD)) { - scp->persist = 0; - scp->addrrem = cb->src_port; - sk->sk_state = TCP_ESTABLISHED; - scp->state = DN_RUN; - scp->services_rem = cb->services; - scp->info_rem = cb->info; - scp->segsize_rem = cb->segsize; - - if ((scp->services_rem & NSP_FC_MASK) == NSP_FC_NONE) - scp->max_window = decnet_no_fc_max_cwnd; - - if (skb->len > 0) { - u16 dlen = *skb->data; - if ((dlen <= 16) && (dlen <= skb->len)) { - scp->conndata_in.opt_optl = cpu_to_le16(dlen); - skb_copy_from_linear_data_offset(skb, 1, - scp->conndata_in.opt_data, dlen); - } - } - dn_nsp_send_link(sk, DN_NOCHANGE, 0); - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - } - -out: - kfree_skb(skb); -} - -static void dn_nsp_conn_ack(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CI) { - scp->state = DN_CD; - scp->persist = 0; - } - - kfree_skb(skb); -} - -static void dn_nsp_disc_init(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned short reason; - - if (skb->len < 2) - goto out; - - reason = le16_to_cpu(*(__le16 *)skb->data); - skb_pull(skb, 2); - - scp->discdata_in.opt_status = cpu_to_le16(reason); - scp->discdata_in.opt_optl = 0; - memset(scp->discdata_in.opt_data, 0, 16); - - if (skb->len > 0) { - u16 dlen = *skb->data; - if ((dlen <= 16) && (dlen <= skb->len)) { - scp->discdata_in.opt_optl = cpu_to_le16(dlen); - skb_copy_from_linear_data_offset(skb, 1, scp->discdata_in.opt_data, dlen); - } - } - - scp->addrrem = cb->src_port; - sk->sk_state = TCP_CLOSE; - - switch (scp->state) { - case DN_CI: - case DN_CD: - scp->state = DN_RJ; - sk->sk_err = ECONNREFUSED; - break; - case DN_RUN: - sk->sk_shutdown |= SHUTDOWN_MASK; - scp->state = DN_DN; - break; - case DN_DI: - scp->state = DN_DIC; - break; - } - - if (!sock_flag(sk, SOCK_DEAD)) { - if (sk->sk_socket->state != SS_UNCONNECTED) - sk->sk_socket->state = SS_DISCONNECTING; - sk->sk_state_change(sk); - } - - /* - * It appears that its possible for remote machines to send disc - * init messages with no port identifier if we are in the CI and - * possibly also the CD state. Obviously we shouldn't reply with - * a message if we don't know what the end point is. - */ - if (scp->addrrem) { - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, GFP_ATOMIC); - } - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - -out: - kfree_skb(skb); -} - -/* - * disc_conf messages are also called no_resources or no_link - * messages depending upon the "reason" field. - */ -static void dn_nsp_disc_conf(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short reason; - - if (skb->len != 2) - goto out; - - reason = le16_to_cpu(*(__le16 *)skb->data); - - sk->sk_state = TCP_CLOSE; - - switch (scp->state) { - case DN_CI: - scp->state = DN_NR; - break; - case DN_DR: - if (reason == NSP_REASON_DC) - scp->state = DN_DRC; - if (reason == NSP_REASON_NL) - scp->state = DN_CN; - break; - case DN_DI: - scp->state = DN_DIC; - break; - case DN_RUN: - sk->sk_shutdown |= SHUTDOWN_MASK; - /* fall through */ - case DN_CC: - scp->state = DN_CN; - } - - if (!sock_flag(sk, SOCK_DEAD)) { - if (sk->sk_socket->state != SS_UNCONNECTED) - sk->sk_socket->state = SS_DISCONNECTING; - sk->sk_state_change(sk); - } - - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - -out: - kfree_skb(skb); -} - -static void dn_nsp_linkservice(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short segnum; - unsigned char lsflags; - signed char fcval; - int wake_up = 0; - char *ptr = skb->data; - unsigned char fctype = scp->services_rem & NSP_FC_MASK; - - if (skb->len != 4) - goto out; - - segnum = le16_to_cpu(*(__le16 *)ptr); - ptr += 2; - lsflags = *(unsigned char *)ptr++; - fcval = *ptr; - - /* - * Here we ignore erronous packets which should really - * should cause a connection abort. It is not critical - * for now though. - */ - if (lsflags & 0xf8) - goto out; - - if (seq_next(scp->numoth_rcv, segnum)) { - seq_add(&scp->numoth_rcv, 1); - switch(lsflags & 0x04) { /* FCVAL INT */ - case 0x00: /* Normal Request */ - switch(lsflags & 0x03) { /* FCVAL MOD */ - case 0x00: /* Request count */ - if (fcval < 0) { - unsigned char p_fcval = -fcval; - if ((scp->flowrem_dat > p_fcval) && - (fctype == NSP_FC_SCMC)) { - scp->flowrem_dat -= p_fcval; - } - } else if (fcval > 0) { - scp->flowrem_dat += fcval; - wake_up = 1; - } - break; - case 0x01: /* Stop outgoing data */ - scp->flowrem_sw = DN_DONTSEND; - break; - case 0x02: /* Ok to start again */ - scp->flowrem_sw = DN_SEND; - dn_nsp_output(sk); - wake_up = 1; - } - break; - case 0x04: /* Interrupt Request */ - if (fcval > 0) { - scp->flowrem_oth += fcval; - wake_up = 1; - } - break; - } - if (wake_up && !sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - } - - dn_nsp_send_oth_ack(sk); - -out: - kfree_skb(skb); -} - -/* - * Copy of sock_queue_rcv_skb (from sock.h) without - * bh_lock_sock() (its already held when this is called) which - * also allows data and other data to be queued to a socket. - */ -static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig, struct sk_buff_head *queue) -{ - int err; - - /* Cast skb->rcvbuf to unsigned... It's pointless, but reduces - number of warnings when compiling with -W --ANK - */ - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned int)sk->sk_rcvbuf) { - err = -ENOMEM; - goto out; - } - - err = sk_filter(sk, skb); - if (err) - goto out; - - skb_set_owner_r(skb, sk); - skb_queue_tail(queue, skb); - - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); -out: - return err; -} - -static void dn_nsp_otherdata(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short segnum; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - int queued = 0; - - if (skb->len < 2) - goto out; - - cb->segnum = segnum = le16_to_cpu(*(__le16 *)skb->data); - skb_pull(skb, 2); - - if (seq_next(scp->numoth_rcv, segnum)) { - - if (dn_queue_skb(sk, skb, SIGURG, &scp->other_receive_queue) == 0) { - seq_add(&scp->numoth_rcv, 1); - scp->other_report = 0; - queued = 1; - } - } - - dn_nsp_send_oth_ack(sk); -out: - if (!queued) - kfree_skb(skb); -} - -static void dn_nsp_data(struct sock *sk, struct sk_buff *skb) -{ - int queued = 0; - unsigned short segnum; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dn_scp *scp = DN_SK(sk); - - if (skb->len < 2) - goto out; - - cb->segnum = segnum = le16_to_cpu(*(__le16 *)skb->data); - skb_pull(skb, 2); - - if (seq_next(scp->numdat_rcv, segnum)) { - if (dn_queue_skb(sk, skb, SIGIO, &sk->sk_receive_queue) == 0) { - seq_add(&scp->numdat_rcv, 1); - queued = 1; - } - - if ((scp->flowloc_sw == DN_SEND) && dn_congested(sk)) { - scp->flowloc_sw = DN_DONTSEND; - dn_nsp_send_link(sk, DN_DONTSEND, 0); - } - } - - dn_nsp_send_data_ack(sk); -out: - if (!queued) - kfree_skb(skb); -} - -/* - * If one of our conninit messages is returned, this function - * deals with it. It puts the socket into the NO_COMMUNICATION - * state. - */ -static void dn_returned_conn_init(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CI) { - scp->state = DN_NC; - sk->sk_state = TCP_CLOSE; - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - } - - kfree_skb(skb); -} - -static int dn_nsp_no_socket(struct sk_buff *skb, unsigned short reason) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - int ret = NET_RX_DROP; - - /* Must not reply to returned packets */ - if (cb->rt_flags & DN_RT_F_RTS) - goto out; - - if ((reason != NSP_REASON_OK) && ((cb->nsp_flags & 0x0c) == 0x08)) { - switch (cb->nsp_flags & 0x70) { - case 0x10: - case 0x60: /* (Retransmitted) Connect Init */ - dn_nsp_return_disc(skb, NSP_DISCINIT, reason); - ret = NET_RX_SUCCESS; - break; - case 0x20: /* Connect Confirm */ - dn_nsp_return_disc(skb, NSP_DISCCONF, reason); - ret = NET_RX_SUCCESS; - break; - } - } - -out: - kfree_skb(skb); - return ret; -} - -static int dn_nsp_rx_packet(struct net *net, struct sock *sk2, - struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct sock *sk = NULL; - unsigned char *ptr = (unsigned char *)skb->data; - unsigned short reason = NSP_REASON_NL; - - if (!pskb_may_pull(skb, 2)) - goto free_out; - - skb_reset_transport_header(skb); - cb->nsp_flags = *ptr++; - - if (decnet_debug_level & 2) - printk(KERN_DEBUG "dn_nsp_rx: Message type 0x%02x\n", (int)cb->nsp_flags); - - if (cb->nsp_flags & 0x83) - goto free_out; - - /* - * Filter out conninits and useless packet types - */ - if ((cb->nsp_flags & 0x0c) == 0x08) { - switch (cb->nsp_flags & 0x70) { - case 0x00: /* NOP */ - case 0x70: /* Reserved */ - case 0x50: /* Reserved, Phase II node init */ - goto free_out; - case 0x10: - case 0x60: - if (unlikely(cb->rt_flags & DN_RT_F_RTS)) - goto free_out; - sk = dn_find_listener(skb, &reason); - goto got_it; - } - } - - if (!pskb_may_pull(skb, 3)) - goto free_out; - - /* - * Grab the destination address. - */ - cb->dst_port = *(__le16 *)ptr; - cb->src_port = 0; - ptr += 2; - - /* - * If not a connack, grab the source address too. - */ - if (pskb_may_pull(skb, 5)) { - cb->src_port = *(__le16 *)ptr; - ptr += 2; - skb_pull(skb, 5); - } - - /* - * Returned packets... - * Swap src & dst and look up in the normal way. - */ - if (unlikely(cb->rt_flags & DN_RT_F_RTS)) { - swap(cb->dst_port, cb->src_port); - swap(cb->dst, cb->src); - } - - /* - * Find the socket to which this skb is destined. - */ - sk = dn_find_by_skb(skb); -got_it: - if (sk != NULL) { - struct dn_scp *scp = DN_SK(sk); - - /* Reset backoff */ - scp->nsp_rxtshift = 0; - - /* - * We linearize everything except data segments here. - */ - if (cb->nsp_flags & ~0x60) { - if (unlikely(skb_linearize(skb))) - goto free_out; - } - - return sk_receive_skb(sk, skb, 0); - } - - return dn_nsp_no_socket(skb, reason); - -free_out: - kfree_skb(skb); - return NET_RX_DROP; -} - -int dn_nsp_rx(struct sk_buff *skb) -{ - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, - &init_net, NULL, skb, skb->dev, NULL, - dn_nsp_rx_packet); -} - -/* - * This is the main receive routine for sockets. It is called - * from the above when the socket is not busy, and also from - * sock_release() when there is a backlog queued up. - */ -int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - if (cb->rt_flags & DN_RT_F_RTS) { - if (cb->nsp_flags == 0x18 || cb->nsp_flags == 0x68) - dn_returned_conn_init(sk, skb); - else - kfree_skb(skb); - return NET_RX_SUCCESS; - } - - /* - * Control packet. - */ - if ((cb->nsp_flags & 0x0c) == 0x08) { - switch (cb->nsp_flags & 0x70) { - case 0x10: - case 0x60: - dn_nsp_conn_init(sk, skb); - break; - case 0x20: - dn_nsp_conn_conf(sk, skb); - break; - case 0x30: - dn_nsp_disc_init(sk, skb); - break; - case 0x40: - dn_nsp_disc_conf(sk, skb); - break; - } - - } else if (cb->nsp_flags == 0x24) { - /* - * Special for connacks, 'cos they don't have - * ack data or ack otherdata info. - */ - dn_nsp_conn_ack(sk, skb); - } else { - int other = 1; - - /* both data and ack frames can kick a CC socket into RUN */ - if ((scp->state == DN_CC) && !sock_flag(sk, SOCK_DEAD)) { - scp->state = DN_RUN; - sk->sk_state = TCP_ESTABLISHED; - sk->sk_state_change(sk); - } - - if ((cb->nsp_flags & 0x1c) == 0) - other = 0; - if (cb->nsp_flags == 0x04) - other = 0; - - /* - * Read out ack data here, this applies equally - * to data, other data, link serivce and both - * ack data and ack otherdata. - */ - dn_process_ack(sk, skb, other); - - /* - * If we've some sort of data here then call a - * suitable routine for dealing with it, otherwise - * the packet is an ack and can be discarded. - */ - if ((cb->nsp_flags & 0x0c) == 0) { - - if (scp->state != DN_RUN) - goto free_out; - - switch (cb->nsp_flags) { - case 0x10: /* LS */ - dn_nsp_linkservice(sk, skb); - break; - case 0x30: /* OD */ - dn_nsp_otherdata(sk, skb); - break; - default: - dn_nsp_data(sk, skb); - } - - } else { /* Ack, chuck it out here */ -free_out: - kfree_skb(skb); - } - } - - return NET_RX_SUCCESS; -} diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c deleted file mode 100644 index a1779de6bd9c..000000000000 --- a/net/decnet/dn_nsp_out.c +++ /dev/null @@ -1,703 +0,0 @@ -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Network Services Protocol (Output) - * - * Author: Eduardo Marcelo Serrat <emserrat@geocities.com> - * - * Changes: - * - * Steve Whitehouse: Split into dn_nsp_in.c and dn_nsp_out.c from - * original dn_nsp.c. - * Steve Whitehouse: Updated to work with my new routing architecture. - * Steve Whitehouse: Added changes from Eduardo Serrat's patches. - * Steve Whitehouse: Now conninits have the "return" bit set. - * Steve Whitehouse: Fixes to check alloc'd skbs are non NULL! - * Moved output state machine into one function - * Steve Whitehouse: New output state machine - * Paul Koning: Connect Confirm message fix. - * Eduardo Serrat: Fix to stop dn_nsp_do_disc() sending malformed packets. - * Steve Whitehouse: dn_nsp_output() and friends needed a spring clean - * Steve Whitehouse: Moved dn_nsp_send() in here from route.h - */ - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. -*******************************************************************************/ - -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/kernel.h> -#include <linux/timer.h> -#include <linux/string.h> -#include <linux/sockios.h> -#include <linux/net.h> -#include <linux/netdevice.h> -#include <linux/inet.h> -#include <linux/route.h> -#include <linux/slab.h> -#include <net/sock.h> -#include <linux/fcntl.h> -#include <linux/mm.h> -#include <linux/termios.h> -#include <linux/interrupt.h> -#include <linux/proc_fs.h> -#include <linux/stat.h> -#include <linux/init.h> -#include <linux/poll.h> -#include <linux/if_packet.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/flow.h> -#include <net/dn.h> -#include <net/dn_nsp.h> -#include <net/dn_dev.h> -#include <net/dn_route.h> - - -static int nsp_backoff[NSP_MAXRXTSHIFT + 1] = { 1, 2, 4, 8, 16, 32, 64, 64, 64, 64, 64, 64, 64 }; - -static void dn_nsp_send(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - struct dn_scp *scp = DN_SK(sk); - struct dst_entry *dst; - struct flowidn fld; - - skb_reset_transport_header(skb); - scp->stamp = jiffies; - - dst = sk_dst_check(sk, 0); - if (dst) { -try_again: - skb_dst_set(skb, dst); - dst_output(&init_net, skb->sk, skb); - return; - } - - memset(&fld, 0, sizeof(fld)); - fld.flowidn_oif = sk->sk_bound_dev_if; - fld.saddr = dn_saddr2dn(&scp->addr); - fld.daddr = dn_saddr2dn(&scp->peer); - dn_sk_ports_copy(&fld, scp); - fld.flowidn_proto = DNPROTO_NSP; - if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, 0) == 0) { - dst = sk_dst_get(sk); - sk->sk_route_caps = dst->dev->features; - goto try_again; - } - - sk->sk_err = EHOSTUNREACH; - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); -} - - -/* - * If sk == NULL, then we assume that we are supposed to be making - * a routing layer skb. If sk != NULL, then we are supposed to be - * creating an skb for the NSP layer. - * - * The eventual aim is for each socket to have a cached header size - * for its outgoing packets, and to set hdr from this when sk != NULL. - */ -struct sk_buff *dn_alloc_skb(struct sock *sk, int size, gfp_t pri) -{ - struct sk_buff *skb; - int hdr = 64; - - if ((skb = alloc_skb(size + hdr, pri)) == NULL) - return NULL; - - skb->protocol = htons(ETH_P_DNA_RT); - skb->pkt_type = PACKET_OUTGOING; - - if (sk) - skb_set_owner_w(skb, sk); - - skb_reserve(skb, hdr); - - return skb; -} - -/* - * Calculate persist timer based upon the smoothed round - * trip time and the variance. Backoff according to the - * nsp_backoff[] array. - */ -unsigned long dn_nsp_persist(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - unsigned long t = ((scp->nsp_srtt >> 2) + scp->nsp_rttvar) >> 1; - - t *= nsp_backoff[scp->nsp_rxtshift]; - - if (t < HZ) t = HZ; - if (t > (600*HZ)) t = (600*HZ); - - if (scp->nsp_rxtshift < NSP_MAXRXTSHIFT) - scp->nsp_rxtshift++; - - /* printk(KERN_DEBUG "rxtshift %lu, t=%lu\n", scp->nsp_rxtshift, t); */ - - return t; -} - -/* - * This is called each time we get an estimate for the rtt - * on the link. - */ -static void dn_nsp_rtt(struct sock *sk, long rtt) -{ - struct dn_scp *scp = DN_SK(sk); - long srtt = (long)scp->nsp_srtt; - long rttvar = (long)scp->nsp_rttvar; - long delta; - - /* - * If the jiffies clock flips over in the middle of timestamp - * gathering this value might turn out negative, so we make sure - * that is it always positive here. - */ - if (rtt < 0) - rtt = -rtt; - /* - * Add new rtt to smoothed average - */ - delta = ((rtt << 3) - srtt); - srtt += (delta >> 3); - if (srtt >= 1) - scp->nsp_srtt = (unsigned long)srtt; - else - scp->nsp_srtt = 1; - - /* - * Add new rtt varience to smoothed varience - */ - delta >>= 1; - rttvar += ((((delta>0)?(delta):(-delta)) - rttvar) >> 2); - if (rttvar >= 1) - scp->nsp_rttvar = (unsigned long)rttvar; - else - scp->nsp_rttvar = 1; - - /* printk(KERN_DEBUG "srtt=%lu rttvar=%lu\n", scp->nsp_srtt, scp->nsp_rttvar); */ -} - -/** - * dn_nsp_clone_and_send - Send a data packet by cloning it - * @skb: The packet to clone and transmit - * @gfp: memory allocation flag - * - * Clone a queued data or other data packet and transmit it. - * - * Returns: The number of times the packet has been sent previously - */ -static inline unsigned int dn_nsp_clone_and_send(struct sk_buff *skb, - gfp_t gfp) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct sk_buff *skb2; - int ret = 0; - - if ((skb2 = skb_clone(skb, gfp)) != NULL) { - ret = cb->xmit_count; - cb->xmit_count++; - cb->stamp = jiffies; - skb2->sk = skb->sk; - dn_nsp_send(skb2); - } - - return ret; -} - -/** - * dn_nsp_output - Try and send something from socket queues - * @sk: The socket whose queues are to be investigated - * - * Try and send the packet on the end of the data and other data queues. - * Other data gets priority over data, and if we retransmit a packet we - * reduce the window by dividing it in two. - * - */ -void dn_nsp_output(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb; - unsigned int reduce_win = 0; - - /* - * First we check for otherdata/linkservice messages - */ - if ((skb = skb_peek(&scp->other_xmit_queue)) != NULL) - reduce_win = dn_nsp_clone_and_send(skb, GFP_ATOMIC); - - /* - * If we may not send any data, we don't. - * If we are still trying to get some other data down the - * channel, we don't try and send any data. - */ - if (reduce_win || (scp->flowrem_sw != DN_SEND)) - goto recalc_window; - - if ((skb = skb_peek(&scp->data_xmit_queue)) != NULL) - reduce_win = dn_nsp_clone_and_send(skb, GFP_ATOMIC); - - /* - * If we've sent any frame more than once, we cut the - * send window size in half. There is always a minimum - * window size of one available. - */ -recalc_window: - if (reduce_win) { - scp->snd_window >>= 1; - if (scp->snd_window < NSP_MIN_WINDOW) - scp->snd_window = NSP_MIN_WINDOW; - } -} - -int dn_nsp_xmit_timeout(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - dn_nsp_output(sk); - - if (!skb_queue_empty(&scp->data_xmit_queue) || - !skb_queue_empty(&scp->other_xmit_queue)) - scp->persist = dn_nsp_persist(sk); - - return 0; -} - -static inline __le16 *dn_mk_common_header(struct dn_scp *scp, struct sk_buff *skb, unsigned char msgflag, int len) -{ - unsigned char *ptr = skb_push(skb, len); - - BUG_ON(len < 5); - - *ptr++ = msgflag; - *((__le16 *)ptr) = scp->addrrem; - ptr += 2; - *((__le16 *)ptr) = scp->addrloc; - ptr += 2; - return (__le16 __force *)ptr; -} - -static __le16 *dn_mk_ack_header(struct sock *sk, struct sk_buff *skb, unsigned char msgflag, int hlen, int other) -{ - struct dn_scp *scp = DN_SK(sk); - unsigned short acknum = scp->numdat_rcv & 0x0FFF; - unsigned short ackcrs = scp->numoth_rcv & 0x0FFF; - __le16 *ptr; - - BUG_ON(hlen < 9); - - scp->ackxmt_dat = acknum; - scp->ackxmt_oth = ackcrs; - acknum |= 0x8000; - ackcrs |= 0x8000; - - /* If this is an "other data/ack" message, swap acknum and ackcrs */ - if (other) - swap(acknum, ackcrs); - - /* Set "cross subchannel" bit in ackcrs */ - ackcrs |= 0x2000; - - ptr = dn_mk_common_header(scp, skb, msgflag, hlen); - - *ptr++ = cpu_to_le16(acknum); - *ptr++ = cpu_to_le16(ackcrs); - - return ptr; -} - -static __le16 *dn_nsp_mk_data_header(struct sock *sk, struct sk_buff *skb, int oth) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - __le16 *ptr = dn_mk_ack_header(sk, skb, cb->nsp_flags, 11, oth); - - if (unlikely(oth)) { - cb->segnum = scp->numoth; - seq_add(&scp->numoth, 1); - } else { - cb->segnum = scp->numdat; - seq_add(&scp->numdat, 1); - } - *(ptr++) = cpu_to_le16(cb->segnum); - - return ptr; -} - -void dn_nsp_queue_xmit(struct sock *sk, struct sk_buff *skb, - gfp_t gfp, int oth) -{ - struct dn_scp *scp = DN_SK(sk); - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned long t = ((scp->nsp_srtt >> 2) + scp->nsp_rttvar) >> 1; - - cb->xmit_count = 0; - dn_nsp_mk_data_header(sk, skb, oth); - - /* - * Slow start: If we have been idle for more than - * one RTT, then reset window to min size. - */ - if ((jiffies - scp->stamp) > t) - scp->snd_window = NSP_MIN_WINDOW; - - if (oth) - skb_queue_tail(&scp->other_xmit_queue, skb); - else - skb_queue_tail(&scp->data_xmit_queue, skb); - - if (scp->flowrem_sw != DN_SEND) - return; - - dn_nsp_clone_and_send(skb, gfp); -} - - -int dn_nsp_check_xmit_queue(struct sock *sk, struct sk_buff *skb, struct sk_buff_head *q, unsigned short acknum) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb2, *n, *ack = NULL; - int wakeup = 0; - int try_retrans = 0; - unsigned long reftime = cb->stamp; - unsigned long pkttime; - unsigned short xmit_count; - unsigned short segnum; - - skb_queue_walk_safe(q, skb2, n) { - struct dn_skb_cb *cb2 = DN_SKB_CB(skb2); - - if (dn_before_or_equal(cb2->segnum, acknum)) - ack = skb2; - - /* printk(KERN_DEBUG "ack: %s %04x %04x\n", ack ? "ACK" : "SKIP", (int)cb2->segnum, (int)acknum); */ - - if (ack == NULL) - continue; - - /* printk(KERN_DEBUG "check_xmit_queue: %04x, %d\n", acknum, cb2->xmit_count); */ - - /* Does _last_ packet acked have xmit_count > 1 */ - try_retrans = 0; - /* Remember to wake up the sending process */ - wakeup = 1; - /* Keep various statistics */ - pkttime = cb2->stamp; - xmit_count = cb2->xmit_count; - segnum = cb2->segnum; - /* Remove and drop ack'ed packet */ - skb_unlink(ack, q); - kfree_skb(ack); - ack = NULL; - - /* - * We don't expect to see acknowledgements for packets we - * haven't sent yet. - */ - WARN_ON(xmit_count == 0); - - /* - * If the packet has only been sent once, we can use it - * to calculate the RTT and also open the window a little - * further. - */ - if (xmit_count == 1) { - if (dn_equal(segnum, acknum)) - dn_nsp_rtt(sk, (long)(pkttime - reftime)); - - if (scp->snd_window < scp->max_window) - scp->snd_window++; - } - - /* - * Packet has been sent more than once. If this is the last - * packet to be acknowledged then we want to send the next - * packet in the send queue again (assumes the remote host does - * go-back-N error control). - */ - if (xmit_count > 1) - try_retrans = 1; - } - - if (try_retrans) - dn_nsp_output(sk); - - return wakeup; -} - -void dn_nsp_send_data_ack(struct sock *sk) -{ - struct sk_buff *skb = NULL; - - if ((skb = dn_alloc_skb(sk, 9, GFP_ATOMIC)) == NULL) - return; - - skb_reserve(skb, 9); - dn_mk_ack_header(sk, skb, 0x04, 9, 0); - dn_nsp_send(skb); -} - -void dn_nsp_send_oth_ack(struct sock *sk) -{ - struct sk_buff *skb = NULL; - - if ((skb = dn_alloc_skb(sk, 9, GFP_ATOMIC)) == NULL) - return; - - skb_reserve(skb, 9); - dn_mk_ack_header(sk, skb, 0x14, 9, 1); - dn_nsp_send(skb); -} - - -void dn_send_conn_ack (struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb = NULL; - struct nsp_conn_ack_msg *msg; - - if ((skb = dn_alloc_skb(sk, 3, sk->sk_allocation)) == NULL) - return; - - msg = skb_put(skb, 3); - msg->msgflg = 0x24; - msg->dstaddr = scp->addrrem; - - dn_nsp_send(skb); -} - -static int dn_nsp_retrans_conn_conf(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CC) - dn_send_conn_conf(sk, GFP_ATOMIC); - - return 0; -} - -void dn_send_conn_conf(struct sock *sk, gfp_t gfp) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb = NULL; - struct nsp_conn_init_msg *msg; - __u8 len = (__u8)le16_to_cpu(scp->conndata_out.opt_optl); - - if ((skb = dn_alloc_skb(sk, 50 + len, gfp)) == NULL) - return; - - msg = skb_put(skb, sizeof(*msg)); - msg->msgflg = 0x28; - msg->dstaddr = scp->addrrem; - msg->srcaddr = scp->addrloc; - msg->services = scp->services_loc; - msg->info = scp->info_loc; - msg->segsize = cpu_to_le16(scp->segsize_loc); - - skb_put_u8(skb, len); - - if (len > 0) - skb_put_data(skb, scp->conndata_out.opt_data, len); - - - dn_nsp_send(skb); - - scp->persist = dn_nsp_persist(sk); - scp->persist_fxn = dn_nsp_retrans_conn_conf; -} - - -static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, - unsigned short reason, gfp_t gfp, - struct dst_entry *dst, - int ddl, unsigned char *dd, __le16 rem, __le16 loc) -{ - struct sk_buff *skb = NULL; - int size = 7 + ddl + ((msgflg == NSP_DISCINIT) ? 1 : 0); - unsigned char *msg; - - if ((dst == NULL) || (rem == 0)) { - net_dbg_ratelimited("DECnet: dn_nsp_do_disc: BUG! Please report this to SteveW@ACM.org rem=%u dst=%p\n", - le16_to_cpu(rem), dst); - return; - } - - if ((skb = dn_alloc_skb(sk, size, gfp)) == NULL) - return; - - msg = skb_put(skb, size); - *msg++ = msgflg; - *(__le16 *)msg = rem; - msg += 2; - *(__le16 *)msg = loc; - msg += 2; - *(__le16 *)msg = cpu_to_le16(reason); - msg += 2; - if (msgflg == NSP_DISCINIT) - *msg++ = ddl; - - if (ddl) { - memcpy(msg, dd, ddl); - } - - /* - * This doesn't go via the dn_nsp_send() function since we need - * to be able to send disc packets out which have no socket - * associations. - */ - skb_dst_set(skb, dst_clone(dst)); - dst_output(&init_net, skb->sk, skb); -} - - -void dn_nsp_send_disc(struct sock *sk, unsigned char msgflg, - unsigned short reason, gfp_t gfp) -{ - struct dn_scp *scp = DN_SK(sk); - int ddl = 0; - - if (msgflg == NSP_DISCINIT) - ddl = le16_to_cpu(scp->discdata_out.opt_optl); - - if (reason == 0) - reason = le16_to_cpu(scp->discdata_out.opt_status); - - dn_nsp_do_disc(sk, msgflg, reason, gfp, __sk_dst_get(sk), ddl, - scp->discdata_out.opt_data, scp->addrrem, scp->addrloc); -} - - -void dn_nsp_return_disc(struct sk_buff *skb, unsigned char msgflg, - unsigned short reason) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - int ddl = 0; - gfp_t gfp = GFP_ATOMIC; - - dn_nsp_do_disc(NULL, msgflg, reason, gfp, skb_dst(skb), ddl, - NULL, cb->src_port, cb->dst_port); -} - - -void dn_nsp_send_link(struct sock *sk, unsigned char lsflags, char fcval) -{ - struct dn_scp *scp = DN_SK(sk); - struct sk_buff *skb; - unsigned char *ptr; - gfp_t gfp = GFP_ATOMIC; - - if ((skb = dn_alloc_skb(sk, DN_MAX_NSP_DATA_HEADER + 2, gfp)) == NULL) - return; - - skb_reserve(skb, DN_MAX_NSP_DATA_HEADER); - ptr = skb_put(skb, 2); - DN_SKB_CB(skb)->nsp_flags = 0x10; - *ptr++ = lsflags; - *ptr = fcval; - - dn_nsp_queue_xmit(sk, skb, gfp, 1); - - scp->persist = dn_nsp_persist(sk); - scp->persist_fxn = dn_nsp_xmit_timeout; -} - -static int dn_nsp_retrans_conninit(struct sock *sk) -{ - struct dn_scp *scp = DN_SK(sk); - - if (scp->state == DN_CI) - dn_nsp_send_conninit(sk, NSP_RCI); - - return 0; -} - -void dn_nsp_send_conninit(struct sock *sk, unsigned char msgflg) -{ - struct dn_scp *scp = DN_SK(sk); - struct nsp_conn_init_msg *msg; - unsigned char aux; - unsigned char menuver; - struct dn_skb_cb *cb; - unsigned char type = 1; - gfp_t allocation = (msgflg == NSP_CI) ? sk->sk_allocation : GFP_ATOMIC; - struct sk_buff *skb = dn_alloc_skb(sk, 200, allocation); - - if (!skb) - return; - - cb = DN_SKB_CB(skb); - msg = skb_put(skb, sizeof(*msg)); - - msg->msgflg = msgflg; - msg->dstaddr = 0x0000; /* Remote Node will assign it*/ - - msg->srcaddr = scp->addrloc; - msg->services = scp->services_loc; /* Requested flow control */ - msg->info = scp->info_loc; /* Version Number */ - msg->segsize = cpu_to_le16(scp->segsize_loc); /* Max segment size */ - - if (scp->peer.sdn_objnum) - type = 0; - - skb_put(skb, dn_sockaddr2username(&scp->peer, - skb_tail_pointer(skb), type)); - skb_put(skb, dn_sockaddr2username(&scp->addr, - skb_tail_pointer(skb), 2)); - - menuver = DN_MENUVER_ACC | DN_MENUVER_USR; - if (scp->peer.sdn_flags & SDF_PROXY) - menuver |= DN_MENUVER_PRX; - if (scp->peer.sdn_flags & SDF_UICPROXY) - menuver |= DN_MENUVER_UIC; - - skb_put_u8(skb, menuver); /* Menu Version */ - - aux = scp->accessdata.acc_userl; - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->accessdata.acc_user, aux); - - aux = scp->accessdata.acc_passl; - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->accessdata.acc_pass, aux); - - aux = scp->accessdata.acc_accl; - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->accessdata.acc_acc, aux); - - aux = (__u8)le16_to_cpu(scp->conndata_out.opt_optl); - skb_put_u8(skb, aux); - if (aux > 0) - skb_put_data(skb, scp->conndata_out.opt_data, aux); - - scp->persist = dn_nsp_persist(sk); - scp->persist_fxn = dn_nsp_retrans_conninit; - - cb->rt_flags = DN_RT_F_RQR; - - dn_nsp_send(skb); -} diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c deleted file mode 100644 index 658191fba94e..000000000000 --- a/net/decnet/dn_route.c +++ /dev/null @@ -1,1929 +0,0 @@ -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Functions (Endnode and Router) - * - * Authors: Steve Whitehouse <SteveW@ACM.org> - * Eduardo Marcelo Serrat <emserrat@geocities.com> - * - * Changes: - * Steve Whitehouse : Fixes to allow "intra-ethernet" and - * "return-to-sender" bits on outgoing - * packets. - * Steve Whitehouse : Timeouts for cached routes. - * Steve Whitehouse : Use dst cache for input routes too. - * Steve Whitehouse : Fixed error values in dn_send_skb. - * Steve Whitehouse : Rework routing functions to better fit - * DECnet routing design - * Alexey Kuznetsov : New SMP locking - * Steve Whitehouse : More SMP locking changes & dn_cache_dump() - * Steve Whitehouse : Prerouting NF hook, now really is prerouting. - * Fixed possible skb leak in rtnetlink funcs. - * Steve Whitehouse : Dave Miller's dynamic hash table sizing and - * Alexey Kuznetsov's finer grained locking - * from ipv4/route.c. - * Steve Whitehouse : Routing is now starting to look like a - * sensible set of code now, mainly due to - * my copying the IPv4 routing code. The - * hooks here are modified and will continue - * to evolve for a while. - * Steve Whitehouse : Real SMP at last :-) Also new netfilter - * stuff. Look out raw sockets your days - * are numbered! - * Steve Whitehouse : Added return-to-sender functions. Added - * backlog congestion level return codes. - * Steve Whitehouse : Fixed bug where routes were set up with - * no ref count on net devices. - * Steve Whitehouse : RCU for the route cache - * Steve Whitehouse : Preparations for the flow cache - * Steve Whitehouse : Prepare for nonlinear skbs - */ - -/****************************************************************************** - (c) 1995-1998 E.M. Serrat emserrat@geocities.com - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. -*******************************************************************************/ - -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/socket.h> -#include <linux/in.h> -#include <linux/kernel.h> -#include <linux/sockios.h> -#include <linux/net.h> -#include <linux/netdevice.h> -#include <linux/inet.h> -#include <linux/route.h> -#include <linux/in_route.h> -#include <linux/slab.h> -#include <net/sock.h> -#include <linux/mm.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/init.h> -#include <linux/rtnetlink.h> -#include <linux/string.h> -#include <linux/netfilter_decnet.h> -#include <linux/rcupdate.h> -#include <linux/times.h> -#include <linux/export.h> -#include <asm/errno.h> -#include <net/net_namespace.h> -#include <net/netlink.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/flow.h> -#include <net/fib_rules.h> -#include <net/dn.h> -#include <net/dn_dev.h> -#include <net/dn_nsp.h> -#include <net/dn_route.h> -#include <net/dn_neigh.h> -#include <net/dn_fib.h> - -struct dn_rt_hash_bucket -{ - struct dn_route __rcu *chain; - spinlock_t lock; -}; - -extern struct neigh_table dn_neigh_table; - - -static unsigned char dn_hiord_addr[6] = {0xAA,0x00,0x04,0x00,0x00,0x00}; - -static const int dn_rt_min_delay = 2 * HZ; -static const int dn_rt_max_delay = 10 * HZ; -static const int dn_rt_mtu_expires = 10 * 60 * HZ; - -static unsigned long dn_rt_deadline; - -static int dn_dst_gc(struct dst_ops *ops); -static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); -static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); -static unsigned int dn_dst_mtu(const struct dst_entry *dst); -static void dn_dst_destroy(struct dst_entry *); -static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); -static void dn_dst_link_failure(struct sk_buff *); -static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb , u32 mtu, - bool confirm_neigh); -static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb); -static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, - struct sk_buff *skb, - const void *daddr); -static int dn_route_input(struct sk_buff *); -static void dn_run_flush(struct timer_list *unused); - -static struct dn_rt_hash_bucket *dn_rt_hash_table; -static unsigned int dn_rt_hash_mask; - -static struct timer_list dn_route_timer; -static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush); -int decnet_dst_gc_interval = 2; - -static struct dst_ops dn_dst_ops = { - .family = PF_DECnet, - .gc_thresh = 128, - .gc = dn_dst_gc, - .check = dn_dst_check, - .default_advmss = dn_dst_default_advmss, - .mtu = dn_dst_mtu, - .cow_metrics = dst_cow_metrics_generic, - .destroy = dn_dst_destroy, - .ifdown = dn_dst_ifdown, - .negative_advice = dn_dst_negative_advice, - .link_failure = dn_dst_link_failure, - .update_pmtu = dn_dst_update_pmtu, - .redirect = dn_dst_redirect, - .neigh_lookup = dn_dst_neigh_lookup, -}; - -static void dn_dst_destroy(struct dst_entry *dst) -{ - struct dn_route *rt = (struct dn_route *) dst; - - if (rt->n) - neigh_release(rt->n); - dst_destroy_metrics_generic(dst); -} - -static void dn_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int how) -{ - if (how) { - struct dn_route *rt = (struct dn_route *) dst; - struct neighbour *n = rt->n; - - if (n && n->dev == dev) { - n->dev = dev_net(dev)->loopback_dev; - dev_hold(n->dev); - dev_put(dev); - } - } -} - -static __inline__ unsigned int dn_hash(__le16 src, __le16 dst) -{ - __u16 tmp = (__u16 __force)(src ^ dst); - tmp ^= (tmp >> 3); - tmp ^= (tmp >> 5); - tmp ^= (tmp >> 10); - return dn_rt_hash_mask & (unsigned int)tmp; -} - -static void dn_dst_check_expire(struct timer_list *unused) -{ - int i; - struct dn_route *rt; - struct dn_route __rcu **rtp; - unsigned long now = jiffies; - unsigned long expire = 120 * HZ; - - for (i = 0; i <= dn_rt_hash_mask; i++) { - rtp = &dn_rt_hash_table[i].chain; - - spin_lock(&dn_rt_hash_table[i].lock); - while ((rt = rcu_dereference_protected(*rtp, - lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { - if (atomic_read(&rt->dst.__refcnt) > 1 || - (now - rt->dst.lastuse) < expire) { - rtp = &rt->dn_next; - continue; - } - *rtp = rt->dn_next; - rt->dn_next = NULL; - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - } - spin_unlock(&dn_rt_hash_table[i].lock); - - if ((jiffies - now) > 0) - break; - } - - mod_timer(&dn_route_timer, now + decnet_dst_gc_interval * HZ); -} - -static int dn_dst_gc(struct dst_ops *ops) -{ - struct dn_route *rt; - struct dn_route __rcu **rtp; - int i; - unsigned long now = jiffies; - unsigned long expire = 10 * HZ; - - for (i = 0; i <= dn_rt_hash_mask; i++) { - - spin_lock_bh(&dn_rt_hash_table[i].lock); - rtp = &dn_rt_hash_table[i].chain; - - while ((rt = rcu_dereference_protected(*rtp, - lockdep_is_held(&dn_rt_hash_table[i].lock))) != NULL) { - if (atomic_read(&rt->dst.__refcnt) > 1 || - (now - rt->dst.lastuse) < expire) { - rtp = &rt->dn_next; - continue; - } - *rtp = rt->dn_next; - rt->dn_next = NULL; - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - break; - } - spin_unlock_bh(&dn_rt_hash_table[i].lock); - } - - return 0; -} - -/* - * The decnet standards don't impose a particular minimum mtu, what they - * do insist on is that the routing layer accepts a datagram of at least - * 230 bytes long. Here we have to subtract the routing header length from - * 230 to get the minimum acceptable mtu. If there is no neighbour, then we - * assume the worst and use a long header size. - * - * We update both the mtu and the advertised mss (i.e. the segment size we - * advertise to the other end). - */ -static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu, - bool confirm_neigh) -{ - struct dn_route *rt = (struct dn_route *) dst; - struct neighbour *n = rt->n; - u32 min_mtu = 230; - struct dn_dev *dn; - - dn = n ? rcu_dereference_raw(n->dev->dn_ptr) : NULL; - - if (dn && dn->use_long == 0) - min_mtu -= 6; - else - min_mtu -= 21; - - if (dst_metric(dst, RTAX_MTU) > mtu && mtu >= min_mtu) { - if (!(dst_metric_locked(dst, RTAX_MTU))) { - dst_metric_set(dst, RTAX_MTU, mtu); - dst_set_expires(dst, dn_rt_mtu_expires); - } - if (!(dst_metric_locked(dst, RTAX_ADVMSS))) { - u32 mss = mtu - DN_MAX_NSP_DATA_HEADER; - u32 existing_mss = dst_metric_raw(dst, RTAX_ADVMSS); - if (!existing_mss || existing_mss > mss) - dst_metric_set(dst, RTAX_ADVMSS, mss); - } - } -} - -static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb) -{ -} - -/* - * When a route has been marked obsolete. (e.g. routing cache flush) - */ -static struct dst_entry *dn_dst_check(struct dst_entry *dst, __u32 cookie) -{ - return NULL; -} - -static struct dst_entry *dn_dst_negative_advice(struct dst_entry *dst) -{ - dst_release(dst); - return NULL; -} - -static void dn_dst_link_failure(struct sk_buff *skb) -{ -} - -static inline int compare_keys(struct flowidn *fl1, struct flowidn *fl2) -{ - return ((fl1->daddr ^ fl2->daddr) | - (fl1->saddr ^ fl2->saddr) | - (fl1->flowidn_mark ^ fl2->flowidn_mark) | - (fl1->flowidn_scope ^ fl2->flowidn_scope) | - (fl1->flowidn_oif ^ fl2->flowidn_oif) | - (fl1->flowidn_iif ^ fl2->flowidn_iif)) == 0; -} - -static int dn_insert_route(struct dn_route *rt, unsigned int hash, struct dn_route **rp) -{ - struct dn_route *rth; - struct dn_route __rcu **rthp; - unsigned long now = jiffies; - - rthp = &dn_rt_hash_table[hash].chain; - - spin_lock_bh(&dn_rt_hash_table[hash].lock); - while ((rth = rcu_dereference_protected(*rthp, - lockdep_is_held(&dn_rt_hash_table[hash].lock))) != NULL) { - if (compare_keys(&rth->fld, &rt->fld)) { - /* Put it first */ - *rthp = rth->dn_next; - rcu_assign_pointer(rth->dn_next, - dn_rt_hash_table[hash].chain); - rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth); - - dst_hold_and_use(&rth->dst, now); - spin_unlock_bh(&dn_rt_hash_table[hash].lock); - - dst_release_immediate(&rt->dst); - *rp = rth; - return 0; - } - rthp = &rth->dn_next; - } - - rcu_assign_pointer(rt->dn_next, dn_rt_hash_table[hash].chain); - rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt); - - dst_hold_and_use(&rt->dst, now); - spin_unlock_bh(&dn_rt_hash_table[hash].lock); - *rp = rt; - return 0; -} - -static void dn_run_flush(struct timer_list *unused) -{ - int i; - struct dn_route *rt, *next; - - for (i = 0; i < dn_rt_hash_mask; i++) { - spin_lock_bh(&dn_rt_hash_table[i].lock); - - if ((rt = xchg((struct dn_route **)&dn_rt_hash_table[i].chain, NULL)) == NULL) - goto nothing_to_declare; - - for(; rt; rt = next) { - next = rcu_dereference_raw(rt->dn_next); - RCU_INIT_POINTER(rt->dn_next, NULL); - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - } - -nothing_to_declare: - spin_unlock_bh(&dn_rt_hash_table[i].lock); - } -} - -static DEFINE_SPINLOCK(dn_rt_flush_lock); - -void dn_rt_cache_flush(int delay) -{ - unsigned long now = jiffies; - int user_mode = !in_interrupt(); - - if (delay < 0) - delay = dn_rt_min_delay; - - spin_lock_bh(&dn_rt_flush_lock); - - if (del_timer(&dn_rt_flush_timer) && delay > 0 && dn_rt_deadline) { - long tmo = (long)(dn_rt_deadline - now); - - if (user_mode && tmo < dn_rt_max_delay - dn_rt_min_delay) - tmo = 0; - - if (delay > tmo) - delay = tmo; - } - - if (delay <= 0) { - spin_unlock_bh(&dn_rt_flush_lock); - dn_run_flush(NULL); - return; - } - - if (dn_rt_deadline == 0) - dn_rt_deadline = now + dn_rt_max_delay; - - dn_rt_flush_timer.expires = now + delay; - add_timer(&dn_rt_flush_timer); - spin_unlock_bh(&dn_rt_flush_lock); -} - -/** - * dn_return_short - Return a short packet to its sender - * @skb: The packet to return - * - */ -static int dn_return_short(struct sk_buff *skb) -{ - struct dn_skb_cb *cb; - unsigned char *ptr; - __le16 *src; - __le16 *dst; - - /* Add back headers */ - skb_push(skb, skb->data - skb_network_header(skb)); - - if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL) - return NET_RX_DROP; - - cb = DN_SKB_CB(skb); - /* Skip packet length and point to flags */ - ptr = skb->data + 2; - *ptr++ = (cb->rt_flags & ~DN_RT_F_RQR) | DN_RT_F_RTS; - - dst = (__le16 *)ptr; - ptr += 2; - src = (__le16 *)ptr; - ptr += 2; - *ptr = 0; /* Zero hop count */ - - swap(*src, *dst); - - skb->pkt_type = PACKET_OUTGOING; - dn_rt_finish_output(skb, NULL, NULL); - return NET_RX_SUCCESS; -} - -/** - * dn_return_long - Return a long packet to its sender - * @skb: The long format packet to return - * - */ -static int dn_return_long(struct sk_buff *skb) -{ - struct dn_skb_cb *cb; - unsigned char *ptr; - unsigned char *src_addr, *dst_addr; - unsigned char tmp[ETH_ALEN]; - - /* Add back all headers */ - skb_push(skb, skb->data - skb_network_header(skb)); - - if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL) - return NET_RX_DROP; - - cb = DN_SKB_CB(skb); - /* Ignore packet length and point to flags */ - ptr = skb->data + 2; - - /* Skip padding */ - if (*ptr & DN_RT_F_PF) { - char padlen = (*ptr & ~DN_RT_F_PF); - ptr += padlen; - } - - *ptr++ = (cb->rt_flags & ~DN_RT_F_RQR) | DN_RT_F_RTS; - ptr += 2; - dst_addr = ptr; - ptr += 8; - src_addr = ptr; - ptr += 6; - *ptr = 0; /* Zero hop count */ - - /* Swap source and destination */ - memcpy(tmp, src_addr, ETH_ALEN); - memcpy(src_addr, dst_addr, ETH_ALEN); - memcpy(dst_addr, tmp, ETH_ALEN); - - skb->pkt_type = PACKET_OUTGOING; - dn_rt_finish_output(skb, dst_addr, src_addr); - return NET_RX_SUCCESS; -} - -/** - * dn_route_rx_packet - Try and find a route for an incoming packet - * @skb: The packet to find a route for - * - * Returns: result of input function if route is found, error code otherwise - */ -static int dn_route_rx_packet(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dn_skb_cb *cb; - int err; - - if ((err = dn_route_input(skb)) == 0) - return dst_input(skb); - - cb = DN_SKB_CB(skb); - if (decnet_debug_level & 4) { - char *devname = skb->dev ? skb->dev->name : "???"; - - printk(KERN_DEBUG - "DECnet: dn_route_rx_packet: rt_flags=0x%02x dev=%s len=%d src=0x%04hx dst=0x%04hx err=%d type=%d\n", - (int)cb->rt_flags, devname, skb->len, - le16_to_cpu(cb->src), le16_to_cpu(cb->dst), - err, skb->pkt_type); - } - - if ((skb->pkt_type == PACKET_HOST) && (cb->rt_flags & DN_RT_F_RQR)) { - switch (cb->rt_flags & DN_RT_PKT_MSK) { - case DN_RT_PKT_SHORT: - return dn_return_short(skb); - case DN_RT_PKT_LONG: - return dn_return_long(skb); - } - } - - kfree_skb(skb); - return NET_RX_DROP; -} - -static int dn_route_rx_long(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned char *ptr = skb->data; - - if (!pskb_may_pull(skb, 21)) /* 20 for long header, 1 for shortest nsp */ - goto drop_it; - - skb_pull(skb, 20); - skb_reset_transport_header(skb); - - /* Destination info */ - ptr += 2; - cb->dst = dn_eth2dn(ptr); - if (memcmp(ptr, dn_hiord_addr, 4) != 0) - goto drop_it; - ptr += 6; - - - /* Source info */ - ptr += 2; - cb->src = dn_eth2dn(ptr); - if (memcmp(ptr, dn_hiord_addr, 4) != 0) - goto drop_it; - ptr += 6; - /* Other junk */ - ptr++; - cb->hops = *ptr++; /* Visit Count */ - - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_rx_packet); - -drop_it: - kfree_skb(skb); - return NET_RX_DROP; -} - - - -static int dn_route_rx_short(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned char *ptr = skb->data; - - if (!pskb_may_pull(skb, 6)) /* 5 for short header + 1 for shortest nsp */ - goto drop_it; - - skb_pull(skb, 5); - skb_reset_transport_header(skb); - - cb->dst = *(__le16 *)ptr; - ptr += 2; - cb->src = *(__le16 *)ptr; - ptr += 2; - cb->hops = *ptr & 0x3f; - - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_rx_packet); - -drop_it: - kfree_skb(skb); - return NET_RX_DROP; -} - -static int dn_route_discard(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - /* - * I know we drop the packet here, but thats considered success in - * this case - */ - kfree_skb(skb); - return NET_RX_SUCCESS; -} - -static int dn_route_ptp_hello(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - dn_dev_hello(skb); - dn_neigh_pointopoint_hello(skb); - return NET_RX_SUCCESS; -} - -int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) -{ - struct dn_skb_cb *cb; - unsigned char flags = 0; - __u16 len = le16_to_cpu(*(__le16 *)skb->data); - struct dn_dev *dn = rcu_dereference(dev->dn_ptr); - unsigned char padlen = 0; - - if (!net_eq(dev_net(dev), &init_net)) - goto dump_it; - - if (dn == NULL) - goto dump_it; - - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) - goto out; - - if (!pskb_may_pull(skb, 3)) - goto dump_it; - - skb_pull(skb, 2); - - if (len > skb->len) - goto dump_it; - - skb_trim(skb, len); - - flags = *skb->data; - - cb = DN_SKB_CB(skb); - cb->stamp = jiffies; - cb->iif = dev->ifindex; - - /* - * If we have padding, remove it. - */ - if (flags & DN_RT_F_PF) { - padlen = flags & ~DN_RT_F_PF; - if (!pskb_may_pull(skb, padlen + 1)) - goto dump_it; - skb_pull(skb, padlen); - flags = *skb->data; - } - - skb_reset_network_header(skb); - - /* - * Weed out future version DECnet - */ - if (flags & DN_RT_F_VER) - goto dump_it; - - cb->rt_flags = flags; - - if (decnet_debug_level & 1) - printk(KERN_DEBUG - "dn_route_rcv: got 0x%02x from %s [%d %d %d]\n", - (int)flags, (dev) ? dev->name : "???", len, skb->len, - padlen); - - if (flags & DN_RT_PKT_CNTL) { - if (unlikely(skb_linearize(skb))) - goto dump_it; - - switch (flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_INIT: - dn_dev_init_pkt(skb); - break; - case DN_RT_PKT_VERI: - dn_dev_veri_pkt(skb); - break; - } - - if (dn->parms.state != DN_DEV_S_RU) - goto dump_it; - - switch (flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_HELO: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_ptp_hello); - - case DN_RT_PKT_L1RT: - case DN_RT_PKT_L2RT: - return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE, - &init_net, NULL, skb, skb->dev, NULL, - dn_route_discard); - case DN_RT_PKT_ERTH: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - &init_net, NULL, skb, skb->dev, NULL, - dn_neigh_router_hello); - - case DN_RT_PKT_EEDH: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - &init_net, NULL, skb, skb->dev, NULL, - dn_neigh_endnode_hello); - } - } else { - if (dn->parms.state != DN_DEV_S_RU) - goto dump_it; - - skb_pull(skb, 1); /* Pull flags */ - - switch (flags & DN_RT_PKT_MSK) { - case DN_RT_PKT_LONG: - return dn_route_rx_long(skb); - case DN_RT_PKT_SHORT: - return dn_route_rx_short(skb); - } - } - -dump_it: - kfree_skb(skb); -out: - return NET_RX_DROP; -} - -static int dn_output(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - struct dn_route *rt = (struct dn_route *)dst; - struct net_device *dev = dst->dev; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - int err = -EINVAL; - - if (rt->n == NULL) - goto error; - - skb->dev = dev; - - cb->src = rt->rt_saddr; - cb->dst = rt->rt_daddr; - - /* - * Always set the Intra-Ethernet bit on all outgoing packets - * originated on this node. Only valid flag from upper layers - * is return-to-sender-requested. Set hop count to 0 too. - */ - cb->rt_flags &= ~DN_RT_F_RQR; - cb->rt_flags |= DN_RT_F_IE; - cb->hops = 0; - - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, - &init_net, sk, skb, NULL, dev, - dn_to_neigh_output); - -error: - net_dbg_ratelimited("dn_output: This should not happen\n"); - - kfree_skb(skb); - - return err; -} - -static int dn_forward(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct dst_entry *dst = skb_dst(skb); - struct dn_dev *dn_db = rcu_dereference(dst->dev->dn_ptr); - struct dn_route *rt; - int header_len; - struct net_device *dev = skb->dev; - - if (skb->pkt_type != PACKET_HOST) - goto drop; - - /* Ensure that we have enough space for headers */ - rt = (struct dn_route *)skb_dst(skb); - header_len = dn_db->use_long ? 21 : 6; - if (skb_cow(skb, LL_RESERVED_SPACE(rt->dst.dev)+header_len)) - goto drop; - - /* - * Hop count exceeded. - */ - if (++cb->hops > 30) - goto drop; - - skb->dev = rt->dst.dev; - - /* - * If packet goes out same interface it came in on, then set - * the Intra-Ethernet bit. This has no effect for short - * packets, so we don't need to test for them here. - */ - cb->rt_flags &= ~DN_RT_F_IE; - if (rt->rt_flags & RTCF_DOREDIRECT) - cb->rt_flags |= DN_RT_F_IE; - - return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, - &init_net, NULL, skb, dev, skb->dev, - dn_to_neigh_output); - -drop: - kfree_skb(skb); - return NET_RX_DROP; -} - -/* - * Used to catch bugs. This should never normally get - * called. - */ -static int dn_rt_bug_out(struct net *net, struct sock *sk, struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - net_dbg_ratelimited("dn_rt_bug: skb from:%04x to:%04x\n", - le16_to_cpu(cb->src), le16_to_cpu(cb->dst)); - - kfree_skb(skb); - - return NET_RX_DROP; -} - -static int dn_rt_bug(struct sk_buff *skb) -{ - struct dn_skb_cb *cb = DN_SKB_CB(skb); - - net_dbg_ratelimited("dn_rt_bug: skb from:%04x to:%04x\n", - le16_to_cpu(cb->src), le16_to_cpu(cb->dst)); - - kfree_skb(skb); - - return NET_RX_DROP; -} - -static unsigned int dn_dst_default_advmss(const struct dst_entry *dst) -{ - return dn_mss_from_pmtu(dst->dev, dst_mtu(dst)); -} - -static unsigned int dn_dst_mtu(const struct dst_entry *dst) -{ - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); - - return mtu ? : dst->dev->mtu; -} - -static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, - struct sk_buff *skb, - const void *daddr) -{ - return __neigh_lookup_errno(&dn_neigh_table, daddr, dst->dev); -} - -static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) -{ - struct dn_fib_info *fi = res->fi; - struct net_device *dev = rt->dst.dev; - unsigned int mss_metric; - struct neighbour *n; - - if (fi) { - if (DN_FIB_RES_GW(*res) && - DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) - rt->rt_gateway = DN_FIB_RES_GW(*res); - dst_init_metrics(&rt->dst, fi->fib_metrics, true); - } - rt->rt_type = res->type; - - if (dev != NULL && rt->n == NULL) { - n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev); - if (IS_ERR(n)) - return PTR_ERR(n); - rt->n = n; - } - - if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) - dst_metric_set(&rt->dst, RTAX_MTU, rt->dst.dev->mtu); - mss_metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS); - if (mss_metric) { - unsigned int mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst)); - if (mss_metric > mss) - dst_metric_set(&rt->dst, RTAX_ADVMSS, mss); - } - return 0; -} - -static inline int dn_match_addr(__le16 addr1, __le16 addr2) -{ - __u16 tmp = le16_to_cpu(addr1) ^ le16_to_cpu(addr2); - int match = 16; - while(tmp) { - tmp >>= 1; - match--; - } - return match; -} - -static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int scope) -{ - __le16 saddr = 0; - struct dn_dev *dn_db; - struct dn_ifaddr *ifa; - int best_match = 0; - int ret; - - rcu_read_lock(); - dn_db = rcu_dereference(dev->dn_ptr); - for (ifa = rcu_dereference(dn_db->ifa_list); - ifa != NULL; - ifa = rcu_dereference(ifa->ifa_next)) { - if (ifa->ifa_scope > scope) - continue; - if (!daddr) { - saddr = ifa->ifa_local; - break; - } - ret = dn_match_addr(daddr, ifa->ifa_local); - if (ret > best_match) - saddr = ifa->ifa_local; - if (best_match == 0) - saddr = ifa->ifa_local; - } - rcu_read_unlock(); - - return saddr; -} - -static inline __le16 __dn_fib_res_prefsrc(struct dn_fib_res *res) -{ - return dnet_select_source(DN_FIB_RES_DEV(*res), DN_FIB_RES_GW(*res), res->scope); -} - -static inline __le16 dn_fib_rules_map_destination(__le16 daddr, struct dn_fib_res *res) -{ - __le16 mask = dnet_make_mask(res->prefixlen); - return (daddr&~mask)|res->fi->fib_nh->nh_gw; -} - -static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *oldflp, int try_hard) -{ - struct flowidn fld = { - .daddr = oldflp->daddr, - .saddr = oldflp->saddr, - .flowidn_scope = RT_SCOPE_UNIVERSE, - .flowidn_mark = oldflp->flowidn_mark, - .flowidn_iif = LOOPBACK_IFINDEX, - .flowidn_oif = oldflp->flowidn_oif, - }; - struct dn_route *rt = NULL; - struct net_device *dev_out = NULL, *dev; - struct neighbour *neigh = NULL; - unsigned int hash; - unsigned int flags = 0; - struct dn_fib_res res = { .fi = NULL, .type = RTN_UNICAST }; - int err; - int free_res = 0; - __le16 gateway = 0; - - if (decnet_debug_level & 16) - printk(KERN_DEBUG - "dn_route_output_slow: dst=%04x src=%04x mark=%d" - " iif=%d oif=%d\n", le16_to_cpu(oldflp->daddr), - le16_to_cpu(oldflp->saddr), - oldflp->flowidn_mark, LOOPBACK_IFINDEX, - oldflp->flowidn_oif); - - /* If we have an output interface, verify its a DECnet device */ - if (oldflp->flowidn_oif) { - dev_out = dev_get_by_index(&init_net, oldflp->flowidn_oif); - err = -ENODEV; - if (dev_out && dev_out->dn_ptr == NULL) { - dev_put(dev_out); - dev_out = NULL; - } - if (dev_out == NULL) - goto out; - } - - /* If we have a source address, verify that its a local address */ - if (oldflp->saddr) { - err = -EADDRNOTAVAIL; - - if (dev_out) { - if (dn_dev_islocal(dev_out, oldflp->saddr)) - goto source_ok; - dev_put(dev_out); - goto out; - } - rcu_read_lock(); - for_each_netdev_rcu(&init_net, dev) { - if (!dev->dn_ptr) - continue; - if (!dn_dev_islocal(dev, oldflp->saddr)) - continue; - if ((dev->flags & IFF_LOOPBACK) && - oldflp->daddr && - !dn_dev_islocal(dev, oldflp->daddr)) - continue; - - dev_out = dev; - break; - } - rcu_read_unlock(); - if (dev_out == NULL) - goto out; - dev_hold(dev_out); -source_ok: - ; - } - - /* No destination? Assume its local */ - if (!fld.daddr) { - fld.daddr = fld.saddr; - - if (dev_out) - dev_put(dev_out); - err = -EINVAL; - dev_out = init_net.loopback_dev; - if (!dev_out->dn_ptr) - goto out; - err = -EADDRNOTAVAIL; - dev_hold(dev_out); - if (!fld.daddr) { - fld.daddr = - fld.saddr = dnet_select_source(dev_out, 0, - RT_SCOPE_HOST); - if (!fld.daddr) - goto out; - } - fld.flowidn_oif = LOOPBACK_IFINDEX; - res.type = RTN_LOCAL; - goto make_route; - } - - if (decnet_debug_level & 16) - printk(KERN_DEBUG - "dn_route_output_slow: initial checks complete." - " dst=%04x src=%04x oif=%d try_hard=%d\n", - le16_to_cpu(fld.daddr), le16_to_cpu(fld.saddr), - fld.flowidn_oif, try_hard); - - /* - * N.B. If the kernel is compiled without router support then - * dn_fib_lookup() will evaluate to non-zero so this if () block - * will always be executed. - */ - err = -ESRCH; - if (try_hard || (err = dn_fib_lookup(&fld, &res)) != 0) { - struct dn_dev *dn_db; - if (err != -ESRCH) - goto out; - /* - * Here the fallback is basically the standard algorithm for - * routing in endnodes which is described in the DECnet routing - * docs - * - * If we are not trying hard, look in neighbour cache. - * The result is tested to ensure that if a specific output - * device/source address was requested, then we honour that - * here - */ - if (!try_hard) { - neigh = neigh_lookup_nodev(&dn_neigh_table, &init_net, &fld.daddr); - if (neigh) { - if ((oldflp->flowidn_oif && - (neigh->dev->ifindex != oldflp->flowidn_oif)) || - (oldflp->saddr && - (!dn_dev_islocal(neigh->dev, - oldflp->saddr)))) { - neigh_release(neigh); - neigh = NULL; - } else { - if (dev_out) - dev_put(dev_out); - if (dn_dev_islocal(neigh->dev, fld.daddr)) { - dev_out = init_net.loopback_dev; - res.type = RTN_LOCAL; - } else { - dev_out = neigh->dev; - } - dev_hold(dev_out); - goto select_source; - } - } - } - - /* Not there? Perhaps its a local address */ - if (dev_out == NULL) - dev_out = dn_dev_get_default(); - err = -ENODEV; - if (dev_out == NULL) - goto out; - dn_db = rcu_dereference_raw(dev_out->dn_ptr); - if (!dn_db) - goto e_inval; - /* Possible improvement - check all devices for local addr */ - if (dn_dev_islocal(dev_out, fld.daddr)) { - dev_put(dev_out); - dev_out = init_net.loopback_dev; - dev_hold(dev_out); - res.type = RTN_LOCAL; - goto select_source; - } - /* Not local either.... try sending it to the default router */ - neigh = neigh_clone(dn_db->router); - BUG_ON(neigh && neigh->dev != dev_out); - - /* Ok then, we assume its directly connected and move on */ -select_source: - if (neigh) - gateway = ((struct dn_neigh *)neigh)->addr; - if (gateway == 0) - gateway = fld.daddr; - if (fld.saddr == 0) { - fld.saddr = dnet_select_source(dev_out, gateway, - res.type == RTN_LOCAL ? - RT_SCOPE_HOST : - RT_SCOPE_LINK); - if (fld.saddr == 0 && res.type != RTN_LOCAL) - goto e_addr; - } - fld.flowidn_oif = dev_out->ifindex; - goto make_route; - } - free_res = 1; - - if (res.type == RTN_NAT) - goto e_inval; - - if (res.type == RTN_LOCAL) { - if (!fld.saddr) - fld.saddr = fld.daddr; - if (dev_out) - dev_put(dev_out); - dev_out = init_net.loopback_dev; - dev_hold(dev_out); - if (!dev_out->dn_ptr) - goto e_inval; - fld.flowidn_oif = dev_out->ifindex; - if (res.fi) - dn_fib_info_put(res.fi); - res.fi = NULL; - goto make_route; - } - - if (res.fi->fib_nhs > 1 && fld.flowidn_oif == 0) - dn_fib_select_multipath(&fld, &res); - - /* - * We could add some logic to deal with default routes here and - * get rid of some of the special casing above. - */ - - if (!fld.saddr) - fld.saddr = DN_FIB_RES_PREFSRC(res); - - if (dev_out) - dev_put(dev_out); - dev_out = DN_FIB_RES_DEV(res); - dev_hold(dev_out); - fld.flowidn_oif = dev_out->ifindex; - gateway = DN_FIB_RES_GW(res); - -make_route: - if (dev_out->flags & IFF_LOOPBACK) - flags |= RTCF_LOCAL; - - rt = dst_alloc(&dn_dst_ops, dev_out, 0, DST_OBSOLETE_NONE, DST_HOST); - if (rt == NULL) - goto e_nobufs; - - rt->dn_next = NULL; - memset(&rt->fld, 0, sizeof(rt->fld)); - rt->fld.saddr = oldflp->saddr; - rt->fld.daddr = oldflp->daddr; - rt->fld.flowidn_oif = oldflp->flowidn_oif; - rt->fld.flowidn_iif = 0; - rt->fld.flowidn_mark = oldflp->flowidn_mark; - - rt->rt_saddr = fld.saddr; - rt->rt_daddr = fld.daddr; - rt->rt_gateway = gateway ? gateway : fld.daddr; - rt->rt_local_src = fld.saddr; - - rt->rt_dst_map = fld.daddr; - rt->rt_src_map = fld.saddr; - - rt->n = neigh; - neigh = NULL; - - rt->dst.lastuse = jiffies; - rt->dst.output = dn_output; - rt->dst.input = dn_rt_bug; - rt->rt_flags = flags; - if (flags & RTCF_LOCAL) - rt->dst.input = dn_nsp_rx; - - err = dn_rt_set_next_hop(rt, &res); - if (err) - goto e_neighbour; - - hash = dn_hash(rt->fld.saddr, rt->fld.daddr); - /* dn_insert_route() increments dst->__refcnt */ - dn_insert_route(rt, hash, (struct dn_route **)pprt); - -done: - if (neigh) - neigh_release(neigh); - if (free_res) - dn_fib_res_put(&res); - if (dev_out) - dev_put(dev_out); -out: - return err; - -e_addr: - err = -EADDRNOTAVAIL; - goto done; -e_inval: - err = -EINVAL; - goto done; -e_nobufs: - err = -ENOBUFS; - goto done; -e_neighbour: - dst_release_immediate(&rt->dst); - goto e_nobufs; -} - - -/* - * N.B. The flags may be moved into the flowi at some future stage. - */ -static int __dn_route_output_key(struct dst_entry **pprt, const struct flowidn *flp, int flags) -{ - unsigned int hash = dn_hash(flp->saddr, flp->daddr); - struct dn_route *rt = NULL; - - if (!(flags & MSG_TRYHARD)) { - rcu_read_lock_bh(); - for (rt = rcu_dereference_bh(dn_rt_hash_table[hash].chain); rt; - rt = rcu_dereference_bh(rt->dn_next)) { - if ((flp->daddr == rt->fld.daddr) && - (flp->saddr == rt->fld.saddr) && - (flp->flowidn_mark == rt->fld.flowidn_mark) && - dn_is_output_route(rt) && - (rt->fld.flowidn_oif == flp->flowidn_oif)) { - dst_hold_and_use(&rt->dst, jiffies); - rcu_read_unlock_bh(); - *pprt = &rt->dst; - return 0; - } - } - rcu_read_unlock_bh(); - } - - return dn_route_output_slow(pprt, flp, flags); -} - -static int dn_route_output_key(struct dst_entry **pprt, struct flowidn *flp, int flags) -{ - int err; - - err = __dn_route_output_key(pprt, flp, flags); - if (err == 0 && flp->flowidn_proto) { - *pprt = xfrm_lookup(&init_net, *pprt, - flowidn_to_flowi(flp), NULL, 0); - if (IS_ERR(*pprt)) { - err = PTR_ERR(*pprt); - *pprt = NULL; - } - } - return err; -} - -int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *fl, struct sock *sk, int flags) -{ - int err; - - err = __dn_route_output_key(pprt, fl, flags & MSG_TRYHARD); - if (err == 0 && fl->flowidn_proto) { - *pprt = xfrm_lookup(&init_net, *pprt, - flowidn_to_flowi(fl), sk, 0); - if (IS_ERR(*pprt)) { - err = PTR_ERR(*pprt); - *pprt = NULL; - } - } - return err; -} - -static int dn_route_input_slow(struct sk_buff *skb) -{ - struct dn_route *rt = NULL; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct net_device *in_dev = skb->dev; - struct net_device *out_dev = NULL; - struct dn_dev *dn_db; - struct neighbour *neigh = NULL; - unsigned int hash; - int flags = 0; - __le16 gateway = 0; - __le16 local_src = 0; - struct flowidn fld = { - .daddr = cb->dst, - .saddr = cb->src, - .flowidn_scope = RT_SCOPE_UNIVERSE, - .flowidn_mark = skb->mark, - .flowidn_iif = skb->dev->ifindex, - }; - struct dn_fib_res res = { .fi = NULL, .type = RTN_UNREACHABLE }; - int err = -EINVAL; - int free_res = 0; - - dev_hold(in_dev); - - if ((dn_db = rcu_dereference(in_dev->dn_ptr)) == NULL) - goto out; - - /* Zero source addresses are not allowed */ - if (fld.saddr == 0) - goto out; - - /* - * In this case we've just received a packet from a source - * outside ourselves pretending to come from us. We don't - * allow it any further to prevent routing loops, spoofing and - * other nasties. Loopback packets already have the dst attached - * so this only affects packets which have originated elsewhere. - */ - err = -ENOTUNIQ; - if (dn_dev_islocal(in_dev, cb->src)) - goto out; - - err = dn_fib_lookup(&fld, &res); - if (err) { - if (err != -ESRCH) - goto out; - /* - * Is the destination us ? - */ - if (!dn_dev_islocal(in_dev, cb->dst)) - goto e_inval; - - res.type = RTN_LOCAL; - } else { - __le16 src_map = fld.saddr; - free_res = 1; - - out_dev = DN_FIB_RES_DEV(res); - if (out_dev == NULL) { - net_crit_ratelimited("Bug in dn_route_input_slow() No output device\n"); - goto e_inval; - } - dev_hold(out_dev); - - if (res.r) - src_map = fld.saddr; /* no NAT support for now */ - - gateway = DN_FIB_RES_GW(res); - if (res.type == RTN_NAT) { - fld.daddr = dn_fib_rules_map_destination(fld.daddr, &res); - dn_fib_res_put(&res); - free_res = 0; - if (dn_fib_lookup(&fld, &res)) - goto e_inval; - free_res = 1; - if (res.type != RTN_UNICAST) - goto e_inval; - flags |= RTCF_DNAT; - gateway = fld.daddr; - } - fld.saddr = src_map; - } - - switch(res.type) { - case RTN_UNICAST: - /* - * Forwarding check here, we only check for forwarding - * being turned off, if you want to only forward intra - * area, its up to you to set the routing tables up - * correctly. - */ - if (dn_db->parms.forwarding == 0) - goto e_inval; - - if (res.fi->fib_nhs > 1 && fld.flowidn_oif == 0) - dn_fib_select_multipath(&fld, &res); - - /* - * Check for out_dev == in_dev. We use the RTCF_DOREDIRECT - * flag as a hint to set the intra-ethernet bit when - * forwarding. If we've got NAT in operation, we don't do - * this optimisation. - */ - if (out_dev == in_dev && !(flags & RTCF_NAT)) - flags |= RTCF_DOREDIRECT; - - local_src = DN_FIB_RES_PREFSRC(res); - - case RTN_BLACKHOLE: - case RTN_UNREACHABLE: - break; - case RTN_LOCAL: - flags |= RTCF_LOCAL; - fld.saddr = cb->dst; - fld.daddr = cb->src; - - /* Routing tables gave us a gateway */ - if (gateway) - goto make_route; - - /* Packet was intra-ethernet, so we know its on-link */ - if (cb->rt_flags & DN_RT_F_IE) { - gateway = cb->src; - goto make_route; - } - - /* Use the default router if there is one */ - neigh = neigh_clone(dn_db->router); - if (neigh) { - gateway = ((struct dn_neigh *)neigh)->addr; - goto make_route; - } - - /* Close eyes and pray */ - gateway = cb->src; - goto make_route; - default: - goto e_inval; - } - -make_route: - rt = dst_alloc(&dn_dst_ops, out_dev, 1, DST_OBSOLETE_NONE, DST_HOST); - if (rt == NULL) - goto e_nobufs; - - rt->dn_next = NULL; - memset(&rt->fld, 0, sizeof(rt->fld)); - rt->rt_saddr = fld.saddr; - rt->rt_daddr = fld.daddr; - rt->rt_gateway = fld.daddr; - if (gateway) - rt->rt_gateway = gateway; - rt->rt_local_src = local_src ? local_src : rt->rt_saddr; - - rt->rt_dst_map = fld.daddr; - rt->rt_src_map = fld.saddr; - - rt->fld.saddr = cb->src; - rt->fld.daddr = cb->dst; - rt->fld.flowidn_oif = 0; - rt->fld.flowidn_iif = in_dev->ifindex; - rt->fld.flowidn_mark = fld.flowidn_mark; - - rt->n = neigh; - rt->dst.lastuse = jiffies; - rt->dst.output = dn_rt_bug_out; - switch (res.type) { - case RTN_UNICAST: - rt->dst.input = dn_forward; - break; - case RTN_LOCAL: - rt->dst.output = dn_output; - rt->dst.input = dn_nsp_rx; - rt->dst.dev = in_dev; - flags |= RTCF_LOCAL; - break; - default: - case RTN_UNREACHABLE: - case RTN_BLACKHOLE: - rt->dst.input = dst_discard; - } - rt->rt_flags = flags; - - err = dn_rt_set_next_hop(rt, &res); - if (err) - goto e_neighbour; - - hash = dn_hash(rt->fld.saddr, rt->fld.daddr); - /* dn_insert_route() increments dst->__refcnt */ - dn_insert_route(rt, hash, &rt); - skb_dst_set(skb, &rt->dst); - -done: - if (neigh) - neigh_release(neigh); - if (free_res) - dn_fib_res_put(&res); - dev_put(in_dev); - if (out_dev) - dev_put(out_dev); -out: - return err; - -e_inval: - err = -EINVAL; - goto done; - -e_nobufs: - err = -ENOBUFS; - goto done; - -e_neighbour: - dst_release_immediate(&rt->dst); - goto done; -} - -static int dn_route_input(struct sk_buff *skb) -{ - struct dn_route *rt; - struct dn_skb_cb *cb = DN_SKB_CB(skb); - unsigned int hash = dn_hash(cb->src, cb->dst); - - if (skb_dst(skb)) - return 0; - - rcu_read_lock(); - for(rt = rcu_dereference(dn_rt_hash_table[hash].chain); rt != NULL; - rt = rcu_dereference(rt->dn_next)) { - if ((rt->fld.saddr == cb->src) && - (rt->fld.daddr == cb->dst) && - (rt->fld.flowidn_oif == 0) && - (rt->fld.flowidn_mark == skb->mark) && - (rt->fld.flowidn_iif == cb->iif)) { - dst_hold_and_use(&rt->dst, jiffies); - rcu_read_unlock(); - skb_dst_set(skb, (struct dst_entry *)rt); - return 0; - } - } - rcu_read_unlock(); - - return dn_route_input_slow(skb); -} - -static int dn_rt_fill_info(struct sk_buff *skb, u32 portid, u32 seq, - int event, int nowait, unsigned int flags) -{ - struct dn_route *rt = (struct dn_route *)skb_dst(skb); - struct rtmsg *r; - struct nlmsghdr *nlh; - long expires; - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags); - if (!nlh) - return -EMSGSIZE; - - r = nlmsg_data(nlh); - r->rtm_family = AF_DECnet; - r->rtm_dst_len = 16; - r->rtm_src_len = 0; - r->rtm_tos = 0; - r->rtm_table = RT_TABLE_MAIN; - r->rtm_type = rt->rt_type; - r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; - r->rtm_scope = RT_SCOPE_UNIVERSE; - r->rtm_protocol = RTPROT_UNSPEC; - - if (rt->rt_flags & RTCF_NOTIFY) - r->rtm_flags |= RTM_F_NOTIFY; - - if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN) < 0 || - nla_put_le16(skb, RTA_DST, rt->rt_daddr) < 0) - goto errout; - - if (rt->fld.saddr) { - r->rtm_src_len = 16; - if (nla_put_le16(skb, RTA_SRC, rt->fld.saddr) < 0) - goto errout; - } - if (rt->dst.dev && - nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex) < 0) - goto errout; - - /* - * Note to self - change this if input routes reverse direction when - * they deal only with inputs and not with replies like they do - * currently. - */ - if (nla_put_le16(skb, RTA_PREFSRC, rt->rt_local_src) < 0) - goto errout; - - if (rt->rt_daddr != rt->rt_gateway && - nla_put_le16(skb, RTA_GATEWAY, rt->rt_gateway) < 0) - goto errout; - - if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) - goto errout; - - expires = rt->dst.expires ? rt->dst.expires - jiffies : 0; - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, - rt->dst.error) < 0) - goto errout; - - if (dn_is_input_route(rt) && - nla_put_u32(skb, RTA_IIF, rt->fld.flowidn_iif) < 0) - goto errout; - - nlmsg_end(skb, nlh); - return 0; - -errout: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - -const struct nla_policy rtm_dn_policy[RTA_MAX + 1] = { - [RTA_DST] = { .type = NLA_U16 }, - [RTA_SRC] = { .type = NLA_U16 }, - [RTA_IIF] = { .type = NLA_U32 }, - [RTA_OIF] = { .type = NLA_U32 }, - [RTA_GATEWAY] = { .type = NLA_U16 }, - [RTA_PRIORITY] = { .type = NLA_U32 }, - [RTA_PREFSRC] = { .type = NLA_U16 }, - [RTA_METRICS] = { .type = NLA_NESTED }, - [RTA_MULTIPATH] = { .type = NLA_NESTED }, - [RTA_TABLE] = { .type = NLA_U32 }, - [RTA_MARK] = { .type = NLA_U32 }, -}; - -/* - * This is called by both endnodes and routers now. - */ -static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(in_skb->sk); - struct rtmsg *rtm = nlmsg_data(nlh); - struct dn_route *rt = NULL; - struct dn_skb_cb *cb; - int err; - struct sk_buff *skb; - struct flowidn fld; - struct nlattr *tb[RTA_MAX+1]; - - if (!net_eq(net, &init_net)) - return -EINVAL; - - err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_dn_policy, - extack); - if (err < 0) - return err; - - memset(&fld, 0, sizeof(fld)); - fld.flowidn_proto = DNPROTO_NSP; - - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb == NULL) - return -ENOBUFS; - skb_reset_mac_header(skb); - cb = DN_SKB_CB(skb); - - if (tb[RTA_SRC]) - fld.saddr = nla_get_le16(tb[RTA_SRC]); - - if (tb[RTA_DST]) - fld.daddr = nla_get_le16(tb[RTA_DST]); - - if (tb[RTA_IIF]) - fld.flowidn_iif = nla_get_u32(tb[RTA_IIF]); - - if (fld.flowidn_iif) { - struct net_device *dev; - dev = __dev_get_by_index(&init_net, fld.flowidn_iif); - if (!dev || !dev->dn_ptr) { - kfree_skb(skb); - return -ENODEV; - } - skb->protocol = htons(ETH_P_DNA_RT); - skb->dev = dev; - cb->src = fld.saddr; - cb->dst = fld.daddr; - local_bh_disable(); - err = dn_route_input(skb); - local_bh_enable(); - memset(cb, 0, sizeof(struct dn_skb_cb)); - rt = (struct dn_route *)skb_dst(skb); - if (!err && -rt->dst.error) - err = rt->dst.error; - } else { - if (tb[RTA_OIF]) - fld.flowidn_oif = nla_get_u32(tb[RTA_OIF]); - - err = dn_route_output_key((struct dst_entry **)&rt, &fld, 0); - } - - skb->dev = NULL; - if (err) - goto out_free; - skb_dst_set(skb, &rt->dst); - if (rtm->rtm_flags & RTM_F_NOTIFY) - rt->rt_flags |= RTCF_NOTIFY; - - err = dn_rt_fill_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); - if (err < 0) { - err = -EMSGSIZE; - goto out_free; - } - - return rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).portid); - -out_free: - kfree_skb(skb); - return err; -} - -/* - * For routers, this is called from dn_fib_dump, but for endnodes its - * called directly from the rtnetlink dispatch table. - */ -int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - struct dn_route *rt; - int h, s_h; - int idx, s_idx; - struct rtmsg *rtm; - - if (!net_eq(net, &init_net)) - return 0; - - if (nlmsg_len(cb->nlh) < sizeof(struct rtmsg)) - return -EINVAL; - - rtm = nlmsg_data(cb->nlh); - if (!(rtm->rtm_flags & RTM_F_CLONED)) - return 0; - - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - for(h = 0; h <= dn_rt_hash_mask; h++) { - if (h < s_h) - continue; - if (h > s_h) - s_idx = 0; - rcu_read_lock_bh(); - for(rt = rcu_dereference_bh(dn_rt_hash_table[h].chain), idx = 0; - rt; - rt = rcu_dereference_bh(rt->dn_next), idx++) { - if (idx < s_idx) - continue; - skb_dst_set(skb, dst_clone(&rt->dst)); - if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWROUTE, - 1, NLM_F_MULTI) < 0) { - skb_dst_drop(skb); - rcu_read_unlock_bh(); - goto done; - } - skb_dst_drop(skb); - } - rcu_read_unlock_bh(); - } - -done: - cb->args[0] = h; - cb->args[1] = idx; - return skb->len; -} - -#ifdef CONFIG_PROC_FS -struct dn_rt_cache_iter_state { - int bucket; -}; - -static struct dn_route *dn_rt_cache_get_first(struct seq_file *seq) -{ - struct dn_route *rt = NULL; - struct dn_rt_cache_iter_state *s = seq->private; - - for(s->bucket = dn_rt_hash_mask; s->bucket >= 0; --s->bucket) { - rcu_read_lock_bh(); - rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); - if (rt) - break; - rcu_read_unlock_bh(); - } - return rt; -} - -static struct dn_route *dn_rt_cache_get_next(struct seq_file *seq, struct dn_route *rt) -{ - struct dn_rt_cache_iter_state *s = seq->private; - - rt = rcu_dereference_bh(rt->dn_next); - while (!rt) { - rcu_read_unlock_bh(); - if (--s->bucket < 0) - break; - rcu_read_lock_bh(); - rt = rcu_dereference_bh(dn_rt_hash_table[s->bucket].chain); - } - return rt; -} - -static void *dn_rt_cache_seq_start(struct seq_file *seq, loff_t *pos) -{ - struct dn_route *rt = dn_rt_cache_get_first(seq); - - if (rt) { - while(*pos && (rt = dn_rt_cache_get_next(seq, rt))) - --*pos; - } - return *pos ? NULL : rt; -} - -static void *dn_rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct dn_route *rt = dn_rt_cache_get_next(seq, v); - ++*pos; - return rt; -} - -static void dn_rt_cache_seq_stop(struct seq_file *seq, void *v) -{ - if (v) - rcu_read_unlock_bh(); -} - -static int dn_rt_cache_seq_show(struct seq_file *seq, void *v) -{ - struct dn_route *rt = v; - char buf1[DN_ASCBUF_LEN], buf2[DN_ASCBUF_LEN]; - - seq_printf(seq, "%-8s %-7s %-7s %04d %04d %04d\n", - rt->dst.dev ? rt->dst.dev->name : "*", - dn_addr2asc(le16_to_cpu(rt->rt_daddr), buf1), - dn_addr2asc(le16_to_cpu(rt->rt_saddr), buf2), - atomic_read(&rt->dst.__refcnt), - rt->dst.__use, 0); - return 0; -} - -static const struct seq_operations dn_rt_cache_seq_ops = { - .start = dn_rt_cache_seq_start, - .next = dn_rt_cache_seq_next, - .stop = dn_rt_cache_seq_stop, - .show = dn_rt_cache_seq_show, -}; -#endif /* CONFIG_PROC_FS */ - -void __init dn_route_init(void) -{ - int i, goal, order; - - dn_dst_ops.kmem_cachep = - kmem_cache_create("dn_dst_cache", sizeof(struct dn_route), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); - dst_entries_init(&dn_dst_ops); - timer_setup(&dn_route_timer, dn_dst_check_expire, 0); - dn_route_timer.expires = jiffies + decnet_dst_gc_interval * HZ; - add_timer(&dn_route_timer); - - goal = totalram_pages >> (26 - PAGE_SHIFT); - - for(order = 0; (1UL << order) < goal; order++) - /* NOTHING */; - - /* - * Only want 1024 entries max, since the table is very, very unlikely - * to be larger than that. - */ - while(order && ((((1UL << order) * PAGE_SIZE) / - sizeof(struct dn_rt_hash_bucket)) >= 2048)) - order--; - - do { - dn_rt_hash_mask = (1UL << order) * PAGE_SIZE / - sizeof(struct dn_rt_hash_bucket); - while(dn_rt_hash_mask & (dn_rt_hash_mask - 1)) - dn_rt_hash_mask--; - dn_rt_hash_table = (struct dn_rt_hash_bucket *) - __get_free_pages(GFP_ATOMIC, order); - } while (dn_rt_hash_table == NULL && --order > 0); - - if (!dn_rt_hash_table) - panic("Failed to allocate DECnet route cache hash table\n"); - - printk(KERN_INFO - "DECnet: Routing cache hash table of %u buckets, %ldKbytes\n", - dn_rt_hash_mask, - (long)(dn_rt_hash_mask*sizeof(struct dn_rt_hash_bucket))/1024); - - dn_rt_hash_mask--; - for(i = 0; i <= dn_rt_hash_mask; i++) { - spin_lock_init(&dn_rt_hash_table[i].lock); - dn_rt_hash_table[i].chain = NULL; - } - - dn_dst_ops.gc_thresh = (dn_rt_hash_mask + 1); - - proc_create_seq_private("decnet_cache", 0444, init_net.proc_net, - &dn_rt_cache_seq_ops, - sizeof(struct dn_rt_cache_iter_state), NULL); - -#ifdef CONFIG_DECNET_ROUTER - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE, - dn_cache_getroute, dn_fib_dump, 0); -#else - rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_GETROUTE, - dn_cache_getroute, dn_cache_dump, 0); -#endif -} - -void __exit dn_route_cleanup(void) -{ - del_timer(&dn_route_timer); - dn_run_flush(NULL); - - remove_proc_entry("decnet_cache", init_net.proc_net); - dst_entries_destroy(&dn_dst_ops); -} diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c deleted file mode 100644 index 4a4e3c17740c..000000000000 --- a/net/decnet/dn_rules.c +++ /dev/null @@ -1,258 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Forwarding Information Base (Rules) - * - * Author: Steve Whitehouse <SteveW@ACM.org> - * Mostly copied from Alexey Kuznetsov's ipv4/fib_rules.c - * - * - * Changes: - * Steve Whitehouse <steve@chygwyn.com> - * Updated for Thomas Graf's generic rules - * - */ -#include <linux/net.h> -#include <linux/init.h> -#include <linux/netlink.h> -#include <linux/rtnetlink.h> -#include <linux/netdevice.h> -#include <linux/spinlock.h> -#include <linux/list.h> -#include <linux/rcupdate.h> -#include <linux/export.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/flow.h> -#include <net/fib_rules.h> -#include <net/dn.h> -#include <net/dn_fib.h> -#include <net/dn_neigh.h> -#include <net/dn_dev.h> -#include <net/dn_route.h> - -static struct fib_rules_ops *dn_fib_rules_ops; - -struct dn_fib_rule -{ - struct fib_rule common; - unsigned char dst_len; - unsigned char src_len; - __le16 src; - __le16 srcmask; - __le16 dst; - __le16 dstmask; - __le16 srcmap; - u8 flags; -}; - - -int dn_fib_lookup(struct flowidn *flp, struct dn_fib_res *res) -{ - struct fib_lookup_arg arg = { - .result = res, - }; - int err; - - err = fib_rules_lookup(dn_fib_rules_ops, - flowidn_to_flowi(flp), 0, &arg); - res->r = arg.rule; - - return err; -} - -static int dn_fib_rule_action(struct fib_rule *rule, struct flowi *flp, - int flags, struct fib_lookup_arg *arg) -{ - struct flowidn *fld = &flp->u.dn; - int err = -EAGAIN; - struct dn_fib_table *tbl; - - switch(rule->action) { - case FR_ACT_TO_TBL: - break; - - case FR_ACT_UNREACHABLE: - err = -ENETUNREACH; - goto errout; - - case FR_ACT_PROHIBIT: - err = -EACCES; - goto errout; - - case FR_ACT_BLACKHOLE: - default: - err = -EINVAL; - goto errout; - } - - tbl = dn_fib_get_table(rule->table, 0); - if (tbl == NULL) - goto errout; - - err = tbl->lookup(tbl, fld, (struct dn_fib_res *)arg->result); - if (err > 0) - err = -EAGAIN; -errout: - return err; -} - -static const struct nla_policy dn_fib_rule_policy[FRA_MAX+1] = { - FRA_GENERIC_POLICY, -}; - -static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) -{ - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - struct flowidn *fld = &fl->u.dn; - __le16 daddr = fld->daddr; - __le16 saddr = fld->saddr; - - if (((saddr ^ r->src) & r->srcmask) || - ((daddr ^ r->dst) & r->dstmask)) - return 0; - - return 1; -} - -static int dn_fib_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh, - struct nlattr **tb, - struct netlink_ext_ack *extack) -{ - int err = -EINVAL; - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - - if (frh->tos) { - NL_SET_ERR_MSG(extack, "Invalid tos value"); - goto errout; - } - - if (rule->table == RT_TABLE_UNSPEC) { - if (rule->action == FR_ACT_TO_TBL) { - struct dn_fib_table *table; - - table = dn_fib_empty_table(); - if (table == NULL) { - err = -ENOBUFS; - goto errout; - } - - rule->table = table->n; - } - } - - if (frh->src_len) - r->src = nla_get_le16(tb[FRA_SRC]); - - if (frh->dst_len) - r->dst = nla_get_le16(tb[FRA_DST]); - - r->src_len = frh->src_len; - r->srcmask = dnet_make_mask(r->src_len); - r->dst_len = frh->dst_len; - r->dstmask = dnet_make_mask(r->dst_len); - err = 0; -errout: - return err; -} - -static int dn_fib_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, - struct nlattr **tb) -{ - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - - if (frh->src_len && (r->src_len != frh->src_len)) - return 0; - - if (frh->dst_len && (r->dst_len != frh->dst_len)) - return 0; - - if (frh->src_len && (r->src != nla_get_le16(tb[FRA_SRC]))) - return 0; - - if (frh->dst_len && (r->dst != nla_get_le16(tb[FRA_DST]))) - return 0; - - return 1; -} - -unsigned int dnet_addr_type(__le16 addr) -{ - struct flowidn fld = { .daddr = addr }; - struct dn_fib_res res; - unsigned int ret = RTN_UNICAST; - struct dn_fib_table *tb = dn_fib_get_table(RT_TABLE_LOCAL, 0); - - res.r = NULL; - - if (tb) { - if (!tb->lookup(tb, &fld, &res)) { - ret = res.type; - dn_fib_res_put(&res); - } - } - return ret; -} - -static int dn_fib_rule_fill(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh) -{ - struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - - frh->dst_len = r->dst_len; - frh->src_len = r->src_len; - frh->tos = 0; - - if ((r->dst_len && - nla_put_le16(skb, FRA_DST, r->dst)) || - (r->src_len && - nla_put_le16(skb, FRA_SRC, r->src))) - goto nla_put_failure; - return 0; - -nla_put_failure: - return -ENOBUFS; -} - -static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) -{ - dn_rt_cache_flush(-1); -} - -static const struct fib_rules_ops __net_initconst dn_fib_rules_ops_template = { - .family = AF_DECnet, - .rule_size = sizeof(struct dn_fib_rule), - .addr_size = sizeof(u16), - .action = dn_fib_rule_action, - .match = dn_fib_rule_match, - .configure = dn_fib_rule_configure, - .compare = dn_fib_rule_compare, - .fill = dn_fib_rule_fill, - .flush_cache = dn_fib_rule_flush_cache, - .nlgroup = RTNLGRP_DECnet_RULE, - .policy = dn_fib_rule_policy, - .owner = THIS_MODULE, - .fro_net = &init_net, -}; - -void __init dn_fib_rules_init(void) -{ - dn_fib_rules_ops = - fib_rules_register(&dn_fib_rules_ops_template, &init_net); - BUG_ON(IS_ERR(dn_fib_rules_ops)); - BUG_ON(fib_default_rule_add(dn_fib_rules_ops, 0x7fff, - RT_TABLE_MAIN, 0)); -} - -void __exit dn_fib_rules_cleanup(void) -{ - rtnl_lock(); - fib_rules_unregister(dn_fib_rules_ops); - rtnl_unlock(); - rcu_barrier(); -} diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c deleted file mode 100644 index f0710b5d037d..000000000000 --- a/net/decnet/dn_table.c +++ /dev/null @@ -1,928 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Forwarding Information Base (Routing Tables) - * - * Author: Steve Whitehouse <SteveW@ACM.org> - * Mostly copied from the IPv4 routing code - * - * - * Changes: - * - */ -#include <linux/string.h> -#include <linux/net.h> -#include <linux/socket.h> -#include <linux/slab.h> -#include <linux/sockios.h> -#include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/proc_fs.h> -#include <linux/netdevice.h> -#include <linux/timer.h> -#include <linux/spinlock.h> -#include <linux/atomic.h> -#include <linux/uaccess.h> -#include <linux/route.h> /* RTF_xxx */ -#include <net/neighbour.h> -#include <net/netlink.h> -#include <net/tcp.h> -#include <net/dst.h> -#include <net/flow.h> -#include <net/fib_rules.h> -#include <net/dn.h> -#include <net/dn_route.h> -#include <net/dn_fib.h> -#include <net/dn_neigh.h> -#include <net/dn_dev.h> - -struct dn_zone -{ - struct dn_zone *dz_next; - struct dn_fib_node **dz_hash; - int dz_nent; - int dz_divisor; - u32 dz_hashmask; -#define DZ_HASHMASK(dz) ((dz)->dz_hashmask) - int dz_order; - __le16 dz_mask; -#define DZ_MASK(dz) ((dz)->dz_mask) -}; - -struct dn_hash -{ - struct dn_zone *dh_zones[17]; - struct dn_zone *dh_zone_list; -}; - -#define dz_key_0(key) ((key).datum = 0) - -#define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\ - for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define endfor_nexthops(fi) } - -#define DN_MAX_DIVISOR 1024 -#define DN_S_ZOMBIE 1 -#define DN_S_ACCESSED 2 - -#define DN_FIB_SCAN(f, fp) \ -for( ; ((f) = *(fp)) != NULL; (fp) = &(f)->fn_next) - -#define DN_FIB_SCAN_KEY(f, fp, key) \ -for( ; ((f) = *(fp)) != NULL && dn_key_eq((f)->fn_key, (key)); (fp) = &(f)->fn_next) - -#define RT_TABLE_MIN 1 -#define DN_FIB_TABLE_HASHSZ 256 -static struct hlist_head dn_fib_table_hash[DN_FIB_TABLE_HASHSZ]; -static DEFINE_RWLOCK(dn_fib_tables_lock); - -static struct kmem_cache *dn_hash_kmem __read_mostly; -static int dn_fib_hash_zombies; - -static inline dn_fib_idx_t dn_hash(dn_fib_key_t key, struct dn_zone *dz) -{ - u16 h = le16_to_cpu(key.datum)>>(16 - dz->dz_order); - h ^= (h >> 10); - h ^= (h >> 6); - h &= DZ_HASHMASK(dz); - return *(dn_fib_idx_t *)&h; -} - -static inline dn_fib_key_t dz_key(__le16 dst, struct dn_zone *dz) -{ - dn_fib_key_t k; - k.datum = dst & DZ_MASK(dz); - return k; -} - -static inline struct dn_fib_node **dn_chain_p(dn_fib_key_t key, struct dn_zone *dz) -{ - return &dz->dz_hash[dn_hash(key, dz).datum]; -} - -static inline struct dn_fib_node *dz_chain(dn_fib_key_t key, struct dn_zone *dz) -{ - return dz->dz_hash[dn_hash(key, dz).datum]; -} - -static inline int dn_key_eq(dn_fib_key_t a, dn_fib_key_t b) -{ - return a.datum == b.datum; -} - -static inline int dn_key_leq(dn_fib_key_t a, dn_fib_key_t b) -{ - return a.datum <= b.datum; -} - -static inline void dn_rebuild_zone(struct dn_zone *dz, - struct dn_fib_node **old_ht, - int old_divisor) -{ - struct dn_fib_node *f, **fp, *next; - int i; - - for(i = 0; i < old_divisor; i++) { - for(f = old_ht[i]; f; f = next) { - next = f->fn_next; - for(fp = dn_chain_p(f->fn_key, dz); - *fp && dn_key_leq((*fp)->fn_key, f->fn_key); - fp = &(*fp)->fn_next) - /* NOTHING */; - f->fn_next = *fp; - *fp = f; - } - } -} - -static void dn_rehash_zone(struct dn_zone *dz) -{ - struct dn_fib_node **ht, **old_ht; - int old_divisor, new_divisor; - u32 new_hashmask; - - old_divisor = dz->dz_divisor; - - switch (old_divisor) { - case 16: - new_divisor = 256; - new_hashmask = 0xFF; - break; - default: - printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n", - old_divisor); - /* fall through */ - case 256: - new_divisor = 1024; - new_hashmask = 0x3FF; - break; - } - - ht = kcalloc(new_divisor, sizeof(struct dn_fib_node*), GFP_KERNEL); - if (ht == NULL) - return; - - write_lock_bh(&dn_fib_tables_lock); - old_ht = dz->dz_hash; - dz->dz_hash = ht; - dz->dz_hashmask = new_hashmask; - dz->dz_divisor = new_divisor; - dn_rebuild_zone(dz, old_ht, old_divisor); - write_unlock_bh(&dn_fib_tables_lock); - kfree(old_ht); -} - -static void dn_free_node(struct dn_fib_node *f) -{ - dn_fib_release_info(DN_FIB_INFO(f)); - kmem_cache_free(dn_hash_kmem, f); -} - - -static struct dn_zone *dn_new_zone(struct dn_hash *table, int z) -{ - int i; - struct dn_zone *dz = kzalloc(sizeof(struct dn_zone), GFP_KERNEL); - if (!dz) - return NULL; - - if (z) { - dz->dz_divisor = 16; - dz->dz_hashmask = 0x0F; - } else { - dz->dz_divisor = 1; - dz->dz_hashmask = 0; - } - - dz->dz_hash = kcalloc(dz->dz_divisor, sizeof(struct dn_fib_node *), GFP_KERNEL); - if (!dz->dz_hash) { - kfree(dz); - return NULL; - } - - dz->dz_order = z; - dz->dz_mask = dnet_make_mask(z); - - for(i = z + 1; i <= 16; i++) - if (table->dh_zones[i]) - break; - - write_lock_bh(&dn_fib_tables_lock); - if (i>16) { - dz->dz_next = table->dh_zone_list; - table->dh_zone_list = dz; - } else { - dz->dz_next = table->dh_zones[i]->dz_next; - table->dh_zones[i]->dz_next = dz; - } - table->dh_zones[z] = dz; - write_unlock_bh(&dn_fib_tables_lock); - return dz; -} - - -static int dn_fib_nh_match(struct rtmsg *r, struct nlmsghdr *nlh, struct nlattr *attrs[], struct dn_fib_info *fi) -{ - struct rtnexthop *nhp; - int nhlen; - - if (attrs[RTA_PRIORITY] && - nla_get_u32(attrs[RTA_PRIORITY]) != fi->fib_priority) - return 1; - - if (attrs[RTA_OIF] || attrs[RTA_GATEWAY]) { - if ((!attrs[RTA_OIF] || nla_get_u32(attrs[RTA_OIF]) == fi->fib_nh->nh_oif) && - (!attrs[RTA_GATEWAY] || nla_get_le16(attrs[RTA_GATEWAY]) != fi->fib_nh->nh_gw)) - return 0; - return 1; - } - - if (!attrs[RTA_MULTIPATH]) - return 0; - - nhp = nla_data(attrs[RTA_MULTIPATH]); - nhlen = nla_len(attrs[RTA_MULTIPATH]); - - for_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - __le16 gw; - - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) - return -EINVAL; - if (nhp->rtnh_ifindex && nhp->rtnh_ifindex != nh->nh_oif) - return 1; - if (attrlen) { - struct nlattr *gw_attr; - - gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY); - gw = gw_attr ? nla_get_le16(gw_attr) : 0; - - if (gw && gw != nh->nh_gw) - return 1; - } - nhp = RTNH_NEXT(nhp); - } endfor_nexthops(fi); - - return 0; -} - -static inline size_t dn_fib_nlmsg_size(struct dn_fib_info *fi) -{ - size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) - + nla_total_size(4) /* RTA_TABLE */ - + nla_total_size(2) /* RTA_DST */ - + nla_total_size(4) /* RTA_PRIORITY */ - + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ - - /* space for nested metrics */ - payload += nla_total_size((RTAX_MAX * nla_total_size(4))); - - if (fi->fib_nhs) { - /* Also handles the special case fib_nhs == 1 */ - - /* each nexthop is packed in an attribute */ - size_t nhsize = nla_total_size(sizeof(struct rtnexthop)); - - /* may contain a gateway attribute */ - nhsize += nla_total_size(4); - - /* all nexthops are packed in a nested attribute */ - payload += nla_total_size(fi->fib_nhs * nhsize); - } - - return payload; -} - -static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, - u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, - struct dn_fib_info *fi, unsigned int flags) -{ - struct rtmsg *rtm; - struct nlmsghdr *nlh; - - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); - if (!nlh) - return -EMSGSIZE; - - rtm = nlmsg_data(nlh); - rtm->rtm_family = AF_DECnet; - rtm->rtm_dst_len = dst_len; - rtm->rtm_src_len = 0; - rtm->rtm_tos = 0; - rtm->rtm_table = tb_id; - rtm->rtm_flags = fi->fib_flags; - rtm->rtm_scope = scope; - rtm->rtm_type = type; - rtm->rtm_protocol = fi->fib_protocol; - - if (nla_put_u32(skb, RTA_TABLE, tb_id) < 0) - goto errout; - - if (rtm->rtm_dst_len && - nla_put(skb, RTA_DST, 2, dst) < 0) - goto errout; - - if (fi->fib_priority && - nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority) < 0) - goto errout; - - if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0) - goto errout; - - if (fi->fib_nhs == 1) { - if (fi->fib_nh->nh_gw && - nla_put_le16(skb, RTA_GATEWAY, fi->fib_nh->nh_gw) < 0) - goto errout; - - if (fi->fib_nh->nh_oif && - nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif) < 0) - goto errout; - } - - if (fi->fib_nhs > 1) { - struct rtnexthop *nhp; - struct nlattr *mp_head; - - if (!(mp_head = nla_nest_start(skb, RTA_MULTIPATH))) - goto errout; - - for_nexthops(fi) { - if (!(nhp = nla_reserve_nohdr(skb, sizeof(*nhp)))) - goto errout; - - nhp->rtnh_flags = nh->nh_flags & 0xFF; - nhp->rtnh_hops = nh->nh_weight - 1; - nhp->rtnh_ifindex = nh->nh_oif; - - if (nh->nh_gw && - nla_put_le16(skb, RTA_GATEWAY, nh->nh_gw) < 0) - goto errout; - - nhp->rtnh_len = skb_tail_pointer(skb) - (unsigned char *)nhp; - } endfor_nexthops(fi); - - nla_nest_end(skb, mp_head); - } - - nlmsg_end(skb, nlh); - return 0; - -errout: - nlmsg_cancel(skb, nlh); - return -EMSGSIZE; -} - - -static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id, - struct nlmsghdr *nlh, struct netlink_skb_parms *req) -{ - struct sk_buff *skb; - u32 portid = req ? req->portid : 0; - int err = -ENOBUFS; - - skb = nlmsg_new(dn_fib_nlmsg_size(DN_FIB_INFO(f)), GFP_KERNEL); - if (skb == NULL) - goto errout; - - err = dn_fib_dump_info(skb, portid, nlh->nlmsg_seq, event, tb_id, - f->fn_type, f->fn_scope, &f->fn_key, z, - DN_FIB_INFO(f), 0); - if (err < 0) { - /* -EMSGSIZE implies BUG in dn_fib_nlmsg_size() */ - WARN_ON(err == -EMSGSIZE); - kfree_skb(skb); - goto errout; - } - rtnl_notify(skb, &init_net, portid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL); - return; -errout: - if (err < 0) - rtnl_set_sk_err(&init_net, RTNLGRP_DECnet_ROUTE, err); -} - -static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb, - struct netlink_callback *cb, - struct dn_fib_table *tb, - struct dn_zone *dz, - struct dn_fib_node *f) -{ - int i, s_i; - - s_i = cb->args[4]; - for(i = 0; f; i++, f = f->fn_next) { - if (i < s_i) - continue; - if (f->fn_state & DN_S_ZOMBIE) - continue; - if (dn_fib_dump_info(skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->n, - (f->fn_state & DN_S_ZOMBIE) ? 0 : f->fn_type, - f->fn_scope, &f->fn_key, dz->dz_order, - f->fn_info, NLM_F_MULTI) < 0) { - cb->args[4] = i; - return -1; - } - } - cb->args[4] = i; - return skb->len; -} - -static __inline__ int dn_hash_dump_zone(struct sk_buff *skb, - struct netlink_callback *cb, - struct dn_fib_table *tb, - struct dn_zone *dz) -{ - int h, s_h; - - s_h = cb->args[3]; - for(h = 0; h < dz->dz_divisor; h++) { - if (h < s_h) - continue; - if (h > s_h) - memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); - if (dz->dz_hash == NULL || dz->dz_hash[h] == NULL) - continue; - if (dn_hash_dump_bucket(skb, cb, tb, dz, dz->dz_hash[h]) < 0) { - cb->args[3] = h; - return -1; - } - } - cb->args[3] = h; - return skb->len; -} - -static int dn_fib_table_dump(struct dn_fib_table *tb, struct sk_buff *skb, - struct netlink_callback *cb) -{ - int m, s_m; - struct dn_zone *dz; - struct dn_hash *table = (struct dn_hash *)tb->data; - - s_m = cb->args[2]; - read_lock(&dn_fib_tables_lock); - for(dz = table->dh_zone_list, m = 0; dz; dz = dz->dz_next, m++) { - if (m < s_m) - continue; - if (m > s_m) - memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0])); - - if (dn_hash_dump_zone(skb, cb, tb, dz) < 0) { - cb->args[2] = m; - read_unlock(&dn_fib_tables_lock); - return -1; - } - } - read_unlock(&dn_fib_tables_lock); - cb->args[2] = m; - - return skb->len; -} - -int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - unsigned int h, s_h; - unsigned int e = 0, s_e; - struct dn_fib_table *tb; - int dumped = 0; - - if (!net_eq(net, &init_net)) - return 0; - - if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) && - ((struct rtmsg *)nlmsg_data(cb->nlh))->rtm_flags&RTM_F_CLONED) - return dn_cache_dump(skb, cb); - - s_h = cb->args[0]; - s_e = cb->args[1]; - - for (h = s_h; h < DN_FIB_TABLE_HASHSZ; h++, s_h = 0) { - e = 0; - hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) { - if (e < s_e) - goto next; - if (dumped) - memset(&cb->args[2], 0, sizeof(cb->args) - - 2 * sizeof(cb->args[0])); - if (tb->dump(tb, skb, cb) < 0) - goto out; - dumped = 1; -next: - e++; - } - } -out: - cb->args[1] = e; - cb->args[0] = h; - - return skb->len; -} - -static int dn_fib_table_insert(struct dn_fib_table *tb, struct rtmsg *r, struct nlattr *attrs[], - struct nlmsghdr *n, struct netlink_skb_parms *req) -{ - struct dn_hash *table = (struct dn_hash *)tb->data; - struct dn_fib_node *new_f, *f, **fp, **del_fp; - struct dn_zone *dz; - struct dn_fib_info *fi; - int z = r->rtm_dst_len; - int type = r->rtm_type; - dn_fib_key_t key; - int err; - - if (z > 16) - return -EINVAL; - - dz = table->dh_zones[z]; - if (!dz && !(dz = dn_new_zone(table, z))) - return -ENOBUFS; - - dz_key_0(key); - if (attrs[RTA_DST]) { - __le16 dst = nla_get_le16(attrs[RTA_DST]); - if (dst & ~DZ_MASK(dz)) - return -EINVAL; - key = dz_key(dst, dz); - } - - if ((fi = dn_fib_create_info(r, attrs, n, &err)) == NULL) - return err; - - if (dz->dz_nent > (dz->dz_divisor << 2) && - dz->dz_divisor > DN_MAX_DIVISOR && - (z==16 || (1<<z) > dz->dz_divisor)) - dn_rehash_zone(dz); - - fp = dn_chain_p(key, dz); - - DN_FIB_SCAN(f, fp) { - if (dn_key_leq(key, f->fn_key)) - break; - } - - del_fp = NULL; - - if (f && (f->fn_state & DN_S_ZOMBIE) && - dn_key_eq(f->fn_key, key)) { - del_fp = fp; - fp = &f->fn_next; - f = *fp; - goto create; - } - - DN_FIB_SCAN_KEY(f, fp, key) { - if (fi->fib_priority <= DN_FIB_INFO(f)->fib_priority) - break; - } - - if (f && dn_key_eq(f->fn_key, key) && - fi->fib_priority == DN_FIB_INFO(f)->fib_priority) { - struct dn_fib_node **ins_fp; - - err = -EEXIST; - if (n->nlmsg_flags & NLM_F_EXCL) - goto out; - - if (n->nlmsg_flags & NLM_F_REPLACE) { - del_fp = fp; - fp = &f->fn_next; - f = *fp; - goto replace; - } - - ins_fp = fp; - err = -EEXIST; - - DN_FIB_SCAN_KEY(f, fp, key) { - if (fi->fib_priority != DN_FIB_INFO(f)->fib_priority) - break; - if (f->fn_type == type && - f->fn_scope == r->rtm_scope && - DN_FIB_INFO(f) == fi) - goto out; - } - - if (!(n->nlmsg_flags & NLM_F_APPEND)) { - fp = ins_fp; - f = *fp; - } - } - -create: - err = -ENOENT; - if (!(n->nlmsg_flags & NLM_F_CREATE)) - goto out; - -replace: - err = -ENOBUFS; - new_f = kmem_cache_zalloc(dn_hash_kmem, GFP_KERNEL); - if (new_f == NULL) - goto out; - - new_f->fn_key = key; - new_f->fn_type = type; - new_f->fn_scope = r->rtm_scope; - DN_FIB_INFO(new_f) = fi; - - new_f->fn_next = f; - write_lock_bh(&dn_fib_tables_lock); - *fp = new_f; - write_unlock_bh(&dn_fib_tables_lock); - dz->dz_nent++; - - if (del_fp) { - f = *del_fp; - write_lock_bh(&dn_fib_tables_lock); - *del_fp = f->fn_next; - write_unlock_bh(&dn_fib_tables_lock); - - if (!(f->fn_state & DN_S_ZOMBIE)) - dn_rtmsg_fib(RTM_DELROUTE, f, z, tb->n, n, req); - if (f->fn_state & DN_S_ACCESSED) - dn_rt_cache_flush(-1); - dn_free_node(f); - dz->dz_nent--; - } else { - dn_rt_cache_flush(-1); - } - - dn_rtmsg_fib(RTM_NEWROUTE, new_f, z, tb->n, n, req); - - return 0; -out: - dn_fib_release_info(fi); - return err; -} - - -static int dn_fib_table_delete(struct dn_fib_table *tb, struct rtmsg *r, struct nlattr *attrs[], - struct nlmsghdr *n, struct netlink_skb_parms *req) -{ - struct dn_hash *table = (struct dn_hash*)tb->data; - struct dn_fib_node **fp, **del_fp, *f; - int z = r->rtm_dst_len; - struct dn_zone *dz; - dn_fib_key_t key; - int matched; - - - if (z > 16) - return -EINVAL; - - if ((dz = table->dh_zones[z]) == NULL) - return -ESRCH; - - dz_key_0(key); - if (attrs[RTA_DST]) { - __le16 dst = nla_get_le16(attrs[RTA_DST]); - if (dst & ~DZ_MASK(dz)) - return -EINVAL; - key = dz_key(dst, dz); - } - - fp = dn_chain_p(key, dz); - - DN_FIB_SCAN(f, fp) { - if (dn_key_eq(f->fn_key, key)) - break; - if (dn_key_leq(key, f->fn_key)) - return -ESRCH; - } - - matched = 0; - del_fp = NULL; - DN_FIB_SCAN_KEY(f, fp, key) { - struct dn_fib_info *fi = DN_FIB_INFO(f); - - if (f->fn_state & DN_S_ZOMBIE) - return -ESRCH; - - matched++; - - if (del_fp == NULL && - (!r->rtm_type || f->fn_type == r->rtm_type) && - (r->rtm_scope == RT_SCOPE_NOWHERE || f->fn_scope == r->rtm_scope) && - (!r->rtm_protocol || - fi->fib_protocol == r->rtm_protocol) && - dn_fib_nh_match(r, n, attrs, fi) == 0) - del_fp = fp; - } - - if (del_fp) { - f = *del_fp; - dn_rtmsg_fib(RTM_DELROUTE, f, z, tb->n, n, req); - - if (matched != 1) { - write_lock_bh(&dn_fib_tables_lock); - *del_fp = f->fn_next; - write_unlock_bh(&dn_fib_tables_lock); - - if (f->fn_state & DN_S_ACCESSED) - dn_rt_cache_flush(-1); - dn_free_node(f); - dz->dz_nent--; - } else { - f->fn_state |= DN_S_ZOMBIE; - if (f->fn_state & DN_S_ACCESSED) { - f->fn_state &= ~DN_S_ACCESSED; - dn_rt_cache_flush(-1); - } - if (++dn_fib_hash_zombies > 128) - dn_fib_flush(); - } - - return 0; - } - - return -ESRCH; -} - -static inline int dn_flush_list(struct dn_fib_node **fp, int z, struct dn_hash *table) -{ - int found = 0; - struct dn_fib_node *f; - - while((f = *fp) != NULL) { - struct dn_fib_info *fi = DN_FIB_INFO(f); - - if (fi && ((f->fn_state & DN_S_ZOMBIE) || (fi->fib_flags & RTNH_F_DEAD))) { - write_lock_bh(&dn_fib_tables_lock); - *fp = f->fn_next; - write_unlock_bh(&dn_fib_tables_lock); - - dn_free_node(f); - found++; - continue; - } - fp = &f->fn_next; - } - - return found; -} - -static int dn_fib_table_flush(struct dn_fib_table *tb) -{ - struct dn_hash *table = (struct dn_hash *)tb->data; - struct dn_zone *dz; - int found = 0; - - dn_fib_hash_zombies = 0; - for(dz = table->dh_zone_list; dz; dz = dz->dz_next) { - int i; - int tmp = 0; - for(i = dz->dz_divisor-1; i >= 0; i--) - tmp += dn_flush_list(&dz->dz_hash[i], dz->dz_order, table); - dz->dz_nent -= tmp; - found += tmp; - } - - return found; -} - -static int dn_fib_table_lookup(struct dn_fib_table *tb, const struct flowidn *flp, struct dn_fib_res *res) -{ - int err; - struct dn_zone *dz; - struct dn_hash *t = (struct dn_hash *)tb->data; - - read_lock(&dn_fib_tables_lock); - for(dz = t->dh_zone_list; dz; dz = dz->dz_next) { - struct dn_fib_node *f; - dn_fib_key_t k = dz_key(flp->daddr, dz); - - for(f = dz_chain(k, dz); f; f = f->fn_next) { - if (!dn_key_eq(k, f->fn_key)) { - if (dn_key_leq(k, f->fn_key)) - break; - else - continue; - } - - f->fn_state |= DN_S_ACCESSED; - - if (f->fn_state&DN_S_ZOMBIE) - continue; - - if (f->fn_scope < flp->flowidn_scope) - continue; - - err = dn_fib_semantic_match(f->fn_type, DN_FIB_INFO(f), flp, res); - - if (err == 0) { - res->type = f->fn_type; - res->scope = f->fn_scope; - res->prefixlen = dz->dz_order; - goto out; - } - if (err < 0) - goto out; - } - } - err = 1; -out: - read_unlock(&dn_fib_tables_lock); - return err; -} - - -struct dn_fib_table *dn_fib_get_table(u32 n, int create) -{ - struct dn_fib_table *t; - unsigned int h; - - if (n < RT_TABLE_MIN) - return NULL; - - if (n > RT_TABLE_MAX) - return NULL; - - h = n & (DN_FIB_TABLE_HASHSZ - 1); - rcu_read_lock(); - hlist_for_each_entry_rcu(t, &dn_fib_table_hash[h], hlist) { - if (t->n == n) { - rcu_read_unlock(); - return t; - } - } - rcu_read_unlock(); - - if (!create) - return NULL; - - if (in_interrupt()) { - net_dbg_ratelimited("DECnet: BUG! Attempt to create routing table from interrupt\n"); - return NULL; - } - - t = kzalloc(sizeof(struct dn_fib_table) + sizeof(struct dn_hash), - GFP_KERNEL); - if (t == NULL) - return NULL; - - t->n = n; - t->insert = dn_fib_table_insert; - t->delete = dn_fib_table_delete; - t->lookup = dn_fib_table_lookup; - t->flush = dn_fib_table_flush; - t->dump = dn_fib_table_dump; - hlist_add_head_rcu(&t->hlist, &dn_fib_table_hash[h]); - - return t; -} - -struct dn_fib_table *dn_fib_empty_table(void) -{ - u32 id; - - for(id = RT_TABLE_MIN; id <= RT_TABLE_MAX; id++) - if (dn_fib_get_table(id, 0) == NULL) - return dn_fib_get_table(id, 1); - return NULL; -} - -void dn_fib_flush(void) -{ - int flushed = 0; - struct dn_fib_table *tb; - unsigned int h; - - for (h = 0; h < DN_FIB_TABLE_HASHSZ; h++) { - hlist_for_each_entry(tb, &dn_fib_table_hash[h], hlist) - flushed += tb->flush(tb); - } - - if (flushed) - dn_rt_cache_flush(-1); -} - -void __init dn_fib_table_init(void) -{ - dn_hash_kmem = kmem_cache_create("dn_fib_info_cache", - sizeof(struct dn_fib_info), - 0, SLAB_HWCACHE_ALIGN, - NULL); -} - -void __exit dn_fib_table_cleanup(void) -{ - struct dn_fib_table *t; - 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, next, &dn_fib_table_hash[h], - hlist) { - hlist_del(&t->hlist); - kfree(t); - } - } - write_unlock(&dn_fib_tables_lock); -} diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c deleted file mode 100644 index aa4155875ca8..000000000000 --- a/net/decnet/dn_timer.c +++ /dev/null @@ -1,104 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Socket Timer Functions - * - * Author: Steve Whitehouse <SteveW@ACM.org> - * - * - * Changes: - * Steve Whitehouse : Made keepalive timer part of the same - * timer idea. - * Steve Whitehouse : Added checks for sk->sock_readers - * David S. Miller : New socket locking - * Steve Whitehouse : Timer grabs socket ref. - */ -#include <linux/net.h> -#include <linux/socket.h> -#include <linux/skbuff.h> -#include <linux/netdevice.h> -#include <linux/timer.h> -#include <linux/spinlock.h> -#include <net/sock.h> -#include <linux/atomic.h> -#include <linux/jiffies.h> -#include <net/flow.h> -#include <net/dn.h> - -/* - * Slow timer is for everything else (n * 500mS) - */ - -#define SLOW_INTERVAL (HZ/2) - -static void dn_slow_timer(struct timer_list *t); - -void dn_start_slow_timer(struct sock *sk) -{ - timer_setup(&sk->sk_timer, dn_slow_timer, 0); - sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); -} - -void dn_stop_slow_timer(struct sock *sk) -{ - sk_stop_timer(sk, &sk->sk_timer); -} - -static void dn_slow_timer(struct timer_list *t) -{ - struct sock *sk = from_timer(sk, t, sk_timer); - struct dn_scp *scp = DN_SK(sk); - - bh_lock_sock(sk); - - if (sock_owned_by_user(sk)) { - sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 10); - goto out; - } - - /* - * The persist timer is the standard slow timer used for retransmits - * in both connection establishment and disconnection as well as - * in the RUN state. The different states are catered for by changing - * the function pointer in the socket. Setting the timer to a value - * of zero turns it off. We allow the persist_fxn to turn the - * timer off in a permant way by returning non-zero, so that - * timer based routines may remove sockets. This is why we have a - * sock_hold()/sock_put() around the timer to prevent the socket - * going away in the middle. - */ - if (scp->persist && scp->persist_fxn) { - if (scp->persist <= SLOW_INTERVAL) { - scp->persist = 0; - - if (scp->persist_fxn(sk)) - goto out; - } else { - scp->persist -= SLOW_INTERVAL; - } - } - - /* - * Check for keepalive timeout. After the other timer 'cos if - * the previous timer caused a retransmit, we don't need to - * do this. scp->stamp is the last time that we sent a packet. - * The keepalive function sends a link service packet to the - * other end. If it remains unacknowledged, the standard - * socket timers will eventually shut the socket down. Each - * time we do this, scp->stamp will be updated, thus - * we won't try and send another until scp->keepalive has passed - * since the last successful transmission. - */ - if (scp->keepalive && scp->keepalive_fxn && (scp->state == DN_RUN)) { - if (time_after_eq(jiffies, scp->stamp + scp->keepalive)) - scp->keepalive_fxn(sk); - } - - sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL); -out: - bh_unlock_sock(sk); - sock_put(sk); -} diff --git a/net/decnet/netfilter/Kconfig b/net/decnet/netfilter/Kconfig deleted file mode 100644 index 8d7c109d5109..000000000000 --- a/net/decnet/netfilter/Kconfig +++ /dev/null @@ -1,16 +0,0 @@ -# -# DECnet netfilter configuration -# - -menu "DECnet: Netfilter Configuration" - depends on DECNET && NETFILTER - depends on NETFILTER_ADVANCED - -config DECNET_NF_GRABULATOR - tristate "Routing message grabulator (for userland routing daemon)" - help - Enable this module if you want to use the userland DECnet routing - daemon. You will also need to enable routing support for DECnet - unless you just want to monitor routing messages from other nodes. - -endmenu diff --git a/net/decnet/netfilter/Makefile b/net/decnet/netfilter/Makefile deleted file mode 100644 index b579e52130aa..000000000000 --- a/net/decnet/netfilter/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -# -# Makefile for DECnet netfilter modules -# - -obj-$(CONFIG_DECNET_NF_GRABULATOR) += dn_rtmsg.o diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c deleted file mode 100644 index a4faacadd8a8..000000000000 --- a/net/decnet/netfilter/dn_rtmsg.c +++ /dev/null @@ -1,160 +0,0 @@ -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet Routing Message Grabulator - * - * (C) 2000 ChyGwyn Limited - http://www.chygwyn.com/ - * This code may be copied under the GPL v.2 or at your option - * any later version. - * - * Author: Steven Whitehouse <steve@chygwyn.com> - * - */ -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/netdevice.h> -#include <linux/netfilter.h> -#include <linux/spinlock.h> -#include <net/netlink.h> -#include <linux/netfilter_decnet.h> - -#include <net/sock.h> -#include <net/flow.h> -#include <net/dn.h> -#include <net/dn_route.h> - -static struct sock *dnrmg = NULL; - - -static struct sk_buff *dnrmg_build_message(struct sk_buff *rt_skb, int *errp) -{ - struct sk_buff *skb = NULL; - size_t size; - sk_buff_data_t old_tail; - struct nlmsghdr *nlh; - unsigned char *ptr; - struct nf_dn_rtmsg *rtm; - - size = NLMSG_ALIGN(rt_skb->len) + - NLMSG_ALIGN(sizeof(struct nf_dn_rtmsg)); - skb = nlmsg_new(size, GFP_ATOMIC); - if (!skb) { - *errp = -ENOMEM; - return NULL; - } - old_tail = skb->tail; - nlh = nlmsg_put(skb, 0, 0, 0, size, 0); - if (!nlh) { - kfree_skb(skb); - *errp = -ENOMEM; - return NULL; - } - rtm = (struct nf_dn_rtmsg *)nlmsg_data(nlh); - rtm->nfdn_ifindex = rt_skb->dev->ifindex; - ptr = NFDN_RTMSG(rtm); - skb_copy_from_linear_data(rt_skb, ptr, rt_skb->len); - nlh->nlmsg_len = skb->tail - old_tail; - return skb; -} - -static void dnrmg_send_peer(struct sk_buff *skb) -{ - struct sk_buff *skb2; - int status = 0; - int group = 0; - unsigned char flags = *skb->data; - - switch (flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_L1RT: - group = DNRNG_NLGRP_L1; - break; - case DN_RT_PKT_L2RT: - group = DNRNG_NLGRP_L2; - break; - default: - return; - } - - skb2 = dnrmg_build_message(skb, &status); - if (skb2 == NULL) - return; - NETLINK_CB(skb2).dst_group = group; - netlink_broadcast(dnrmg, skb2, 0, group, GFP_ATOMIC); -} - - -static unsigned int dnrmg_hook(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - dnrmg_send_peer(skb); - return NF_ACCEPT; -} - - -#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err), NULL); return; } while (0) - -static inline void dnrmg_receive_user_skb(struct sk_buff *skb) -{ - struct nlmsghdr *nlh = nlmsg_hdr(skb); - - if (skb->len < sizeof(*nlh) || - nlh->nlmsg_len < sizeof(*nlh) || - skb->len < nlh->nlmsg_len) - return; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - RCV_SKB_FAIL(-EPERM); - - /* Eventually we might send routing messages too */ - - RCV_SKB_FAIL(-EINVAL); -} - -static const struct nf_hook_ops dnrmg_ops = { - .hook = dnrmg_hook, - .pf = NFPROTO_DECNET, - .hooknum = NF_DN_ROUTE, - .priority = NF_DN_PRI_DNRTMSG, -}; - -static int __init dn_rtmsg_init(void) -{ - int rv = 0; - struct netlink_kernel_cfg cfg = { - .groups = DNRNG_NLGRP_MAX, - .input = dnrmg_receive_user_skb, - }; - - dnrmg = netlink_kernel_create(&init_net, NETLINK_DNRTMSG, &cfg); - if (dnrmg == NULL) { - printk(KERN_ERR "dn_rtmsg: Cannot create netlink socket"); - return -ENOMEM; - } - - rv = nf_register_net_hook(&init_net, &dnrmg_ops); - if (rv) { - netlink_kernel_release(dnrmg); - } - - return rv; -} - -static void __exit dn_rtmsg_fini(void) -{ - nf_unregister_net_hook(&init_net, &dnrmg_ops); - netlink_kernel_release(dnrmg); -} - - -MODULE_DESCRIPTION("DECnet Routing Message Grabulator"); -MODULE_AUTHOR("Steven Whitehouse <steve@chygwyn.com>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_DNRTMSG); - -module_init(dn_rtmsg_init); -module_exit(dn_rtmsg_fini); diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c deleted file mode 100644 index 55bf64a22b59..000000000000 --- a/net/decnet/sysctl_net_decnet.c +++ /dev/null @@ -1,373 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * DECnet An implementation of the DECnet protocol suite for the LINUX - * operating system. DECnet is implemented using the BSD Socket - * interface as the means of communication with the user level. - * - * DECnet sysctl support functions - * - * Author: Steve Whitehouse <SteveW@ACM.org> - * - * - * Changes: - * Steve Whitehouse - C99 changes and default device handling - * Steve Whitehouse - Memory buffer settings, like the tcp ones - * - */ -#include <linux/mm.h> -#include <linux/sysctl.h> -#include <linux/fs.h> -#include <linux/netdevice.h> -#include <linux/string.h> -#include <net/neighbour.h> -#include <net/dst.h> -#include <net/flow.h> - -#include <linux/uaccess.h> - -#include <net/dn.h> -#include <net/dn_dev.h> -#include <net/dn_route.h> - - -int decnet_debug_level; -int decnet_time_wait = 30; -int decnet_dn_count = 1; -int decnet_di_count = 3; -int decnet_dr_count = 3; -int decnet_log_martians = 1; -int decnet_no_fc_max_cwnd = NSP_MIN_WINDOW; - -/* Reasonable defaults, I hope, based on tcp's defaults */ -long sysctl_decnet_mem[3] = { 768 << 3, 1024 << 3, 1536 << 3 }; -int sysctl_decnet_wmem[3] = { 4 * 1024, 16 * 1024, 128 * 1024 }; -int sysctl_decnet_rmem[3] = { 4 * 1024, 87380, 87380 * 2 }; - -#ifdef CONFIG_SYSCTL -extern int decnet_dst_gc_interval; -static int min_decnet_time_wait[] = { 5 }; -static int max_decnet_time_wait[] = { 600 }; -static int min_state_count[] = { 1 }; -static int max_state_count[] = { NSP_MAXRXTSHIFT }; -static int min_decnet_dst_gc_interval[] = { 1 }; -static int max_decnet_dst_gc_interval[] = { 60 }; -static int min_decnet_no_fc_max_cwnd[] = { NSP_MIN_WINDOW }; -static int max_decnet_no_fc_max_cwnd[] = { NSP_MAX_WINDOW }; -static char node_name[7] = "???"; - -static struct ctl_table_header *dn_table_header = NULL; - -/* - * ctype.h :-) - */ -#define ISNUM(x) (((x) >= '0') && ((x) <= '9')) -#define ISLOWER(x) (((x) >= 'a') && ((x) <= 'z')) -#define ISUPPER(x) (((x) >= 'A') && ((x) <= 'Z')) -#define ISALPHA(x) (ISLOWER(x) || ISUPPER(x)) -#define INVALID_END_CHAR(x) (ISNUM(x) || ISALPHA(x)) - -static void strip_it(char *str) -{ - for(;;) { - switch (*str) { - case ' ': - case '\n': - case '\r': - case ':': - *str = 0; - /* Fallthrough */ - case 0: - return; - } - str++; - } -} - -/* - * Simple routine to parse an ascii DECnet address - * into a network order address. - */ -static int parse_addr(__le16 *addr, char *str) -{ - __u16 area, node; - - while(*str && !ISNUM(*str)) str++; - - if (*str == 0) - return -1; - - area = (*str++ - '0'); - if (ISNUM(*str)) { - area *= 10; - area += (*str++ - '0'); - } - - if (*str++ != '.') - return -1; - - if (!ISNUM(*str)) - return -1; - - node = *str++ - '0'; - if (ISNUM(*str)) { - node *= 10; - node += (*str++ - '0'); - } - if (ISNUM(*str)) { - node *= 10; - node += (*str++ - '0'); - } - if (ISNUM(*str)) { - node *= 10; - node += (*str++ - '0'); - } - - if ((node > 1023) || (area > 63)) - return -1; - - if (INVALID_END_CHAR(*str)) - return -1; - - *addr = cpu_to_le16((area << 10) | node); - - return 0; -} - -static int dn_node_address_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - char addr[DN_ASCBUF_LEN]; - size_t len; - __le16 dnaddr; - - if (!*lenp || (*ppos && !write)) { - *lenp = 0; - return 0; - } - - if (write) { - len = (*lenp < DN_ASCBUF_LEN) ? *lenp : (DN_ASCBUF_LEN-1); - - if (copy_from_user(addr, buffer, len)) - return -EFAULT; - - addr[len] = 0; - strip_it(addr); - - if (parse_addr(&dnaddr, addr)) - return -EINVAL; - - dn_dev_devices_off(); - - decnet_address = dnaddr; - - dn_dev_devices_on(); - - *ppos += len; - - return 0; - } - - dn_addr2asc(le16_to_cpu(decnet_address), addr); - len = strlen(addr); - addr[len++] = '\n'; - - if (len > *lenp) len = *lenp; - - if (copy_to_user(buffer, addr, len)) - return -EFAULT; - - *lenp = len; - *ppos += len; - - return 0; -} - -static int dn_def_dev_handler(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - size_t len; - struct net_device *dev; - char devname[17]; - - if (!*lenp || (*ppos && !write)) { - *lenp = 0; - return 0; - } - - if (write) { - if (*lenp > 16) - return -E2BIG; - - if (copy_from_user(devname, buffer, *lenp)) - return -EFAULT; - - devname[*lenp] = 0; - strip_it(devname); - - dev = dev_get_by_name(&init_net, devname); - if (dev == NULL) - return -ENODEV; - - if (dev->dn_ptr == NULL) { - dev_put(dev); - return -ENODEV; - } - - if (dn_dev_set_default(dev, 1)) { - dev_put(dev); - return -ENODEV; - } - *ppos += *lenp; - - return 0; - } - - dev = dn_dev_get_default(); - if (dev == NULL) { - *lenp = 0; - return 0; - } - - strcpy(devname, dev->name); - dev_put(dev); - len = strlen(devname); - devname[len++] = '\n'; - - if (len > *lenp) len = *lenp; - - if (copy_to_user(buffer, devname, len)) - return -EFAULT; - - *lenp = len; - *ppos += len; - - return 0; -} - -static struct ctl_table dn_table[] = { - { - .procname = "node_address", - .maxlen = 7, - .mode = 0644, - .proc_handler = dn_node_address_handler, - }, - { - .procname = "node_name", - .data = node_name, - .maxlen = 7, - .mode = 0644, - .proc_handler = proc_dostring, - }, - { - .procname = "default_device", - .maxlen = 16, - .mode = 0644, - .proc_handler = dn_def_dev_handler, - }, - { - .procname = "time_wait", - .data = &decnet_time_wait, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_decnet_time_wait, - .extra2 = &max_decnet_time_wait - }, - { - .procname = "dn_count", - .data = &decnet_dn_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_state_count, - .extra2 = &max_state_count - }, - { - .procname = "di_count", - .data = &decnet_di_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_state_count, - .extra2 = &max_state_count - }, - { - .procname = "dr_count", - .data = &decnet_dr_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_state_count, - .extra2 = &max_state_count - }, - { - .procname = "dst_gc_interval", - .data = &decnet_dst_gc_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_decnet_dst_gc_interval, - .extra2 = &max_decnet_dst_gc_interval - }, - { - .procname = "no_fc_max_cwnd", - .data = &decnet_no_fc_max_cwnd, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_decnet_no_fc_max_cwnd, - .extra2 = &max_decnet_no_fc_max_cwnd - }, - { - .procname = "decnet_mem", - .data = &sysctl_decnet_mem, - .maxlen = sizeof(sysctl_decnet_mem), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax - }, - { - .procname = "decnet_rmem", - .data = &sysctl_decnet_rmem, - .maxlen = sizeof(sysctl_decnet_rmem), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "decnet_wmem", - .data = &sysctl_decnet_wmem, - .maxlen = sizeof(sysctl_decnet_wmem), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "debug", - .data = &decnet_debug_level, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { } -}; - -void dn_register_sysctl(void) -{ - dn_table_header = register_net_sysctl(&init_net, "net/decnet", dn_table); -} - -void dn_unregister_sysctl(void) -{ - unregister_net_sysctl_table(dn_table_header); -} - -#else /* CONFIG_SYSCTL */ -void dn_unregister_sysctl(void) -{ -} -void dn_register_sysctl(void) -{ -} - -#endif diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 4183e4ba27a5..81f620a3c32b 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -8,6 +8,7 @@ config NET_DSA tristate "Distributed Switch Architecture" depends on HAVE_NET_DSA && MAY_USE_DEVLINK depends on BRIDGE || BRIDGE=n + select GRO_CELLS select NET_SWITCHDEV select PHYLINK ---help--- diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 601534a5bfe8..598200e9d522 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -191,7 +191,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, if (dsa_skb_defer_rx_timestamp(p, skb)) return 0; - netif_receive_skb(skb); + gro_cells_receive(&p->gcells, skb); return 0; } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index b036c55f5cb1..05aadb25e294 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -261,6 +261,7 @@ static int dsa_port_setup(struct dsa_port *dp) int err = 0; memset(&dp->devlink_port, 0, sizeof(dp->devlink_port)); + dp->mac = of_get_mac_address(dp->dn); if (dp->type != DSA_PORT_TYPE_UNUSED) err = devlink_port_register(ds->devlink, &dp->devlink_port, @@ -595,6 +596,7 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) struct net_device *master; master = of_find_net_device_by_node(ethernet); + of_node_put(ethernet); if (!master) return -EPROBE_DEFER; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 3964c6f7a7c0..79d17507609a 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -15,6 +15,7 @@ #include <linux/netdevice.h> #include <linux/netpoll.h> #include <net/dsa.h> +#include <net/gro_cells.h> enum { DSA_NOTIFIER_AGEING_TIME, @@ -72,6 +73,8 @@ struct dsa_slave_priv { struct pcpu_sw_netstats *stats64; + struct gro_cells gcells; + /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; diff --git a/net/dsa/master.c b/net/dsa/master.c index aae478d61101..22e9ce6e51a4 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -87,8 +87,7 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, struct dsa_switch *ds = cpu_dp->ds; int port = cpu_dp->index; int len = ETH_GSTRING_LEN; - int mcount = 0, count; - unsigned int i; + int mcount = 0, count, i; uint8_t pfx[4]; uint8_t *ndata; @@ -118,6 +117,8 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, */ ds->ops->get_strings(ds, port, stringset, ndata); count = ds->ops->get_sset_count(ds, port, stringset); + if (count < 0) + return; for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 8ee28b6016d8..f7c122357a96 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -598,13 +598,15 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { - int count; + int count = 0; - count = 4; - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, dp->index, sset); + if (ds->ops->get_sset_count) { + count = ds->ops->get_sset_count(ds, dp->index, sset); + if (count < 0) + return count; + } - return count; + return count + 4; } return -EOPNOTSUPP; @@ -1224,13 +1226,11 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) * use the switch internal MDIO bus instead */ ret = dsa_slave_phy_connect(slave_dev, dp->index); - if (ret) { - netdev_err(slave_dev, - "failed to connect to port %d: %d\n", - dp->index, ret); - phylink_destroy(dp->pl); - return ret; - } + } + if (ret) { + netdev_err(slave_dev, "failed to connect to PHY: %pe\n", + ERR_PTR(ret)); + phylink_destroy(dp->pl); } return ret; @@ -1313,7 +1313,10 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->features = master->vlan_features | NETIF_F_HW_TC; slave_dev->hw_features |= NETIF_F_HW_TC; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; - eth_hw_addr_inherit(slave_dev, master); + if (port->mac && is_valid_ether_addr(port->mac)) + ether_addr_copy(slave_dev->dev_addr, port->mac); + else + eth_hw_addr_inherit(slave_dev, master); slave_dev->priv_flags |= IFF_NO_QUEUE; slave_dev->netdev_ops = &dsa_slave_netdev_ops; slave_dev->switchdev_ops = &dsa_slave_switchdev_ops; @@ -1334,6 +1337,11 @@ int dsa_slave_create(struct dsa_port *port) free_netdev(slave_dev); return -ENOMEM; } + + ret = gro_cells_init(&p->gcells, slave_dev); + if (ret) + goto out_free; + p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); p->xmit = cpu_dp->tag_ops->xmit; @@ -1344,7 +1352,7 @@ int dsa_slave_create(struct dsa_port *port) ret = dsa_slave_phy_setup(slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); - goto out_free; + goto out_gcells; } dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); @@ -1363,6 +1371,8 @@ out_phy: phylink_disconnect_phy(p->dp->pl); rtnl_unlock(); phylink_destroy(p->dp->pl); +out_gcells: + gro_cells_destroy(&p->gcells); out_free: free_percpu(p->stats64); free_netdev(slave_dev); @@ -1383,6 +1393,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); unregister_netdev(slave_dev); phylink_destroy(dp->pl); + gro_cells_destroy(&p->gcells); free_percpu(p->stats64); free_netdev(slave_dev); } diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 6574425ad94c..1f57dce969f7 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -20,6 +20,7 @@ #define MTK_HDR_LEN 4 #define MTK_HDR_XMIT_UNTAGGED 0 #define MTK_HDR_XMIT_TAGGED_TPID_8100 1 +#define MTK_HDR_XMIT_TAGGED_TPID_88A8 2 #define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) #define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0) #define MTK_HDR_XMIT_SA_DIS BIT(6) @@ -28,8 +29,8 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); + u8 xmit_tpid; u8 *mtk_tag; - bool is_vlan_skb = true; unsigned char *dest = eth_hdr(skb)->h_dest; bool is_multicast_skb = is_multicast_ether_addr(dest) && !is_broadcast_ether_addr(dest); @@ -40,13 +41,20 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, * the both special and VLAN tag at the same time and then look up VLAN * table with VID. */ - if (!skb_vlan_tagged(skb)) { + switch (skb->protocol) { + case htons(ETH_P_8021Q): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_8100; + break; + case htons(ETH_P_8021AD): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_88A8; + break; + default: if (skb_cow_head(skb, MTK_HDR_LEN) < 0) return NULL; + xmit_tpid = MTK_HDR_XMIT_UNTAGGED; skb_push(skb, MTK_HDR_LEN); memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN); - is_vlan_skb = false; } mtk_tag = skb->data + 2 * ETH_ALEN; @@ -54,8 +62,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, /* Mark tag attribute on special tag insertion to notify hardware * whether that's a combined special tag with 802.1Q header. */ - mtk_tag[0] = is_vlan_skb ? MTK_HDR_XMIT_TAGGED_TPID_8100 : - MTK_HDR_XMIT_UNTAGGED; + mtk_tag[0] = xmit_tpid; mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; /* Disable SA learning for multicast frames */ @@ -63,7 +70,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS; /* Tag control information is kept for 802.1Q */ - if (!is_vlan_skb) { + if (xmit_tpid == MTK_HDR_XMIT_UNTAGGED) { mtk_tag[2] = 0; mtk_tag[3] = 0; } diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 04b5450c5a55..adfb49760678 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -207,17 +207,18 @@ static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev, struct hsr_node *node_src) { bool was_multicast_frame; - int res; + int res, recv_len; was_multicast_frame = (skb->pkt_type == PACKET_MULTICAST); hsr_addr_subst_source(node_src, skb); skb_pull(skb, ETH_HLEN); + recv_len = skb->len; res = netif_rx(skb); if (res == NET_RX_DROP) { dev->stats.rx_dropped++; } else { dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->stats.rx_bytes += recv_len; if (was_multicast_frame) dev->stats.multicast++; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index f5a3601948ca..37795502bb51 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -310,7 +310,8 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, node_dst = find_node_by_AddrA(&port->hsr->node_db, eth_hdr(skb)->h_dest); if (!node_dst) { - WARN_ONCE(1, "%s: Unknown node\n", __func__); + if (net_ratelimit()) + netdev_err(skb->dev, "%s: Unknown node\n", __func__); return; } if (port->type != node_dst->AddrB_port) diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index d3cbb3258718..7531cb1665d2 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -559,9 +559,7 @@ ieee802154_llsec_parse_key_id(struct genl_info *info, desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]); if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) { - if (!info->attrs[IEEE802154_ATTR_PAN_ID] && - !(info->attrs[IEEE802154_ATTR_SHORT_ADDR] || - info->attrs[IEEE802154_ATTR_HW_ADDR])) + if (!info->attrs[IEEE802154_ATTR_PAN_ID]) return -EINVAL; desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]); @@ -570,6 +568,9 @@ ieee802154_llsec_parse_key_id(struct genl_info *info, desc->device_addr.mode = IEEE802154_ADDR_SHORT; desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]); } else { + if (!info->attrs[IEEE802154_ATTR_HW_ADDR]) + return -EINVAL; + desc->device_addr.mode = IEEE802154_ADDR_LONG; desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); } @@ -687,8 +688,10 @@ int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info) nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) || nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER, be32_to_cpu(params.frame_counter)) || - ieee802154_llsec_fill_key_id(msg, ¶ms.out_key)) + ieee802154_llsec_fill_key_id(msg, ¶ms.out_key)) { + rc = -ENOBUFS; goto out_free; + } dev_put(dev); diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index b231e40f006a..ca1dd9ff07ab 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -249,8 +249,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info) } if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || - nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name)) + nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name)) { + rc = -EMSGSIZE; goto nla_put_failure; + } dev_put(dev); wpan_phy_put(phy); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 99f6c254ea77..3407ee1159f7 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -836,8 +836,13 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, goto nla_put_failure; #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + goto out; + if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0) goto nla_put_failure; + +out: #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ genlmsg_end(msg, hdr); @@ -1310,19 +1315,20 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla, nl802154_dev_addr_policy, NULL)) return -EINVAL; - if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || - !attrs[NL802154_DEV_ADDR_ATTR_MODE] || - !(attrs[NL802154_DEV_ADDR_ATTR_SHORT] || - attrs[NL802154_DEV_ADDR_ATTR_EXTENDED])) + if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || !attrs[NL802154_DEV_ADDR_ATTR_MODE]) return -EINVAL; addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]); addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]); switch (addr->mode) { case NL802154_DEV_ADDR_SHORT: + if (!attrs[NL802154_DEV_ADDR_ATTR_SHORT]) + return -EINVAL; addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]); break; case NL802154_DEV_ADDR_EXTENDED: + if (!attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]) + return -EINVAL; addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]); break; default: @@ -1402,6 +1408,9 @@ static int nl802154_set_llsec_params(struct sk_buff *skb, u32 changed = 0; int ret; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (info->attrs[NL802154_ATTR_SEC_ENABLED]) { u8 enabled; @@ -1450,7 +1459,7 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1508,6 +1517,11 @@ nl802154_dump_llsec_key(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -1562,7 +1576,8 @@ static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info) struct ieee802154_llsec_key_id id = { }; u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { }; - if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX, + if (!info->attrs[NL802154_ATTR_SEC_KEY] || + nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; @@ -1612,7 +1627,8 @@ static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info) struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; struct ieee802154_llsec_key_id id; - if (nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX, + if (!info->attrs[NL802154_ATTR_SEC_KEY] || + nla_parse_nested(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; @@ -1634,7 +1650,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1678,6 +1694,11 @@ nl802154_dump_llsec_dev(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -1765,6 +1786,9 @@ static int nl802154_add_llsec_dev(struct sk_buff *skb, struct genl_info *info) struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_device dev_desc; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE], &dev_desc) < 0) return -EINVAL; @@ -1780,7 +1804,8 @@ static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info) struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; __le64 extended_addr; - if (nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX, + if (!info->attrs[NL802154_ATTR_SEC_DEVICE] || + nla_parse_nested(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack)) return -EINVAL; @@ -1803,7 +1828,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1850,6 +1875,11 @@ nl802154_dump_llsec_devkey(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -1907,6 +1937,9 @@ static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info struct ieee802154_llsec_device_key key; __le64 extended_addr; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], @@ -1940,7 +1973,8 @@ static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info struct ieee802154_llsec_device_key key; __le64 extended_addr; - if (nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX, + if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || + nla_parse_nested(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack)) return -EINVAL; @@ -1971,7 +2005,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -2015,6 +2049,11 @@ nl802154_dump_llsec_seclevel(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -2100,6 +2139,9 @@ static int nl802154_add_llsec_seclevel(struct sk_buff *skb, struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; @@ -2115,6 +2157,9 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (!info->attrs[NL802154_ATTR_SEC_LEVEL] || llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 89819745e482..ee1536de5fca 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -213,8 +213,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) int err = 0; struct net_device *dev = NULL; - if (len < sizeof(*uaddr)) - return -EINVAL; + err = ieee802154_sockaddr_check_size(uaddr, len); + if (err < 0) + return err; uaddr = (struct sockaddr_ieee802154 *)_uaddr; if (uaddr->family != AF_IEEE802154) @@ -284,6 +285,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) err = -EMSGSIZE; goto out_dev; } + if (!size) { + err = 0; + goto out_dev; + } hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; @@ -509,11 +514,14 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) ro->bound = 0; - if (len < sizeof(*addr)) + err = ieee802154_sockaddr_check_size(addr, len); + if (err < 0) goto out; - if (addr->family != AF_IEEE802154) + if (addr->family != AF_IEEE802154) { + err = -EINVAL; goto out; + } ieee802154_addr_from_sa(&haddr, &addr->addr); dev = ieee802154_get_dev(sock_net(sk), &haddr); @@ -580,8 +588,9 @@ static int dgram_connect(struct sock *sk, struct sockaddr *uaddr, struct dgram_sock *ro = dgram_sk(sk); int err = 0; - if (len < sizeof(*addr)) - return -EINVAL; + err = ieee802154_sockaddr_check_size(addr, len); + if (err < 0) + return err; if (addr->family != AF_IEEE802154) return -EINVAL; @@ -620,6 +629,7 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) struct ieee802154_mac_cb *cb; struct dgram_sock *ro = dgram_sk(sk); struct ieee802154_addr dst_addr; + DECLARE_SOCKADDR(struct sockaddr_ieee802154*, daddr, msg->msg_name); int hlen, tlen; int err; @@ -628,10 +638,20 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) return -EOPNOTSUPP; } - if (!ro->connected && !msg->msg_name) - return -EDESTADDRREQ; - else if (ro->connected && msg->msg_name) - return -EISCONN; + if (msg->msg_name) { + if (ro->connected) + return -EISCONN; + if (msg->msg_namelen < IEEE802154_MIN_NAMELEN) + return -EINVAL; + err = ieee802154_sockaddr_check_size(daddr, msg->msg_namelen); + if (err < 0) + return err; + ieee802154_addr_from_sa(&dst_addr, &daddr->addr); + } else { + if (!ro->connected) + return -EDESTADDRREQ; + dst_addr = ro->dst_addr; + } if (!ro->bound) dev = dev_getfirstbyhwtype(sock_net(sk), ARPHRD_IEEE802154); @@ -667,16 +687,6 @@ static int dgram_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) cb = mac_cb_init(skb); cb->type = IEEE802154_FC_TYPE_DATA; cb->ackreq = ro->want_ack; - - if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_ieee802154*, - daddr, msg->msg_name); - - ieee802154_addr_from_sa(&dst_addr, &daddr->addr); - } else { - dst_addr = ro->dst_addr; - } - cb->secen = ro->secen; cb->secen_override = ro->secen_override; cb->seclevel = ro->seclevel; @@ -1002,6 +1012,11 @@ static const struct proto_ops ieee802154_dgram_ops = { #endif }; +static void ieee802154_sock_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + /* Create a socket. Initialise the socket, blank the addresses * set the state. */ @@ -1042,7 +1057,7 @@ static int ieee802154_create(struct net *net, struct socket *sock, sock->ops = ops; sock_init_data(sock, sk); - /* FIXME: sk->sk_destruct */ + sk->sk_destruct = ieee802154_sock_destruct; sk->sk_family = PF_IEEE802154; /* Checksums on by default */ diff --git a/net/ife/ife.c b/net/ife/ife.c index 13bbf8cb6a39..be05b690b9ef 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -82,6 +82,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) if (unlikely(!pskb_may_pull(skb, total_pull))) return NULL; + ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len); skb_set_mac_header(skb, total_pull); __skb_pull(skb, total_pull); *metalen = ifehdrln - IFE_METAHDRLEN; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 2e12f848203a..8acfa1487478 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -388,6 +388,16 @@ config INET_IPCOMP If unsure, say Y. +config INET_TABLE_PERTURB_ORDER + int "INET: Source port perturbation table size (as power of 2)" if EXPERT + default 16 + help + Source port perturbation table size (as power of 2) for + RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm. + + The default is almost always what you want. + Only change this if you know what you are doing. + config INET_XFRM_TUNNEL tristate select INET_TUNNEL diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index bbf3b3daa999..7c902a1efbbf 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -157,7 +157,7 @@ void inet_sock_destruct(struct sock *sk) kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); - dst_release(sk->sk_rx_dst); + dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1)); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); @@ -218,7 +218,7 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { @@ -578,6 +578,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; + sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -593,6 +594,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; + sk->sk_wait_pending--; return timeo; } @@ -865,7 +867,7 @@ int inet_shutdown(struct socket *sock, int how) EPOLLHUP, even on eg. unconnected UDP sockets -- RR */ /* fall through */ default: - sk->sk_shutdown |= how; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | how); if (sk->sk_prot->shutdown) sk->sk_prot->shutdown(sk, how); break; @@ -1209,7 +1211,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) if (new_saddr == old_saddr) return 0; - if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } @@ -1264,7 +1266,7 @@ int inet_sk_rebuild_header(struct sock *sk) * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ - if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr || + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) @@ -1338,8 +1340,11 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, } ops = rcu_dereference(inet_offloads[proto]); - if (likely(ops && ops->callbacks.gso_segment)) + if (likely(ops && ops->callbacks.gso_segment)) { segs = ops->callbacks.gso_segment(skb, features); + if (!segs) + skb->network_header = skb_mac_header(skb) + nhoff - skb->head; + } if (IS_ERR_OR_NULL(segs)) goto out; @@ -1675,12 +1680,7 @@ static const struct net_protocol igmp_protocol = { }; #endif -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol tcp_protocol = { - .early_demux = tcp_v4_early_demux, - .early_demux_handler = tcp_v4_early_demux, +static const struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, @@ -1688,12 +1688,7 @@ static struct net_protocol tcp_protocol = { .icmp_strict_tag_validation = 1, }; -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol udp_protocol = { - .early_demux = udp_v4_early_demux, - .early_demux_handler = udp_v4_early_demux, +static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, @@ -1955,6 +1950,10 @@ static int __init inet_init(void) ip_init(); + /* Initialise per-cpu ipv4 mibs */ + if (init_ipv4_mibs()) + panic("%s: Cannot init ipv4 mibs\n", __func__); + /* Setup TCP slab cache for open requests. */ tcp_init(); @@ -1983,12 +1982,6 @@ static int __init inet_init(void) if (init_inet_pernet_ops()) pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__); - /* - * Initialise per-cpu ipv4 mibs - */ - - if (init_ipv4_mibs()) - pr_crit("%s: Cannot init ipv4 mibs\n", __func__); ipv4_proc_init(); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9e17cd05daff..0f2dac5c25bb 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1121,13 +1121,18 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) return err; } -static int arp_invalidate(struct net_device *dev, __be32 ip) +int arp_invalidate(struct net_device *dev, __be32 ip, bool force) { struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev); int err = -ENXIO; struct neigh_table *tbl = &arp_tbl; if (neigh) { + if ((neigh->nud_state & NUD_VALID) && !force) { + neigh_release(neigh); + return 0; + } + if (neigh->nud_state & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| @@ -1174,7 +1179,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r, if (!dev) return -EINVAL; } - return arp_invalidate(dev, ip); + return arp_invalidate(dev, ip, true); } /* diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 5535b722f66d..8dcf9aec7b77 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -254,7 +254,7 @@ static int cipso_v4_cache_check(const unsigned char *key, struct cipso_v4_map_cache_entry *prev_entry = NULL; u32 hash; - if (!cipso_v4_cache_enabled) + if (!READ_ONCE(cipso_v4_cache_enabled)) return -ENOENT; hash = cipso_v4_map_cache_hash(key, key_len); @@ -311,13 +311,14 @@ static int cipso_v4_cache_check(const unsigned char *key, int cipso_v4_cache_add(const unsigned char *cipso_ptr, const struct netlbl_lsm_secattr *secattr) { + int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize); int ret_val = -EPERM; u32 bkt; struct cipso_v4_map_cache_entry *entry = NULL; struct cipso_v4_map_cache_entry *old_entry = NULL; u32 cipso_ptr_len; - if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0) + if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0) return 0; cipso_ptr_len = cipso_ptr[1]; @@ -337,7 +338,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1); spin_lock_bh(&cipso_v4_cache[bkt].lock); - if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) { + if (cipso_v4_cache[bkt].size < bkt_size) { list_add(&entry->list, &cipso_v4_cache[bkt].list); cipso_v4_cache[bkt].size += 1; } else { @@ -486,6 +487,7 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) kfree(doi_def->map.std->lvl.local); kfree(doi_def->map.std->cat.cipso); kfree(doi_def->map.std->cat.local); + kfree(doi_def->map.std); break; } kfree(doi_def); @@ -533,16 +535,10 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!refcount_dec_and_test(&doi_def->refcount)) { - spin_unlock(&cipso_v4_doi_list_lock); - ret_val = -EBUSY; - goto doi_remove_return; - } list_del_rcu(&doi_def->list); spin_unlock(&cipso_v4_doi_list_lock); - cipso_v4_cache_invalidate(); - call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu); + cipso_v4_doi_putdef(doi_def); ret_val = 0; doi_remove_return: @@ -599,9 +595,6 @@ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) if (!refcount_dec_and_test(&doi_def->refcount)) return; - spin_lock(&cipso_v4_doi_list_lock); - list_del_rcu(&doi_def->list); - spin_unlock(&cipso_v4_doi_list_lock); cipso_v4_cache_invalidate(); call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu); @@ -1222,7 +1215,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def, /* This will send packets using the "optimized" format when * possible as specified in section 3.4.2.6 of the * CIPSO draft. */ - if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10) + if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 && + ret_val <= 10) tag_len = 14; else tag_len = 4 + ret_val; @@ -1625,7 +1619,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) * all the CIPSO validations here but it doesn't * really specify _exactly_ what we need to validate * ... so, just make it a sysctl tunable. */ - if (cipso_v4_rbm_strictvalid) { + if (READ_ONCE(cipso_v4_rbm_strictvalid)) { if (cipso_v4_map_lvl_valid(doi_def, tag[3]) < 0) { err_offset = opt_iter + 3; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 12a2cea9d606..e2ab8cdb7134 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2354,7 +2354,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, free: kfree(t); out: - return -ENOBUFS; + return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 114f9def1ec5..24cd5c9c7839 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -270,7 +270,6 @@ static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struc int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { u8 *tail; - u8 *vaddr; int nfrags; int esph_offset; struct page *page; @@ -285,6 +284,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * return err; } + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) + goto cow; + if (!skb_cloned(skb)) { if (tailen <= skb_tailroom(skb)) { nfrags = 1; @@ -312,14 +315,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * page = pfrag->page; get_page(page); - vaddr = kmap_atomic(page); - - tail = vaddr + pfrag->offset; + tail = page_address(page) + pfrag->offset; esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto); - kunmap_atomic(vaddr); - nfrags = skb_shinfo(skb)->nr_frags; __skb_fill_page_desc(skb, nfrags, page, pfrag->offset, @@ -566,7 +565,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 58834a10c0be..93045373e44b 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -237,6 +237,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ secpath_reset(skb); + if (skb_needs_linearize(skb, skb->dev->features) && + __skb_linearize(skb)) + return -ENOMEM; return 0; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7f4ec36e5f70..9aa48b4c4096 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -302,7 +302,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, - .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), + .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; @@ -353,6 +353,8 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; + } else { + swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) @@ -555,6 +557,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, cfg->fc_scope = RT_SCOPE_UNIVERSE; } + if (!cfg->fc_table) + cfg->fc_table = RT_TABLE_MAIN; + if (cmd == SIOCDELRT) return 0; @@ -915,9 +920,11 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) return; /* Add broadcast address, if it is explicitly assigned. */ - if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) + if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); + arp_invalidate(dev, ifa->ifa_broadcast, false); + } if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { @@ -933,6 +940,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) prim, 0); fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); + arp_invalidate(dev, prefix | ~mask, false); } } } diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index ad9ea82daeb3..9376b30cf626 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -133,7 +133,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, * to 0 and sets the configured key in the * inner erspan header field */ - if (greh->protocol == htons(ETH_P_ERSPAN) || + if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) || greh->protocol == htons(ETH_P_ERSPAN2)) { struct erspan_base_hdr *ershdr; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 4efa5e33513e..af0ddaa55e43 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -244,7 +244,7 @@ static struct { /** * icmp_global_allow - Are we allowed to send one more ICMP message ? * - * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec. + * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. * Note: called with BH disabled */ @@ -266,13 +266,17 @@ bool icmp_global_allow(void) spin_lock(&icmp_global.lock); delta = min_t(u32, now - icmp_global.stamp, HZ); if (delta >= HZ / 50) { - incr = sysctl_icmp_msgs_per_sec * delta / HZ ; + incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ; if (incr) WRITE_ONCE(icmp_global.stamp, now); } - credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); + credit = min_t(u32, icmp_global.credit + incr, + READ_ONCE(sysctl_icmp_msgs_burst)); if (credit) { - credit--; + /* We want to use a credit of one in average, but need to randomize + * it for security reasons. + */ + credit = max_t(int, credit - prandom_u32_max(3), 0); rc = true; } WRITE_ONCE(icmp_global.credit, credit); @@ -291,7 +295,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code) return true; /* Limit if icmp type is enabled in ratemask. */ - if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask)) + if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask))) return true; return false; @@ -329,7 +333,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, vif = l3mdev_master_ifindex(dst->dev); peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); - rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); + rc = inet_peer_xrlim_allow(peer, + READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); if (peer) inet_putpeer(peer); out: @@ -462,6 +467,23 @@ out_bh_enable: local_bh_enable(); } +/* + * The device used for looking up which routing table to use for sending an ICMP + * error is preferably the source whenever it is set, which should ensure the + * icmp error can be sent to the source host, else lookup using the routing + * table of the destination device, else use the main routing table (index 0). + */ +static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb) +{ + struct net_device *route_lookup_dev = NULL; + + if (skb->dev) + route_lookup_dev = skb->dev; + else if (skb_dst(skb)) + route_lookup_dev = skb_dst(skb)->dev; + return route_lookup_dev; +} + static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, struct sk_buff *skb_in, @@ -470,6 +492,7 @@ static struct rtable *icmp_route_lookup(struct net *net, int type, int code, struct icmp_bxm *param) { + struct net_device *route_lookup_dev; struct rtable *rt, *rt2; struct flowi4 fl4_dec; int err; @@ -484,7 +507,8 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev); + route_lookup_dev = icmp_get_route_lookup_dev(skb_in); + fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = ip_route_output_key_hash(net, fl4, skb_in); @@ -508,7 +532,7 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev, + if (inet_addr_type_dev_table(net, route_lookup_dev, fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) @@ -735,12 +759,24 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, room = 576; room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen; room -= sizeof(struct icmphdr); + /* Guard against tiny mtu. We need to include at least one + * IP network header for this message to make any sense. + */ + if (room <= (int)sizeof(struct iphdr)) + goto ende; icmp_param.data_len = skb_in->len - icmp_param.offset; if (icmp_param.data_len > room) icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); + /* if we don't have a source address at this point, fall back to the + * dummy address instead of sending out a packet with a source address + * of 0.0.0.0 + */ + if (!fl4.saddr) + fl4.saddr = htonl(INADDR_DUMMY); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); @@ -752,6 +788,40 @@ out:; } EXPORT_SYMBOL(__icmp_send); +#if IS_ENABLED(CONFIG_NF_NAT) +#include <net/netfilter/nf_conntrack.h> +void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + struct sk_buff *cloned_skb = NULL; + struct ip_options opts = { 0 }; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + __be32 orig_ip; + + ct = nf_ct_get(skb_in, &ctinfo); + if (!ct || !(ct->status & IPS_SRC_NAT)) { + __icmp_send(skb_in, type, code, info, &opts); + return; + } + + if (skb_shared(skb_in)) + skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); + + if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || + (skb_network_header(skb_in) + sizeof(struct iphdr)) > + skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, + skb_network_offset(skb_in) + sizeof(struct iphdr)))) + goto out; + + orig_ip = ip_hdr(skb_in)->saddr; + ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; + __icmp_send(skb_in, type, code, info, &opts); + ip_hdr(skb_in)->saddr = orig_ip; +out: + consume_skb(cloned_skb); +} +EXPORT_SYMBOL(icmp_ndo_send); +#endif static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 523d26f5e22e..5edf426fa414 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -221,8 +221,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) int tv = prandom_u32() % max_delay; im->tm_running = 1; - if (!mod_timer(&im->timer, jiffies+tv+2)) - refcount_inc(&im->refcnt); + if (refcount_inc_not_zero(&im->refcnt)) { + if (mod_timer(&im->timer, jiffies + tv + 2)) + ip_ma_put(im); + } } static void igmp_gq_start_timer(struct in_device *in_dev) @@ -357,8 +359,9 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - unsigned int size = mtu; + unsigned int size; + size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); @@ -471,7 +474,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; - if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(pmc->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); @@ -597,7 +601,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -740,7 +744,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) @@ -807,10 +812,17 @@ static void igmp_gq_timer_expire(struct timer_list *t) static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); + u32 mr_ifc_count; igmpv3_send_cr(in_dev); - if (in_dev->mr_ifc_count) { - in_dev->mr_ifc_count--; +restart: + mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); + + if (mr_ifc_count) { + if (cmpxchg(&in_dev->mr_ifc_count, + mr_ifc_count, + mr_ifc_count - 1) != mr_ifc_count) + goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } @@ -822,7 +834,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } @@ -917,7 +929,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return false; - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); @@ -961,7 +974,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, in_dev->mr_qri; } /* cancel the interface change timer */ - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ @@ -1003,7 +1016,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * received value was zero, use the default or statically * configured value. */ - in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: @@ -1042,7 +1055,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) @@ -1182,7 +1195,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; @@ -1233,9 +1246,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) - psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); @@ -1292,7 +1307,8 @@ static void igmp_group_dropped(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; @@ -1329,13 +1345,14 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; - im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; + im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); @@ -1349,7 +1366,7 @@ static void igmp_group_added(struct ip_mc_list *im) * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif @@ -1650,7 +1667,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches @@ -1739,7 +1756,7 @@ void ip_mc_down(struct in_device *in_dev) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST - in_dev->mr_ifc_count = 0; + WRITE_ONCE(in_dev->mr_ifc_count, 0); if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; @@ -1757,7 +1774,7 @@ static void ip_mc_reset(struct in_device *in_dev) in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) @@ -1816,6 +1833,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; + ip_mc_clear_src(i); ip_ma_put(i); } } @@ -1890,7 +1908,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; @@ -1954,8 +1972,8 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); @@ -2133,8 +2151,8 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - in_dev->mr_ifc_count = pmc->crcount; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); + WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); @@ -2199,7 +2217,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, count++; } err = -ENOBUFS; - if (count >= net->ipv4.sysctl_igmp_max_memberships) + if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) @@ -2408,9 +2426,10 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ @@ -2508,11 +2527,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); - kfree_rcu(psl, rcu); - } else + } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); + } rcu_assign_pointer(pmc->sflist, newpsl); + if (psl) + kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: @@ -2735,6 +2756,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u rv = 1; } else if (im) { if (src_addr) { + spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; @@ -2745,6 +2767,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; + spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 534e2598981d..7392a744c677 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -698,12 +698,15 @@ static bool reqsk_queue_unlink(struct request_sock_queue *queue, return found; } -void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { - if (reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req)) { + bool unlinked = reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req); + + if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } + return unlinked; } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); @@ -790,7 +793,7 @@ static void reqsk_queue_hash_req(struct request_sock *req, timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL); + inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ @@ -823,6 +826,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); + newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; @@ -900,11 +904,25 @@ void inet_csk_prepare_forced_close(struct sock *sk) } EXPORT_SYMBOL(inet_csk_prepare_forced_close); +static int inet_ulp_can_listen(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + if (icsk->icsk_ulp_ops) + return -EINVAL; + + return 0; +} + int inet_csk_listen_start(struct sock *sk, int backlog) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - int err = -EADDRINUSE; + int err; + + err = inet_ulp_can_listen(sk); + if (unlikely(err)) + return err; reqsk_queue_alloc(&icsk->icsk_accept_queue); @@ -917,6 +935,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog) * It is OK, because this socket enters to hash table only * after validation is complete. */ + err = -EADDRINUSE; inet_sk_state_store(sk, TCP_LISTEN); if (!sk->sk_prot->get_port(sk, inet->inet_num)) { inet->inet_sport = htons(inet->inet_num); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f0957ebf82cf..d07917059d70 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -392,8 +392,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, r->idiag_inode = 0; if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, - inet_rsk(reqsk)->ir_mark)) + inet_rsk(reqsk)->ir_mark)) { + nlmsg_cancel(skb, nlh); return -EMSGSIZE; + } nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3a5f12f011cb..c6d670cd872f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -24,6 +24,9 @@ #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/inet6_hashtables.h> +#endif #include <net/secure_seq.h> #include <net/ip.h> #include <net/tcp.h> @@ -504,7 +507,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet_sk_port_offset(const struct sock *sk) +static u64 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -513,10 +516,52 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -/* insert a socket into ehash, and eventually remove another one - * (The another one can be a SYN_RECV or TIMEWAIT +/* Searches for an exsiting socket in the ehash bucket list. + * Returns true if found, false otherwise. + */ +static bool inet_ehash_lookup_by_sk(struct sock *sk, + struct hlist_nulls_head *list) +{ + const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num); + const int sdif = sk->sk_bound_dev_if; + const int dif = sk->sk_bound_dev_if; + const struct hlist_nulls_node *node; + struct net *net = sock_net(sk); + struct sock *esk; + + INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr); + + sk_nulls_for_each_rcu(esk, node, list) { + if (esk->sk_hash != sk->sk_hash) + continue; + if (sk->sk_family == AF_INET) { + if (unlikely(INET_MATCH(esk, net, acookie, + sk->sk_daddr, + sk->sk_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#if IS_ENABLED(CONFIG_IPV6) + else if (sk->sk_family == AF_INET6) { + if (unlikely(INET6_MATCH(esk, net, + &sk->sk_v6_daddr, + &sk->sk_v6_rcv_saddr, + ports, dif, sdif))) { + return true; + } + } +#endif + } + return false; +} + +/* Insert a socket into ehash, and eventually remove another one + * (The another one can be a SYN_RECV or TIMEWAIT) + * If an existing socket already exists, socket sk is not inserted, + * and sets found_dup_sk parameter to true. */ -bool inet_ehash_insert(struct sock *sk, struct sock *osk) +bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; @@ -535,16 +580,23 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk) if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { + *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); + if (*found_dup_sk) + ret = false; } + if (ret) __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); + return ret; } -bool inet_ehash_nolisten(struct sock *sk, struct sock *osk) +bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk) { - bool ok = inet_ehash_insert(sk, osk); + bool ok = inet_ehash_insert(sk, osk, found_dup_sk); if (ok) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -588,7 +640,7 @@ int __inet_hash(struct sock *sk, struct sock *osk) int err = 0; if (sk->sk_state != TCP_LISTEN) { - inet_ehash_nolisten(sk, osk); + inet_ehash_nolisten(sk, osk, NULL); return 0; } WARN_ON(!sk_unhashed(sk)); @@ -662,8 +714,21 @@ unlock: } EXPORT_SYMBOL_GPL(inet_unhash); +/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm + * Note that we use 32bit integers (vs RFC 'short integers') + * because 2^16 is not a multiple of num_ephemeral and this + * property might be used by clever attacker. + * + * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though + * attacks were since demonstrated, thus we use 65536 by default instead + * to really give more isolation and privacy, at the expense of 256kB + * of kernel memory. + */ +#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER) +static u32 *table_perturb; + int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)) { @@ -675,20 +740,10 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; u32 remaining, offset; int ret, i, low, high; - static u32 hint; + u32 index; if (port) { - head = &hinfo->bhash[inet_bhashfn(net, port, - hinfo->bhash_size)]; - tb = inet_csk(sk)->icsk_bind_hash; - spin_lock_bh(&head->lock); - if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) { - inet_ehash_nolisten(sk, NULL); - spin_unlock_bh(&head->lock); - return 0; - } - spin_unlock(&head->lock); - /* No definite answer... Walk to established hash table */ + local_bh_disable(); ret = check_established(death_row, sk, port, NULL); local_bh_enable(); return ret; @@ -700,7 +755,13 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U; - offset = (hint + port_offset) % remaining; + get_random_slow_once(table_perturb, + INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); + index = port_offset & (INET_TABLE_PERTURB_SIZE - 1); + + offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32); + offset %= remaining; + /* In first pass we try ports of @low parity. * inet_csk_get_port() does the opposite choice. */ @@ -753,13 +814,19 @@ next_port: return -EADDRNOTAVAIL; ok: - hint += i + 2; + /* Here we want to add a little bit of randomness to the next source + * port that will be chosen. We use a max() with a random here so that + * on low contention the randomness is maximal and on high contention + * it may be inexistent. + */ + i = max_t(int, i, (prandom_u32() & 7) * 2); + WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - inet_ehash_nolisten(sk, (struct sock *)tw); + inet_ehash_nolisten(sk, (struct sock *)tw, NULL); } if (tw) inet_twsk_bind_unhash(tw, hinfo); @@ -776,7 +843,7 @@ ok: int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet_sk_port_offset(sk); @@ -822,6 +889,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, INIT_HLIST_HEAD(&h->lhash2[i].head); h->lhash2[i].count = 0; } + + /* this one is used for source ports of outgoing connections */ + table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE, + sizeof(*table_perturb), GFP_KERNEL); + if (!table_perturb) + panic("TCP: failed to alloc table_perturb"); } int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index ff327a62c9ce..a18668552d33 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -148,16 +148,20 @@ static void inet_peer_gc(struct inet_peer_base *base, struct inet_peer *gc_stack[], unsigned int gc_cnt) { + int peer_threshold, peer_maxttl, peer_minttl; struct inet_peer *p; __u32 delta, ttl; int i; - if (base->total >= inet_peer_threshold) + peer_threshold = READ_ONCE(inet_peer_threshold); + peer_maxttl = READ_ONCE(inet_peer_maxttl); + peer_minttl = READ_ONCE(inet_peer_minttl); + + if (base->total >= peer_threshold) ttl = 0; /* be aggressive */ else - ttl = inet_peer_maxttl - - (inet_peer_maxttl - inet_peer_minttl) / HZ * - base->total / inet_peer_threshold * HZ; + ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ * + base->total / peer_threshold * HZ; for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ffcb5983107d..38c8db78cda1 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -435,14 +435,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, - tunnel->parms.o_flags, proto, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + flags, proto, tunnel->parms.o_key, + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -548,7 +546,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -576,7 +574,6 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) int tunnel_hlen; int version; int nhoff; - int thoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -606,15 +603,21 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) truncate = true; } - nhoff = skb_network_header(skb) - skb_mac_header(skb); + nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; - thoff = skb_transport_header(skb) - skb_mac_header(skb); - if (skb->protocol == htons(ETH_P_IPV6) && - (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) - truncate = true; + if (skb->protocol == htons(ETH_P_IPV6)) { + int thoff; + + if (skb_transport_header_was_set(skb)) + thoff = skb_transport_offset(skb); + else + thoff = nhoff + sizeof(struct ipv6hdr); + if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) + truncate = true; + } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), @@ -632,7 +635,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -680,18 +683,23 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { - /* Need space for new headers */ - if (skb_cow_head(skb, dev->needed_headroom - - (tunnel->hlen + sizeof(struct iphdr)))) + int pull_len = tunnel->hlen + sizeof(struct iphdr); + + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing - * to gre header. - */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + if (!pskb_network_may_pull(skb, pull_len)) + goto free_skb; + + /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ + skb_pull(skb, pull_len); skb_reset_mac_header(skb); + + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start(skb) < skb->data) + goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; @@ -800,7 +808,11 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu) len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; - dev->needed_headroom = dev->needed_headroom + len; + if (dev->header_ops) + dev->hard_header_len += len; + else + dev->needed_headroom += len; + if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); @@ -1003,6 +1015,7 @@ static void __gre_tunnel_init(struct net_device *dev) tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; + dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; @@ -1046,10 +1059,14 @@ static int ipgre_tunnel_init(struct net_device *dev) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; + dev->hard_header_len = tunnel->hlen + sizeof(*iph); + dev->needed_headroom = 0; } return ip_tunnel_init(dev); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index c3a0683e83df..7ead5192b2a9 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -306,28 +306,38 @@ drop: return true; } +int udp_v4_early_demux(struct sk_buff *); +int tcp_v4_early_demux(struct sk_buff *); static int ip_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); - int (*edemux)(struct sk_buff *skb); struct rtable *rt; int err; - if (net->ipv4.sysctl_ip_early_demux && + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && !ip_is_fragment(iph)) { - const struct net_protocol *ipprot; - int protocol = iph->protocol; + switch (iph->protocol) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) { + tcp_v4_early_demux(skb); - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - err = edemux(skb); - if (unlikely(err)) - goto drop_error; - /* must reload iph, skb->head might have changed */ - iph = ip_hdr(skb); + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { + err = udp_v4_early_demux(skb); + if (unlikely(err)) + goto drop_error; + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f0faf1193dd8..6936f703758b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -160,12 +160,19 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - if (ip_dont_fragment(sk, &rt->dst)) { + /* Do not bother generating IPID for small packets (eg SYNACK) */ + if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; - __ip_select_ident(net, iph, 1); + /* TCP packets here are SYNACK with fat IPv4/TCP options. + * Avoid using the hashed IP ident generator. + */ + if (sk->sk_protocol == IPPROTO_TCP) + iph->id = (__force __be16)prandom_u32(); + else + __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { @@ -214,7 +221,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); - if (res < 0 || res == LWTUNNEL_XMIT_DONE) + if (res != LWTUNNEL_XMIT_CONTINUE) return res; } @@ -312,7 +319,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); - if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU)) + if (skb->len > mtu || IPCB(skb)->frag_max_size) return ip_fragment(net, sk, skb, mtu, ip_finish_output2); return ip_finish_output2(net, sk, skb); @@ -419,8 +426,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) { BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); - memcpy(&iph->saddr, &fl4->saddr, - sizeof(fl4->saddr) + sizeof(fl4->daddr)); + + iph->saddr = fl4->saddr; + iph->daddr = fl4->daddr; } /* Note: skb->sk can be different from sk, in case of tunnels */ @@ -940,7 +948,7 @@ static int __ip_append_data(struct sock *sk, unsigned int datalen; unsigned int fraglen; unsigned int fraggap; - unsigned int alloclen; + unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: @@ -960,35 +968,39 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; pagedlen = 0; + alloc_extra = hh_len + 15; + alloc_extra += exthdrlen; + + /* The last fragment gets additional space at tail. + * Note, with MSG_MORE we overallocate on fragments, + * because we have no idea what fragment will be + * the last. + */ + if (datalen == length + fraggap) + alloc_extra += rt->dst.trailer_len; + if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else if (!paged) + else if (!paged && + (fraglen + alloc_extra < SKB_MAX_ALLOC || + !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } - alloclen += exthdrlen; - - /* The last fragment gets additional space at tail. - * Note, with MSG_MORE we overallocate on fragments, - * because we have no idea what fragment will be - * the last. - */ - if (datalen == length + fraggap) - alloclen += rt->dst.trailer_len; + alloclen += alloc_extra; if (transhdrlen) { - skb = sock_alloc_send_skb(sk, - alloclen + hh_len + 15, + skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = alloc_skb(alloclen + hh_len + 15, + skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; @@ -1431,9 +1443,19 @@ struct sk_buff *__ip_make_skb(struct sock *sk, cork->dst = NULL; skb_dst_set(skb, &rt->dst); - if (iph->protocol == IPPROTO_ICMP) - icmp_out_count(net, ((struct icmphdr *) - skb_transport_header(skb))->type); + if (iph->protocol == IPPROTO_ICMP) { + u8 icmp_type; + + /* For such sockets, transhdrlen is zero when do ip_append_data(), + * so icmphdr does not in skb linear region and can not get icmp_type + * by icmp_hdr(skb)->type. + */ + if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + icmp_type = fl4->fl4_icmp_type; + else + icmp_type = icmp_hdr(skb)->type; + icmp_out_count(net, icmp_type); + } ip_cork_release(cork); out: diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 82f341e84fae..fbf39077fc54 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -316,7 +316,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1522,6 +1529,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MINTTL: val = inet->min_ttl; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 375d0e516d85..9c2381cf675d 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -330,7 +330,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) } dev->needed_headroom = t_hlen + hlen; - mtu -= (dev->hard_header_len + t_hlen); + mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0); if (mtu < IPV4_MIN_MTU) mtu = IPV4_MIN_MTU; @@ -360,7 +360,10 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, nt = netdev_priv(dev); t_hlen = nt->hlen + sizeof(struct iphdr); dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; + dev->max_mtu = IP_MAX_MTU - t_hlen; + if (dev->type == ARPHRD_ETHER) + dev->max_mtu -= dev->hard_header_len; + ip_tunnel_add(itn, nt); return nt; @@ -502,14 +505,18 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, const struct iphdr *inner_iph) { struct ip_tunnel *tunnel = netdev_priv(dev); - int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len; + int pkt_size; int mtu; - if (df) - mtu = dst_mtu(&rt->dst) - dev->hard_header_len - - sizeof(struct iphdr) - tunnel->hlen; - else + pkt_size = skb->len - tunnel->hlen; + pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; + + if (df) { + mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel->hlen); + mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0; + } else { mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; + } skb_dst_update_pmtu_no_confirm(skb, mtu); @@ -602,10 +609,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) else if (skb->protocol == htons(ETH_P_IP)) df = inner_iph->frag_off & htons(IP_DF); headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > dev->needed_headroom) - dev->needed_headroom = headroom; + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); goto tx_dropped; } @@ -736,7 +743,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) { + df = tnl_params->frag_off; + if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df) + df |= (inner_iph->frag_off & htons(IP_DF)); + + if (tnl_update_pmtu(dev, skb, rt, df, inner_iph)) { ip_rt_put(rt); goto tx_error; } @@ -764,16 +775,12 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ttl = ip4_dst_hoplimit(&rt->dst); } - df = tnl_params->frag_off; - if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df) - df |= (inner_iph->frag_off&htons(IP_DF)); - max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); @@ -935,7 +942,10 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); - int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen; + int max_mtu = IP_MAX_MTU - t_hlen; + + if (dev->type == ARPHRD_ETHER) + max_mtu -= dev->hard_header_len; if (new_mtu < ETH_MIN_MTU) return -EINVAL; @@ -1112,10 +1122,12 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], mtu = ip_tunnel_bind_dev(dev); if (tb[IFLA_MTU]) { - unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen; + unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr)); + + if (dev->type == ARPHRD_ETHER) + max -= dev->hard_header_len; - mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, - (unsigned int)(max - sizeof(struct iphdr))); + mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max); } err = dev_set_mtu(dev, mtu); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 15c71b08c2df..a3536dfe9b16 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -319,12 +319,12 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; default: goto tx_err; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 88212615bf4c..58719b9635d9 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -866,7 +866,7 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d /* - * Copy BOOTP-supplied string if not already set. + * Copy BOOTP-supplied string */ static int __init ic_bootp_string(char *dest, char *src, int len, int max) { @@ -915,12 +915,15 @@ static void __init ic_do_bootp_ext(u8 *ext) } break; case 12: /* Host name */ - ic_bootp_string(utsname()->nodename, ext+1, *ext, - __NEW_UTS_LEN); - ic_host_name_set = 1; + if (!ic_host_name_set) { + ic_bootp_string(utsname()->nodename, ext+1, *ext, + __NEW_UTS_LEN); + ic_host_name_set = 1; + } break; case 15: /* Domain name (DNS) */ - ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); + if (!ic_domain[0]) + ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); break; case 17: /* Root path */ if (!root_server_path[0]) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index d235478d9ca3..2085af224a41 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -265,7 +265,9 @@ static int __net_init ipmr_rules_init(struct net *net) return 0; err2: + rtnl_lock(); ipmr_free_table(mrt); + rtnl_unlock(); err1: fib_rules_unregister(ops); return err; diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 04311f7067e2..9a6b01d85cd0 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -1,4 +1,5 @@ #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/ip.h> @@ -24,6 +25,7 @@ int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, if (type > RTAX_MAX) return -EINVAL; + type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 8d2e5dc9a827..3d670d5aea34 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,17 +17,19 @@ #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type) +int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; - const struct sock *sk = skb_to_full_sk(skb); - __u8 flags = sk ? inet_sk_flowi_flags(sk) : 0; + __u8 flags; struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; + sk = sk_to_full_sk(sk); + flags = sk ? inet_sk_flowi_flags(sk) : 0; + if (addr_type == RTN_UNSPEC) addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) @@ -91,8 +93,8 @@ int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, skb, - RTN_UNSPEC); + return ip_route_me_harder(entry->state.net, entry->state.sk, + skb, RTN_UNSPEC); } return 0; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 10d8f95eb771..fba56cd95896 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1195,6 +1195,8 @@ static int translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e77872c93c20..730a40dc829a 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1433,6 +1433,8 @@ translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 2fa196325988..954c96f4ddd0 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -509,8 +509,11 @@ static int clusterip_tg_check(const struct xt_tgchk_param *par) if (IS_ERR(config)) return PTR_ERR(config); } - } else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN)) + } else if (memcmp(&config->clustermac, &cipinfo->clustermac, ETH_ALEN)) { + clusterip_config_entry_put(config); + clusterip_config_put(config); return -EINVAL; + } ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) { diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 690b17ef6a44..d64b1ef43c10 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -54,7 +54,7 @@ synproxy_send_tcp(struct net *net, skb_dst_set_noref(nskb, skb_dst(skb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; if (nfct) { diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 74b19a5c572e..088320ce77a1 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -94,7 +94,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - flow.flowi4_tos = RT_TOS(iph->tos); + flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par)); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index dea138ca8925..0829f46ddfdd 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -65,7 +65,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c index df5c2a2061a4..19fff2c589fa 100644 --- a/net/ipv4/netfilter/nf_log_arp.c +++ b/net/ipv4/netfilter/nf_log_arp.c @@ -46,16 +46,31 @@ static void dump_arp_packet(struct nf_log_buf *m, const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int nhoff) { - const struct arphdr *ah; - struct arphdr _arph; const struct arppayload *ap; struct arppayload _arpp; + const struct arphdr *ah; + unsigned int logflags; + struct arphdr _arph; ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL) { nf_log_buf_add(m, "TRUNCATED"); return; } + + if (info->type == NF_LOG_TYPE_LOG) + logflags = info->u.log.logflags; + else + logflags = NF_LOG_DEFAULT_MASK; + + if (logflags & NF_LOG_MACDECODE) { + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); + } + nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d", ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op)); diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c index 1e6f28c97d3a..cde1918607e9 100644 --- a/net/ipv4/netfilter/nf_log_ipv4.c +++ b/net/ipv4/netfilter/nf_log_ipv4.c @@ -287,8 +287,10 @@ static void dump_ipv4_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", ntohs(eth_hdr(skb)->h_proto)); return; default: diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 6115bf1ff6f0..6a27766b7d0f 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -329,7 +329,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 5cd06ba3535d..4996db1f64a1 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -129,7 +129,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC)) goto free_nskb; niph = ip_hdr(nskb); diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c index 4824b1e183a1..bff2b85c5fd6 100644 --- a/net/ipv4/netfilter/nf_socket_ipv4.c +++ b/net/ipv4/netfilter/nf_socket_ipv4.c @@ -96,11 +96,11 @@ nf_socket_get_sock_v4(struct net *net, struct sk_buff *skb, const int doff, struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb, const struct net_device *indev) { - __be32 uninitialized_var(daddr), uninitialized_var(saddr); - __be16 uninitialized_var(dport), uninitialized_var(sport); + __be32 daddr, saddr; + __be16 dport, sport; const struct iphdr *iph = ip_hdr(skb); struct sk_buff *data_skb = NULL; - u8 uninitialized_var(protocol); + u8 protocol; #if IS_ENABLED(CONFIG_NF_CONNTRACK) enum ip_conntrack_info ctinfo; struct nf_conn const *ct; diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index 7d82934c46f4..61003768e52b 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -50,7 +50,7 @@ static unsigned int nf_route_table_hook(void *priv, iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index 0af3d8df70dd..157bca240edc 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -16,8 +16,8 @@ #include <net/netfilter/ipv4/nf_dup_ipv4.h> struct nft_dup_ipv4 { - enum nft_registers sreg_addr:8; - enum nft_registers sreg_dev:8; + u8 sreg_addr; + u8 sreg_dev; }; static void nft_dup_ipv4_eval(const struct nft_expr *expr, @@ -43,16 +43,16 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); - err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr)); + err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + sizeof(struct in_addr)); if (err < 0) return err; - if (tb[NFTA_DUP_SREG_DEV] != NULL) { - priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); - } - return 0; + if (tb[NFTA_DUP_SREG_DEV]) + err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + &priv->sreg_dev, sizeof(int)); + + return err; } static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index e50976e3c213..3b2e8ac45d4e 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -95,6 +95,9 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, else oif = NULL; + if (priv->flags & NFTA_FIB_F_IIF) + fl4.flowi4_oif = l3mdev_master_ifindex_rcu(oif); + if (nft_hook(pkt) == NF_INET_PRE_ROUTING && nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { nft_fib_store_result(dest, priv, pkt, diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index c59144502ee8..2e7abad48d83 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -177,16 +177,22 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) struct sock *sk = NULL; struct inet_sock *isk; struct hlist_nulls_node *hnode; - int dif = skb->dev->ifindex; + int dif, sdif; if (skb->protocol == htons(ETH_P_IP)) { + dif = inet_iif(skb); + sdif = inet_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", (int)ident, &ip_hdr(skb)->daddr, dif); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { + dif = inet6_iif(skb); + sdif = inet6_sdif(skb); pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n", (int)ident, &ipv6_hdr(skb)->daddr, dif); #endif + } else { + return NULL; } read_lock_bh(&ping_table.lock); @@ -225,7 +231,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) continue; } - if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && + sk->sk_bound_dev_if != sdif) continue; sock_hold(sk); @@ -302,6 +309,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; + u32 tb_id = RT_TABLE_LOCAL; int chk_addr_ret; if (addr_len < sizeof(*addr)) @@ -315,7 +323,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) chk_addr_ret = RTN_LOCAL; @@ -356,6 +365,14 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return -ENODEV; } } + + if (!dev && sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + } has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, scoped); rcu_read_unlock(); @@ -968,6 +985,7 @@ bool ping_rcv(struct sk_buff *skb) struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + bool rc = false; /* We assume the packet has already been checked by icmp_rcv */ @@ -982,14 +1000,15 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); - if (skb2) - ping_queue_rcv_skb(sk, skb2); + if (skb2 && !ping_queue_rcv_skb(sk, skb2)) + rc = true; sock_put(sk); - return true; } - pr_debug("no socket, dropping\n"); - return false; + if (!rc) + pr_debug("no socket, dropping\n"); + + return rc; } EXPORT_SYMBOL_GPL(ping_rcv); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 21800979ed62..8ad120c07096 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -391,7 +391,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->ip_summed = CHECKSUM_NONE; - sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); @@ -563,6 +563,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW; if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -630,7 +633,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); @@ -725,6 +728,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int ret = -EINVAL; int chk_addr_ret; + lock_sock(sk); if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in)) goto out; @@ -744,7 +748,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); ret = 0; -out: return ret; +out: + release_sock(sk); + return ret; } /* diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3db428242b22..f4d41ceef946 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -70,6 +70,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/bootmem.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> @@ -470,8 +471,10 @@ static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) __ipv4_confirm_neigh(dev, *(__force u32 *)pkey); } -#define IP_IDENTS_SZ 2048u - +/* Hash tables of size 2048..262144 depending on RAM size. + * Each bucket uses 8 bytes. + */ +static u32 ip_idents_mask __read_mostly; static atomic_t *ip_idents __read_mostly; static u32 *ip_tstamps __read_mostly; @@ -481,12 +484,16 @@ static u32 *ip_tstamps __read_mostly; */ u32 ip_idents_reserve(u32 hash, int segs) { - u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ; - atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; - u32 old = READ_ONCE(*p_tstamp); - u32 now = (u32)jiffies; + u32 bucket, old, now = (u32)jiffies; + atomic_t *p_id; + u32 *p_tstamp; u32 delta = 0; + bucket = hash & ip_idents_mask; + p_tstamp = ip_tstamps + bucket; + p_id = ip_idents + bucket; + old = READ_ONCE(*p_tstamp); + if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); @@ -597,28 +604,35 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe) } } -static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash) +static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { - struct fib_nh_exception *fnhe, *oldest; + struct fib_nh_exception __rcu **fnhe_p, **oldest_p; + struct fib_nh_exception *fnhe, *oldest = NULL; - oldest = rcu_dereference(hash->chain); - for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe; - fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) + for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { + fnhe = rcu_dereference_protected(*fnhe_p, + lockdep_is_held(&fnhe_lock)); + if (!fnhe) + break; + if (!oldest || + time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; + oldest_p = fnhe_p; + } } fnhe_flush_routes(oldest); - return oldest; + *oldest_p = oldest->fnhe_next; + kfree_rcu(oldest, rcu); } -static inline u32 fnhe_hashfun(__be32 daddr) +static u32 fnhe_hashfun(__be32 daddr) { - static u32 fnhe_hashrnd __read_mostly; - u32 hval; + static siphash_key_t fnhe_hash_key __read_mostly; + u64 hval; - net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd)); - hval = jhash_1word((__force u32) daddr, fnhe_hashrnd); - return hash_32(hval, FNHE_HASH_SHIFT); + net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); + hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); + return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) @@ -685,16 +699,21 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, if (rt) fill_route_from_fnhe(rt, fnhe); } else { - if (depth > FNHE_RECLAIM_DEPTH) - fnhe = fnhe_oldest(hash); - else { - fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); - if (!fnhe) - goto out_unlock; - - fnhe->fnhe_next = hash->chain; - rcu_assign_pointer(hash->chain, fnhe); + /* Randomize max depth to avoid some side channels attacks. */ + int max_depth = FNHE_RECLAIM_DEPTH + + prandom_u32_max(FNHE_RECLAIM_DEPTH); + + while (depth > max_depth) { + fnhe_remove_oldest(hash); + depth--; } + + fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); + if (!fnhe) + goto out_unlock; + + fnhe->fnhe_next = hash->chain; + fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; @@ -702,6 +721,8 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); + rcu_assign_pointer(hash->chain, fnhe); + /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. @@ -770,7 +791,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { @@ -1194,6 +1215,7 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) static void ipv4_send_dest_unreach(struct sk_buff *skb) { + struct net_device *dev; struct ip_options opt; int res; @@ -1211,7 +1233,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); - res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); + dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; + res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) @@ -1311,7 +1334,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = READ_ONCE(dst->dev->mtu); @@ -1320,6 +1343,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = 576; } +out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); @@ -1397,7 +1421,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) struct net_device *dev = nh->nh_dev; u32 mtu = 0; - if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu || + if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; @@ -1706,6 +1730,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif RT_CACHE_STAT_INC(in_slow_mc); + skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return 0; } @@ -2634,10 +2659,12 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, if (IS_ERR(rt)) return rt; - if (flp4->flowi4_proto) + if (flp4->flowi4_proto) { + flp4->flowi4_oif = rt->dst.dev->ifindex; rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0); + } return rt; } @@ -2791,7 +2818,7 @@ static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; - udph->len = sizeof(struct udphdr); + udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } @@ -2874,7 +2901,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, memset(&fl4, 0, sizeof(fl4)); fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos; + fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -2898,8 +2925,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos, - dev, &res); + err = ip_route_input_rcu(skb, dst, src, + rtm->rtm_tos & IPTOS_RT_MASK, dev, + &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) @@ -3194,18 +3222,25 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; int __init ip_rt_init(void) { + void *idents_hash; int cpu; - ip_idents = kmalloc_array(IP_IDENTS_SZ, sizeof(*ip_idents), - GFP_KERNEL); - if (!ip_idents) - panic("IP: failed to allocate ip_idents\n"); + /* For modern hosts, this will use 2 MB of memory */ + idents_hash = alloc_large_system_hash("IP idents", + sizeof(*ip_idents) + sizeof(*ip_tstamps), + 0, + 16, /* one bucket per 64 KB */ + HASH_ZERO, + NULL, + &ip_idents_mask, + 2048, + 256*1024); + + ip_idents = idents_hash; - prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); + prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); - ip_tstamps = kcalloc(IP_IDENTS_SZ, sizeof(*ip_tstamps), GFP_KERNEL); - if (!ip_tstamps) - panic("IP: failed to allocate ip_tstamps\n"); + ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f66b2e6d97a7..929f989de1f6 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -296,7 +296,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct rtable *rt; __u8 rcv_wscale; struct flowi4 fl4; @@ -337,6 +337,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); treq = tcp_rsk(req); + treq->af_specific = &tcp_request_sock_ipv4_ops; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; treq->ts_off = 0; @@ -391,8 +392,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ad132b6e8cfa..c97ba2a44b8b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -332,61 +332,6 @@ bad_key: return ret; } -static void proc_configure_early_demux(int enabled, int protocol) -{ - struct net_protocol *ipprot; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_protocol *ip6prot; -#endif - - rcu_read_lock(); - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot) - ipprot->early_demux = enabled ? ipprot->early_demux_handler : - NULL; - -#if IS_ENABLED(CONFIG_IPV6) - ip6prot = rcu_dereference(inet6_protos[protocol]); - if (ip6prot) - ip6prot->early_demux = enabled ? ip6prot->early_demux_handler : - NULL; -#endif - rcu_read_unlock(); -} - -static int proc_tcp_early_demux(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_tcp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_TCP); - } - - return ret; -} - -static int proc_udp_early_demux(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_udp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_UDP); - } - - return ret; -} - static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, int write, void __user *buffer, @@ -638,14 +583,14 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_udp_early_demux + .proc_handler = proc_douintvec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_tcp_early_demux + .proc_handler = proc_douintvec_minmax, }, { .procname = "ip_default_ttl", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4ce3397e6fcf..00648a478c6a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -436,7 +436,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; - tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering; + tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; @@ -495,6 +495,8 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, return true; if (tcp_rmem_pressure(sk)) return true; + if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss) + return true; } if (sk->sk_prot->stream_memory_read) return sk->sk_prot->stream_memory_read(sk); @@ -513,6 +515,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); + u8 shutdown; int state; sock_poll_wait(file, sock, wait); @@ -555,9 +558,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ - if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) + shutdown = READ_ONCE(sk->sk_shutdown); + if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ @@ -565,7 +569,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) (state != TCP_SYN_RECV || tp->fastopen_rsk)) { int target = sock_rcvlowat(sk, 0, INT_MAX); - if (tp->urg_seq == tp->copied_seq && + if (tp->urg_seq == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) target++; @@ -573,8 +577,8 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tcp_stream_is_readable(tp, target, sk)) mask |= EPOLLIN | EPOLLRDNORM; - if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_is_writeable(sk)) { + if (!(shutdown & SEND_SHUTDOWN)) { + if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -586,7 +590,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * pairs with the input side. */ smp_mb__after_atomic(); - if (sk_stream_is_writeable(sk)) + if (__sk_stream_is_writeable(sk, 1)) mask |= EPOLLOUT | EPOLLWRNORM; } } else @@ -626,7 +630,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && tp->urg_seq == tp->copied_seq; + answ = tp->urg_data && tp->urg_seq == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) @@ -635,7 +639,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_una; + answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) @@ -644,7 +648,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_nxt; + answ = READ_ONCE(tp->write_seq) - tp->snd_nxt; break; default: return -ENOIOCTLCMD; @@ -704,7 +708,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && - sock_net(sk)->ipv4.sysctl_tcp_autocorking && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) && !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } @@ -950,7 +954,7 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) */ static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) { - if (skb && !skb->len) { + if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { tcp_unlink_write_queue(skb, sk); if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); @@ -1035,7 +1039,7 @@ new_segment: sk->sk_wmem_queued += copy; sk_mem_charge(sk, copy); skb->ip_summed = CHECKSUM_PARTIAL; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1158,7 +1162,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -1389,7 +1394,7 @@ new_segment: if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1667,11 +1672,13 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, if (!copied) copied = used; break; - } else if (used <= len) { - seq += used; - copied += used; - offset += used; } + if (WARN_ON_ONCE(used > len)) + used = len; + seq += used; + copied += used; + offset += used; + /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it @@ -1694,9 +1701,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb); if (!desc->count) break; - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); } - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -1833,7 +1840,7 @@ static int tcp_zerocopy_receive(struct sock *sk, out: up_read(¤t->mm->mmap_sem); if (length) { - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ @@ -2110,7 +2117,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { - ++*seq; + WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; @@ -2132,7 +2139,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, } } - *seq += used; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; @@ -2161,7 +2168,7 @@ skip_copy: found_fin_ok: /* Process the FIN. */ - ++*seq; + WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; @@ -2333,14 +2340,13 @@ bool tcp_check_oom(struct sock *sk, int shift) return too_many_orphans || out_of_socket_memory; } -void tcp_close(struct sock *sk, long timeout) +void __tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; int data_was_unread = 0; int state; - lock_sock(sk); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); @@ -2500,6 +2506,12 @@ adjudge_to_death: out: bh_unlock_sock(sk); local_bh_enable(); +} + +void tcp_close(struct sock *sk, long timeout) +{ + lock_sock(sk); + __tcp_close(sk, timeout); release_sock(sk); sock_put(sk); } @@ -2554,6 +2566,13 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + u32 seq; + + /* Deny disconnect if other threads are blocked in sk_wait_event() + * or inet_wait_for_connect(). + */ + if (sk->sk_wait_pending) + return -EBUSY; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -2576,7 +2595,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); @@ -2587,17 +2606,22 @@ int tcp_disconnect(struct sock *sk, int flags) if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); - sk->sk_shutdown = 0; + WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->rcv_rtt_last_tsecr = 0; - tp->write_seq += tp->max_window + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + + seq = tp->write_seq + tp->max_window + 2; + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; + tp->is_cwnd_limited = 0; + tp->max_packets_out = 0; tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; @@ -2615,8 +2639,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - dst_release(sk->sk_rx_dst); - sk->sk_rx_dst = NULL; + dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL)); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; @@ -2880,16 +2903,23 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_QUEUE_SEQ: - if (sk->sk_state != TCP_CLOSE) + if (sk->sk_state != TCP_CLOSE) { err = -EPERM; - else if (tp->repair_queue == TCP_SEND_QUEUE) - tp->write_seq = val; - else if (tp->repair_queue == TCP_RECV_QUEUE) { - WRITE_ONCE(tp->rcv_nxt, val); - WRITE_ONCE(tp->copied_seq, val); - } - else + } else if (tp->repair_queue == TCP_SEND_QUEUE) { + if (!tcp_rtx_queue_empty(sk)) + err = -EPERM; + else + WRITE_ONCE(tp->write_seq, val); + } else if (tp->repair_queue == TCP_RECV_QUEUE) { + if (tp->rcv_nxt != tp->copied_seq) { + err = -EPERM; + } else { + WRITE_ONCE(tp->rcv_nxt, val); + WRITE_ONCE(tp->copied_seq, val); + } + } else { err = -EINVAL; + } break; case TCP_REPAIR_OPTIONS: @@ -2970,18 +3000,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; - else if (val > net->ipv4.sysctl_tcp_fin_timeout / HZ) - tp->linger2 = 0; + WRITE_ONCE(tp->linger2, -1); + else if (val > TCP_FIN_TIMEOUT_MAX / HZ) + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -3041,7 +3071,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else @@ -3068,7 +3099,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -3345,7 +3376,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; - if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) + if (tp->rx_opt.user_mss && + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; @@ -3369,13 +3401,14 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) - val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ; + val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -3521,7 +3554,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: @@ -3536,7 +3569,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = tcp_time_stamp_raw() + tp->tsoffset; break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; @@ -3673,12 +3706,16 @@ static void __tcp_alloc_md5sig_pool(void) * to memory. See smp_rmb() in tcp_get_md5sig_pool() */ smp_wmb(); - tcp_md5sig_pool_populated = true; + /* Paired with READ_ONCE() from tcp_alloc_md5sig_pool() + * and tcp_get_md5sig_pool(). + */ + WRITE_ONCE(tcp_md5sig_pool_populated, true); } bool tcp_alloc_md5sig_pool(void) { - if (unlikely(!tcp_md5sig_pool_populated)) { + /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ + if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) { mutex_lock(&tcp_md5sig_mutex); if (!tcp_md5sig_pool_populated) @@ -3686,7 +3723,8 @@ bool tcp_alloc_md5sig_pool(void) mutex_unlock(&tcp_md5sig_mutex); } - return tcp_md5sig_pool_populated; + /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ + return READ_ONCE(tcp_md5sig_pool_populated); } EXPORT_SYMBOL(tcp_alloc_md5sig_pool); @@ -3702,7 +3740,8 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { local_bh_disable(); - if (tcp_md5sig_pool_populated) { + /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */ + if (READ_ONCE(tcp_md5sig_pool_populated)) { /* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */ smp_rmb(); return this_cpu_ptr(&tcp_md5sig_pool); @@ -3778,7 +3817,7 @@ void tcp_done(struct sock *sk) if (req) reqsk_fastopen_remove(sk, req, false); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 93f176336297..1740de053072 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -917,7 +917,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) filter_expired = after(tcp_jiffies32, bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ); if (rs->rtt_us >= 0 && - (rs->rtt_us <= bbr->min_rtt_us || + (rs->rtt_us < bbr->min_rtt_us || (filter_expired && !rs->is_ack_delayed))) { bbr->min_rtt_us = rs->rtt_us; bbr->min_rtt_stamp = tcp_jiffies32; @@ -985,7 +985,7 @@ static void bbr_init(struct sock *sk) bbr->prior_cwnd = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; bbr->rtt_cnt = 0; - bbr->next_rtt_delivered = 0; + bbr->next_rtt_delivered = tp->delivered; bbr->prev_ca_state = TCP_CA_Open; bbr->packet_conservation = 0; diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 06fbe102a425..10daea1fcefc 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -374,6 +374,7 @@ static void tcp_cdg_init(struct sock *sk) struct cdg *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); + ca->gradients = NULL; /* We silently fall back to window = 1 if allocation fails. */ if (window > 1) ca->gradients = kcalloc(window, sizeof(ca->gradients[0]), @@ -387,6 +388,7 @@ static void tcp_cdg_release(struct sock *sk) struct cdg *ca = inet_csk_ca(sk); kfree(ca->gradients); + ca->gradients = NULL; } static struct tcp_congestion_ops tcp_cdg __read_mostly = { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 32c3162baf3e..533f8d84d2f7 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -196,6 +196,11 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } @@ -223,6 +228,10 @@ int tcp_set_default_congestion_control(struct net *net, const char *name) ret = -ENOENT; } else if (!try_module_get(ca->owner)) { ret = -EBUSY; + } else if (!net_eq(net, &init_net) && + !(ca->flags & TCP_CONG_NON_RESTRICTED)) { + /* Only init netns can set default to a restricted algorithm */ + ret = -EPERM; } else { prev = xchg(&net->ipv4.tcp_congestion_control, ca); if (prev) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 8b5ba0a5cd38..93530bd33247 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -340,8 +340,6 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; if (tcp_in_slow_start(tp)) { - if (hystart && after(ack, ca->end_seq)) - bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); if (!acked) return; @@ -383,6 +381,9 @@ static void hystart_update(struct sock *sk, u32 delay) if (ca->found & hystart_detect) return; + if (after(tp->snd_una, ca->end_seq)) + bictcp_hystart_reset(sk); + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock(); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index c9e97f304f98..2a46f9f81ba0 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -30,8 +30,9 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); - r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - tp->copied_seq, 0); - r->idiag_wqueue = tp->write_seq - tp->snd_una; + r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); + r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 018a48477355..f7bb78b443fa 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -276,6 +276,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; + int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying @@ -288,10 +289,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq->max_qlen == 0) + max_qlen = READ_ONCE(fastopenq->max_qlen); + if (max_qlen == 0) return false; - if (fastopenq->qlen >= fastopenq->max_qlen) { + if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; @@ -313,7 +315,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk, const struct dst_entry *dst, int flag) { - return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) || + return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) || tcp_sk(sk)->fastopen_no_cookie || (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); } @@ -328,7 +330,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; - int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; @@ -342,8 +344,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, return NULL; } - if (syn_data && - tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) + if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ @@ -454,8 +455,15 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); + /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ + WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); + + /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). + * We want net->ipv4.tfo_active_disable_stamp to be updated first. + */ + smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); - net->ipv4.tfo_active_disable_stamp = jiffies; + NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } @@ -473,10 +481,16 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) if (!tfo_da_times) return false; + /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ + smp_rmb(); + /* Limit timout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); - timeout = multiplier * tfo_bh_timeout * HZ; - if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) + + /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ + timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + + multiplier * tfo_bh_timeout * HZ; + if (time_before(jiffies, timeout)) return true; /* Mark check bit so we can check for successful active TFO diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9813d62de631..407ad07dc598 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -172,6 +172,19 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (unlikely(len > icsk->icsk_ack.rcv_mss + MAX_TCP_OPTION_SPACE)) tcp_gro_dev_warn(sk, skb, len); + /* If the skb has a len of exactly 1*MSS and has the PSH bit + * set then it is likely the end of an application write. So + * more data may not be arriving soon, and yet the data sender + * may be waiting for an ACK if cwnd-bound or using TX zero + * copy. So we set ICSK_ACK_PUSHED here so that + * tcp_cleanup_rbuf() will send an ACK immediately if the app + * reads all of the data and is not ping-pong. If len > MSS + * then this logic does not matter (and does not hurt) because + * tcp_cleanup_rbuf() will always ACK immediately if the app + * reads data and there is more than an MSS of unACKed data. + */ + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_PSH) + icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. @@ -216,7 +229,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -224,7 +237,6 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } -EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. @@ -432,14 +444,13 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) */ void tcp_init_buffer_space(struct sock *sk) { - int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win; + int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win); struct tcp_sock *tp = tcp_sk(sk); int maxwin; if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) tcp_sndbuf_expand(sk); - tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -463,6 +474,8 @@ void tcp_init_buffer_space(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; + tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd, + (u32)TCP_INIT_CWND * tp->advmss); } /* 4. Recalculate window clamp after socket hit its memory bounds. */ @@ -580,10 +593,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; u32 delta_us; - if (!delta) - delta = 1; - delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - tcp_rcv_rtt_update(tp, delta_us, 0); + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + tcp_rcv_rtt_update(tp, delta_us, 0); + } } } @@ -890,7 +905,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, tp->undo_marker ? tp->undo_retrans : 0); #endif tp->reordering = min_t(u32, (metric + mss - 1) / mss, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); } /* This exciting event is worth to be remembered. 8) */ @@ -1194,7 +1209,7 @@ static u8 tcp_sacktag_one(struct sock *sk, if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) - tp->undo_retrans--; + tp->undo_retrans = max_t(int, 0, tp->undo_retrans - pcount); if ((sacked & TCPCB_SACKED_ACKED) && before(start_seq, state->reord)) state->reord = start_seq; @@ -1875,7 +1890,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) return; tp->reordering = min_t(u32, tp->packets_out + addend, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); tp->reord_seen++; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } @@ -1935,7 +1950,8 @@ static inline void tcp_init_undo(struct tcp_sock *tp) static bool tcp_is_rack(const struct sock *sk) { - return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION; + return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_LOSS_DETECTION; } /* If we detect SACK reneging, forget all SACK information @@ -1979,6 +1995,7 @@ void tcp_enter_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; + u8 reordering; tcp_timeout_mark_lost(sk); @@ -1999,10 +2016,12 @@ void tcp_enter_loss(struct sock *sk) /* Timeout in disordered state after receiving substantial DUPACKs * suggests that the degree of reordering is over-estimated. */ + reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering); if (icsk->icsk_ca_state <= TCP_CA_Disorder && - tp->sacked_out >= net->ipv4.sysctl_tcp_reordering) + tp->sacked_out >= reordering) tp->reordering = min_t(unsigned int, tp->reordering, - net->ipv4.sysctl_tcp_reordering); + reordering); + tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); @@ -2011,7 +2030,7 @@ void tcp_enter_loss(struct sock *sk) * loss recovery is underway except recurring timeout(s) on * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing */ - tp->frto = net->ipv4.sysctl_tcp_frto && + tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) && (new_recovery || icsk->icsk_retransmits) && !inet_csk(sk)->icsk_mtup.probe_size; } @@ -2028,7 +2047,8 @@ void tcp_enter_loss(struct sock *sk) */ static bool tcp_check_sack_reneging(struct sock *sk, int flag) { - if (flag & FLAG_SACK_RENEGING) { + if (flag & FLAG_SACK_RENEGING && + flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); @@ -2365,6 +2385,21 @@ static inline bool tcp_may_undo(const struct tcp_sock *tp) return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp)); } +static bool tcp_is_non_sack_preventing_reopen(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { + /* Hold old state until something *above* high_seq + * is ACKed. For Reno it is MUST to prevent false + * fast retransmits (RFC2582). SACK TCP is safe. */ + if (!tcp_any_retrans_done(sk)) + tp->retrans_stamp = 0; + return true; + } + return false; +} + /* People celebrate: "We love our President!" */ static bool tcp_try_undo_recovery(struct sock *sk) { @@ -2387,14 +2422,8 @@ static bool tcp_try_undo_recovery(struct sock *sk) } else if (tp->rack.reo_wnd_persist) { tp->rack.reo_wnd_persist--; } - if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { - /* Hold old state until something *above* high_seq - * is ACKed. For Reno it is MUST to prevent false - * fast retransmits (RFC2582). SACK TCP is safe. */ - if (!tcp_any_retrans_done(sk)) - tp->retrans_stamp = 0; + if (tcp_is_non_sack_preventing_reopen(sk)) return true; - } tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; return false; @@ -2430,6 +2459,8 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUSRTOS); inet_csk(sk)->icsk_retransmits = 0; + if (tcp_is_non_sack_preventing_reopen(sk)) + return true; if (frto_undo || tcp_is_sack(tp)) { tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; @@ -2563,12 +2594,15 @@ static void tcp_mtup_probe_success(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + u64 val; - /* FIXME: breaks with very large cwnd */ tp->prior_ssthresh = tcp_current_ssthresh(sk); - tp->snd_cwnd = tp->snd_cwnd * - tcp_mss_to_mtu(sk, tp->mss_cache) / - icsk->icsk_mtup.probe_size; + + val = (u64)tp->snd_cwnd * tcp_mss_to_mtu(sk, tp->mss_cache); + do_div(val, icsk->icsk_mtup.probe_size); + WARN_ON_ONCE((u32)val != val); + tp->snd_cwnd = max_t(u32, 1U, val); + tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_ssthresh = tcp_current_ssthresh(sk); @@ -2749,7 +2783,8 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) } else if (tcp_is_rack(sk)) { u32 prior_retrans = tp->retrans_out; - tcp_rack_mark_lost(sk); + if (tcp_rack_mark_lost(sk)) + *ack_flag &= ~FLAG_SET_XMIT_TIMER; if (prior_retrans > tp->retrans_out) *ack_flag |= FLAG_LOST_RETRANS; } @@ -2892,7 +2927,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag) { - u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ; + u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ; struct tcp_sock *tp = tcp_sk(sk); if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) { @@ -2929,9 +2964,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - seq_rtt_us = ca_rtt_us = delta_us; + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + ca_rtt_us = seq_rtt_us; + } } rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) @@ -3294,7 +3331,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ - if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering) + if (tcp_sk(sk)->reordering > + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering)) return flag & FLAG_FORWARD_PROGRESS; return flag & FLAG_DATA_ACKED; @@ -3403,16 +3441,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, u32 *last_oow_ack_time) { - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); + /* Paired with the WRITE_ONCE() in this function. */ + u32 val = READ_ONCE(*last_oow_ack_time); - if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) { + if (val) { + s32 elapsed = (s32)(tcp_jiffies32 - val); + + if (0 <= elapsed && + elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) { NET_INC_STATS(net, mib_idx); return true; /* rate-limited: don't send yet! */ } } - *last_oow_ack_time = tcp_jiffies32; + /* Paired with the prior READ_ONCE() and with itself, + * as we might be lockless. + */ + WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32); return false; /* not rate-limited: go ahead, send dupack now! */ } @@ -3453,11 +3498,11 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; - if (now != challenge_timestamp) { - u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit; + if (now != READ_ONCE(challenge_timestamp)) { + u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit); u32 half = (ack_limit + 1) >> 1; - challenge_timestamp = now; + WRITE_ONCE(challenge_timestamp, now); WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit)); } count = READ_ONCE(challenge_count); @@ -3595,8 +3640,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { + u32 max_window; + + /* do not accept ACK for bytes we never sent. */ + max_window = min_t(u64, tp->max_window, tp->bytes_acked); /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ - if (before(ack, prior_snd_una - tp->max_window)) { + if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk, skb); return -1; @@ -3692,9 +3741,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); - /* If needed, reset TLP/RTO timer; RACK may later override this. */ - if (flag & FLAG_SET_XMIT_TIMER) - tcp_set_xmit_timer(sk); if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); @@ -3702,6 +3748,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) &rexmit); } + /* If needed, reset TLP/RTO timer when RACK doesn't set. */ + if (flag & FLAG_SET_XMIT_TIMER) + tcp_set_xmit_timer(sk); + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); @@ -4102,7 +4152,7 @@ void tcp_fin(struct sock *sk) inet_csk_schedule_ack(sk); - sk->sk_shutdown |= RCV_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); sock_set_flag(sk, SOCK_DONE); switch (sk->sk_state) { @@ -4182,7 +4232,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); - if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4217,7 +4267,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); - if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) @@ -4704,7 +4754,8 @@ void tcp_data_ready(struct sock *sk) int avail = tp->rcv_nxt - tp->copied_seq; if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && - !sock_flag(sk, SOCK_DONE)) + !sock_flag(sk, SOCK_DONE) && + tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss) return; sk->sk_data_ready(sk); @@ -5159,7 +5210,17 @@ static void tcp_new_space(struct sock *sk) sk->sk_write_space(sk); } -static void tcp_check_space(struct sock *sk) +/* Caller made space either from: + * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced) + * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt) + * + * We might be able to generate EPOLLOUT to the application if: + * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2 + * 2) notsent amount (tp->write_seq - tp->snd_nxt) became + * small enough that tcp_stream_memory_free() decides it + * is time to generate EPOLLOUT. + */ +void tcp_check_space(struct sock *sk) { if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) { sock_reset_flag(sk, SOCK_QUEUE_SHRUNK); @@ -5212,7 +5273,7 @@ send_now: } if (!tcp_is_sack(tp) || - tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr) + tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)) goto send_now; if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) { @@ -5235,7 +5296,8 @@ send_now: if (tp->srtt_us && tp->srtt_us < rtt) rtt = tp->srtt_us; - delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns, + delay = min_t(unsigned long, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns), rtt * (NSEC_PER_USEC >> 3)/20); sock_hold(sk); hrtimer_start(&tp->compressed_ack_timer, ns_to_ktime(delay), @@ -5266,7 +5328,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) struct tcp_sock *tp = tcp_sk(sk); u32 ptr = ntohs(th->urg_ptr); - if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg) + if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg)) ptr--; ptr += ntohl(th->seq); @@ -5513,7 +5575,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) trace_tcp_probe(sk, skb); tcp_mstamp_refresh(tp); - if (unlikely(!sk->sk_rx_dst)) + if (unlikely(!rcu_access_pointer(sk->sk_rx_dst))) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. @@ -5631,6 +5693,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tcp_data_snd_check(sk); if (!inet_csk_ack_scheduled(sk)) goto no_ack; + } else { + tcp_update_wl(tp, TCP_SKB_CB(skb)->seq); } __tcp_ack_snd_check(sk, 0); @@ -5883,7 +5947,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); smc_check_reset_syn(tp); @@ -5958,7 +6022,7 @@ discard: } WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -6120,7 +6184,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_rearm_rto(sk); } else { tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); @@ -6167,7 +6231,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) break; tcp_set_state(sk, TCP_FIN_WAIT2); - sk->sk_shutdown |= SEND_SHUTDOWN; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | SEND_SHUTDOWN); sk_dst_confirm(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7536f4c0bbf4..bd374eac9a75 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -110,10 +110,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { + int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); - int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse; if (reuse == 2) { /* Still does not detect *everything* that goes through @@ -169,9 +169,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) * without appearing to create any others. */ if (likely(!tp->repair)) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + u32 seq = tcptw->tw_snd_nxt + 65535 + 2; + + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } @@ -258,7 +260,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; @@ -296,10 +298,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port); + WRITE_ONCE(tp->write_seq, + secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); @@ -325,6 +328,8 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; @@ -345,7 +350,7 @@ void tcp_v4_mtu_reduced(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - mtu = tcp_sk(sk)->mtu_info; + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -513,7 +518,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (sk->sk_state == TCP_LISTEN) goto out; - tp->mtu_info = info; + WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { @@ -1369,7 +1374,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { .syn_ack_timeout = tcp_syn_ack_timeout, }; -static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { +const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, @@ -1412,6 +1417,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, bool *own_req) { struct inet_request_sock *ireq; + bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1482,12 +1488,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { newinet->inet_opt = NULL; + + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; + } } return newsk; @@ -1530,15 +1546,18 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || !dst->ops->check(dst, 0)) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } tcp_rcv_established(sk, skb); @@ -1613,7 +1632,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -1918,7 +1937,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } } @@ -2174,6 +2193,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) static void *tcp_seek_last_pos(struct seq_file *seq) { struct tcp_iter_state *st = seq->private; + int bucket = st->bucket; int offset = st->offset; int orig_num = st->num; void *rc = NULL; @@ -2184,7 +2204,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) break; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_next(seq, NULL); - while (offset-- && rc) + while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); if (rc) break; @@ -2195,7 +2215,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq) if (st->bucket > tcp_hashinfo.ehash_mask) break; rc = established_get_first(seq); - while (offset-- && rc) + while (offset-- && rc && bucket == st->bucket) rc = established_get_next(seq, rc); } @@ -2340,12 +2360,12 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - - tp->copied_seq, 0); + READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 03b51cdcc731..60619b1f4acd 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -40,7 +40,7 @@ struct tcp_fastopen_metrics { struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; - possible_net_t tcpm_net; + struct net *tcpm_net; struct inetpeer_addr tcpm_saddr; struct inetpeer_addr tcpm_daddr; unsigned long tcpm_stamp; @@ -51,34 +51,38 @@ struct tcp_metrics_block { struct rcu_head rcu_head; }; -static inline struct net *tm_net(struct tcp_metrics_block *tm) +static inline struct net *tm_net(const struct tcp_metrics_block *tm) { - return read_pnet(&tm->tcpm_net); + /* Paired with the WRITE_ONCE() in tcpm_new() */ + return READ_ONCE(tm->tcpm_net); } static bool tcp_metric_locked(struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_lock & (1 << idx); + /* Paired with WRITE_ONCE() in tcpm_suck_dst() */ + return READ_ONCE(tm->tcpm_lock) & (1 << idx); } -static u32 tcp_metric_get(struct tcp_metrics_block *tm, +static u32 tcp_metric_get(const struct tcp_metrics_block *tm, enum tcp_metric_index idx) { - return tm->tcpm_vals[idx]; + /* Paired with WRITE_ONCE() in tcp_metric_set() */ + return READ_ONCE(tm->tcpm_vals[idx]); } static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) { - tm->tcpm_vals[idx] = val; + /* Paired with READ_ONCE() in tcp_metric_get() */ + WRITE_ONCE(tm->tcpm_vals[idx], val); } static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - return inetpeer_addr_cmp(a, b) == 0; + return (a->family == b->family) && !inetpeer_addr_cmp(a, b); } struct tcpm_hash_bucket { @@ -89,6 +93,7 @@ static struct tcpm_hash_bucket *tcp_metrics_hash __read_mostly; static unsigned int tcp_metrics_hash_log __read_mostly; static DEFINE_SPINLOCK(tcp_metrics_lock); +static DEFINE_SEQLOCK(fastopen_seqlock); static void tcpm_suck_dst(struct tcp_metrics_block *tm, const struct dst_entry *dst, @@ -97,7 +102,7 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, u32 msval; u32 val; - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); val = 0; if (dst_metric_locked(dst, RTAX_RTT)) @@ -110,30 +115,42 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, val |= 1 << TCP_METRIC_CWND; if (dst_metric_locked(dst, RTAX_REORDERING)) val |= 1 << TCP_METRIC_REORDERING; - tm->tcpm_lock = val; + /* Paired with READ_ONCE() in tcp_metric_locked() */ + WRITE_ONCE(tm->tcpm_lock, val); msval = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + tcp_metric_set(tm, TCP_METRIC_RTT, msval * USEC_PER_MSEC); msval = dst_metric_raw(dst, RTAX_RTTVAR); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; - tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); - tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); - tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, msval * USEC_PER_MSEC); + tcp_metric_set(tm, TCP_METRIC_SSTHRESH, + dst_metric_raw(dst, RTAX_SSTHRESH)); + tcp_metric_set(tm, TCP_METRIC_CWND, + dst_metric_raw(dst, RTAX_CWND)); + tcp_metric_set(tm, TCP_METRIC_REORDERING, + dst_metric_raw(dst, RTAX_REORDERING)); if (fastopen_clear) { + write_seqlock(&fastopen_seqlock); tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; tm->tcpm_fastopen.try_exp = 0; tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; + write_sequnlock(&fastopen_seqlock); } } #define TCP_METRICS_TIMEOUT (60 * 60 * HZ) -static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst) +static void tcpm_check_stamp(struct tcp_metrics_block *tm, + const struct dst_entry *dst) { - if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT))) + unsigned long limit; + + if (!tm) + return; + limit = READ_ONCE(tm->tcpm_stamp) + TCP_METRICS_TIMEOUT; + if (unlikely(time_after(jiffies, limit))) tcpm_suck_dst(tm, dst, false); } @@ -174,20 +191,23 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst, oldest = deref_locked(tcp_metrics_hash[hash].chain); for (tm = deref_locked(oldest->tcpm_next); tm; tm = deref_locked(tm->tcpm_next)) { - if (time_before(tm->tcpm_stamp, oldest->tcpm_stamp)) + if (time_before(READ_ONCE(tm->tcpm_stamp), + READ_ONCE(oldest->tcpm_stamp))) oldest = tm; } tm = oldest; } else { - tm = kmalloc(sizeof(*tm), GFP_ATOMIC); + tm = kzalloc(sizeof(*tm), GFP_ATOMIC); if (!tm) goto out_unlock; } - write_pnet(&tm->tcpm_net, net); + /* Paired with the READ_ONCE() in tm_net() */ + WRITE_ONCE(tm->tcpm_net, net); + tm->tcpm_saddr = *saddr; tm->tcpm_daddr = *daddr; - tcpm_suck_dst(tm, dst, true); + tcpm_suck_dst(tm, dst, reclaim); if (likely(!reclaim)) { tm->tcpm_next = tcp_metrics_hash[hash].chain; @@ -329,7 +349,7 @@ void tcp_update_metrics(struct sock *sk) int m; sk_dst_confirm(sk); - if (net->ipv4.sysctl_tcp_nometrics_save || !dst) + if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst) return; rcu_read_lock(); @@ -425,12 +445,13 @@ void tcp_update_metrics(struct sock *sk) if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) { val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val < tp->reordering && - tp->reordering != net->ipv4.sysctl_tcp_reordering) + tp->reordering != + READ_ONCE(net->ipv4.sysctl_tcp_reordering)) tcp_metric_set(tm, TCP_METRIC_REORDERING, tp->reordering); } } - tm->tcpm_stamp = jiffies; + WRITE_ONCE(tm->tcpm_stamp, jiffies); out_unlock: rcu_read_unlock(); } @@ -445,11 +466,15 @@ void tcp_init_metrics(struct sock *sk) u32 val, crtt = 0; /* cached RTT scaled by 8 */ sk_dst_confirm(sk); + /* ssthresh may have been reduced unnecessarily during. + * 3WHS. Restore it back to its initial default. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; if (!dst) goto reset; rcu_read_lock(); - tm = tcp_get_metrics(sk, dst, true); + tm = tcp_get_metrics(sk, dst, false); if (!tm) { rcu_read_unlock(); goto reset; @@ -463,11 +488,6 @@ void tcp_init_metrics(struct sock *sk) tp->snd_ssthresh = val; if (tp->snd_ssthresh > tp->snd_cwnd_clamp) tp->snd_ssthresh = tp->snd_cwnd_clamp; - } else { - /* ssthresh may have been reduced unnecessarily during. - * 3WHS. Restore it back to its initial default. - */ - tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; } val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val && tp->reordering != val) @@ -543,8 +563,6 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst) return ret; } -static DEFINE_SEQLOCK(fastopen_seqlock); - void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { @@ -651,7 +669,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, } if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE, - jiffies - tm->tcpm_stamp, + jiffies - READ_ONCE(tm->tcpm_stamp), TCP_METRICS_ATTR_PAD) < 0) goto nla_put_failure; @@ -662,7 +680,7 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, if (!nest) goto nla_put_failure; for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { - u32 val = tm->tcpm_vals[i]; + u32 val = tcp_metric_get(tm, i); if (!val) continue; @@ -894,7 +912,7 @@ static void tcp_metrics_flush_all(struct net *net) match = net ? net_eq(tm_net(tm), net) : !refcount_read(&tm_net(tm)->count); if (match) { - *pp = tm->tcpm_next; + rcu_assign_pointer(*pp, tm->tcpm_next); kfree_rcu(tm, rcu_head); } else { pp = &tm->tcpm_next; @@ -935,7 +953,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) if (addr_same(&tm->tcpm_daddr, &daddr) && (!src || addr_same(&tm->tcpm_saddr, &saddr)) && net_eq(tm_net(tm), net)) { - *pp = tm->tcpm_next; + rcu_assign_pointer(*pp, tm->tcpm_next); kfree_rcu(tm, rcu_head); found = true; } else { diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7ba8a90772b0..bae0199a943b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -179,7 +179,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * Oh well... nobody has a sufficient solution to this * protocol bug yet. */ - if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) { + if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) { kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; @@ -470,7 +470,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, seq = treq->rcv_isn + 1; newtp->rcv_wup = seq; - newtp->copied_seq = seq; + WRITE_ONCE(newtp->copied_seq, seq); WRITE_ONCE(newtp->rcv_nxt, seq); newtp->segs_in = 1; @@ -510,7 +510,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->app_limited = ~0U; tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1); newtp->rx_opt.saw_tstamp = 0; @@ -550,7 +550,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) + if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req))) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) @@ -582,6 +582,9 @@ EXPORT_SYMBOL(tcp_create_openreq_child); * validation and inside tcp_v4_reqsk_send_ack(). Can we do better? * * We don't need to initialize tmp_opt.sack_ok as we don't use the results + * + * Note: If @fastopen is true, this can be called from process context. + * Otherwise, this is from BH context. */ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, @@ -734,7 +737,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, &tcp_rsk(req)->last_oow_ack_time)) req->rsk_ops->send_ack(sk, skb, req); if (paws_reject) - __NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); return NULL; } @@ -753,7 +756,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * "fourth, check the SYN bit" */ if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) { - __TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); goto embryonic_reset; } @@ -815,8 +818,11 @@ embryonic_reset: tcp_reset(sk); } if (!fastopen) { - inet_csk_reqsk_queue_drop(sk, req); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + bool unlinked = inet_csk_reqsk_queue_drop(sk, req); + + if (unlinked) + __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + *req_stolen = !unlinked; } return NULL; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 74fb211e0ea6..670804d4c169 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -69,6 +69,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); + tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one @@ -163,8 +164,7 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, - u32 rcv_nxt) +static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -178,7 +178,7 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ - tcp_dec_quickack_mode(sk, pkts); + tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -968,6 +968,8 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + ktime_t expire, now; u64 len_ns; u32 rate; @@ -979,12 +981,28 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) len_ns = (u64)skb->len * NSEC_PER_SEC; do_div(len_ns, rate); - hrtimer_start(&tcp_sk(sk)->pacing_timer, - ktime_add_ns(ktime_get(), len_ns), + now = ktime_get(); + /* If hrtimer is already armed, then our caller has not + * used tcp_pacing_check(). + */ + if (unlikely(hrtimer_is_queued(&tp->pacing_timer))) { + expire = hrtimer_get_softexpires(&tp->pacing_timer); + if (ktime_after(expire, now)) + now = expire; + if (hrtimer_try_to_cancel(&tp->pacing_timer) == 1) + __sock_put(sk); + } + hrtimer_start(&tp->pacing_timer, ktime_add_ns(now, len_ns), HRTIMER_MODE_ABS_PINNED_SOFT); sock_hold(sk); } +static bool tcp_pacing_check(const struct sock *sk) +{ + return tcp_needs_internal_pacing(sk) && + hrtimer_is_queued(&tcp_sk(sk)->pacing_timer); +} + static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) { skb->skb_mstamp = tp->tcp_mstamp; @@ -1072,7 +1090,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb_set_hash_from_sk(skb, sk); refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); + skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm)); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; @@ -1120,7 +1138,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); + tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -1175,7 +1193,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ - tp->write_seq = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; @@ -1472,6 +1490,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } +EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) @@ -1503,7 +1522,7 @@ void tcp_mtup_init(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); - icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1; + icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); @@ -1618,14 +1637,20 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); - /* Track the maximum number of outstanding packets in each - * window, and remember whether we were cwnd-limited then. + /* Track the strongest available signal of the degree to which the cwnd + * is fully utilized. If cwnd-limited then remember that fact for the + * current window. If not cwnd-limited then track the maximum number of + * outstanding packets in the current window. (If cwnd-limited then we + * chose to not update tp->max_packets_out to avoid an extra else + * clause with no functional impact.) */ - if (!before(tp->snd_una, tp->max_packets_seq) || - tp->packets_out > tp->max_packets_out) { - tp->max_packets_out = tp->packets_out; - tp->max_packets_seq = tp->snd_nxt; + if (!before(tp->snd_una, tp->cwnd_usage_seq) || + is_cwnd_limited || + (!tp->is_cwnd_limited && + tp->packets_out > tp->max_packets_out)) { tp->is_cwnd_limited = is_cwnd_limited; + tp->max_packets_out = tp->packets_out; + tp->cwnd_usage_seq = tp->snd_nxt; } if (tcp_is_cwnd_limited(sk)) { @@ -1637,7 +1662,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; - if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); @@ -1724,7 +1749,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) min_tso = ca_ops->min_tso_segs ? ca_ops->min_tso_segs(sk) : - sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs; + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs); @@ -2009,7 +2034,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) u32 interval; s32 delta; - interval = net->ipv4.sysctl_tcp_probe_interval; + interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval); delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); @@ -2091,7 +2116,7 @@ static int tcp_mtu_probe(struct sock *sk) * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || - interval < net->ipv4.sysctl_tcp_probe_threshold) { + interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) { /* Check whether enough time has elaplased for * another round of probing. */ @@ -2119,6 +2144,9 @@ static int tcp_mtu_probe(struct sock *sk) if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) return -1; + if (tcp_pacing_check(sk)) + return -1; + /* We're allowed to probe. Build it now. */ nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) @@ -2192,10 +2220,16 @@ static int tcp_mtu_probe(struct sock *sk) return -1; } -static bool tcp_pacing_check(const struct sock *sk) +static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) { - return tcp_needs_internal_pacing(sk) && - hrtimer_is_queued(&tcp_sk(sk)->pacing_timer); + const struct rb_node *node = sk->tcp_rtx_queue.rb_node; + + /* No skb in the rtx queue. */ + if (!node) + return true; + + /* Only one skb in rtx queue. */ + return !node->rb_left && !node->rb_right; } /* TCP Small Queues : @@ -2220,12 +2254,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit <<= factor; if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send skb if rtx queue is empty. + /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (tcp_rtx_queue_empty(sk)) + if (tcp_rtx_queue_empty_or_single_skb(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2407,6 +2441,10 @@ repair: else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); + is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); + if (likely(sent_pkts || is_cwnd_limited)) + tcp_cwnd_validate(sk, is_cwnd_limited); + if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; @@ -2414,8 +2452,6 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); - is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); - tcp_cwnd_validate(sk, is_cwnd_limited); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); @@ -2425,7 +2461,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, rto_delta_us; + u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS @@ -2434,7 +2470,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) if (tp->fastopen_rsk) return false; - early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; + early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans); /* Schedule a loss probe in 2*RTT for SACK capable connections * not in loss recovery, that are either limited by cwnd or application. */ @@ -2449,11 +2485,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { - timeout = usecs_to_jiffies(tp->srtt_us >> 2); + timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) - timeout += TCP_RTO_MIN; + timeout_us += tcp_rto_min_us(sk); else - timeout += TCP_TIMEOUT_MIN; + timeout_us += TCP_TIMEOUT_MIN_US; + timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } @@ -2796,7 +2833,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, struct sk_buff *skb = to, *tmp; bool first = true; - if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; @@ -2836,7 +2873,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) struct tcp_sock *tp = tcp_sk(sk); unsigned int cur_mss; int diff, len, err; - + int avail_wnd; /* Inconclusive MTU probe */ if (icsk->icsk_mtup.probe_size) @@ -2853,7 +2890,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (skb_still_in_host_queue(sk, skb)) return -EBUSY; +start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { + if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(skb)->seq++; + goto start; + } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; @@ -2866,17 +2909,25 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) return -EHOSTUNREACH; /* Routing failure or similar. */ cur_mss = tcp_current_mss(sk); + avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case - * our retransmit serves as a zero window probe. + * our retransmit of one segment serves as a zero window probe. */ - if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) && - TCP_SKB_CB(skb)->seq != tp->snd_una) - return -EAGAIN; + if (avail_wnd <= 0) { + if (TCP_SKB_CB(skb)->seq != tp->snd_una) + return -EAGAIN; + avail_wnd = cur_mss; + } len = cur_mss * segs; + if (len > avail_wnd) { + len = rounddown(avail_wnd, cur_mss); + if (!len) + len = avail_wnd; + } if (skb->len > len) { if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, cur_mss, GFP_ATOMIC)) @@ -2890,8 +2941,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) diff -= tcp_skb_pcount(skb); if (diff) tcp_adjust_pcount(sk, skb, diff); - if (skb->len < cur_mss) - tcp_retrans_try_collapse(sk, skb, cur_mss); + avail_wnd = min_t(int, avail_wnd, cur_mss); + if (skb->len < avail_wnd) + tcp_retrans_try_collapse(sk, skb, avail_wnd); } /* RFC3168, section 6.1.1.1. ECN fallback */ @@ -2954,13 +3006,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) #endif TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); - - /* Save stamp of the first retransmit. */ - if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_skb_timestamp(skb); - } + /* Save stamp of the first (attempted) retransmit. */ + if (!tp->retrans_stamp) + tp->retrans_stamp = tcp_skb_timestamp(skb); + if (tp->undo_retrans < 0) tp->undo_retrans = 0; tp->undo_retrans += tcp_skb_pcount(skb); @@ -3051,11 +3102,12 @@ void tcp_xmit_retransmit_queue(struct sock *sk) */ void sk_forced_mem_schedule(struct sock *sk, int size) { - int amt; + int delta, amt; - if (size <= sk->sk_forward_alloc) + delta = size - sk->sk_forward_alloc; + if (delta <= 0) return; - amt = sk_mem_pages(size); + amt = sk_mem_pages(delta); sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; sk_memory_allocated_add(sk, amt); @@ -3273,7 +3325,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); - __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ @@ -3378,7 +3430,7 @@ static void tcp_connect_init(struct sock *sk) else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; @@ -3394,7 +3446,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) __skb_header_release(skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); - tp->write_seq = tcb->end_seq; + WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } @@ -3407,6 +3459,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) */ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { + struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; int space, err = 0; @@ -3421,8 +3474,10 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) * private TCP options. The cost is reduced data space in SYN :( */ tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp); + /* Sync mss_cache after updating the mss_clamp */ + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); - space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - + space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; space = min_t(size_t, space, fo->size); @@ -3754,7 +3809,7 @@ void tcp_send_probe0(struct sock *sk) } if (err <= 0) { - if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) + if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; icsk->icsk_probes_out++; probe_max = TCP_RTO_MAX; @@ -3783,8 +3838,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) tcp_rsk(req)->txhash = net_tx_rndhash(); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL); if (!res) { - __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); if (unlikely(tcp_passive_fastopen(sk))) tcp_sk(sk)->total_retrans++; trace_tcp_retransmit_synack(sk, req); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index c81aadff769b..844ff390f726 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -33,7 +33,8 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk) return 0; if (tp->sacked_out >= tp->reordering && - !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH)) + !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_NO_DUPTHRESH)) return 0; } @@ -109,22 +110,23 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout) } } -void tcp_rack_mark_lost(struct sock *sk) +bool tcp_rack_mark_lost(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 timeout; if (!tp->rack.advanced) - return; + return false; /* Reset the advanced flag to avoid unnecessary queue scanning */ tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { - timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN; + timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US); inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } + return !!timeout; } /* Record the most recently (re)sent time among the (s)acked packets @@ -202,7 +204,8 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); - if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND || + if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_STATIC_REO_WND) || !rs->prior_delivered) return; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 681882a40968..d8d28ba169b4 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,33 +22,21 @@ #include <linux/gfp.h> #include <net/tcp.h> -static u32 tcp_retransmit_stamp(const struct sock *sk) -{ - u32 start_ts = tcp_sk(sk)->retrans_stamp; - - if (unlikely(!start_ts)) { - struct sk_buff *head = tcp_rtx_queue_head(sk); - - if (!head) - return 0; - start_ts = tcp_skb_timestamp(head); - } - return start_ts; -} - static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 elapsed, start_ts; + s32 remaining; - start_ts = tcp_retransmit_stamp(sk); - if (!icsk->icsk_user_timeout || !start_ts) + start_ts = tcp_sk(sk)->retrans_stamp; + if (!icsk->icsk_user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; - if (elapsed >= icsk->icsk_user_timeout) + remaining = icsk->icsk_user_timeout - elapsed; + if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ - else - return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed)); + + return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } /** @@ -136,7 +124,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) */ static int tcp_orphan_retries(struct sock *sk, bool alive) { - int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */ + int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (sk->sk_err_soft && !alive) @@ -156,7 +144,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) int mss; /* Black hole detection */ - if (!net->ipv4.sysctl_tcp_mtu_probing) + if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { @@ -172,7 +160,20 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } +static unsigned int tcp_model_timeout(struct sock *sk, + unsigned int boundary, + unsigned int rto_base) +{ + unsigned int linear_backoff_thresh, timeout; + linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base); + if (boundary <= linear_backoff_thresh) + timeout = ((2 << boundary) - 1) * rto_base; + else + timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; + return jiffies_to_msecs(timeout); +} /** * retransmits_timed_out() - returns true if this connection has timed out * @sk: The current socket @@ -190,27 +191,21 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - const unsigned int rto_base = TCP_RTO_MIN; - unsigned int linear_backoff_thresh, start_ts; + unsigned int start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; - start_ts = tcp_retransmit_stamp(sk); - if (!start_ts) - return false; - + start_ts = tcp_sk(sk)->retrans_stamp; if (likely(timeout == 0)) { - linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); - - if (boundary <= linear_backoff_thresh) - timeout = ((2 << boundary) - 1) * rto_base; - else - timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + - (boundary - linear_backoff_thresh) * TCP_RTO_MAX; - timeout = jiffies_to_msecs(timeout); + unsigned int rto_base = TCP_RTO_MIN; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + timeout = tcp_model_timeout(sk, boundary, rto_base); } - return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout; + + return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ @@ -231,7 +226,7 @@ static int tcp_write_timeout(struct sock *sk) retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; expired = icsk->icsk_retransmits >= retry_until; } else { - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) { + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); @@ -240,7 +235,7 @@ static int tcp_write_timeout(struct sock *sk) sk_rethink_txhash(sk); } - retry_until = net->ipv4.sysctl_tcp_retries2; + retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < TCP_RTO_MAX; @@ -367,7 +362,7 @@ static void tcp_probe_timer(struct sock *sk) (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) goto abort; - max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; + max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; @@ -550,18 +545,20 @@ out_reset_timer: * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && - (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) && + (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; - icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); + icsk->icsk_rto = clamp(__tcp_set_rto(tp), + tcp_rto_min(sk), + TCP_RTO_MAX); } else { /* Use normal (exponential) backoff */ icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0)) + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2aacf2b34834..a6048cc7fc35 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -798,7 +798,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, kfree_skb(skb); return -EINVAL; } - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } @@ -935,7 +935,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; @@ -997,7 +997,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); - ipc.gso_size = up->gso_size; + ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); @@ -1243,7 +1243,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, } up->len += size; - if (!(up->corkflag || (flags&MSG_MORE))) + if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) ret = udp_push_pending_frames(sk); if (!ret) ret = size; @@ -1458,7 +1458,7 @@ drop: } EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); -void udp_destruct_sock(struct sock *sk) +void udp_destruct_common(struct sock *sk) { /* reclaim completely the forward allocated memory */ struct udp_sock *up = udp_sk(sk); @@ -1471,10 +1471,14 @@ void udp_destruct_sock(struct sock *sk) kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); +} +EXPORT_SYMBOL_GPL(udp_destruct_common); +static void udp_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); inet_sock_destruct(sk); } -EXPORT_SYMBOL_GPL(udp_destruct_sock); int udp_init_sock(struct sock *sk) { @@ -1482,7 +1486,6 @@ int udp_init_sock(struct sock *sk) sk->sk_destruct = udp_destruct_sock; return 0; } -EXPORT_SYMBOL_GPL(udp_init_sock); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { @@ -2050,7 +2053,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old; if (dst_hold_safe(dst)) { - old = xchg(&sk->sk_rx_dst, dst); + old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); dst_release(old); return old != dst; } @@ -2240,7 +2243,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); @@ -2398,7 +2401,7 @@ int udp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -2416,7 +2419,8 @@ int udp_v4_early_demux(struct sk_buff *skb) */ if (!inet_sk(sk)->inet_daddr && in_dev) return ip_mc_validate_source(skb, iph->daddr, - iph->saddr, iph->tos, + iph->saddr, + iph->tos & IPTOS_RT_MASK, skb->dev, in_dev, &itag); } return 0; @@ -2431,6 +2435,9 @@ void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { @@ -2464,9 +2471,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: if (val != 0) { - up->corkflag = 1; + WRITE_ONCE(up->corkflag, 1); } else { - up->corkflag = 0; + WRITE_ONCE(up->corkflag, 0); lock_sock(sk); push_pending_frames(sk); release_sock(sk); @@ -2501,7 +2508,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case UDP_SEGMENT: if (val < 0 || val > USHRT_MAX) return -EINVAL; - up->gso_size = val; + WRITE_ONCE(up->gso_size, val); break; /* @@ -2579,7 +2586,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: - val = up->corkflag; + val = READ_ONCE(up->corkflag); break; case UDP_ENCAP: @@ -2595,7 +2602,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, break; case UDP_SEGMENT: - val = up->gso_size; + val = READ_ONCE(up->gso_size); break; /* The following two cannot be changed on UDP sockets, the return is @@ -2672,10 +2679,17 @@ int udp_abort(struct sock *sk, int err) { lock_sock(sk); + /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing + * with close() + */ + if (sock_flag(sk, SOCK_DEAD)) + goto out; + sk->sk_err = err; sk->sk_error_report(sk); __udp_disconnect(sk, 0); +out: release_sock(sk); return 0; @@ -2834,7 +2848,7 @@ int udp4_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) - seq_puts(seq, " sl local_address rem_address st tx_queue " + seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode ref pointer drops"); else { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index aa343654abfc..2d22d39952da 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -359,7 +359,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct sock *sk; if (NAPI_GRO_CB(skb)->encap_mark || - (skb->ip_summed != CHECKSUM_PARTIAL && + (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 6539ff15e9a3..d03d74388870 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -186,6 +186,7 @@ EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb); void udp_tunnel_sock_release(struct socket *sock) { rcu_assign_sk_user_data(sock->sk, NULL); + synchronize_rcu(); kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 8545457752fb..27173549b000 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -20,6 +20,14 @@ struct udp_table udplite_table __read_mostly; EXPORT_SYMBOL(udplite_table); +/* Designate sk as UDP-Lite socket */ +static int udplite_sk_init(struct sock *sk) +{ + udp_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplite_rcv(struct sk_buff *skb) { return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); @@ -56,6 +64,8 @@ struct proto udplite_prot = { .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 1e5e2e4be0b2..e85b5f57d3e9 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -17,6 +17,7 @@ #include <net/xfrm.h> #include <net/ip.h> #include <net/l3mdev.h> +#include <net/inet_ecn.h> static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, int tos, int oif, @@ -126,7 +127,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) fl4->flowi4_proto = iph->protocol; fl4->daddr = reverse ? iph->saddr : iph->daddr; fl4->saddr = reverse ? iph->daddr : iph->saddr; - fl4->flowi4_tos = iph->tos; + fl4->flowi4_tos = iph->tos & ~INET_ECN_MASK; if (!ip_is_fragment(iph)) { switch (iph->protocol) { diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index 8dd0e6ab8606..0e1f5dc2766b 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -297,4 +297,3 @@ void __init xfrm4_protocol_init(void) { xfrm_input_register_afinfo(&xfrm4_input_afinfo); } -EXPORT_SYMBOL(xfrm4_protocol_init); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 627cd24b7c0d..5ffa8777ab09 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -316,9 +316,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) static void addrconf_mod_rs_timer(struct inet6_dev *idev, unsigned long when) { - if (!timer_pending(&idev->rs_timer)) + if (!mod_timer(&idev->rs_timer, jiffies + when)) in6_dev_hold(idev); - mod_timer(&idev->rs_timer, jiffies + when); } static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, @@ -739,6 +738,7 @@ static void dev_forward_change(struct inet6_dev *idev) { struct net_device *dev; struct inet6_ifaddr *ifa; + LIST_HEAD(tmp_addr_list); if (!idev) return; @@ -757,14 +757,24 @@ static void dev_forward_change(struct inet6_dev *idev) } } + read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa->flags&IFA_F_TENTATIVE) continue; + list_add_tail(&ifa->if_list_aux, &tmp_addr_list); + } + read_unlock_bh(&idev->lock); + + while (!list_empty(&tmp_addr_list)) { + ifa = list_first_entry(&tmp_addr_list, + struct inet6_ifaddr, if_list_aux); + list_del(&ifa->if_list_aux); if (idev->cnf.forwarding) addrconf_join_anycast(ifa); else addrconf_leave_anycast(ifa); } + inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &idev->cnf); @@ -1311,7 +1321,7 @@ retry: * idev->desync_factor if it's larger */ cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft); - max_desync_factor = min_t(__u32, + max_desync_factor = min_t(long, idev->cnf.max_desync_factor, cnf_temp_preferred_lft - regen_advance); @@ -2395,8 +2405,9 @@ static void addrconf_add_mroute(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, - .fc_type = RTN_UNICAST, + .fc_type = RTN_MULTICAST, .fc_nlinfo.nl_net = dev_net(dev), + .fc_protocol = RTPROT_KERNEL, }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); @@ -2477,12 +2488,18 @@ static void manage_tempaddrs(struct inet6_dev *idev, ipv6_ifa_notify(0, ift); } - if ((create || list_empty(&idev->tempaddr_list)) && - idev->cnf.use_tempaddr > 0) { + /* Also create a temporary address if it's enabled but no temporary + * address currently exists. + * However, we get called with valid_lft == 0, prefered_lft == 0, create == false + * as part of cleanup (ie. deleting the mngtmpaddr). + * We don't want that to result in creating a new temporary ip address. + */ + if (list_empty(&idev->tempaddr_list) && (valid_lft || prefered_lft)) + create = true; + + if (create && idev->cnf.use_tempaddr > 0) { /* When a new public address is created as described * in [ADDRCONF], also create a new temporary address. - * Also create a temporary address if it's enabled but - * no temporary address currently exists. */ read_unlock_bh(&idev->lock); ipv6_create_tempaddr(ifp, NULL, false); @@ -3053,6 +3070,9 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4); if (idev->dev->flags&IFF_POINTOPOINT) { + if (idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_NONE) + return; + addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; plen = 64; @@ -3654,7 +3674,8 @@ static int addrconf_ifdown(struct net_device *dev, int how) unsigned long event = how ? NETDEV_UNREGISTER : NETDEV_DOWN; struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa, *tmp; + struct inet6_ifaddr *ifa; + LIST_HEAD(tmp_addr_list); bool keep_addr = false; int state, i; @@ -3742,16 +3763,23 @@ restart: write_lock_bh(&idev->lock); } - list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + list_for_each_entry(ifa, &idev->addr_list, if_list) + list_add_tail(&ifa->if_list_aux, &tmp_addr_list); + write_unlock_bh(&idev->lock); + + while (!list_empty(&tmp_addr_list)) { struct fib6_info *rt = NULL; bool keep; + ifa = list_first_entry(&tmp_addr_list, + struct inet6_ifaddr, if_list_aux); + list_del(&ifa->if_list_aux); + addrconf_del_dad_work(ifa); keep = keep_addr && (ifa->flags & IFA_F_PERMANENT) && !addr_is_local(&ifa->addr); - write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); if (keep) { @@ -3782,15 +3810,14 @@ restart: addrconf_leave_solict(ifa->idev, &ifa->addr); } - write_lock_bh(&idev->lock); if (!keep) { + write_lock_bh(&idev->lock); list_del_rcu(&ifa->if_list); + write_unlock_bh(&idev->lock); in6_ifa_put(ifa); } } - write_unlock_bh(&idev->lock); - /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4121,7 +4148,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id, send_rs = send_mld && ipv6_accept_ra(ifp->idev) && ifp->idev->cnf.rtr_solicits != 0 && - (dev->flags&IFF_LOOPBACK) == 0; + (dev->flags & IFF_LOOPBACK) == 0 && + (dev->type != ARPHRD_TUNNEL); read_unlock_bh(&ifp->idev->lock); /* While dad is in progress mld report's source address is in6_addrany. diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 1d6ced37ad71..7fdd433b968e 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -306,7 +306,9 @@ static int ip6addrlbl_del(struct net *net, /* add default label */ static int __net_init ip6addrlbl_net_init(struct net *net) { - int err = 0; + struct ip6addrlbl_entry *p = NULL; + struct hlist_node *n; + int err; int i; ADDRLABEL(KERN_DEBUG "%s\n", __func__); @@ -315,14 +317,20 @@ static int __net_init ip6addrlbl_net_init(struct net *net) INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { - int ret = ip6addrlbl_add(net, - ip6addrlbl_init_table[i].prefix, - ip6addrlbl_init_table[i].prefixlen, - 0, - ip6addrlbl_init_table[i].label, 0); - /* XXX: should we free all rules when we catch an error? */ - if (ret && (!err || err != -ENOMEM)) - err = ret; + err = ip6addrlbl_add(net, + ip6addrlbl_init_table[i].prefix, + ip6addrlbl_init_table[i].prefixlen, + 0, + ip6addrlbl_init_table[i].label, 0); + if (err) + goto err_ip6addrlbl_add; + } + return 0; + +err_ip6addrlbl_add: + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { + hlist_del_rcu(&p->list); + kfree_rcu(p, rcu); } return err; } @@ -429,6 +437,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, { struct ifaddrlblmsg *ifal = nlmsg_data(nlh); ifal->ifal_family = AF_INET6; + ifal->__ifal_reserved = 0; ifal->ifal_prefixlen = prefixlen; ifal->ifal_flags = 0; ifal->ifal_index = ifindex; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 5c2351deedc8..c8f39d61b51e 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -107,6 +107,13 @@ static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } +void inet6_sock_destruct(struct sock *sk) +{ + inet6_cleanup_sock(sk); + inet_sock_destruct(sk); +} +EXPORT_SYMBOL_GPL(inet6_sock_destruct); + static int inet6_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -199,7 +206,7 @@ lookup_protocol: inet->hdrincl = 1; } - sk->sk_destruct = inet_sock_destruct; + sk->sk_destruct = inet6_sock_destruct; sk->sk_family = PF_INET6; sk->sk_protocol = protocol; @@ -502,6 +509,12 @@ void inet6_destroy_sock(struct sock *sk) } EXPORT_SYMBOL_GPL(inet6_destroy_sock); +void inet6_cleanup_sock(struct sock *sk) +{ + inet6_destroy_sock(sk); +} +EXPORT_SYMBOL_GPL(inet6_cleanup_sock); + /* * This does both peername and sockname. */ diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 78c974391567..2b68bd7c83c4 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -600,7 +600,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); memset(ah->auth_data, 0, ahp->icv_trunc_len); - if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) + err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN); + if (err) goto out_free; ip6h->priority = 0; diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 70611784c071..afc76062e1a1 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -97,6 +97,9 @@ struct calipso_map_cache_entry { static struct calipso_map_cache_bkt *calipso_cache; +static void calipso_cache_invalidate(void); +static void calipso_doi_putdef(struct calipso_doi *doi_def); + /* Label Mapping Cache Functions */ @@ -458,15 +461,10 @@ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) ret_val = -ENOENT; goto doi_remove_return; } - if (!refcount_dec_and_test(&doi_def->refcount)) { - spin_unlock(&calipso_doi_list_lock); - ret_val = -EBUSY; - goto doi_remove_return; - } list_del_rcu(&doi_def->list); spin_unlock(&calipso_doi_list_lock); - call_rcu(&doi_def->rcu, calipso_doi_free_rcu); + calipso_doi_putdef(doi_def); ret_val = 0; doi_remove_return: @@ -522,10 +520,8 @@ static void calipso_doi_putdef(struct calipso_doi *doi_def) if (!refcount_dec_and_test(&doi_def->refcount)) return; - spin_lock(&calipso_doi_list_lock); - list_del_rcu(&doi_def->list); - spin_unlock(&calipso_doi_list_lock); + calipso_cache_invalidate(); call_rcu(&doi_def->rcu, calipso_doi_free_rcu); } diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 727f958dd869..45ece6a898bf 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -54,7 +54,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk) fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = inet->inet_dport; fl6->fl6_sport = inet->inet_sport; - fl6->flowlabel = np->flow_label; + fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_uid = sk->sk_uid; if (!fl6->flowi6_oif) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index a7d996148eed..6529e46ad091 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -237,12 +237,15 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto) int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) { u8 *tail; - u8 *vaddr; int nfrags; struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; + if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE || + ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE) + goto cow; + if (!skb_cloned(skb)) { if (tailen <= skb_tailroom(skb)) { nfrags = 1; @@ -270,14 +273,10 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info page = pfrag->page; get_page(page); - vaddr = kmap_atomic(page); - - tail = vaddr + pfrag->offset; + tail = page_address(page) + pfrag->offset; esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto); - kunmap_atomic(vaddr); - nfrags = skb_shinfo(skb)->nr_frags; __skb_fill_page_desc(skb, nfrags, page, pfrag->offset, @@ -518,7 +517,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index eeee64a8a72c..69313ec24264 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -272,6 +272,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features secpath_reset(skb); + if (skb_needs_linearize(skb, skb->dev->features) && + __skb_linearize(skb)) + return -ENOMEM; return 0; } diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 20291c2036fc..fe2497ae4523 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -138,18 +138,23 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, len -= 2; while (len > 0) { - int optlen = nh[off + 1] + 2; - int i; + int optlen, i; - switch (nh[off]) { - case IPV6_TLV_PAD1: - optlen = 1; + if (nh[off] == IPV6_TLV_PAD1) { padlen++; if (padlen > 7) goto bad; - break; + off++; + len--; + continue; + } + if (len < 2) + goto bad; + optlen = nh[off + 1] + 2; + if (optlen > len) + goto bad; - case IPV6_TLV_PADN: + if (nh[off] == IPV6_TLV_PADN) { /* RFC 2460 states that the purpose of PadN is * to align the containing header to multiples * of 8. 7 is therefore the highest valid value. @@ -166,12 +171,7 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, if (nh[off + i] != 0) goto bad; } - break; - - default: /* Other TLV code so scan list */ - if (optlen > len) - goto bad; - + } else { tlv_count++; if (tlv_count > max_count) goto bad; @@ -191,7 +191,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, return false; padlen = 0; - break; } off += optlen; len -= optlen; @@ -309,7 +308,7 @@ fail_and_free: #endif if (ip6_parse_tlv(tlvprocdestopt_lst, skb, - init_net.ipv6.sysctl.max_dst_opts_cnt)) { + net->ipv6.sysctl.max_dst_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) @@ -848,7 +847,7 @@ fail_and_free: opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(tlvprochopopt_lst, skb, - init_net.ipv6.sysctl.max_hbh_opts_cnt)) { + net->ipv6.sysctl.max_hbh_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index ae365df8abf7..f356d3049143 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -142,6 +142,8 @@ int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type) optlen = 1; break; default: + if (len < 2) + goto bad; optlen = nh[offset + 1] + 2; if (optlen > len) goto bad; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 6d14cbe443f8..bfafd7649ccb 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -309,10 +309,9 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st } #if IS_ENABLED(CONFIG_IPV6_MIP6) -static void mip6_addr_swap(struct sk_buff *skb) +static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) { struct ipv6hdr *iph = ipv6_hdr(skb); - struct inet6_skb_parm *opt = IP6CB(skb); struct ipv6_destopt_hao *hao; struct in6_addr tmp; int off; @@ -329,7 +328,7 @@ static void mip6_addr_swap(struct sk_buff *skb) } } #else -static inline void mip6_addr_swap(struct sk_buff *skb) {} +static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {} #endif static struct dst_entry *icmpv6_route_lookup(struct net *net, @@ -396,30 +395,39 @@ relookup_failed: return ERR_PTR(err); } -static int icmp6_iif(const struct sk_buff *skb) +static struct net_device *icmp6_dev(const struct sk_buff *skb) { - int iif = skb->dev->ifindex; + struct net_device *dev = skb->dev; /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so * get the real device index. Same is needed for replies to a link * local address on a device enslaved to an L3 master device */ - if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { + if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); - if (rt6) - iif = rt6->rt6i_idev->dev->ifindex; + /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), + * and ip6_null_entry could be set to skb if no route is found. + */ + if (rt6 && rt6->rt6i_idev) + dev = rt6->rt6i_idev->dev; } - return iif; + return dev; +} + +static int icmp6_iif(const struct sk_buff *skb) +{ + return icmp6_dev(skb)->ifindex; } /* * Send an ICMP message in response to a packet in error */ -static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, - const struct in6_addr *force_saddr) +void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct in6_addr *force_saddr, + const struct inet6_skb_parm *parm) { struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); @@ -512,7 +520,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!(skb->dev->flags&IFF_LOOPBACK) && !icmpv6_global_allow(type)) goto out_bh_enable; - mip6_addr_swap(skb); + mip6_addr_swap(skb, parm); memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; @@ -592,12 +600,13 @@ out: out_bh_enable: local_bh_enable(); } +EXPORT_SYMBOL(icmp6_send); /* Slightly more convenient version of icmp6_send. */ void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { - icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL); + icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb)); kfree_skb(skb); } @@ -654,10 +663,10 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, } if (type == ICMP_TIME_EXCEEDED) icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); else icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, - info, &temp_saddr); + info, &temp_saddr, IP6CB(skb2)); if (rt) ip6_rt_put(rt); @@ -799,7 +808,7 @@ out: static int icmpv6_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); - struct net_device *dev = skb->dev; + struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; struct icmp6hdr *hdr; diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 7858fa9ea103..87744eb8d0c4 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -480,6 +480,7 @@ int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) rcu_read_lock(); + ret = -ESRCH; ila = ila_lookup_by_params(&xp, ilan); if (ila) { ret = ila_dump_info(ila, diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index d9e2575dad94..d8391921363f 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -311,7 +311,7 @@ not_unique: return -EADDRNOTAVAIL; } -static u32 inet6_sk_port_offset(const struct sock *sk) +static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); @@ -323,7 +323,7 @@ static u32 inet6_sk_port_offset(const struct sock *sk) int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { - u32 port_offset = 0; + u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b924941b96a3..92bc56028b8b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -112,7 +112,7 @@ void fib6_update_sernum(struct net *net, struct fib6_info *f6i) fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) - fn->fn_sernum = fib6_new_sernum(net); + WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); } /* @@ -544,12 +544,13 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; - cb->args[5] = w->root->fn_sernum; + cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { - if (cb->args[5] != w->root->fn_sernum) { + int sernum = READ_ONCE(w->root->fn_sernum); + if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ - cb->args[5] = w->root->fn_sernum; + cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; @@ -906,6 +907,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, { struct fib6_table *table = rt->fib6_table; + /* Flush all cached dst in exception table */ + rt6_flush_exceptions(rt); if (rt->rt6i_pcpu) fib6_drop_pcpu_from(rt, table); @@ -1201,7 +1204,7 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt, /* paired with smp_rmb() in rt6_get_cookie_safe() */ smp_wmb(); while (fn) { - fn->fn_sernum = sernum; + WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } @@ -1348,13 +1351,9 @@ out: if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); -#if RT6_DEBUG >= 2 - if (!pn_leaf) { - WARN_ON(!pn_leaf); + if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; - } -#endif fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } @@ -1756,9 +1755,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; - /* Flush all cached dst in exception table */ - rt6_flush_exceptions(rt); - /* Reset round-robin state, if necessary */ if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; @@ -1984,8 +1980,8 @@ static int fib6_clean_node(struct fib6_walker *w) }; if (c->sernum != FIB6_NO_SERNUM_CHANGE && - w->node->fn_sernum != c->sernum) - w->node->fn_sernum = c->sernum; + READ_ONCE(w->node->fn_sernum) != c->sernum) + WRITE_ONCE(w->node->fn_sernum, c->sernum); if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); @@ -2333,7 +2329,7 @@ static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; - iter->sernum = iter->w.root->fn_sernum; + iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } @@ -2361,8 +2357,10 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { - if (iter->sernum != iter->w.root->fn_sernum) { - iter->sernum = iter->w.root->fn_sernum; + int sernum = READ_ONCE(iter->w.root->fn_sernum); + + if (iter->sernum != sernum) { + iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); @@ -2417,8 +2415,10 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) iter->skip = *pos; if (iter->tbl) { + loff_t p = 0; + ipv6_route_seq_setup_walk(iter, net); - return ipv6_route_seq_next(seq, NULL, pos); + return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index f994f50e1516..1858cf783a4f 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -518,7 +518,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) { - int uninitialized_var(err); + int err; struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_flowlabel_req freq; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 7cc9cd83ecb5..aa8ada354a39 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -392,7 +392,6 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net, if (!(nt->parms.o_flags & TUNNEL_SEQ)) dev->features |= NETIF_F_LLTX; - dev_hold(dev); ip6gre_tunnel_link(ign, nt); return nt; @@ -732,6 +731,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, { struct ip6_tnl *tunnel = netdev_priv(dev); __be16 protocol; + __be16 flags; if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -741,16 +741,13 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, else fl6->daddr = tunnel->parms.raddr; - if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) - return -ENOMEM; - /* Push GRE header. */ protocol = (dev->type == ARPHRD_ETHER) ? htons(ETH_P_TEB) : proto; if (tunnel->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - __be16 flags; + int tun_hlen; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || @@ -768,21 +765,27 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, dsfield = key->tos; flags = key->tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); - tunnel->tun_hlen = gre_calc_hlen(flags); + tun_hlen = gre_calc_hlen(flags); - gre_build_header(skb, tunnel->tun_hlen, + if (skb_cow_head(skb, dev->needed_headroom ?: tun_hlen + tunnel->encap_hlen)) + return -ENOMEM; + + gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + if (skb_cow_head(skb, dev->needed_headroom ?: tunnel->hlen)) + return -ENOMEM; + + flags = tunnel->parms.o_flags; - gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -946,7 +949,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, __be16 proto; __u32 mtu; int nhoff; - int thoff; if (!pskb_inet_may_pull(skb)) goto tx_err; @@ -958,19 +960,26 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto tx_err; truncate = true; } - nhoff = skb_network_header(skb) - skb_mac_header(skb); + nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; - thoff = skb_transport_header(skb) - skb_mac_header(skb); - if (skb->protocol == htons(ETH_P_IPV6) && - (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) - truncate = true; + if (skb->protocol == htons(ETH_P_IPV6)) { + int thoff; + + if (skb_transport_header_was_set(skb)) + thoff = skb_transport_offset(skb); + else + thoff = nhoff + sizeof(struct ipv6hdr); + if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) + truncate = true; + } if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; @@ -1013,12 +1022,14 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, ntohl(tun_id), ntohl(md->u.index), truncate, false); + proto = htons(ETH_P_ERSPAN); } else if (md->version == 2) { erspan_build_header_v2(skb, ntohl(tun_id), md->u.md2.dir, get_hwid(&md->u.md2), truncate, false); + proto = htons(ETH_P_ERSPAN2); } else { goto tx_err; } @@ -1041,25 +1052,26 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, break; } - if (t->parms.erspan_ver == 1) + if (t->parms.erspan_ver == 1) { erspan_build_header(skb, ntohl(t->parms.o_key), t->parms.index, truncate, false); - else if (t->parms.erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (t->parms.erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(t->parms.o_key), t->parms.dir, t->parms.hwid, truncate, false); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto tx_err; + } fl6.daddr = t->parms.raddr; } /* Push GRE header. */ - proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) - : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) @@ -1140,18 +1152,25 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu, return; if (rt->dst.dev) { - dev->needed_headroom = rt->dst.dev->hard_header_len + - t_hlen; + unsigned short dst_len = rt->dst.dev->hard_header_len + + t_hlen; + + if (t->dev->header_ops) + dev->hard_header_len = dst_len; + else + dev->needed_headroom = dst_len; if (set_mtu) { - dev->mtu = rt->dst.dev->mtu - t_hlen; + int mtu = rt->dst.dev->mtu - t_hlen; + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; if (dev->type == ARPHRD_ETHER) - dev->mtu -= ETH_HLEN; + mtu -= ETH_HLEN; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } } ip6_rt_put(rt); @@ -1166,7 +1185,12 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel) tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; t_hlen = tunnel->hlen + sizeof(struct ipv6hdr); - tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + + if (tunnel->dev->header_ops) + tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen; + else + tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen; + return t_hlen; } @@ -1493,6 +1517,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) } ip6gre_tnl_init_features(dev); + dev_hold(dev); return 0; cleanup_dst_cache_init: @@ -1535,8 +1560,6 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev) strcpy(tunnel->parms.name, dev->name); tunnel->hlen = sizeof(struct ipv6hdr) + 4; - - dev_hold(dev); } static struct inet6_protocol ip6gre_protocol __read_mostly = { @@ -1886,6 +1909,7 @@ static int ip6erspan_tap_init(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip6erspan_tnl_link_config(tunnel, 1); + dev_hold(dev); return 0; cleanup_dst_cache_init: @@ -1991,8 +2015,6 @@ static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev, if (tb[IFLA_MTU]) ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); - dev_hold(dev); - out: return err; } diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 02045494c24c..9e3574880cb0 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -9,6 +9,8 @@ #if IS_ENABLED(CONFIG_IPV6) +#if !IS_BUILTIN(CONFIG_IPV6) + static ip6_icmp_send_t __rcu *ip6_icmp_send; int inet6_register_icmp_sender(ip6_icmp_send_t *fn) @@ -31,18 +33,52 @@ int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) } EXPORT_SYMBOL(inet6_unregister_icmp_sender); -void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) +void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, + const struct inet6_skb_parm *parm) { ip6_icmp_send_t *send; rcu_read_lock(); send = rcu_dereference(ip6_icmp_send); + if (send) + send(skb, type, code, info, NULL, parm); + rcu_read_unlock(); +} +EXPORT_SYMBOL(__icmpv6_send); +#endif + +#if IS_ENABLED(CONFIG_NF_NAT) +#include <net/netfilter/nf_conntrack.h> +void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) +{ + struct inet6_skb_parm parm = { 0 }; + struct sk_buff *cloned_skb = NULL; + enum ip_conntrack_info ctinfo; + struct in6_addr orig_ip; + struct nf_conn *ct; - if (!send) + ct = nf_ct_get(skb_in, &ctinfo); + if (!ct || !(ct->status & IPS_SRC_NAT)) { + __icmpv6_send(skb_in, type, code, info, &parm); + return; + } + + if (skb_shared(skb_in)) + skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); + + if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || + (skb_network_header(skb_in) + sizeof(struct ipv6hdr)) > + skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, + skb_network_offset(skb_in) + sizeof(struct ipv6hdr)))) goto out; - send(skb, type, code, info, NULL); + + orig_ip = ipv6_hdr(skb_in)->saddr; + ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; + __icmpv6_send(skb_in, type, code, info, &parm); + ipv6_hdr(skb_in)->saddr = orig_ip; out: - rcu_read_unlock(); + consume_skb(cloned_skb); } -EXPORT_SYMBOL(icmpv6_send); +EXPORT_SYMBOL(icmpv6_ndo_send); +#endif #endif diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index acf0749ee5bb..2bdb03a45baf 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -47,18 +47,25 @@ #include <net/inet_ecn.h> #include <net/dst_metadata.h> +void udp_v6_early_demux(struct sk_buff *); +void tcp_v6_early_demux(struct sk_buff *); static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) { - void (*edemux)(struct sk_buff *skb); - - if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { - const struct inet6_protocol *ipprot; - - ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) - edemux(skb); + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && + !skb_dst(skb) && !skb->sk) { + switch (ipv6_hdr(skb)->nexthdr) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) + tcp_v6_early_demux(skb); + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) + udp_v6_early_demux(skb); + break; + } } + if (!skb_valid_dst(skb)) ip6_route_input(skb); } @@ -222,16 +229,6 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, if (ipv6_addr_is_multicast(&hdr->saddr)) goto err; - /* While RFC4291 is not explicit about v4mapped addresses - * in IPv6 headers, it seems clear linux dual-stack - * model can not deal properly with these. - * Security models could be fooled by ::ffff:127.0.0.1 for example. - * - * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02 - */ - if (ipv6_addr_v4mapped(&hdr->saddr)) - goto err; - skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index c7e495f12011..6c47cd0ef240 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -98,6 +98,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); segs = ops->callbacks.gso_segment(skb, features); + if (!segs) + skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 22665e3638ac..0872df066a4e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -106,7 +106,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * if (lwtunnel_xmit_redirect(dst->lwtstate)) { int res = lwtunnel_xmit(skb); - if (res < 0 || res == LWTUNNEL_XMIT_DONE) + if (res != LWTUNNEL_XMIT_CONTINUE) return res; } @@ -128,8 +128,48 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * return -EINVAL; } +static int +ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, + struct sk_buff *skb, unsigned int mtu) +{ + struct sk_buff *segs, *nskb; + netdev_features_t features; + int ret = 0; + + /* Please see corresponding comment in ip_finish_output_gso + * describing the cases where GSO segment length exceeds the + * egress MTU. + */ + features = netif_skb_features(skb); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + skb_list_walk_safe(segs, segs, nskb) { + int err; + + skb_mark_not_on_list(segs); + /* Last GSO segment can be smaller than gso_size (and MTU). + * Adding a fragment header would produce an "atomic fragment", + * which is considered harmful (RFC-8021). Avoid that. + */ + err = segs->len > mtu ? + ip6_fragment(net, sk, segs, ip6_finish_output2) : + ip6_finish_output2(net, sk, segs); + if (err && ret == 0) + ret = err; + } + + return ret; +} + static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { + unsigned int mtu; int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); @@ -141,12 +181,16 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; + IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif - if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || + mtu = ip6_skb_dst_mtu(skb); + if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu)) + return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); + + if ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)) || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); @@ -421,7 +465,9 @@ int ip6_forward(struct sk_buff *skb) if (skb_warn_if_lro(skb)) goto drop; - if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { + if (!net->ipv6.devconf_all->disable_policy && + (!idev || !idev->cnf.disable_policy) && + !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -694,6 +740,9 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); + /* We prevent @rt from being freed. */ + rcu_read_lock(); + for (;;) { /* Prepare header of the next frame, * before previous one went down. */ @@ -736,6 +785,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); + rcu_read_unlock(); return 0; } @@ -743,6 +793,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); + rcu_read_unlock(); return err; slow_path_clean: @@ -1219,8 +1270,6 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (np->frag_size) mtu = np->frag_size; } - if (mtu < IPV6_MIN_MTU) - return -EINVAL; cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; @@ -1280,8 +1329,6 @@ static int __ip6_append_data(struct sock *sk, fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - - sizeof(struct frag_hdr); headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + @@ -1289,6 +1336,13 @@ static int __ip6_append_data(struct sock *sk, sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; + if (mtu <= fragheaderlen || + ((mtu - fragheaderlen) & ~7) + fragheaderlen <= sizeof(struct frag_hdr)) + goto emsgsize; + + maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - + sizeof(struct frag_hdr); + /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ @@ -1356,7 +1410,7 @@ emsgsize: unsigned int datalen; unsigned int fraglen; unsigned int fraggap; - unsigned int alloclen; + unsigned int alloclen, alloc_extra; unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ @@ -1383,17 +1437,28 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; pagedlen = 0; + alloc_extra = hh_len; + alloc_extra += dst_exthdrlen; + alloc_extra += rt->dst.trailer_len; + + /* We just reserve space for fragment header. + * Note: this may be overallocation if the message + * (without MSG_MORE) fits into the MTU. + */ + alloc_extra += sizeof(struct frag_hdr); + if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else if (!paged) + else if (!paged && + (fraglen + alloc_extra < SKB_MAX_ALLOC || + !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } - - alloclen += dst_exthdrlen; + alloclen += alloc_extra; if (datalen != length + fraggap) { /* @@ -1403,30 +1468,21 @@ alloc_new_skb: datalen += rt->dst.trailer_len; } - alloclen += rt->dst.trailer_len; fraglen = datalen + fragheaderlen; - /* - * We just reserve space for fragment header. - * Note: this may be overallocation if the message - * (without MSG_MORE) fits into the MTU. - */ - alloclen += sizeof(struct frag_hdr); - copy = datalen - transhdrlen - fraggap - pagedlen; if (copy < 0) { err = -EINVAL; goto error; } if (transhdrlen) { - skb = sock_alloc_send_skb(sk, - alloclen + hh_len, + skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = alloc_skb(alloclen + hh_len, + skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; @@ -1680,8 +1736,13 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + u8 icmp6_type; - ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type); + if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + icmp6_type = fl6->fl6_icmp_type; + else + icmp6_type = icmp6_hdr(skb)->icmp6_type; + ICMP6MSGOUT_INC_STATS(net, idev, icmp6_type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index b825ac025d5b..56309c851928 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -272,7 +272,6 @@ static int ip6_tnl_create2(struct net_device *dev) strcpy(t->parms.name, dev->name); - dev_hold(dev); ip6_tnl_link(ip6n, t); return 0; @@ -405,7 +404,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; unsigned int nhoff = raw - skb->data; unsigned int off = nhoff + sizeof(*ipv6h); - u8 next, nexthdr = ipv6h->nexthdr; + u8 nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { struct ipv6_opt_hdr *hdr; @@ -416,25 +415,25 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { - struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr; - if (frag_hdr->frag_off) - break; optlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { optlen = (hdr->hdrlen + 2) << 2; } else { optlen = ipv6_optlen(hdr); } - /* cache hdr->nexthdr, since pskb_may_pull() might - * invalidate hdr - */ - next = hdr->nexthdr; - if (nexthdr == NEXTHDR_DEST) { - u16 i = 2; - /* Remember : hdr is no longer valid at this point. */ - if (!pskb_may_pull(skb, off + optlen)) + if (!pskb_may_pull(skb, off + optlen)) + break; + + hdr = (struct ipv6_opt_hdr *)(skb->data + off); + if (nexthdr == NEXTHDR_FRAGMENT) { + struct frag_hdr *frag_hdr = (struct frag_hdr *)hdr; + + if (frag_hdr->frag_off) break; + } + if (nexthdr == NEXTHDR_DEST) { + u16 i = 2; while (1) { struct ipv6_tlv_tnl_enc_lim *tel; @@ -455,7 +454,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) i++; } } - nexthdr = next; + nexthdr = hdr->nexthdr; off += optlen; } return 0; @@ -1006,14 +1005,14 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) - pr_warn("%s xmit: Local address not yet configured!\n", - p->name); + pr_warn_ratelimited("%s xmit: Local address not yet configured!\n", + p->name); else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE))) - pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", - p->name); + pr_warn_ratelimited("%s xmit: Routing loop! Remote address found on this node!\n", + p->name); else ret = 1; rcu_read_unlock(); @@ -1207,8 +1206,8 @@ route_lookup: */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) @@ -1436,6 +1435,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; int t_hlen; + int mtu; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); @@ -1478,12 +1478,13 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) dev->hard_header_len = rt->dst.dev->hard_header_len + t_hlen; - dev->mtu = rt->dst.dev->mtu - t_hlen; + mtu = rt->dst.dev->mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) - dev->mtu -= 8; + mtu -= 8; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); } ip6_rt_put(rt); } @@ -1866,6 +1867,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev) dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; + dev_hold(dev); return 0; destroy_dst: @@ -1909,7 +1911,6 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); t->parms.proto = IPPROTO_IPV6; - dev_hold(dev); rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; @@ -2222,6 +2223,16 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head t = rtnl_dereference(t->next); } } + + t = rtnl_dereference(ip6n->tnls_wc[0]); + while (t) { + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, list); + t = rtnl_dereference(t->next); + } } static int __net_init ip6_tnl_init_net(struct net *net) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 94f16e82a458..a64050e77588 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -196,7 +196,6 @@ static int vti6_tnl_create2(struct net_device *dev) strcpy(t->parms.name, dev->name); - dev_hold(dev); vti6_tnl_link(ip6n, t); return 0; @@ -563,12 +562,12 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); break; default: goto tx_err; @@ -800,6 +799,8 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); + memset(&p1, 0, sizeof(p1)); + switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { @@ -925,6 +926,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev) dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; + dev_hold(dev); return 0; } @@ -956,7 +958,6 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) struct vti6_net *ip6n = net_generic(net, vti6_net_id); t->parms.proto = IPPROTO_IPV6; - dev_hold(dev); rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 35e7092eceb3..329bad6cbb76 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -245,7 +245,9 @@ static int __net_init ip6mr_rules_init(struct net *net) return 0; err2: + rtnl_lock(); ip6mr_free_table(mrt); + rtnl_unlock(); err1: fib_rules_unregister(ops); return err; @@ -1062,7 +1064,7 @@ static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, And all this only to mangle msg->im6_msgtype and to set msg->im6_mbz to "mbz" :-) */ - skb_push(skb, -skb_network_offset(pkt)); + __skb_pull(skb, skb_network_offset(pkt)); skb_push(skb, sizeof(*msg)); skb_reset_transport_header(skb); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4e1da6cb9ed7..1c155e610c06 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -166,15 +166,18 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, rtnl_lock(); lock_sock(sk); + /* Another thread has converted the socket into IPv4 with + * IPV6_ADDRFORM concurrently. + */ + if (unlikely(sk->sk_family != AF_INET6)) + goto unlock; + switch (optname) { case IPV6_ADDRFORM: if (optlen < sizeof(int)) goto e_inval; if (val == PF_INET) { - struct ipv6_txoptions *opt; - struct sk_buff *pktopt; - if (sk->sk_type == SOCK_RAW) break; @@ -205,7 +208,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, break; } - fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); __ipv6_sock_ac_close(sk); @@ -240,14 +242,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sk->sk_socket->ops = &inet_dgram_ops; sk->sk_family = PF_INET; } - opt = xchg((__force struct ipv6_txoptions **)&np->opt, - NULL); - if (opt) { - atomic_sub(opt->tot_len, &sk->sk_omem_alloc); - txopt_put(opt); - } - pktopt = xchg(&np->pktoptions, NULL); - kfree_skb(pktopt); + + /* Disable all options not to allocate memory anymore, + * but there is still a race. See the lockless path + * in udpv6_sendmsg() and ipv6_local_rxpmtu(). + */ + np->rxopt.all = 0; + + inet6_cleanup_sock(sk); /* * ... and add it to the refcnt debug socks count @@ -913,6 +915,7 @@ pref_skip_coa: break; } +unlock: release_sock(sk); if (needs_rtnl) rtnl_unlock(); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index f2f8551416c3..3d048401141f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1606,10 +1606,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) IPV6_TLV_PADN, 0 }; /* we assume size > sizeof(ra) here */ - /* limit our allocations to order-0 page */ - size = min_t(int, size, SKB_MAX_ORDER(0, 0)); skb = sock_alloc_send_skb(sk, size, 1, &err); - if (!skb) return NULL; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 673a4a932f2a..a640deb9ab14 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -195,7 +195,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || ndisc_ops_is_useropt(dev, opt->nd_opt_type); } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 6d0b1f3e927b..5679fa3f696a 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -17,10 +17,10 @@ #include <net/xfrm.h> #include <net/netfilter/nf_queue.h> -int ip6_route_me_harder(struct net *net, struct sk_buff *skb) +int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); - struct sock *sk = sk_to_full_sk(skb->sk); + struct sock *sk = sk_to_full_sk(sk_partial); unsigned int hh_len; struct dst_entry *dst; int strict = (ipv6_addr_type(&iph->daddr) & @@ -81,7 +81,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) - return ip6_route_me_harder(entry->state.net, skb); + return ip6_route_me_harder(entry->state.net, entry->state.sk, skb); } return 0; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index daf2e9e9193d..d93490ac8275 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -276,6 +276,7 @@ ip6t_do_table(struct sk_buff *skb, * things we don't know, ie. tcp syn flag or ports). If the * rule is also a fragment-specific rule, non-fragments won't * match it. */ + acpar.fragoff = 0; acpar.hotdrop = false; acpar.state = state; @@ -1448,6 +1449,8 @@ translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index b0524b18c4fb..acba3757ff60 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -60,7 +60,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(state->net, skb); + err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c index c6bf580d0f33..c456e2f902b9 100644 --- a/net/ipv6/netfilter/nf_log_ipv6.c +++ b/net/ipv6/netfilter/nf_log_ipv6.c @@ -300,9 +300,11 @@ static void dump_ipv6_mac_header(struct nf_log_buf *m, switch (dev->type) { case ARPHRD_ETHER: - nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", - eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, - ntohs(eth_hdr(skb)->h_proto)); + nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest); + nf_log_dump_vlan(m, skb); + nf_log_buf_add(m, "MACPROTO=%04x ", + ntohs(eth_hdr(skb)->h_proto)); return; default: break; diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index ca6d38698b1a..2b6a3b27f670 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -352,7 +352,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = ip6_route_me_harder(state->net, skb); + err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c index f14de4b6d639..5e5463459563 100644 --- a/net/ipv6/netfilter/nf_socket_ipv6.c +++ b/net/ipv6/netfilter/nf_socket_ipv6.c @@ -102,9 +102,9 @@ nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff, struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, const struct net_device *indev) { - __be16 uninitialized_var(dport), uninitialized_var(sport); + __be16 dport, sport; const struct in6_addr *daddr = NULL, *saddr = NULL; - struct ipv6hdr *iph = ipv6_hdr(skb); + struct ipv6hdr *iph = ipv6_hdr(skb), ipv6_var; struct sk_buff *data_skb = NULL; int doff = 0; int thoff = 0, tproto; @@ -134,8 +134,6 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, thoff + sizeof(*hp); } else if (tproto == IPPROTO_ICMPV6) { - struct ipv6hdr ipv6_var; - if (extract_icmp6_fields(skb, thoff, &tproto, &saddr, &daddr, &sport, &dport, &ipv6_var)) return NULL; diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index da3f1f8cb325..afe79cb46e63 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -52,7 +52,7 @@ static unsigned int nf_route_table_hook(void *priv, skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(state->net, skb); + err = ip6_route_me_harder(state->net, state->sk, skb); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index d8b5b60b7d53..d8bb7c85287c 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -16,8 +16,8 @@ #include <net/netfilter/ipv6/nf_dup_ipv6.h> struct nft_dup_ipv6 { - enum nft_registers sreg_addr:8; - enum nft_registers sreg_dev:8; + u8 sreg_addr; + u8 sreg_dev; }; static void nft_dup_ipv6_eval(const struct nft_expr *expr, @@ -41,16 +41,16 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); - err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in6_addr)); + err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + sizeof(struct in6_addr)); if (err < 0) return err; - if (tb[NFTA_DUP_SREG_DEV] != NULL) { - priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); - } - return 0; + if (tb[NFTA_DUP_SREG_DEV]) + err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + &priv->sreg_dev, sizeof(int)); + + return err; } static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 36be3cf0adef..fa71e40789ed 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -41,6 +41,9 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv, if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) { lookup_flags |= RT6_LOOKUP_F_IFACE; fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev); + } else if ((priv->flags & NFTA_FIB_F_IIF) && + (netif_is_l3_master(dev) || netif_is_l3_slave(dev))) { + fl6->flowi6_oif = dev->ifindex; } if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST) @@ -189,7 +192,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev) + if (oif && oif != rt->rt6i_idev->dev && + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex) goto put_rt_err; switch (priv->result) { diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 868ae23dbae1..3829b565c645 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -14,29 +14,11 @@ static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { - const struct { - struct in6_addr dst; - struct in6_addr src; - } __aligned(SIPHASH_ALIGNMENT) combined = { - .dst = *dst, - .src = *src, - }; - u32 hash, id; - - /* Note the following code is not safe, but this is okay. */ - if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) - get_random_bytes(&net->ipv4.ip_id_key, - sizeof(net->ipv4.ip_id_key)); - - hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key); - - /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, - * set the hight order instead thus minimizing possible future - * collisions. - */ - id = ip_idents_reserve(hash, 1); - if (unlikely(!id)) - id = 1 << 31; + u32 id; + + do { + id = prandom_u32(); + } while (!id); return id; } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 5c9be8594483..e065f49a4ae3 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -101,7 +101,8 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) addr_type = ipv6_addr_type(daddr); if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || (addr_type & IPV6_ADDR_MAPPED) || - (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if && + l3mdev_master_ifindex_by_index(sock_net(sk), oif) != sk->sk_bound_dev_if)) return -EINVAL; /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8d19729f8516..31aad22c59fc 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -303,7 +303,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && - !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) { + !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { @@ -544,6 +544,7 @@ csum_copy_err: static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { + struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; @@ -561,6 +562,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; + opt = inet6_sk(sk)->cork.opt; + total_len -= opt ? opt->opt_flen : 0; + if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); @@ -660,7 +664,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->ip_summed = CHECKSUM_NONE; - sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); @@ -828,7 +832,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) @@ -1255,8 +1260,6 @@ static void raw6_destroy(struct sock *sk) lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - - inet6_destroy_sock(sk); } static int rawv6_init_sk(struct sock *sk) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index c6132e39ab16..b596727f0497 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -302,7 +302,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_network_header_len(skb)); rcu_read_lock(); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); + __IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMOKS); rcu_read_unlock(); fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; @@ -317,7 +317,7 @@ out_oom: net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n"); out_fail: rcu_read_lock(); - __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); + __IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS); rcu_read_unlock(); inet_frag_kill(&fq->q); return -1; @@ -347,7 +347,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - if (!(fhdr->frag_off & htons(0xFFF9))) { + if (!(fhdr->frag_off & htons(IP6_OFFSET | IP6_MF))) { /* It is not a fragmented frame */ skb->transport_header += sizeof(struct frag_hdr); __IP6_INC_STATS(net, @@ -355,6 +355,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb) IP6CB(skb)->nhoff = (u8 *)fhdr - skb_network_header(skb); IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = ntohs(hdr->payload_len) + + sizeof(struct ipv6hdr); return 1; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dad35cd48807..9dbc9c0cbc5a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -45,6 +45,7 @@ #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/jhash.h> +#include <linux/siphash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> @@ -91,7 +92,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static int ip6_dst_gc(struct dst_ops *ops); +static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -1337,17 +1338,24 @@ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { - static u32 seed __read_mostly; - u32 val; + static siphash_key_t rt6_exception_key __read_mostly; + struct { + struct in6_addr dst; + struct in6_addr src; + } __aligned(SIPHASH_ALIGNMENT) combined = { + .dst = *dst, + }; + u64 val; - net_get_random_once(&seed, sizeof(seed)); - val = jhash(dst, sizeof(*dst), seed); + net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) - val = jhash(src, sizeof(*src), val); + combined.src = *src; #endif - return hash_32(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); + val = siphash(&combined, sizeof(combined), &rt6_exception_key); + + return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table @@ -1446,6 +1454,7 @@ static int rt6_insert_exception(struct rt6_info *nrt, struct rt6_exception_bucket *bucket; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; + int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); @@ -1507,7 +1516,9 @@ static int rt6_insert_exception(struct rt6_info *nrt, bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; - if (bucket->depth > FIB6_MAX_DEPTH) + /* Randomize max depth to avoid some side channels attacks. */ + max_depth = FIB6_MAX_DEPTH + prandom_u32_max(FIB6_MAX_DEPTH); + while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: @@ -2309,7 +2320,7 @@ static void ip6_link_failure(struct sk_buff *skb) if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) - fn->fn_sernum = -1; + WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); @@ -2756,29 +2767,30 @@ out: return dst; } -static int ip6_dst_gc(struct dst_ops *ops) +static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; - int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; + unsigned int val; int entries; entries = dst_entries_get_fast(ops); - if (time_after(rt_last_gc + rt_min_interval, jiffies) && - entries <= rt_max_size) + if (entries > ops->gc_thresh) + entries = dst_entries_get_slow(ops); + + if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; - net->ipv6.ip6_rt_gc_expire++; - fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, true); + fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) - net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1; + atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: - net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity; - return entries > rt_max_size; + val = atomic_read(&net->ipv6.ip6_rt_gc_expire); + atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); } static int ip6_convert_metrics(struct net *net, struct fib6_info *rt, @@ -4402,6 +4414,19 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } +static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + if (nla_len(nla) < sizeof(*gw)) { + NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY"); + return -EINVAL; + } + + *gw = nla_get_in6_addr(nla); + + return 0; +} + static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { @@ -4442,7 +4467,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { - r_cfg.fc_gateway = nla_get_in6_addr(nla); + err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, + extack); + if (err) + goto cleanup; + r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); @@ -4514,9 +4543,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, * nexthops have been replaced by first new, the rest should * be added to it. */ - cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | - NLM_F_REPLACE); - cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; + if (cfg->fc_nlinfo.nlh) { + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | + NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; + } nhn++; } @@ -4574,7 +4605,13 @@ static int ip6_route_multipath_del(struct fib6_config *cfg, nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { - nla_memcpy(&r_cfg.fc_gateway, nla, 16); + err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, + extack); + if (err) { + last_err = err; + goto next_rtnh; + } + r_cfg.fc_flags |= RTF_GATEWAY; } } @@ -4582,6 +4619,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg, if (err) last_err = err; +next_rtnh: rtnh = rtnh_next(rtnh, &remaining); } @@ -5295,7 +5333,7 @@ static int __net_init ip6_route_net_init(struct net *net) #endif net->ipv6.sysctl.flush_delay = 0; - net->ipv6.sysctl.ip6_rt_max_size = 4096; + net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; @@ -5303,7 +5341,7 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; - net->ipv6.ip6_rt_gc_expire = 30*HZ; + atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: @@ -5337,10 +5375,16 @@ static void __net_exit ip6_route_net_exit(struct net *net) static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, - sizeof(struct ipv6_route_iter)); - proc_create_net_single("rt6_stats", 0444, net->proc_net, - rt6_stats_seq_show, NULL); + if (!proc_create_net("ipv6_route", 0, net->proc_net, + &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter))) + return -ENOMEM; + + if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, + rt6_stats_seq_show, NULL)) { + remove_proc_entry("ipv6_route", net->proc_net); + return -ENOMEM; + } #endif return 0; } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 9b2f272ca164..89d55770ac74 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -130,6 +130,11 @@ static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } + if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) { + err = -EINVAL; + goto out_unlock; + } + if (hinfo) { err = seg6_hmac_info_del(net, hmackeyid); if (err) diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 8546f94f30d4..b801283da28d 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -406,7 +406,6 @@ int __init seg6_hmac_init(void) { return seg6_hmac_init_algo(); } -EXPORT_SYMBOL(seg6_hmac_init); int __net_init seg6_hmac_net_init(struct net *net) { @@ -416,7 +415,6 @@ int __net_init seg6_hmac_net_init(struct net *net) return 0; } -EXPORT_SYMBOL(seg6_hmac_net_init); void seg6_hmac_exit(void) { diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index ee5403cbe655..2e90672852c8 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -148,6 +148,14 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + + /* the control block has been erased, so we have to set the + * iif once again. + * We read the receiving interface index directly from the + * skb->skb_iif as it is done in the IPv4 receiving path (i.e.: + * ip_rcv_core(...)). + */ + IP6CB(skb)->iif = skb->skb_iif; } hdr->nexthdr = NEXTHDR_ROUTING; @@ -168,6 +176,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } #endif + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_postpush_rcsum(skb, hdr, tot_len); return 0; @@ -220,6 +230,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) } #endif + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen); return 0; @@ -281,7 +293,6 @@ static int seg6_do_srh(struct sk_buff *skb) break; } - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return 0; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 607709a8847c..18970f6a68c6 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -415,7 +415,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) if (err) goto drop; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); seg6_lookup_nexthop(skb, NULL, 0); @@ -447,7 +446,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb, if (err) goto drop; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); seg6_lookup_nexthop(skb, NULL, 0); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index bfed7508ba19..ec1de1e6b8e3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -215,8 +215,6 @@ static int ipip6_tunnel_create(struct net_device *dev) ipip6_tunnel_clone_6rd(dev, sitn); - dev_hold(dev); - ipip6_tunnel_link(sitn, t); return 0; @@ -316,9 +314,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) : NULL; - rcu_read_lock(); - - ca = t->prl_count < cmax ? t->prl_count : cmax; + ca = min(t->prl_count, cmax); if (!kp) { /* We don't try hard to allocate much memory for @@ -333,7 +329,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, } } - c = 0; + rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; @@ -345,7 +341,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, if (kprl.addr != htonl(INADDR_ANY)) break; } -out: + rcu_read_unlock(); len = sizeof(*kp) * c; @@ -354,7 +350,7 @@ out: ret = -EFAULT; kfree(kp); - +out: return ret; } @@ -1057,12 +1053,13 @@ tx_err: static void ipip6_tunnel_bind_dev(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + int t_hlen = tunnel->hlen + sizeof(struct iphdr); struct net_device *tdev = NULL; - struct ip_tunnel *tunnel; + int hlen = LL_MAX_HEADER; const struct iphdr *iph; struct flowi4 fl4; - tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; if (iph->daddr) { @@ -1085,13 +1082,15 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev && !netif_is_l3_master(tdev)) { - int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int mtu; - dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); - dev->mtu = tdev->mtu - t_hlen; - if (dev->mtu < IPV6_MIN_MTU) - dev->mtu = IPV6_MIN_MTU; + mtu = tdev->mtu - t_hlen; + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + WRITE_ONCE(dev->mtu, mtu); + hlen = tdev->hard_header_len + tdev->needed_headroom; } + dev->needed_headroom = t_hlen + hlen; } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p, @@ -1377,7 +1376,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; @@ -1409,7 +1407,7 @@ static int ipip6_tunnel_init(struct net_device *dev) dev->tstats = NULL; return err; } - + dev_hold(dev); return 0; } @@ -1425,7 +1423,6 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; - dev_hold(dev); rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } @@ -1598,8 +1595,11 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev, } #ifdef CONFIG_IPV6_SIT_6RD - if (ipip6_netlink_6rd_parms(data, &ip6rd)) + if (ipip6_netlink_6rd_parms(data, &ip6rd)) { err = ipip6_tunnel_update_6rd(nt, &ip6rd); + if (err < 0) + unregister_netdevice_queue(dev, NULL); + } #endif return err; @@ -1817,9 +1817,9 @@ static void __net_exit sit_destroy_tunnels(struct net *net, if (dev->rtnl_link_ops == &sit_link_ops) unregister_netdevice_queue(dev, head); - for (prio = 1; prio < 4; prio++) { + for (prio = 0; prio < 4; prio++) { int h; - for (h = 0; h < IP6_SIT_HASH_SIZE; h++) { + for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) { struct ip_tunnel *t; t = rtnl_dereference(sitn->tunnels[prio][h]); @@ -1877,7 +1877,6 @@ static int __net_init sit_init_net(struct net *net) return 0; err_reg_dev: - ipip6_dev_free(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index a377be8a9fb4..ab073ac3d7ac 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -141,7 +141,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct dst_entry *dst; __u8 rcv_wscale; u32 tsoff = 0; @@ -181,16 +181,18 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); treq = tcp_rsk(req); + treq->af_specific = &tcp_request_sock_ipv6_ops; treq->tfo_listener = false; - if (security_inet_conn_request(sk, skb, req)) - goto out_free; - req->mss = mss; ireq->ir_rmt_port = th->source; ireq->ir_num = ntohs(th->dest); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + + if (security_inet_conn_request(sk, skb, req)) + goto out_free; + if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { @@ -246,7 +248,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; + + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2e76ebfdc907..033cf81f3483 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -97,7 +97,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - sk->sk_rx_dst = dst; + rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); } @@ -206,7 +206,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; @@ -257,6 +257,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl6.flowi6_proto = IPPROTO_TCP; fl6.daddr = sk->sk_v6_daddr; fl6.saddr = saddr ? *saddr : np->saddr; + fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; @@ -304,10 +305,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport); + WRITE_ONCE(tp->write_seq, + secure_tcpv6_seq(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); @@ -326,6 +328,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; @@ -335,11 +339,20 @@ failure: static void tcp_v6_mtu_reduced(struct sock *sk) { struct dst_entry *dst; + u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; - dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info); + mtu = READ_ONCE(tcp_sk(sk)->mtu_info); + + /* Drop requests trying to increase our current mss. + * Check done in __ip6_rt_update_pmtu() is too late. + */ + if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache) + return; + + dst = inet6_csk_update_pmtu(sk, mtu); if (!dst) return; @@ -418,6 +431,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } if (type == ICMPV6_PKT_TOOBIG) { + u32 mtu = ntohl(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). @@ -428,7 +443,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!ip6_sk_accept_pmtu(sk)) goto out; - tp->mtu_info = ntohl(info); + if (mtu < IPV6_MIN_MTU) + goto out; + + WRITE_ONCE(tp->mtu_info, mtu); + if (!sock_owned_by_user(sk)) tcp_v6_mtu_reduced(sk); else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, @@ -502,7 +521,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt, + np->tclass); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -772,7 +792,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .syn_ack_timeout = tcp_syn_ack_timeout, }; -static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { +const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG @@ -1038,6 +1058,11 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; + if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { + __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); + return 0; + } + return tcp_conn_request(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, skb); @@ -1068,6 +1093,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * struct ipv6_txoptions *opt; struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; + bool found_dup_sk = false; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG @@ -1236,20 +1262,27 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * tcp_done(newsk); goto out; } - *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash)); + *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), + &found_dup_sk); if (*own_req) { tcp_move_syn(newtp, req); /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { - newnp->pktoptions = skb_clone(ireq->pktopts, - sk_gfp_mask(sk, GFP_ATOMIC)); + newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk); consume_skb(ireq->pktopts); ireq->pktopts = NULL; - if (newnp->pktoptions) { + if (newnp->pktoptions) tcp_v6_restore_cb(newnp->pktoptions); - skb_set_owner_r(newnp->pktoptions, newsk); - } + } + } else { + if (!req_unhash && found_dup_sk) { + /* This code path should only be executed in the + * syncookie case only + */ + bh_unlock_sock(newsk); + sock_put(newsk); + newsk = NULL; } } @@ -1308,18 +1341,21 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + opt_skb = skb_clone_and_charge_r(skb, sk); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ - struct dst_entry *dst = sk->sk_rx_dst; + struct dst_entry *dst; + + dst = rcu_dereference_protected(sk->sk_rx_dst, + lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || dst->ops->check(dst, np->rx_dst_cookie) == NULL) { + RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); - sk->sk_rx_dst = NULL; } } @@ -1387,7 +1423,6 @@ ipv6_pktoptions: if (np->repflow) np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb)); if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) { - skb_set_owner_r(opt_skb, sk); tcp_v6_restore_cb(opt_skb); opt_skb = xchg(&np->pktoptions, opt_skb); } else { @@ -1637,7 +1672,7 @@ do_time_wait: goto discard_it; } -static void tcp_v6_early_demux(struct sk_buff *skb) +void tcp_v6_early_demux(struct sk_buff *skb) { const struct ipv6hdr *hdr; const struct tcphdr *th; @@ -1664,7 +1699,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { - struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); + struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); @@ -1757,12 +1792,6 @@ static int tcp_v6_init_sock(struct sock *sk) return 0; } -static void tcp_v6_destroy_sock(struct sock *sk) -{ - tcp_v4_destroy_sock(sk); - inet6_destroy_sock(sk); -} - #ifdef CONFIG_PROC_FS /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, @@ -1839,7 +1868,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - - tp->copied_seq, 0); + READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " @@ -1850,7 +1879,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), @@ -1955,7 +1984,7 @@ struct proto tcpv6_prot = { .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v6_init_sock, - .destroy = tcp_v6_destroy_sock, + .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, @@ -1992,12 +2021,7 @@ struct proto tcpv6_prot = { .diag_destroy = tcp_abort, }; -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol tcpv6_protocol = { - .early_demux = tcp_v6_early_demux, - .early_demux_handler = tcp_v6_early_demux, +static const struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6799ad462be3..cf0bbe2e3a79 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -66,6 +66,19 @@ static bool udp6_lib_exact_dif_match(struct net *net, struct sk_buff *skb) return false; } +static void udpv6_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); + inet6_sock_destruct(sk); +} + +int udpv6_init_sock(struct sock *sk) +{ + skb_queue_head_init(&udp_sk(sk)->reader_queue); + sk->sk_destruct = udpv6_destruct_sock; + return 0; +} + static u32 udp6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, @@ -86,7 +99,7 @@ static u32 udp6_ehashfn(const struct net *net, fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, - udp_ipv6_hash_secret + net_hash_mix(net)); + udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) @@ -828,7 +841,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); if (!uh->check && !udp_sk(sk)->no_check6_rx) { @@ -912,7 +925,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, return NULL; } -static void udp_v6_early_demux(struct sk_buff *skb) +void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; @@ -940,7 +953,7 @@ static void udp_v6_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); @@ -1069,7 +1082,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -EINVAL; } - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } @@ -1169,13 +1182,13 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); - ipc6.gso_size = up->gso_size; + ipc6.gso_size = READ_ONCE(up->gso_size); ipc6.sockc.tsflags = sk->sk_tsflags; /* destination address check */ @@ -1219,9 +1232,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (__ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = __ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } @@ -1476,6 +1491,9 @@ void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); @@ -1485,8 +1503,6 @@ void udpv6_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - - inet6_destroy_sock(sk); } /* @@ -1530,12 +1546,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname, } #endif -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol udpv6_protocol = { - .early_demux = udp_v6_early_demux, - .early_demux_handler = udp_v6_early_demux, +static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, @@ -1595,7 +1606,7 @@ struct proto udpv6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udp_init_sock, + .init = udpv6_init_sock, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 7903e21c178b..e5d067b09ccf 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -12,6 +12,7 @@ int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int); void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int, __be32, struct udp_table *); +int udpv6_init_sock(struct sock *sk); int udp_v6_get_port(struct sock *sk, unsigned short snum); int udpv6_getsockopt(struct sock *sk, int level, int optname, diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index 5000ad6878e6..a26a4b5da09c 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -15,6 +15,13 @@ #include <linux/proc_fs.h> #include "udp_impl.h" +static int udplitev6_sk_init(struct sock *sk) +{ + udpv6_init_sock(sk); + udp_sk(sk)->pcflag = UDPLITE_BIT; + return 0; +} + static int udplitev6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); @@ -40,7 +47,7 @@ struct proto udplitev6_prot = { .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, - .init = udplite_sk_init, + .init = udplitev6_sk_init, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, @@ -51,6 +58,8 @@ struct proto udplitev6_prot = { .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 71d022704923..fbcec4827071 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -142,11 +142,24 @@ static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buf return x->outer_mode->afinfo->output_finish(sk, skb); } +static int xfrm6_noneed_fragment(struct sk_buff *skb) +{ + struct frag_hdr *fh; + u8 prevhdr = ipv6_hdr(skb)->nexthdr; + + if (prevhdr != NEXTHDR_FRAGMENT) + return 0; + fh = (struct frag_hdr *)(skb->data + sizeof(struct ipv6hdr)); + if (fh->nexthdr == NEXTHDR_ESP || fh->nexthdr == NEXTHDR_AUTH) + return 1; + return 0; +} + static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; - int mtu; + unsigned int mtu; bool toobig; #ifdef CONFIG_NETFILTER @@ -170,6 +183,9 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) xfrm6_local_rxpmtu(skb, mtu); kfree_skb(skb); return -EMSGSIZE; + } else if (toobig && xfrm6_noneed_fragment(skb)) { + skb->ignore_df = 1; + goto skip_frag; } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); kfree_skb(skb); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 30232591cf2b..a1dfe4f5ed3a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -243,11 +243,11 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt6.rt6i_idev)) - in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); if (xdst->u.rt6.rt6i_uncached_list) rt6_uncached_list_del(&xdst->u.rt6); + if (likely(xdst->u.rt6.rt6i_idev)) + in6_dev_put(xdst->u.rt6.rt6i_idev); xfrm_dst_destroy(xdst); } @@ -416,9 +416,13 @@ int __init xfrm6_init(void) if (ret) goto out_state; - register_pernet_subsys(&xfrm6_net_ops); + ret = register_pernet_subsys(&xfrm6_net_ops); + if (ret) + goto out_protocol; out: return ret; +out_protocol: + xfrm6_protocol_fini(); out_state: xfrm6_state_fini(); out_policy: diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 23a1002ed86d..d59f2341bfec 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1571,7 +1571,8 @@ static int iucv_sock_shutdown(struct socket *sock, int how) break; } - if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) { + if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) && + sk->sk_state == IUCV_CONNECTED) { if (iucv->transport == AF_IUCV_TRANS_IUCV) { txmsg.class = 0; txmsg.tag = 0; @@ -1781,7 +1782,7 @@ static int iucv_callback_connreq(struct iucv_path *path, } /* Create the new socket */ - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); if (!nsk) { err = pr_iucv->path_sever(path, user_data); iucv_path_free(path); @@ -1991,7 +1992,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) goto out; } - nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0); + nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0); bh_lock_sock(sk); if ((sk->sk_state != IUCV_LISTEN) || sk_acceptq_is_full(sk) || diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index eb502c6290c2..aacaa5119b45 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -119,7 +119,7 @@ struct iucv_irq_data { u16 ippathid; u8 ipflags1; u8 iptype; - u32 res2[8]; + u32 res2[9]; }; struct iucv_irq_list { diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index b919db02c7f9..a82892c28860 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -164,7 +164,8 @@ static void kcm_rcv_ready(struct kcm_sock *kcm) /* Buffer limit is okay now, add to ready list */ list_add_tail(&kcm->wait_rx_list, &kcm->mux->kcm_rx_waiters); - kcm->rx_wait = true; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, true); } static void kcm_rfree(struct sk_buff *skb) @@ -180,7 +181,7 @@ static void kcm_rfree(struct sk_buff *skb) /* For reading rx_wait and rx_psock without holding lock */ smp_mb__after_atomic(); - if (!kcm->rx_wait && !kcm->rx_psock && + if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) && sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) { spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); @@ -223,7 +224,7 @@ static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head) struct sk_buff *skb; struct kcm_sock *kcm; - while ((skb = __skb_dequeue(head))) { + while ((skb = skb_dequeue(head))) { /* Reset destructor to avoid calling kcm_rcv_ready */ skb->destructor = sock_rfree; skb_orphan(skb); @@ -239,7 +240,8 @@ try_again: if (kcm_queue_rcv_skb(&kcm->sk, skb)) { /* Should mean socket buffer full */ list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); /* Commit rx_wait to read in kcm_free */ smp_wmb(); @@ -282,10 +284,12 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock, kcm = list_first_entry(&mux->kcm_rx_waiters, struct kcm_sock, wait_rx_list); list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); psock->rx_kcm = kcm; - kcm->rx_psock = psock; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_psock, psock); spin_unlock_bh(&mux->rx_lock); @@ -312,7 +316,8 @@ static void unreserve_rx_kcm(struct kcm_psock *psock, spin_lock_bh(&mux->rx_lock); psock->rx_kcm = NULL; - kcm->rx_psock = NULL; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_psock, NULL); /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with * kcm_rfree @@ -1060,15 +1065,18 @@ partial_message: out_error: kcm_push(kcm); - if (copied && sock->type == SOCK_SEQPACKET) { + if (sock->type == SOCK_SEQPACKET) { /* Wrote some bytes before encountering an * error, return partial success. */ - goto partial_message; - } - - if (head != kcm->seq_skb) + if (copied) + goto partial_message; + if (head != kcm->seq_skb) + kfree_skb(head); + } else { kfree_skb(head); + kcm->seq_skb = NULL; + } err = sk_stream_error(sk, msg->msg_flags, err); @@ -1080,53 +1088,18 @@ out_error: return err; } -static struct sk_buff *kcm_wait_data(struct sock *sk, int flags, - long timeo, int *err) -{ - struct sk_buff *skb; - - while (!(skb = skb_peek(&sk->sk_receive_queue))) { - if (sk->sk_err) { - *err = sock_error(sk); - return NULL; - } - - if (sock_flag(sk, SOCK_DONE)) - return NULL; - - if ((flags & MSG_DONTWAIT) || !timeo) { - *err = -EAGAIN; - return NULL; - } - - sk_wait_data(sk, &timeo, NULL); - - /* Handle signals */ - if (signal_pending(current)) { - *err = sock_intr_errno(timeo); - return NULL; - } - } - - return skb; -} - static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { + int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); int err = 0; - long timeo; struct strp_msg *stm; int copied = 0; struct sk_buff *skb; - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - skb = kcm_wait_data(sk, flags, timeo, &err); + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; @@ -1157,14 +1130,11 @@ msg_finished: /* Finished with message */ msg->msg_flags |= MSG_EOR; KCM_STATS_INCR(kcm->stats.rx_msgs); - skb_unlink(skb, &sk->sk_receive_queue); - kfree_skb(skb); } } out: - release_sock(sk); - + skb_free_datagram(sk, skb); return copied ? : err; } @@ -1172,9 +1142,9 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { + int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct kcm_sock *kcm = kcm_sk(sk); - long timeo; struct strp_msg *stm; int err = 0; ssize_t copied; @@ -1182,11 +1152,7 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, /* Only support splice for SOCKSEQPACKET */ - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - - lock_sock(sk); - - skb = kcm_wait_data(sk, flags, timeo, &err); + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto err_out; @@ -1214,13 +1180,11 @@ static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos, * finish reading the message. */ - release_sock(sk); - + skb_free_datagram(sk, skb); return copied; err_out: - release_sock(sk); - + skb_free_datagram(sk, skb); return err; } @@ -1240,7 +1204,8 @@ static void kcm_recv_disable(struct kcm_sock *kcm) if (!kcm->rx_psock) { if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); } requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue); @@ -1412,12 +1377,6 @@ static int kcm_attach(struct socket *sock, struct socket *csock, psock->sk = csk; psock->bpf_prog = prog; - err = strp_init(&psock->strp, csk, &cb); - if (err) { - kmem_cache_free(kcm_psockp, psock); - goto out; - } - write_lock_bh(&csk->sk_callback_lock); /* Check if sk_user_data is aready by KCM or someone else. @@ -1425,13 +1384,18 @@ static int kcm_attach(struct socket *sock, struct socket *csock, */ if (csk->sk_user_data) { write_unlock_bh(&csk->sk_callback_lock); - strp_stop(&psock->strp); - strp_done(&psock->strp); kmem_cache_free(kcm_psockp, psock); err = -EALREADY; goto out; } + err = strp_init(&psock->strp, csk, &cb); + if (err) { + write_unlock_bh(&csk->sk_callback_lock); + kmem_cache_free(kcm_psockp, psock); + goto out; + } + psock->save_data_ready = csk->sk_data_ready; psock->save_write_space = csk->sk_write_space; psock->save_state_change = csk->sk_state_change; @@ -1794,7 +1758,8 @@ static void kcm_done(struct kcm_sock *kcm) if (kcm->rx_wait) { list_del(&kcm->wait_rx_list); - kcm->rx_wait = false; + /* paired with lockless reads in kcm_rfree() */ + WRITE_ONCE(kcm->rx_wait, false); } /* Move any pending receive messages to other kcm sockets */ requeue_rx_msgs(mux, &sk->sk_receive_queue); @@ -1839,10 +1804,10 @@ static int kcm_release(struct socket *sock) kcm = kcm_sk(sk); mux = kcm->mux; + lock_sock(sk); sock_orphan(sk); kfree_skb(kcm->seq_skb); - lock_sock(sk); /* Purge queue under lock to avoid race condition with tx_work trying * to act when queue is nonempty. If tx_work runs after this point * it will just return. @@ -2021,6 +1986,8 @@ static __net_exit void kcm_exit_net(struct net *net) * that all multiplexors and psocks have been destroyed. */ WARN_ON(!list_empty(&knet->mux_list)); + + mutex_destroy(&knet->mutex); } static struct pernet_operations kcm_net_ops = { diff --git a/net/key/af_key.c b/net/key/af_key.c index e340e97224c3..47ffa69ca6f6 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1707,9 +1707,12 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad pfk->registered |= (1<<hdr->sadb_msg_satype); } + mutex_lock(&pfkey_mutex); xfrm_probe_algs(); - supp_skb = compose_sadb_supported(hdr, GFP_KERNEL); + supp_skb = compose_sadb_supported(hdr, GFP_KERNEL | __GFP_ZERO); + mutex_unlock(&pfkey_mutex); + if (!supp_skb) { if (hdr->sadb_msg_satype != SADB_SATYPE_UNSPEC) pfk->registered &= ~(1<<hdr->sadb_msg_satype); @@ -1855,9 +1858,9 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; - if ((xfilter->sadb_x_filter_splen >= + if ((xfilter->sadb_x_filter_splen > (sizeof(xfrm_address_t) << 3)) || - (xfilter->sadb_x_filter_dplen >= + (xfilter->sadb_x_filter_dplen > (sizeof(xfrm_address_t) << 3))) { mutex_unlock(&pfk->dump_lock); return -EINVAL; @@ -1947,7 +1950,8 @@ static u32 gen_reqid(struct net *net) } static int -parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) +parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_policy *pol, + struct sadb_x_ipsecrequest *rq) { struct net *net = xp_net(xp); struct xfrm_tmpl *t = xp->xfrm_vec + xp->xfrm_nr; @@ -1965,9 +1969,12 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq) if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0) return -EINVAL; t->mode = mode; - if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) + if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_USE) { + if ((mode == XFRM_MODE_TUNNEL || mode == XFRM_MODE_BEET) && + pol->sadb_x_policy_dir == IPSEC_DIR_OUTBOUND) + return -EINVAL; t->optional = 1; - else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { + } else if (rq->sadb_x_ipsecrequest_level == IPSEC_LEVEL_UNIQUE) { t->reqid = rq->sadb_x_ipsecrequest_reqid; if (t->reqid > IPSEC_MANUAL_REQID_MAX) t->reqid = 0; @@ -2009,7 +2016,7 @@ parse_ipsecrequests(struct xfrm_policy *xp, struct sadb_x_policy *pol) rq->sadb_x_ipsecrequest_len < sizeof(*rq)) return -EINVAL; - if ((err = parse_ipsecrequest(xp, rq)) < 0) + if ((err = parse_ipsecrequest(xp, pol, rq)) < 0) return err; len -= rq->sadb_x_ipsecrequest_len; rq = (void*)((u8*)rq + rq->sadb_x_ipsecrequest_len); @@ -2413,7 +2420,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2633,7 +2640,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, - kma ? &k : NULL, net, NULL); + kma ? &k : NULL, net, NULL, 0); out: return err; @@ -2664,7 +2671,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; @@ -2836,6 +2843,10 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; + /* Non-zero return value of pfkey_broadcast() does not always signal + * an error and even on an actual error we may still want to process + * the message so rather ignore the return value. + */ pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); @@ -2908,7 +2919,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2926,7 +2937,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { @@ -2937,16 +2948,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } -static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -2974,13 +2986,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } -static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -3022,8 +3038,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) @@ -3153,6 +3172,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; + int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -3164,16 +3184,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) - size += count_ah_combs(t); + alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) - size += count_esp_combs(t); + alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } - skb = alloc_skb(size + 16, GFP_ATOMIC); + skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -3227,10 +3247,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ + alg_size = 0; if (x->id.proto == IPPROTO_AH) - dump_ah_combs(skb, t); + alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) - dump_esp_combs(skb, t); + alg_size = dump_esp_combs(skb, t); + + hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 9abdc0a04d99..bf2a53d455a1 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -889,8 +889,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) } if (tunnel->version == L2TP_HDR_VER_3 && - l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { + l2tp_session_dec_refcount(session); goto error; + } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 2ff25c445b82..7342344d99a9 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -272,8 +272,6 @@ static void l2tp_ip6_destroy_sock(struct sock *sk) if (tunnel) l2tp_tunnel_delete(tunnel); - - inet6_destroy_sock(sk); } static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -519,13 +517,13 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int transhdrlen = 4; /* zero session-id */ - int ulen = len + transhdrlen; + int ulen; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ - if (len > INT_MAX) + if (len > INT_MAX - transhdrlen) return -EMSGSIZE; /* Mirror BSD error message compatibility */ @@ -650,6 +648,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); + ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c index eda726e22f64..621c66f00117 100644 --- a/net/lapb/lapb_out.c +++ b/net/lapb/lapb_out.c @@ -87,7 +87,8 @@ void lapb_kick(struct lapb_cb *lapb) skb = skb_dequeue(&lapb->write_queue); do { - if ((skbn = skb_clone(skb, GFP_ATOMIC)) == NULL) { + skbn = skb_copy(skb, GFP_ATOMIC); + if (!skbn) { skb_queue_head(&lapb->write_queue, skb); break; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index bcba579e292f..5cba9199c3c9 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -98,8 +98,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) { u8 rc = LLC_PDU_LEN_U; - if (addr->sllc_test || addr->sllc_xid) + if (addr->sllc_test) rc = LLC_PDU_LEN_U; + else if (addr->sllc_xid) + /* We need to expand header to sizeof(struct llc_xid_info) + * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header + * as XID PDU. In llc_ui_sendmsg() we reserved header size and then + * filled all other space with user data. If we won't reserve this + * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data + */ + rc = LLC_PDU_LEN_U_XID; else if (sk->sk_type == SOCK_STREAM) rc = LLC_PDU_LEN_I; return rc; @@ -268,6 +276,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) { struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); + struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; @@ -279,14 +288,14 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { - llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); - if (llc->dev && addr->sllc_arphrd != llc->dev->type) { - dev_put(llc->dev); - llc->dev = NULL; + dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); + if (dev && addr->sllc_arphrd != dev->type) { + dev_put(dev); + dev = NULL; } } else - llc->dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); - if (!llc->dev) + dev = dev_getfirstbyhwtype(&init_net, addr->sllc_arphrd); + if (!dev) goto out; rc = -EUSERS; llc->laddr.lsap = llc_ui_autoport(); @@ -296,6 +305,11 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) sap = llc_sap_open(llc->laddr.lsap, NULL); if (!sap) goto out; + + /* Note: We do not expect errors from this point. */ + llc->dev = dev; + dev = NULL; + memcpy(llc->laddr.mac, llc->dev->dev_addr, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); /* assign new connection to its SAP */ @@ -303,6 +317,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) sock_reset_flag(sk, SOCK_ZAPPED); rc = 0; out: + dev_put(dev); return rc; } @@ -325,6 +340,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); + struct net_device *dev = NULL; struct llc_sap *sap; int rc = -EINVAL; @@ -341,25 +357,26 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) rc = -ENODEV; rcu_read_lock(); if (sk->sk_bound_dev_if) { - llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); - if (llc->dev) { + dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); + if (dev) { if (is_zero_ether_addr(addr->sllc_mac)) - memcpy(addr->sllc_mac, llc->dev->dev_addr, + memcpy(addr->sllc_mac, dev->dev_addr, IFHWADDRLEN); - if (addr->sllc_arphrd != llc->dev->type || + if (addr->sllc_arphrd != dev->type || !ether_addr_equal(addr->sllc_mac, - llc->dev->dev_addr)) { + dev->dev_addr)) { rc = -EINVAL; - llc->dev = NULL; + dev = NULL; } } - } else - llc->dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, + } else { + dev = dev_getbyhwaddr_rcu(&init_net, addr->sllc_arphrd, addr->sllc_mac); - if (llc->dev) - dev_hold(llc->dev); + } + if (dev) + dev_hold(dev); rcu_read_unlock(); - if (!llc->dev) + if (!dev) goto out; if (!addr->sllc_sap) { rc = -EUSERS; @@ -392,6 +409,11 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) goto out_put; } } + + /* Note: We do not expect errors from this point. */ + llc->dev = dev; + dev = NULL; + llc->laddr.lsap = addr->sllc_sap; memcpy(llc->laddr.mac, addr->sllc_mac, IFHWADDRLEN); memcpy(&llc->addr, addr, sizeof(llc->addr)); @@ -402,6 +424,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) out_put: llc_sap_put(sap); out: + dev_put(dev); release_sock(sk); return rc; } diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 82cb93f66b9b..f4fb309185ce 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -127,8 +127,14 @@ static inline int llc_fixup_skb(struct sk_buff *skb) skb->transport_header += llc_len; skb_pull(skb, llc_len); if (skb->protocol == htons(ETH_P_802_2)) { - __be16 pdulen = eth_hdr(skb)->h_proto; - s32 data_size = ntohs(pdulen) - llc_len; + __be16 pdulen; + s32 data_size; + + if (skb->mac_len < ETH_HLEN) + return 0; + + pdulen = eth_hdr(skb)->h_proto; + data_size = ntohs(pdulen) - llc_len; if (data_size < 0 || !pskb_may_pull(skb, data_size)) @@ -162,9 +168,6 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index 7ae4cc684d3a..df26557a0244 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) struct llc_sap_state_ev *ev = llc_sap_ev(skb); int rc; - llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, + llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); @@ -153,6 +153,9 @@ int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb) int rc = 1; u32 data_size; + if (skb->mac_len < ETH_HLEN) + return 1; + llc_pdu_decode_sa(skb, mac_da); llc_pdu_decode_da(skb, mac_sa); llc_pdu_decode_ssap(skb, &dsap); diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index c29170e767a8..64e2c67e16ba 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -77,6 +77,9 @@ static int llc_station_ac_send_test_r(struct sk_buff *skb) u32 data_size; struct sk_buff *nskb; + if (skb->mac_len < ETH_HLEN) + goto out; + /* The test request command is type U (llc_len = 3) */ data_size = ntohs(eth_hdr(skb)->h_proto) - 3; nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, data_size); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 54821fb1a960..79138225e880 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -109,7 +109,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.addba_req.start_seq_num = cpu_to_le16(start_seq_num << 4); - ieee80211_tx_skb(sdata, skb); + ieee80211_tx_skb_tid(sdata, skb, tid); } void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index b6670e74aeb7..77d8ed184c1c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -664,7 +664,8 @@ void sta_set_rate_info_tx(struct sta_info *sta, u16 brate; sband = ieee80211_get_sband(sta->sdata); - if (sband) { + WARN_ON_ONCE(sband && !sband->bitrates); + if (sband && sband->bitrates) { brate = sband->bitrates[rate->idx].bitrate; rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); } @@ -1547,8 +1548,10 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) + sta->sdata->u.vlan.sta) { + ieee80211_clear_fast_rx(sta); RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); + } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); @@ -1820,13 +1823,11 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, const struct mesh_setup *setup) { u8 *new_ie; - const u8 *old_ie; struct ieee80211_sub_if_data *sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); /* allocate information elements */ new_ie = NULL; - old_ie = ifmsh->ie; if (setup->ie_len) { new_ie = kmemdup(setup->ie, setup->ie_len, @@ -1836,7 +1837,6 @@ static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, } ifmsh->ie_len = setup->ie_len; ifmsh->ie = new_ie; - kfree(old_ie); /* now copy the rest of the setup parameters */ ifmsh->mesh_id_len = setup->mesh_id_len; @@ -2452,6 +2452,10 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy, else *dbm = sdata->vif.bss_conf.txpower; + /* INT_MIN indicates no power level was set yet */ + if (*dbm == INT_MIN) + return -EINVAL; + return 0; } @@ -2776,14 +2780,14 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, continue; for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { - if (~sdata->rc_rateidx_mcs_mask[i][j]) { + if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) { sdata->rc_has_mcs_mask[i] = true; break; } } for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { - if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) { + if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) { sdata->rc_has_vht_mcs_mask[i] = true; break; } @@ -3136,9 +3140,6 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_MESH_POINT: { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - if (params->chandef.width != sdata->vif.bss_conf.chandef.width) - return -EINVAL; - /* changes into another band are not supported */ if (sdata->vif.bss_conf.chandef.chan->band != params->chandef.chan->band) diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index d9558ffb8acf..6d95ce1c4a27 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1638,12 +1638,9 @@ int ieee80211_vif_use_reserved_context(struct ieee80211_sub_if_data *sdata) if (new_ctx->replace_state == IEEE80211_CHANCTX_REPLACE_NONE) { if (old_ctx) - err = ieee80211_vif_use_reserved_reassign(sdata); - else - err = ieee80211_vif_use_reserved_assign(sdata); + return ieee80211_vif_use_reserved_reassign(sdata); - if (err) - return err; + return ieee80211_vif_use_reserved_assign(sdata); } /* diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 4105081dc1df..6f390c2e4c8e 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -80,6 +80,7 @@ static const char * const sta_flag_names[] = { FLAG(MPSP_OWNER), FLAG(MPSP_RECIPIENT), FLAG(PS_DELIVER), + FLAG(USES_ENCRYPTION), #undef FLAG }; diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index f783d1377d9a..9f0f437a09b9 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -128,8 +128,11 @@ int drv_sta_state(struct ieee80211_local *local, } else if (old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC) { ret = drv_sta_add(local, sdata, &sta->sta); - if (ret == 0) + if (ret == 0) { sta->uploaded = true; + if (rcu_access_pointer(sta->sta.rates)) + drv_sta_rate_tbl_update(local, sdata, &sta->sta); + } } else if (old_state == IEEE80211_STA_ASSOC && new_state == IEEE80211_STA_AUTH) { drv_sta_remove(local, sdata, &sta->sta); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index f0f5fedb8caa..38383b7e4419 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -544,6 +544,10 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata) sdata_assert_lock(sdata); + /* When not connected/joined, sending CSA doesn't make sense. */ + if (ifibss->state != IEEE80211_IBSS_MLME_JOINED) + return -ENOLINK; + /* update cfg80211 bss information with the new channel */ if (!is_zero_ether_addr(ifibss->bssid)) { cbss = cfg80211_get_bss(sdata->local->hw.wiphy, @@ -1861,6 +1865,8 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) /* remove beacon */ kfree(sdata->u.ibss.ie); + sdata->u.ibss.ie = NULL; + sdata->u.ibss.ie_len = 0; /* on the next join, re-program HT parameters */ memset(&ifibss->ht_capa, 0, sizeof(ifibss->ht_capa)); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a879d8071712..c5e5e978d3ed 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -53,12 +53,6 @@ struct ieee80211_local; #define IEEE80211_ENCRYPT_HEADROOM 8 #define IEEE80211_ENCRYPT_TAILROOM 18 -/* IEEE 802.11 (Ch. 9.5 Defragmentation) requires support for concurrent - * reception of at least three fragmented frames. This limit can be increased - * by changing this define, at the cost of slower frame reassembly and - * increased memory use (about 2 kB of RAM per entry). */ -#define IEEE80211_FRAGMENT_MAX 4 - /* power level hasn't been configured (or set to automatic) */ #define IEEE80211_UNSET_POWER_LEVEL INT_MIN @@ -91,18 +85,6 @@ extern const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS]; #define IEEE80211_MAX_NAN_INSTANCE_ID 255 -struct ieee80211_fragment_entry { - struct sk_buff_head skb_list; - unsigned long first_frag_time; - u16 seq; - u16 extra_len; - u16 last_frag; - u8 rx_queue; - bool check_sequential_pn; /* needed for CCMP/GCMP */ - u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ -}; - - struct ieee80211_bss { u32 device_ts_beacon, device_ts_presp; @@ -243,8 +225,15 @@ struct ieee80211_rx_data { */ int security_idx; - u32 tkip_iv32; - u16 tkip_iv16; + union { + struct { + u32 iv32; + u16 iv16; + } tkip; + struct { + u8 pn[IEEE80211_CCMP_PN_LEN]; + } ccm_gcm; + }; }; struct ieee80211_csa_settings { @@ -638,6 +627,26 @@ struct mesh_csa_settings { struct cfg80211_csa_settings settings; }; +/** + * struct mesh_table + * + * @known_gates: list of known mesh gates and their mpaths by the station. The + * gate's mpath may or may not be resolved and active. + * @gates_lock: protects updates to known_gates + * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @walk_head: linked list containing all mesh_path objects + * @walk_lock: lock protecting walk_head + * @entries: number of entries in the table + */ +struct mesh_table { + struct hlist_head known_gates; + spinlock_t gates_lock; + struct rhashtable rhead; + struct hlist_head walk_head; + spinlock_t walk_lock; + atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ +}; + struct ieee80211_if_mesh { struct timer_list housekeeping_timer; struct timer_list mesh_path_timer; @@ -712,8 +721,8 @@ struct ieee80211_if_mesh { /* offset from skb->data while building IE */ int meshconf_offset; - struct mesh_table *mesh_paths; - struct mesh_table *mpp_paths; /* Store paths for MPP&MAP */ + struct mesh_table mesh_paths; + struct mesh_table mpp_paths; /* Store paths for MPP&MAP */ int mesh_paths_generation; int mpp_paths_generation; }; @@ -884,9 +893,7 @@ struct ieee80211_sub_if_data { char name[IFNAMSIZ]; - /* Fragment table for host-based reassembly */ - struct ieee80211_fragment_entry fragments[IEEE80211_FRAGMENT_MAX]; - unsigned int fragment_next; + struct ieee80211_fragment_cache frags; /* TID bitmap for NoAck policy */ u16 noack_map; @@ -1051,6 +1058,7 @@ enum queue_stop_reason { IEEE80211_QUEUE_STOP_REASON_FLUSH, IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN, IEEE80211_QUEUE_STOP_REASON_RESERVE_TID, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE, IEEE80211_QUEUE_STOP_REASONS, }; @@ -1084,6 +1092,9 @@ struct tpt_led_trigger { * a scan complete for an aborted scan. * @SCAN_HW_CANCELLED: Set for our scan work function when the scan is being * cancelled. + * @SCAN_BEACON_WAIT: Set whenever we're passive scanning because of radar/no-IR + * and could send a probe request after receiving a beacon. + * @SCAN_BEACON_DONE: Beacon received, we can now send a probe request */ enum { SCAN_SW_SCANNING, @@ -1092,6 +1103,8 @@ enum { SCAN_COMPLETED, SCAN_ABORTED, SCAN_HW_CANCELLED, + SCAN_BEACON_WAIT, + SCAN_BEACON_DONE, }; /** @@ -1410,7 +1423,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (WARN_ON_ONCE(!chanctx_conf)) { + if (!chanctx_conf) { rcu_read_unlock(); return NULL; } @@ -2203,4 +2216,7 @@ extern const struct ethtool_ops ieee80211_ethtool_ops; #define debug_noinline #endif +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache); +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache); + #endif /* IEEE80211_I_H */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 152d4365f961..358028a09ce4 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -7,7 +7,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1111,16 +1111,12 @@ static void ieee80211_set_multicast_list(struct net_device *dev) */ static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata) { - int i; - /* free extra data */ ieee80211_free_keys(sdata, false); ieee80211_debugfs_remove_netdev(sdata); - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - __skb_queue_purge(&sdata->fragments[i].skb_list); - sdata->fragment_next = 0; + ieee80211_destroy_frag_cache(&sdata->frags); if (ieee80211_vif_is_mesh(&sdata->vif)) ieee80211_mesh_teardown_sdata(sdata); @@ -1542,6 +1538,10 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, if (ret) return ret; + ieee80211_stop_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); + synchronize_net(); + ieee80211_do_stop(sdata, false); ieee80211_teardown_sdata(sdata); @@ -1562,6 +1562,8 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, err = ieee80211_do_open(&sdata->wdev, false); WARN(err, "type change: do_open returned %d", err); + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE); return ret; } @@ -1826,8 +1828,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->wdev.wiphy = local->hw.wiphy; sdata->local = local; - for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) - skb_queue_head_init(&sdata->fragments[i].skb_list); + ieee80211_init_frag_cache(&sdata->frags); INIT_LIST_HEAD(&sdata->key_list); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index f20bb39f492d..7fc55177db84 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -341,6 +341,7 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (sta) { if (pairwise) { rcu_assign_pointer(sta->ptk[idx], new); + set_sta_flag(sta, WLAN_STA_USES_ENCRYPTION); sta->ptk_idx = idx; ieee80211_check_fast_xmit(sta); } else { @@ -653,6 +654,7 @@ int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { + static atomic_t key_color = ATOMIC_INIT(0); struct ieee80211_local *local = sdata->local; struct ieee80211_key *old_key; int idx = key->conf.keyidx; @@ -688,6 +690,12 @@ int ieee80211_key_link(struct ieee80211_key *key, key->sdata = sdata; key->sta = sta; + /* + * Assign a unique ID to every key so we can easily prevent mixed + * key and fragment cache attacks. + */ + key->color = atomic_inc_return(&key_color); + increment_tailroom_need_count(sdata); ieee80211_key_replace(sdata, sta, pairwise, old_key, key); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index ebdb80b85dc3..d8e187bcb751 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -127,6 +127,8 @@ struct ieee80211_key { } debugfs; #endif + unsigned int color; + /* * key config, must be last because it contains key * material as variable length member diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 68db2a356443..e8c4e9c0c5a0 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -931,8 +931,19 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) continue; if (!dflt_chandef.chan) { + /* + * Assign the first enabled channel to dflt_chandef + * from the list of channels + */ + for (i = 0; i < sband->n_channels; i++) + if (!(sband->channels[i].flags & + IEEE80211_CHAN_DISABLED)) + break; + /* if none found then use the first anyway */ + if (i == sband->n_channels) + i = 0; cfg80211_chandef_create(&dflt_chandef, - &sband->channels[0], + &sband->channels[i], NL80211_CHAN_NO_HT); /* init channel we're on */ if (!local->use_chanctx && !local->_oper_chandef.chan) { @@ -1069,8 +1080,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (local->hw.wiphy->max_scan_ie_len) local->hw.wiphy->max_scan_ie_len -= local->scan_ies_len; - WARN_ON(!ieee80211_cs_list_valid(local->hw.cipher_schemes, - local->hw.n_cipher_schemes)); + if (WARN_ON(!ieee80211_cs_list_valid(local->hw.cipher_schemes, + local->hw.n_cipher_schemes))) { + result = -EINVAL; + goto fail_workqueue; + } result = ieee80211_init_cipher_suites(local); if (result < 0) diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index e84103b40534..e60444039e76 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -128,26 +128,6 @@ struct mesh_path { bool is_gate; }; -/** - * struct mesh_table - * - * @known_gates: list of known mesh gates and their mpaths by the station. The - * gate's mpath may or may not be resolved and active. - * @gates_lock: protects updates to known_gates - * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr - * @walk_head: linked list containging all mesh_path objects - * @walk_lock: lock protecting walk_head - * @entries: number of entries in the table - */ -struct mesh_table { - struct hlist_head known_gates; - spinlock_t gates_lock; - struct rhashtable rhead; - struct hlist_head walk_head; - spinlock_t walk_lock; - atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ -}; - /* Recent multicast cache */ /* RMC_BUCKETS must be a power of 2, maximum 256 */ #define RMC_BUCKETS 256 @@ -300,7 +280,7 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, void mesh_path_assign_nexthop(struct mesh_path *mpath, struct sta_info *sta); void mesh_path_flush_pending(struct mesh_path *mpath); void mesh_path_tx_pending(struct mesh_path *mpath); -int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); +void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata); void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata); int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr); void mesh_path_timer(struct timer_list *t); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 6219b6b0c7e1..18158855d98c 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -355,7 +355,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, */ tx_time = (device_constant + 10 * test_frame_len / rate); estimated_retx = ((1 << (2 * ARITH_SHIFT)) / (s_unit - err)); - result = (tx_time * estimated_retx) >> (2 * ARITH_SHIFT); + result = ((u64)tx_time * estimated_retx) >> (2 * ARITH_SHIFT); return (u32)result; } diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 4fc720c77e37..8efb2bf08bf4 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -50,28 +50,24 @@ static void mesh_path_rht_free(void *ptr, void *tblptr) mesh_path_free_rcu(tbl, mpath); } -static struct mesh_table *mesh_table_alloc(void) +static void mesh_table_init(struct mesh_table *tbl) { - struct mesh_table *newtbl; + INIT_HLIST_HEAD(&tbl->known_gates); + INIT_HLIST_HEAD(&tbl->walk_head); + atomic_set(&tbl->entries, 0); + spin_lock_init(&tbl->gates_lock); + spin_lock_init(&tbl->walk_lock); - newtbl = kmalloc(sizeof(struct mesh_table), GFP_ATOMIC); - if (!newtbl) - return NULL; - - INIT_HLIST_HEAD(&newtbl->known_gates); - INIT_HLIST_HEAD(&newtbl->walk_head); - atomic_set(&newtbl->entries, 0); - spin_lock_init(&newtbl->gates_lock); - spin_lock_init(&newtbl->walk_lock); - - return newtbl; + /* rhashtable_init() may fail only in case of wrong + * mesh_rht_params + */ + WARN_ON(rhashtable_init(&tbl->rhead, &mesh_rht_params)); } static void mesh_table_free(struct mesh_table *tbl) { rhashtable_free_and_destroy(&tbl->rhead, mesh_path_rht_free, tbl); - kfree(tbl); } /** @@ -239,13 +235,13 @@ static struct mesh_path *mpath_lookup(struct mesh_table *tbl, const u8 *dst, struct mesh_path * mesh_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(sdata->u.mesh.mesh_paths, dst, sdata); + return mpath_lookup(&sdata->u.mesh.mesh_paths, dst, sdata); } struct mesh_path * mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) { - return mpath_lookup(sdata->u.mesh.mpp_paths, dst, sdata); + return mpath_lookup(&sdata->u.mesh.mpp_paths, dst, sdata); } static struct mesh_path * @@ -282,7 +278,7 @@ __mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) struct mesh_path * mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - return __mesh_path_lookup_by_idx(sdata->u.mesh.mesh_paths, idx); + return __mesh_path_lookup_by_idx(&sdata->u.mesh.mesh_paths, idx); } /** @@ -297,7 +293,7 @@ mesh_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) struct mesh_path * mpp_path_lookup_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { - return __mesh_path_lookup_by_idx(sdata->u.mesh.mpp_paths, idx); + return __mesh_path_lookup_by_idx(&sdata->u.mesh.mpp_paths, idx); } /** @@ -310,7 +306,7 @@ int mesh_path_add_gate(struct mesh_path *mpath) int err; rcu_read_lock(); - tbl = mpath->sdata->u.mesh.mesh_paths; + tbl = &mpath->sdata->u.mesh.mesh_paths; spin_lock_bh(&mpath->state_lock); if (mpath->is_gate) { @@ -420,7 +416,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, if (!new_mpath) return ERR_PTR(-ENOMEM); - tbl = sdata->u.mesh.mesh_paths; + tbl = &sdata->u.mesh.mesh_paths; spin_lock_bh(&tbl->walk_lock); do { ret = rhashtable_lookup_insert_fast(&tbl->rhead, @@ -469,7 +465,7 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, return -ENOMEM; memcpy(new_mpath->mpp, mpp, ETH_ALEN); - tbl = sdata->u.mesh.mpp_paths; + tbl = &sdata->u.mesh.mpp_paths; spin_lock_bh(&tbl->walk_lock); ret = rhashtable_lookup_insert_fast(&tbl->rhead, @@ -498,7 +494,7 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, void mesh_plink_broken(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; - struct mesh_table *tbl = sdata->u.mesh.mesh_paths; + struct mesh_table *tbl = &sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; @@ -557,7 +553,7 @@ static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) void mesh_path_flush_by_nexthop(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; - struct mesh_table *tbl = sdata->u.mesh.mesh_paths; + struct mesh_table *tbl = &sdata->u.mesh.mesh_paths; struct mesh_path *mpath; struct hlist_node *n; @@ -572,7 +568,7 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, const u8 *proxy) { - struct mesh_table *tbl = sdata->u.mesh.mpp_paths; + struct mesh_table *tbl = &sdata->u.mesh.mpp_paths; struct mesh_path *mpath; struct hlist_node *n; @@ -606,8 +602,8 @@ static void table_flush_by_iface(struct mesh_table *tbl) */ void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) { - table_flush_by_iface(sdata->u.mesh.mesh_paths); - table_flush_by_iface(sdata->u.mesh.mpp_paths); + table_flush_by_iface(&sdata->u.mesh.mesh_paths); + table_flush_by_iface(&sdata->u.mesh.mpp_paths); } /** @@ -653,7 +649,7 @@ int mesh_path_del(struct ieee80211_sub_if_data *sdata, const u8 *addr) /* flush relevant mpp entries first */ mpp_flush_by_proxy(sdata, addr); - err = table_path_del(sdata->u.mesh.mesh_paths, sdata, addr); + err = table_path_del(&sdata->u.mesh.mesh_paths, sdata, addr); sdata->u.mesh.mesh_paths_generation++; return err; } @@ -691,7 +687,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) struct mesh_path *gate; bool copy = false; - tbl = sdata->u.mesh.mesh_paths; + tbl = &sdata->u.mesh.mesh_paths; rcu_read_lock(); hlist_for_each_entry_rcu(gate, &tbl->known_gates, gate_list) { @@ -727,7 +723,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { - kfree_skb(skb); + ieee80211_free_txskb(&sdata->local->hw, skb); sdata->u.mesh.mshstats.dropped_frames_no_route++; } @@ -771,32 +767,10 @@ void mesh_path_fix_nexthop(struct mesh_path *mpath, struct sta_info *next_hop) mesh_path_tx_pending(mpath); } -int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) +void mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) { - struct mesh_table *tbl_path, *tbl_mpp; - int ret; - - tbl_path = mesh_table_alloc(); - if (!tbl_path) - return -ENOMEM; - - tbl_mpp = mesh_table_alloc(); - if (!tbl_mpp) { - ret = -ENOMEM; - goto free_path; - } - - rhashtable_init(&tbl_path->rhead, &mesh_rht_params); - rhashtable_init(&tbl_mpp->rhead, &mesh_rht_params); - - sdata->u.mesh.mesh_paths = tbl_path; - sdata->u.mesh.mpp_paths = tbl_mpp; - - return 0; - -free_path: - mesh_table_free(tbl_path); - return ret; + mesh_table_init(&sdata->u.mesh.mesh_paths); + mesh_table_init(&sdata->u.mesh.mpp_paths); } static @@ -818,12 +792,12 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, void mesh_path_expire(struct ieee80211_sub_if_data *sdata) { - mesh_path_tbl_expire(sdata, sdata->u.mesh.mesh_paths); - mesh_path_tbl_expire(sdata, sdata->u.mesh.mpp_paths); + mesh_path_tbl_expire(sdata, &sdata->u.mesh.mesh_paths); + mesh_path_tbl_expire(sdata, &sdata->u.mesh.mpp_paths); } void mesh_pathtbl_unregister(struct ieee80211_sub_if_data *sdata) { - mesh_table_free(sdata->u.mesh.mesh_paths); - mesh_table_free(sdata->u.mesh.mpp_paths); + mesh_table_free(&sdata->u.mesh.mesh_paths); + mesh_table_free(&sdata->u.mesh.mpp_paths); } diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index 5b5b0f95ffd1..c7f47dba884e 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -1022,8 +1022,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_OPEN: if (!matches_local) event = OPN_RJCT; - if (!mesh_plink_free_count(sdata) || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + (sta->mesh->plid && sta->mesh->plid != plid)) event = OPN_IGNR; else event = OPN_ACPT; @@ -1031,9 +1031,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_CONFIRM: if (!matches_local) event = CNF_RJCT; - if (!mesh_plink_free_count(sdata) || - sta->mesh->llid != llid || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + sta->mesh->llid != llid || + (sta->mesh->plid && sta->mesh->plid != plid)) event = CNF_IGNR; else event = CNF_ACPT; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index c53a332f7d65..8603168b70e4 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1185,6 +1185,11 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_sub_if_data *sdata) sdata->vif.csa_active = false; ifmgd->csa_waiting_bcn = false; + /* + * If the CSA IE is still present on the beacon after the switch, + * we need to consider it as a new CSA (possibly to self). + */ + ifmgd->beacon_crc_valid = false; ret = drv_post_channel_switch(sdata); if (ret) { @@ -2346,11 +2351,18 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata, u16 tx_time) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u16 tid = ieee80211_get_tid(hdr); - int ac = ieee80211_ac_from_tid(tid); - struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; + u16 tid; + int ac; + struct ieee80211_sta_tx_tspec *tx_tspec; unsigned long now = jiffies; + if (!ieee80211_is_data_qos(hdr->frame_control)) + return; + + tid = ieee80211_get_tid(hdr); + ac = ieee80211_ac_from_tid(tid); + tx_tspec = &ifmgd->tx_tspec[ac]; + if (likely(!tx_tspec->admitted_time)) return; @@ -4776,7 +4788,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, */ if (new_sta) { u32 rates = 0, basic_rates = 0; - bool have_higher_than_11mbit; + bool have_higher_than_11mbit = false; int min_rate = INT_MAX, min_rate_index = -1; const struct cfg80211_bss_ies *ies; int shift = ieee80211_vif_get_shift(&sdata->vif); diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 76f303fda3ed..954b932fd7b8 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -941,7 +941,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw, if (old) kfree_rcu(old, rcu_head); - drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta); + if (sta->uploaded) + drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta); ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta)); diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 07fb219327d6..1f3c420c01c7 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -276,7 +276,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, success = !!(info->flags & IEEE80211_TX_STAT_ACK); for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { - if (ar[i].idx < 0) + if (ar[i].idx < 0 || !ar[i].count) break; ndx = rix_to_ndx(mi, ar[i].idx); @@ -289,12 +289,6 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband, mi->r[ndx].stats.success += success; } - if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && (i >= 0)) - mi->sample_packets++; - - if (mi->sample_deferred > 0) - mi->sample_deferred--; - if (time_after(jiffies, mi->last_stats_update + (mp->update_interval * HZ) / 1000)) minstrel_update_stats(mp, mi); @@ -373,7 +367,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; delta = (mi->total_packets * sampling_ratio / 100) - - (mi->sample_packets + mi->sample_deferred / 2); + mi->sample_packets; /* delta < 0: no sampling required */ prev_sample = mi->prev_sample; @@ -382,7 +376,6 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, return; if (mi->total_packets >= 10000) { - mi->sample_deferred = 0; mi->sample_packets = 0; mi->total_packets = 0; } else if (delta > mi->n_rates * 2) { @@ -407,19 +400,8 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, * rate sampling method should be used. * Respect such rates that are not sampled for 20 interations. */ - if (mrr_capable && - msr->perfect_tx_time > mr->perfect_tx_time && - msr->stats.sample_skipped < 20) { - /* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark - * packets that have the sampling rate deferred to the - * second MRR stage. Increase the sample counter only - * if the deferred sample rate was actually used. - * Use the sample_deferred counter to make sure that - * the sampling is not done in large bursts */ - info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; - rate++; - mi->sample_deferred++; - } else { + if (msr->perfect_tx_time < mr->perfect_tx_time || + msr->stats.sample_skipped >= 20) { if (!msr->sample_limit) return; @@ -439,6 +421,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta, rate->idx = mi->r[ndx].rix; rate->count = minstrel_get_retry_count(&mi->r[ndx], info); + info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; } diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index be6c3f35f48b..d60413adb215 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -98,7 +98,6 @@ struct minstrel_sta_info { u8 max_prob_rate; unsigned int total_packets; unsigned int sample_packets; - int sample_deferred; unsigned int sample_row; unsigned int sample_column; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5e56719f999c..3598ebe52d08 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -5,7 +5,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1322,8 +1322,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, goto dont_reorder; /* not part of a BA session */ - if (ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_BLOCKACK && - ack_policy != IEEE80211_QOS_CTL_ACK_POLICY_NORMAL) + if (ack_policy == IEEE80211_QOS_CTL_ACK_POLICY_NOACK) goto dont_reorder; /* new, potentially un-ordered, ampdu frame - process it */ @@ -2009,19 +2008,34 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) return result; } +void ieee80211_init_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + skb_queue_head_init(&cache->entries[i].skb_list); +} + +void ieee80211_destroy_frag_cache(struct ieee80211_fragment_cache *cache) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cache->entries); i++) + __skb_queue_purge(&cache->entries[i].skb_list); +} + static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_add(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct sk_buff **skb) { struct ieee80211_fragment_entry *entry; - entry = &sdata->fragments[sdata->fragment_next++]; - if (sdata->fragment_next >= IEEE80211_FRAGMENT_MAX) - sdata->fragment_next = 0; + entry = &cache->entries[cache->next++]; + if (cache->next >= IEEE80211_FRAGMENT_MAX) + cache->next = 0; - if (!skb_queue_empty(&entry->skb_list)) - __skb_queue_purge(&entry->skb_list); + __skb_queue_purge(&entry->skb_list); __skb_queue_tail(&entry->skb_list, *skb); /* no need for locking */ *skb = NULL; @@ -2036,14 +2050,14 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, } static inline struct ieee80211_fragment_entry * -ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, +ieee80211_reassemble_find(struct ieee80211_fragment_cache *cache, unsigned int frag, unsigned int seq, int rx_queue, struct ieee80211_hdr *hdr) { struct ieee80211_fragment_entry *entry; int i, idx; - idx = sdata->fragment_next; + idx = cache->next; for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) { struct ieee80211_hdr *f_hdr; @@ -2051,7 +2065,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, if (idx < 0) idx = IEEE80211_FRAGMENT_MAX - 1; - entry = &sdata->fragments[idx]; + entry = &cache->entries[idx]; if (skb_queue_empty(&entry->skb_list) || entry->seq != seq || entry->rx_queue != rx_queue || entry->last_frag + 1 != frag) @@ -2078,15 +2092,27 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, return NULL; } +static bool requires_sequential_pn(struct ieee80211_rx_data *rx, __le16 fc) +{ + return rx->key && + (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && + ieee80211_has_protected(fc); +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) { + struct ieee80211_fragment_cache *cache = &rx->sdata->frags; struct ieee80211_hdr *hdr; u16 sc; __le16 fc; unsigned int frag, seq; struct ieee80211_fragment_entry *entry; struct sk_buff *skb; + struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); hdr = (struct ieee80211_hdr *)rx->skb->data; fc = hdr->frame_control; @@ -2097,14 +2123,15 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (is_multicast_ether_addr(hdr->addr1)) { - I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount); - goto out_no_led; - } + if (rx->sta) + cache = &rx->sta->frags; if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) goto out; + if (is_multicast_ether_addr(hdr->addr1)) + return RX_DROP_MONITOR; + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -2120,20 +2147,17 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (frag == 0) { /* This is the first fragment of a new frame. */ - entry = ieee80211_reassemble_add(rx->sdata, frag, seq, + entry = ieee80211_reassemble_add(cache, frag, seq, rx->seqno_idx, &(rx->skb)); - if (rx->key && - (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && - ieee80211_has_protected(fc)) { + if (requires_sequential_pn(rx, fc)) { int queue = rx->security_idx; /* Store CCMP/GCMP PN so that we can verify that the * next fragment has a sequential PN value. */ entry->check_sequential_pn = true; + entry->is_protected = true; + entry->key_color = rx->key->color; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); @@ -2145,6 +2169,11 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sizeof(rx->key->u.gcmp.rx_pn[queue])); BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != IEEE80211_GCMP_PN_LEN); + } else if (rx->key && + (ieee80211_has_protected(fc) || + (status->flag & RX_FLAG_DECRYPTED))) { + entry->is_protected = true; + entry->key_color = rx->key->color; } return RX_QUEUED; } @@ -2152,7 +2181,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) /* This is a fragment for a frame that should already be pending in * fragment cache. Add this fragment to the end of the pending entry. */ - entry = ieee80211_reassemble_find(rx->sdata, frag, seq, + entry = ieee80211_reassemble_find(cache, frag, seq, rx->seqno_idx, hdr); if (!entry) { I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag); @@ -2167,25 +2196,39 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; - int queue; - if (!rx->key || - (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) + if (!requires_sequential_pn(rx, fc)) + return RX_DROP_UNUSABLE; + + /* Prevent mixed key and fragment cache attacks */ + if (entry->key_color != rx->key->color) return RX_DROP_UNUSABLE; + memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { pn[i]++; if (pn[i]) break; } - queue = rx->security_idx; - rpn = rx->key->u.ccmp.rx_pn[queue]; + + rpn = rx->ccm_gcm.pn; if (memcmp(pn, rpn, IEEE80211_CCMP_PN_LEN)) return RX_DROP_UNUSABLE; memcpy(entry->last_pn, pn, IEEE80211_CCMP_PN_LEN); + } else if (entry->is_protected && + (!rx->key || + (!ieee80211_has_protected(fc) && + !(status->flag & RX_FLAG_DECRYPTED)) || + rx->key->color != entry->key_color)) { + /* Drop this as a mixed key or fragment cache attack, even + * if for TKIP Michael MIC should protect us, and WEP is a + * lost cause anyway. + */ + return RX_DROP_UNUSABLE; + } else if (entry->is_protected && rx->key && + entry->key_color != rx->key->color && + (status->flag & RX_FLAG_DECRYPTED)) { + return RX_DROP_UNUSABLE; } skb_pull(rx->skb, ieee80211_hdrlen(fc)); @@ -2214,7 +2257,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) out: ieee80211_led_rx(rx->local); - out_no_led: if (rx->sta) rx->sta->rx_stats.packets++; return RX_CONTINUE; @@ -2371,13 +2413,13 @@ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx, __le16 fc) struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; /* - * Allow EAPOL frames to us/the PAE group address regardless - * of whether the frame was encrypted or not. + * Allow EAPOL frames to us/the PAE group address regardless of + * whether the frame was encrypted or not, and always disallow + * all other destination addresses for them. */ - if (ehdr->h_proto == rx->sdata->control_port_protocol && - (ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || - ether_addr_equal(ehdr->h_dest, pae_group_addr))) - return true; + if (unlikely(ehdr->h_proto == rx->sdata->control_port_protocol)) + return ether_addr_equal(ehdr->h_dest, rx->sdata->vif.addr) || + ether_addr_equal(ehdr->h_dest, pae_group_addr); if (ieee80211_802_1x_port_control(rx) || ieee80211_drop_unencrypted(rx, fc)) @@ -2401,8 +2443,28 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { + struct ethhdr *ehdr = (void *)skb_mac_header(skb); + memset(skb->cb, 0, sizeof(skb->cb)); + /* + * 802.1X over 802.11 requires that the authenticator address + * be used for EAPOL frames. However, 802.1X allows the use of + * the PAE group address instead. If the interface is part of + * a bridge and we pass the frame with the PAE group address, + * then the bridge will forward it to the network (even if the + * client was not associated yet), which isn't supposed to + * happen. + * To avoid that, rewrite the destination address to our own + * address, so that the authenticator (e.g. hostapd) will see + * the frame, but bridge won't forward it anywhere else. Note + * that due to earlier filtering, the only other address can + * be the PAE group address. + */ + if (unlikely(skb->protocol == sdata->control_port_protocol && + !ether_addr_equal(ehdr->h_dest, sdata->vif.addr))) + ether_addr_copy(ehdr->h_dest, sdata->vif.addr); + /* deliver to local stack */ if (rx->napi) napi_gro_receive(rx->napi, skb); @@ -2442,6 +2504,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx) if ((sdata->vif.type == NL80211_IFTYPE_AP || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && !(sdata->flags & IEEE80211_SDATA_DONT_BRIDGE_PACKETS) && + ehdr->h_proto != rx->sdata->control_port_protocol && (sdata->vif.type != NL80211_IFTYPE_AP_VLAN || !sdata->u.vlan.sta)) { if (is_multicast_ether_addr(ehdr->h_dest) && ieee80211_vif_get_num_mcast_if(sdata) != 0) { @@ -2550,7 +2613,7 @@ __ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx, u8 data_offset) if (ieee80211_data_to_8023_exthdr(skb, ðhdr, rx->sdata->vif.addr, rx->sdata->vif.type, - data_offset)) + data_offset, true)) return RX_DROP_UNUSABLE; ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr, @@ -2607,6 +2670,23 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) if (is_multicast_ether_addr(hdr->addr1)) return RX_DROP_UNUSABLE; + if (rx->key) { + /* + * We should not receive A-MSDUs on pre-HT connections, + * and HT connections cannot use old ciphers. Thus drop + * them, as in those cases we couldn't even have SPP + * A-MSDUs or such. + */ + switch (rx->key->conf.cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + case WLAN_CIPHER_SUITE_TKIP: + return RX_DROP_UNUSABLE; + default: + break; + } + } + return __ieee80211_rx_h_amsdu(rx, 0); } @@ -2693,13 +2773,13 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) ether_addr_equal(sdata->vif.addr, hdr->addr3)) return RX_CONTINUE; - ac = ieee80211_select_queue_80211(sdata, skb, hdr); + ac = ieee802_1d_to_ac[skb->priority]; q = sdata->vif.hw_queue[ac]; if (ieee80211_queue_stopped(&local->hw, q)) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion); return RX_DROP_MONITOR; } - skb_set_queue_mapping(skb, q); + skb_set_queue_mapping(skb, ac); if (!--mesh_hdr->ttl) { if (!is_multicast_ether_addr(hdr->addr1)) @@ -3794,7 +3874,8 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) if (!bssid) return false; if (ether_addr_equal(sdata->vif.addr, hdr->addr2) || - ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2)) + ether_addr_equal(sdata->u.ibss.bssid, hdr->addr2) || + !is_valid_ether_addr(hdr->addr2)) return false; if (ieee80211_is_beacon(hdr->frame_control)) return true; @@ -4003,6 +4084,8 @@ void ieee80211_check_fast_rx(struct sta_info *sta) rcu_read_lock(); key = rcu_dereference(sta->ptk[sta->ptk_idx]); + if (!key) + key = rcu_dereference(sdata->default_unicast_key); if (key) { switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: @@ -4536,7 +4619,7 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, goto drop; break; case RX_ENC_VHT: - if (WARN_ONCE(status->rate_idx > 9 || + if (WARN_ONCE(status->rate_idx > 11 || !status->nss || status->nss > 8, "Rate marked as a VHT rate but data is invalid: MCS: %d, NSS: %d\n", diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 5d2a11777718..e3d8be4feea5 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -222,6 +222,16 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) if (likely(!sdata1 && !sdata2)) return; + if (test_and_clear_bit(SCAN_BEACON_WAIT, &local->scanning)) { + /* + * we were passive scanning because of radar/no-IR, but + * the beacon/proberesp rx gives us an opportunity to upgrade + * to active scan + */ + set_bit(SCAN_BEACON_DONE, &local->scanning); + ieee80211_queue_delayed_work(&local->hw, &local->scan_work, 0); + } + if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; @@ -402,10 +412,6 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->mtx)); - if (scan_req != local->int_scan_req) { - local->scan_info.aborted = aborted; - cfg80211_scan_done(scan_req, &local->scan_info); - } RCU_INIT_POINTER(local->scan_req, NULL); scan_sdata = rcu_dereference_protected(local->scan_sdata, @@ -415,6 +421,13 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) local->scanning = 0; local->scan_chandef.chan = NULL; + synchronize_rcu(); + + if (scan_req != local->int_scan_req) { + local->scan_info.aborted = aborted; + cfg80211_scan_done(scan_req, &local->scan_info); + } + /* Set power back to normal operating levels. */ ieee80211_hw_config(local, 0); @@ -706,6 +719,8 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, IEEE80211_CHAN_RADAR)) || !req->n_ssids) { next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; + if (req->n_ssids) + set_bit(SCAN_BEACON_WAIT, &local->scanning); } else { ieee80211_scan_state_send_probe(local, &next_delay); next_delay = IEEE80211_CHANNEL_TIME; @@ -886,6 +901,8 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, !scan_req->n_ssids) { *next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; + if (scan_req->n_ssids) + set_bit(SCAN_BEACON_WAIT, &local->scanning); return; } @@ -978,6 +995,8 @@ void ieee80211_scan_work(struct work_struct *work) goto out; } + clear_bit(SCAN_BEACON_WAIT, &local->scanning); + /* * as long as no delay is required advance immediately * without scheduling a new work @@ -988,6 +1007,10 @@ void ieee80211_scan_work(struct work_struct *work) goto out_complete; } + if (test_and_clear_bit(SCAN_BEACON_DONE, &local->scanning) && + local->next_scan_state == SCAN_DECISION) + local->next_scan_state = SCAN_SEND_PROBE; + switch (local->next_scan_state) { case SCAN_DECISION: /* if no more bands/channels left, complete scan */ diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2a82d438991b..5c209f72de70 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -3,7 +3,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -244,6 +244,24 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, */ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) { + /* + * If we had used sta_info_pre_move_state() then we might not + * have gone through the state transitions down again, so do + * it here now (and warn if it's inserted). + * + * This will clear state such as fast TX/RX that may have been + * allocated during state transitions. + */ + while (sta->sta_state > IEEE80211_STA_NONE) { + int ret; + + WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED)); + + ret = sta_info_move_state(sta, sta->sta_state - 1); + if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret)) + break; + } + if (sta->rate_ctrl) rate_control_free_sta(sta); @@ -351,6 +369,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, u64_stats_init(&sta->rx_stats.syncp); + ieee80211_init_frag_cache(&sta->frags); + sta->sta_state = IEEE80211_STA_NONE; /* Mark TID as unreserved */ @@ -616,7 +636,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_drop_sta: local->num_sta--; synchronize_net(); - __cleanup_single_sta(sta); + cleanup_single_sta(sta); out_err: mutex_unlock(&local->sta_mtx); kfree(sinfo); @@ -635,19 +655,13 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) err = sta_info_insert_check(sta); if (err) { + sta_info_free(local, sta); mutex_unlock(&local->sta_mtx); rcu_read_lock(); - goto out_free; + return err; } - err = sta_info_insert_finish(sta); - if (err) - goto out_free; - - return 0; - out_free: - sta_info_free(local, sta); - return err; + return sta_info_insert_finish(sta); } int sta_info_insert(struct sta_info *sta) @@ -955,7 +969,8 @@ static int __must_check __sta_info_destroy_part1(struct sta_info *sta) list_del_rcu(&sta->list); sta->removed = true; - drv_sta_pre_rcu_remove(local, sta->sdata, sta); + if (sta->uploaded) + drv_sta_pre_rcu_remove(local, sta->sdata, sta); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && rcu_access_pointer(sdata->u.vlan.sta) == sta) @@ -1020,6 +1035,8 @@ static void __sta_info_destroy_part2(struct sta_info *sta) rate_control_remove_sta_debugfs(sta); ieee80211_sta_debugfs_remove(sta); + ieee80211_destroy_frag_cache(&sta->frags); + cleanup_single_sta(sta); } @@ -1328,11 +1345,6 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, struct ieee80211_tx_info *info; struct ieee80211_chanctx_conf *chanctx_conf; - /* Don't send NDPs when STA is connected HE */ - if (sdata->vif.type == NL80211_IFTYPE_STATION && - !(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) - return; - if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC | @@ -2009,6 +2021,10 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, int rate_idx = STA_STATS_GET(LEGACY_IDX, rate); sband = local->hw.wiphy->bands[band]; + + if (WARN_ON_ONCE(!sband->bitrates)) + break; + brate = sband->bitrates[rate_idx].bitrate; if (rinfo->bw == RATE_INFO_BW_5) shift = 2; @@ -2032,7 +2048,7 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo) { - u16 rate = READ_ONCE(sta_get_last_rx_stats(sta)->last_rate); + u32 rate = READ_ONCE(sta_get_last_rx_stats(sta)->last_rate); if (rate == STA_STATS_RATE_INVALID) return -EINVAL; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 9a04327d71d1..75d982ff7f3d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -2,6 +2,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH + * Copyright(c) 2020-2021 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -101,6 +102,7 @@ enum ieee80211_sta_info_flags { WLAN_STA_MPSP_OWNER, WLAN_STA_MPSP_RECIPIENT, WLAN_STA_PS_DELIVER, + WLAN_STA_USES_ENCRYPTION, NUM_WLAN_STA_FLAGS, }; @@ -412,6 +414,34 @@ struct ieee80211_sta_rx_stats { }; /* + * IEEE 802.11-2016 (10.6 "Defragmentation") recommends support for "concurrent + * reception of at least one MSDU per access category per associated STA" + * on APs, or "at least one MSDU per access category" on other interface types. + * + * This limit can be increased by changing this define, at the cost of slower + * frame reassembly and increased memory use while fragments are pending. + */ +#define IEEE80211_FRAGMENT_MAX 4 + +struct ieee80211_fragment_entry { + struct sk_buff_head skb_list; + unsigned long first_frag_time; + u16 seq; + u16 extra_len; + u16 last_frag; + u8 rx_queue; + u8 check_sequential_pn:1, /* needed for CCMP/GCMP */ + is_protected:1; + u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ + unsigned int key_color; +}; + +struct ieee80211_fragment_cache { + struct ieee80211_fragment_entry entries[IEEE80211_FRAGMENT_MAX]; + unsigned int next; +}; + +/* * The bandwidth threshold below which the per-station CoDel parameters will be * scaled to be more lenient (to prevent starvation of slow stations). This * value will be scaled by the number of active stations when it is being @@ -482,6 +512,7 @@ struct ieee80211_sta_rx_stats { * @pcpu_rx_stats: per-CPU RX statistics, assigned only if the driver needs * this (by advertising the USES_RSS hw flag) * @status_stats: TX status statistics + * @frags: fragment cache */ struct sta_info { /* General information, mostly static */ @@ -583,6 +614,8 @@ struct sta_info { struct cfg80211_chan_def tdls_chandef; + struct ieee80211_fragment_cache frags; + /* keep last! */ struct ieee80211_sta sta; }; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 3160ffd93a15..3a0aadf881fc 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -593,10 +593,13 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data; - if (unlikely(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) + if (unlikely(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) { tx->key = NULL; - else if (tx->sta && - (key = rcu_dereference(tx->sta->ptk[tx->sta->ptk_idx]))) + return TX_CONTINUE; + } + + if (tx->sta && + (key = rcu_dereference(tx->sta->ptk[tx->sta->ptk_idx]))) tx->key = key; else if (ieee80211_is_group_privacy_action(tx->skb) && (key = rcu_dereference(tx->sdata->default_multicast_key))) @@ -651,12 +654,16 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) } if (unlikely(tx->key && tx->key->flags & KEY_FLAG_TAINTED && - !ieee80211_is_deauth(hdr->frame_control))) + !ieee80211_is_deauth(hdr->frame_control)) && + tx->skb->protocol != tx->sdata->control_port_protocol) return TX_DROP; if (!skip_hw && tx->key && tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) info->control.hw_key = &tx->key->conf; + } else if (!ieee80211_is_mgmt(hdr->frame_control) && tx->sta && + test_sta_flag(tx->sta, WLAN_STA_USES_ENCRYPTION)) { + return TX_DROP; } return TX_CONTINUE; @@ -1908,19 +1915,24 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, /* device xmit handlers */ +enum ieee80211_encrypt { + ENCRYPT_NO, + ENCRYPT_MGMT, + ENCRYPT_DATA, +}; + static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, - int head_need, bool may_encrypt) + int head_need, + enum ieee80211_encrypt encrypt) { struct ieee80211_local *local = sdata->local; - struct ieee80211_hdr *hdr; bool enc_tailroom; int tail_need = 0; - hdr = (struct ieee80211_hdr *) skb->data; - enc_tailroom = may_encrypt && - (sdata->crypto_tx_tailroom_needed_cnt || - ieee80211_is_mgmt(hdr->frame_control)); + enc_tailroom = encrypt == ENCRYPT_MGMT || + (encrypt == ENCRYPT_DATA && + sdata->crypto_tx_tailroom_needed_cnt); if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; @@ -1952,23 +1964,29 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; int headroom; - bool may_encrypt; + enum ieee80211_encrypt encrypt; - may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT); + if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT) + encrypt = ENCRYPT_NO; + else if (ieee80211_is_mgmt(hdr->frame_control)) + encrypt = ENCRYPT_MGMT; + else + encrypt = ENCRYPT_DATA; headroom = local->tx_headroom; - if (may_encrypt) + if (encrypt != ENCRYPT_NO) headroom += sdata->encrypt_headroom; headroom -= skb_headroom(skb); headroom = max_t(int, 0, headroom); - if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) { + if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) { ieee80211_free_txskb(&local->hw, skb); return; } + /* reload after potential resize */ hdr = (struct ieee80211_hdr *) skb->data; info->control.vif = &sdata->vif; @@ -2109,7 +2127,11 @@ static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local, } vht_mcs = iterator.this_arg[4] >> 4; + if (vht_mcs > 11) + vht_mcs = 0; vht_nss = iterator.this_arg[4] & 0xF; + if (!vht_nss || vht_nss > 8) + vht_nss = 1; break; /* @@ -2751,7 +2773,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, head_need += sdata->encrypt_headroom; head_need += local->tx_headroom; head_need = max_t(int, 0, head_need); - if (ieee80211_skb_resize(sdata, skb, head_need, true)) { + if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) { ieee80211_free_txskb(&local->hw, skb); skb = NULL; return ERR_PTR(-ENOMEM); @@ -3125,7 +3147,9 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata, if (info->control.flags & IEEE80211_TX_CTRL_AMSDU) return true; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr))) + if (!ieee80211_amsdu_realloc_pad(local, skb, + sizeof(*amsdu_hdr) + + local->hw.extra_tx_headroom)) return false; data = skb_push(skb, sizeof(*amsdu_hdr)); @@ -3245,6 +3269,14 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) goto out; + /* If n == 2, the "while (*frag_tail)" loop above didn't execute + * and frag_tail should be &skb_shinfo(head)->frag_list. + * However, ieee80211_amsdu_prepare_head() can reallocate it. + * Reload frag_tail to have it pointing to the correct place. + */ + if (n == 2) + frag_tail = &skb_shinfo(head)->frag_list; + /* * Pad out the previous subframe to a multiple of 4 by adding the * padding to the next one, that's being added. Note that head->len @@ -3414,7 +3446,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, if (unlikely(ieee80211_skb_resize(sdata, skb, max_t(int, extra_head + hw_headroom - skb_headroom(skb), 0), - false))) { + ENCRYPT_NO))) { kfree_skb(skb); return true; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 7fa9871b1db9..9c1a20ca6344 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1102,6 +1102,8 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->max_idle_period_ie = (void *)pos; break; case WLAN_EID_EXTENSION: + if (!elen) + break; if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA && elen >= (sizeof(*elems->mu_edca_param_set) + 1)) { elems->mu_edca_param_set = (void *)&pos[1]; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 4d154efb80c8..d691c2f2e92e 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -421,12 +421,18 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) * IEEE80211-2016 specification makes higher bandwidth operation * possible on the TDLS link if the peers have wider bandwidth * capability. + * + * However, in this case, and only if the TDLS peer is authorized, + * limit to the tdls_chandef so that the configuration here isn't + * wider than what's actually requested on the channel context. */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && - test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW)) - return bw; - - bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); + test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) && + test_sta_flag(sta, WLAN_STA_AUTHORIZED) && + sta->tdls_chandef.chan) + bw = min(bw, ieee80211_chan_width_to_rx_bw(sta->tdls_chandef.width)); + else + bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width)); return bw; } diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 5dd48f0a4b1b..b1d2e2b54f85 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -2,6 +2,7 @@ * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen <j@w1.fi> * Copyright (C) 2016-2017 Intel Deutschland GmbH + * Copyright (C) 2020-2021 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -170,8 +171,8 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) update_iv: /* update IV in key information to be able to detect replays */ - rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip_iv32; - rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip_iv16; + rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip.iv32; + rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip.iv16; return RX_CONTINUE; @@ -297,8 +298,8 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, hdr->addr1, hwaccel, rx->security_idx, - &rx->tkip_iv32, - &rx->tkip_iv16); + &rx->tkip.iv32, + &rx->tkip.iv16); if (res != TKIP_DECRYPT_OK) return RX_DROP_UNUSABLE; @@ -522,6 +523,9 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; @@ -556,6 +560,8 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, } memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove CCMP header and MIC */ @@ -749,6 +755,9 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_UNUSABLE; } + /* reload hdr - skb might have been reallocated */ + hdr = (void *)rx->skb->data; + data_len = skb->len - hdrlen - IEEE80211_GCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_UNUSABLE; @@ -784,6 +793,8 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) } memcpy(key->u.gcmp.rx_pn[queue], pn, IEEE80211_GCMP_PN_LEN); + if (unlikely(ieee80211_is_frag(hdr))) + memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove GCMP header and MIC */ diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index bd88a9b80773..8c2aedf3fa74 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -669,6 +669,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, sdata->dev = ndev; sdata->wpan_dev.wpan_phy = local->hw.phy; sdata->local = local; + INIT_LIST_HEAD(&sdata->wpan_dev.list); /* setup type-dependent data */ ret = ieee802154_setup_sdata(sdata, type); diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 2fb703d70803..d742e635ad07 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -160,7 +160,7 @@ err_tfm0: crypto_free_skcipher(key->tfm0); err_tfm: for (i = 0; i < ARRAY_SIZE(key->tfm); i++) - if (key->tfm[i]) + if (!IS_ERR_OR_NULL(key->tfm[i])) crypto_free_aead(key->tfm[i]); kzfree(key); diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 4dcf6e18563a..dc1a384bc137 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -52,7 +52,7 @@ ieee802154_subif_frame(struct ieee802154_sub_if_data *sdata, switch (mac_cb(skb)->dest.mode) { case IEEE802154_ADDR_NONE: - if (mac_cb(skb)->dest.mode != IEEE802154_ADDR_NONE) + if (hdr->source.mode != IEEE802154_ADDR_NONE) /* FIXME: check if we are PAN coordinator */ skb->pkt_type = PACKET_OTHERHOST; else @@ -140,7 +140,7 @@ static int ieee802154_parse_frame_start(struct sk_buff *skb, struct ieee802154_hdr *hdr) { int hlen; - struct ieee802154_mac_cb *cb = mac_cb_init(skb); + struct ieee802154_mac_cb *cb = mac_cb(skb); skb_reset_mac_header(skb); @@ -302,8 +302,9 @@ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi) { struct ieee802154_local *local = hw_to_local(hw); + struct ieee802154_mac_cb *cb = mac_cb_init(skb); - mac_cb(skb)->lqi = lqi; + cb->lqi = lqi; skb->pkt_type = IEEE802154_RX_MSG; skb_queue_tail(&local->skb_queue, skb); tasklet_schedule(&local->tasklet); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7623d9aec636..40b3e6a52f92 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1375,6 +1375,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, free: kfree(table); out: + mdev->sysctl = NULL; return -ENOBUFS; } @@ -1384,6 +1385,9 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev, struct net *net = dev_net(dev); struct ctl_table *table; + if (!mdev->sysctl) + return; + table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); @@ -1438,22 +1442,52 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head) kfree(mdev); } -static void mpls_ifdown(struct net_device *dev, int event) +static int mpls_ifdown(struct net_device *dev, int event) { struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); - u8 alive, deleted; unsigned index; platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { struct mpls_route *rt = rtnl_dereference(platform_label[index]); + bool nh_del = false; + u8 alive = 0; if (!rt) continue; - alive = 0; - deleted = 0; + if (event == NETDEV_UNREGISTER) { + u8 deleted = 0; + + for_nexthops(rt) { + struct net_device *nh_dev = + rtnl_dereference(nh->nh_dev); + + if (!nh_dev || nh_dev == dev) + deleted++; + if (nh_dev == dev) + nh_del = true; + } endfor_nexthops(rt); + + /* if there are no more nexthops, delete the route */ + if (deleted == rt->rt_nhn) { + mpls_route_update(net, index, NULL, NULL); + continue; + } + + if (nh_del) { + size_t size = sizeof(*rt) + rt->rt_nhn * + rt->rt_nh_size; + struct mpls_route *orig = rt; + + rt = kmalloc(size, GFP_KERNEL); + if (!rt) + return -ENOMEM; + memcpy(rt, orig, size); + } + } + change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; @@ -1477,16 +1511,15 @@ static void mpls_ifdown(struct net_device *dev, int event) next: if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))) alive++; - if (!rtnl_dereference(nh->nh_dev)) - deleted++; } endfor_nexthops(rt); WRITE_ONCE(rt->rt_nhn_alive, alive); - /* if there are no more nexthops, delete the route */ - if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn) - mpls_route_update(net, index, NULL, NULL); + if (nh_del) + mpls_route_update(net, index, rt, NULL); } + + return 0; } static void mpls_ifup(struct net_device *dev, unsigned int flags) @@ -1554,8 +1587,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, return NOTIFY_OK; switch (event) { + int err; + case NETDEV_DOWN: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); break; case NETDEV_UP: flags = dev_get_flags(dev); @@ -1566,13 +1603,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, break; case NETDEV_CHANGE: flags = dev_get_flags(dev); - if (flags & (IFF_RUNNING | IFF_LOWER_UP)) + if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); - else - mpls_ifdown(dev, event); + } else { + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); + } break; case NETDEV_UNREGISTER: - mpls_ifdown(dev, event); + err = mpls_ifdown(dev, event); + if (err) + return notifier_from_errno(err); mdev = mpls_dev_get(dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); @@ -1583,8 +1625,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, case NETDEV_CHANGENAME: mdev = mpls_dev_get(dev); if (mdev) { - int err; - mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) diff --git a/net/mpls/mpls_gso.c b/net/mpls/mpls_gso.c index b4da6d8e8632..2129856b5933 100644 --- a/net/mpls/mpls_gso.c +++ b/net/mpls/mpls_gso.c @@ -18,6 +18,7 @@ #include <linux/netdev_features.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <net/mpls.h> static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -31,6 +32,8 @@ static struct sk_buff *mpls_gso_segment(struct sk_buff *skb, skb_reset_network_header(skb); mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb); + if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN)) + goto out; if (unlikely(!pskb_may_pull(skb, mpls_hlen))) goto out; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 8055e3965cef..2477caf9c967 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -69,9 +69,12 @@ enum { }; struct ncsi_channel_version { - u32 version; /* Supported BCD encoded NCSI version */ - u32 alpha2; /* Supported BCD encoded NCSI version */ - u8 fw_name[12]; /* Firware name string */ + u8 major; /* NCSI version major */ + u8 minor; /* NCSI version minor */ + u8 update; /* NCSI version update */ + char alpha1; /* NCSI version alpha1 */ + char alpha2; /* NCSI version alpha2 */ + u8 fw_name[12]; /* Firmware name string */ u32 fw_version; /* Firmware version */ u16 pci_ids[4]; /* PCI identification */ u32 mf_id; /* Manufacture ID */ diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 091284760d21..9fd20fa90000 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -84,13 +84,20 @@ static void ncsi_channel_monitor(struct timer_list *t) monitor_state = nc->monitor.state; spin_unlock_irqrestore(&nc->lock, flags); - if (!enabled || chained) { - ncsi_stop_channel_monitor(nc); - return; - } + if (!enabled) + return; /* expected race disabling timer */ + if (WARN_ON_ONCE(chained)) + goto bad_state; + if (state != NCSI_CHANNEL_INACTIVE && state != NCSI_CHANNEL_ACTIVE) { - ncsi_stop_channel_monitor(nc); +bad_state: + netdev_warn(ndp->ndev.dev, + "Bad NCSI monitor state channel %d 0x%x %s queue\n", + nc->id, state, chained ? "on" : "off"); + spin_lock_irqsave(&nc->lock, flags); + nc->monitor.enabled = false; + spin_unlock_irqrestore(&nc->lock, flags); return; } @@ -117,10 +124,9 @@ static void ncsi_channel_monitor(struct timer_list *t) ndp->flags |= NCSI_DEV_RESHUFFLE; } - ncsi_stop_channel_monitor(nc); - ncm = &nc->modes[NCSI_MODE_LINK]; spin_lock_irqsave(&nc->lock, flags); + nc->monitor.enabled = false; nc->state = NCSI_CHANNEL_INVISIBLE; ncm->data[2] &= ~0x1; spin_unlock_irqrestore(&nc->lock, flags); @@ -1484,9 +1490,6 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, ndp->ptype.dev = dev; dev_add_pack(&ndp->ptype); - /* Set up generic netlink interface */ - ncsi_init_netlink(dev); - return nd; } EXPORT_SYMBOL_GPL(ncsi_register_dev); @@ -1566,8 +1569,6 @@ void ncsi_unregister_dev(struct ncsi_dev *nd) #endif spin_unlock_irqrestore(&ncsi_dev_lock, flags); - ncsi_unregister_netlink(nd->dev); - kfree(ndp); } EXPORT_SYMBOL_GPL(ncsi_unregister_dev); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 45f33d6dedf7..d0169bf0fcce 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -71,8 +71,8 @@ static int ncsi_write_channel_info(struct sk_buff *skb, if (ndp->force_channel == nc) nla_put_flag(skb, NCSI_CHANNEL_ATTR_FORCED); - nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.version); - nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.alpha2); + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.major); + nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MINOR, nc->version.minor); nla_put_string(skb, NCSI_CHANNEL_ATTR_VERSION_STR, nc->version.fw_name); vid_nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); @@ -397,24 +397,8 @@ static struct genl_family ncsi_genl_family __ro_after_init = { .n_ops = ARRAY_SIZE(ncsi_ops), }; -int ncsi_init_netlink(struct net_device *dev) +static int __init ncsi_init_netlink(void) { - int rc; - - rc = genl_register_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to register netlink family\n"); - - return rc; -} - -int ncsi_unregister_netlink(struct net_device *dev) -{ - int rc; - - rc = genl_unregister_family(&ncsi_genl_family); - if (rc) - netdev_err(dev, "ncsi: failed to unregister netlink family\n"); - - return rc; + return genl_register_family(&ncsi_genl_family); } +subsys_initcall(ncsi_init_netlink); diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h index 91a5c256f8c4..6c55a6775157 100644 --- a/net/ncsi/ncsi-netlink.h +++ b/net/ncsi/ncsi-netlink.h @@ -14,7 +14,4 @@ #include "internal.h" -int ncsi_init_netlink(struct net_device *dev); -int ncsi_unregister_netlink(struct net_device *dev); - #endif /* __NCSI_NETLINK_H__ */ diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h index 91b4b66438df..0bf62b4883d4 100644 --- a/net/ncsi/ncsi-pkt.h +++ b/net/ncsi/ncsi-pkt.h @@ -164,9 +164,12 @@ struct ncsi_rsp_gls_pkt { /* Get Version ID */ struct ncsi_rsp_gvi_pkt { struct ncsi_rsp_pkt_hdr rsp; /* Response header */ - __be32 ncsi_version; /* NCSI version */ + unsigned char major; /* NCSI version major */ + unsigned char minor; /* NCSI version minor */ + unsigned char update; /* NCSI version update */ + unsigned char alpha1; /* NCSI version alpha1 */ unsigned char reserved[3]; /* Reserved */ - unsigned char alpha2; /* NCSI version */ + unsigned char alpha2; /* NCSI version alpha2 */ unsigned char fw_name[12]; /* f/w name string */ __be32 fw_version; /* f/w version */ __be16 pci_ids[4]; /* PCI IDs */ diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 930c1d3796f0..05dea43bbc66 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -20,6 +20,19 @@ #include "internal.h" #include "ncsi-pkt.h" +/* Nibbles within [0xA, 0xF] add zero "0" to the returned value. + * Optional fields (encoded as 0xFF) will default to zero. + */ +static u8 decode_bcd_u8(u8 x) +{ + int lo = x & 0xF; + int hi = x >> 4; + + lo = lo < 0xA ? lo : 0; + hi = hi < 0xA ? hi : 0; + return lo + hi * 10; +} + static int ncsi_validate_rsp_pkt(struct ncsi_request *nr, unsigned short payload) { @@ -611,9 +624,18 @@ static int ncsi_rsp_handler_gvi(struct ncsi_request *nr) if (!nc) return -ENODEV; - /* Update to channel's version info */ + /* Update channel's version info + * + * Major, minor, and update fields are supposed to be + * unsigned integers encoded as packed BCD. + * + * Alpha1 and alpha2 are ISO/IEC 8859-1 characters. + */ ncv = &nc->version; - ncv->version = ntohl(rsp->ncsi_version); + ncv->major = decode_bcd_u8(rsp->major); + ncv->minor = decode_bcd_u8(rsp->minor); + ncv->update = decode_bcd_u8(rsp->update); + ncv->alpha1 = rsp->alpha1; ncv->alpha2 = rsp->alpha2; memcpy(ncv->fw_name, rsp->fw_name, 12); ncv->fw_version = ntohl(rsp->fw_version); @@ -949,7 +971,7 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, int payload, i, ret; /* Find the NCSI device */ - nd = ncsi_find_dev(dev); + nd = ncsi_find_dev(orig_dev); ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; if (!ndp) return -ENODEV; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index e0fb56d67d42..92e0514f624f 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -93,7 +93,7 @@ config NF_CONNTRACK_MARK config NF_CONNTRACK_SECMARK bool 'Connection tracking security mark support' depends on NETWORK_SECMARK - default m if NETFILTER_ADVANCED=n + default y if NETFILTER_ADVANCED=n help This option enables security markings to be applied to connections. Typically they are copied to connections from @@ -117,7 +117,6 @@ config NF_CONNTRACK_ZONES config NF_CONNTRACK_PROCFS bool "Supply CT list in procfs (OBSOLETE)" - default y depends on PROC_FS ---help--- This option enables for the list of known conntrack entries diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 93aaec3a54ec..0c6540780cb4 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -289,12 +289,6 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum)) return NULL; return net->nf.hooks_ipv6 + hooknum; -#if IS_ENABLED(CONFIG_DECNET) - case NFPROTO_DECNET: - if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_decnet) <= hooknum)) - return NULL; - return net->nf.hooks_decnet + hooknum; -#endif default: WARN_ON_ONCE(1); return NULL; @@ -335,14 +329,15 @@ static int __nf_register_net_hook(struct net *net, int pf, p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); - if (!IS_ERR(new_hooks)) + if (!IS_ERR(new_hooks)) { + hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); + } mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); - hooks_validate(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) net_inc_ingress_queue(); @@ -645,10 +640,6 @@ static int __net_init netfilter_net_init(struct net *net) #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge)); #endif -#if IS_ENABLED(CONFIG_DECNET) - __netfilter_net_init(net->nf.hooks_decnet, ARRAY_SIZE(net->nf.hooks_decnet)); -#endif - #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index e3257077158f..1b9df64c6236 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -299,8 +299,8 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -IPSET_ERR_BITMAP_RANGE; pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask); - hosts = 2 << (32 - netmask - 1); - elements = 2 << (netmask - mask_bits - 1); + hosts = 2U << (32 - netmask - 1); + elements = 2UL << (netmask - mask_bits - 1); } if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 36ebc40a4313..031bb83aed70 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -64,6 +64,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); ip_set_dereference((inst)->ip_set_list)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] +#define ip_set_dereference_nfnl(p) \ + rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -488,13 +490,14 @@ ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext, if (SET_WITH_COUNTER(set)) { struct ip_set_counter *counter = ext_counter(data, set); + ip_set_update_counter(counter, ext, flags); + if (flags & IPSET_FLAG_MATCH_COUNTERS && !(ip_set_match_counter(ip_set_get_packets(counter), mext->packets, mext->packets_op) && ip_set_match_counter(ip_set_get_bytes(counter), mext->bytes, mext->bytes_op))) return false; - ip_set_update_counter(counter, ext, flags); } if (SET_WITH_SKBINFO(set)) ip_set_get_skbinfo(ext_skbinfo(data, set), @@ -551,15 +554,10 @@ __ip_set_put_netlink(struct ip_set *set) static inline struct ip_set * ip_set_rcu_get(struct net *net, ip_set_id_t index) { - struct ip_set *set; struct ip_set_net *inst = ip_set_pernet(net); - rcu_read_lock(); - /* ip_set_list itself needs to be protected */ - set = rcu_dereference(inst->ip_set_list)[index]; - rcu_read_unlock(); - - return set; + /* ip_set_list and the set pointer need to be protected */ + return ip_set_dereference_nfnl(inst->ip_set_list)[index]; } int @@ -790,20 +788,9 @@ static struct nlmsghdr * start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags, enum ipset_cmd cmd) { - struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; - - nlh = nlmsg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd), - sizeof(*nfmsg), flags); - if (!nlh) - return NULL; - - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = NFPROTO_IPV4; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - - return nlh; + return nfnl_msg_put(skb, portid, seq, + nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd), flags, + NFPROTO_IPV4, NFNETLINK_V0, 0); } /* Create a set */ @@ -1237,6 +1224,9 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); + /* Make sure all readers of the old set pointers are completed. */ + synchronize_rcu(); + return 0; } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index ddfe06d7530b..b4b474556339 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -104,31 +104,17 @@ htable_size(u8 hbits) { size_t hsize; - /* We must fit both into u32 in jhash and size_t */ + /* We must fit both into u32 in jhash and INT_MAX in kvmalloc_node() */ if (hbits > 31) return 0; hsize = jhash_size(hbits); - if ((((size_t)-1) - sizeof(struct htable)) / sizeof(struct hbucket *) + if ((INT_MAX - sizeof(struct htable)) / sizeof(struct hbucket *) < hsize) return 0; return hsize * sizeof(struct hbucket *) + sizeof(struct htable); } -/* Compute htable_bits from the user input parameter hashsize */ -static u8 -htable_bits(u32 hashsize) -{ - /* Assume that hashsize == 2^htable_bits */ - u8 bits = fls(hashsize - 1); - - if (jhash_size(bits) != hashsize) - /* Round up to the first 2^n value */ - bits = fls(hashsize); - - return bits; -} - #ifdef IP_SET_HASH_WITH_NETS #if IPSET_NET_COUNT > 1 #define __CIDR(cidr, i) (cidr[i]) @@ -1287,7 +1273,11 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (!h) return -ENOMEM; - hbits = htable_bits(hashsize); + /* Compute htable_bits from the user input parameter hashsize. + * Assume that hashsize == 2^htable_bits, + * otherwise round up to the first 2^n value. + */ + hbits = fls(hashsize - 1); hsize = htable_size(hbits); if (hsize == 0) { kfree(h); diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 613e18e720a4..9290a4d7b862 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -39,6 +39,7 @@ MODULE_ALIAS("ip_set_hash:net,port,net"); #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS #define IPSET_NET_COUNT 2 +#define IP_SET_HASH_WITH_NET0 /* IPv4 variant */ diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 80759aadd3e0..21149f4e0b6e 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -604,13 +604,19 @@ static const struct seq_operations ip_vs_app_seq_ops = { int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->app_list); - proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops, - sizeof(struct seq_net_private)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, + &ip_vs_app_seq_ops, + sizeof(struct seq_net_private))) + return -ENOMEM; +#endif return 0; } void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { unregister_ip_vs_app(ipvs, NULL /* all */); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_app", ipvs->net->proc_net); +#endif } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 5b2b17867cb1..51679d1e2d7d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1230,8 +1230,8 @@ static inline int todrop_entry(struct ip_vs_conn *cp) * The drop rate array needs tuning for real environments. * Called from timer bh only => no locking */ - static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; - static char todrop_counter[9] = {0}; + static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; + static signed char todrop_counter[9] = {0}; int i; /* if the conn entry hasn't lasted for 60 seconds, don't drop it. @@ -1378,20 +1378,36 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { atomic_set(&ipvs->conn_count, 0); - proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, - &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state)); - proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, - &ip_vs_conn_sync_seq_ops, - sizeof(struct ip_vs_iter_state)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, + &ip_vs_conn_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn; + + if (!proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, + &ip_vs_conn_sync_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn_sync; +#endif + return 0; + +#ifdef CONFIG_PROC_FS +err_conn_sync: + remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); +err_conn: + return -ENOMEM; +#endif } void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net); +#endif } int __init ip_vs_conn_init(void) @@ -1399,6 +1415,10 @@ int __init ip_vs_conn_init(void) int idx; /* Compute size and mask */ + if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) { + pr_info("conn_tab_bits not in [8, 20]. Using default value\n"); + ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; + } ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; @@ -1422,7 +1442,7 @@ int __init ip_vs_conn_init(void) pr_info("Connection hash table configured " "(size=%d, memory=%ldKbytes)\n", ip_vs_conn_tab_size, - (long)(ip_vs_conn_tab_size*sizeof(struct list_head))/1024); + (long)(ip_vs_conn_tab_size*sizeof(*ip_vs_conn_tab))/1024); IP_VS_DBG(0, "Each connection entry needs %zd bytes at least\n", sizeof(struct ip_vs_conn)); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index d5e4329579e2..f20b08db9fe9 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -725,12 +725,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && - ip6_route_me_harder(ipvs->net, skb) != 0) + ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0) + ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0) return 1; return 0; @@ -1850,7 +1850,6 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; - int conn_reuse_mode; struct sock *sk; /* Already marked as IPVS request or reply? */ @@ -1926,15 +1925,16 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int */ cp = pp->conn_in_get(ipvs, af, skb, &iph); - conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { + int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + } else if (conn_reuse_mode && + is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c339b5e386b7..0909f32eabfd 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1269,7 +1269,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ip_vs_addr_copy(svc->af, &svc->addr, &u->addr); svc->port = u->port; svc->fwmark = u->fwmark; - svc->flags = u->flags; + svc->flags = u->flags & ~IP_VS_SVC_F_HASHED; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; svc->ipvs = ipvs; @@ -1656,6 +1656,7 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs) #ifdef CONFIG_SYSCTL static int zero; +static int one = 1; static int three = 3; static int @@ -1667,12 +1668,18 @@ proc_do_defense_mode(struct ctl_table *table, int write, int val = *valp; int rc; - rc = proc_dointvec(table, write, buffer, lenp, ppos); + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(int), + .mode = table->mode, + }; + + rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write && (*valp != val)) { - if ((*valp < 0) || (*valp > 3)) { - /* Restore the correct value */ - *valp = val; + if (val < 0 || val > 3) { + rc = -EINVAL; } else { + *valp = val; update_defense_level(ipvs); } } @@ -1683,37 +1690,27 @@ static int proc_do_sync_threshold(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; int val[2]; int rc; + struct ctl_table tmp = { + .data = &val, + .maxlen = table->maxlen, + .mode = table->mode, + }; - /* backup the value first */ + mutex_lock(&ipvs->sync_mutex); memcpy(val, valp, sizeof(val)); - - rc = proc_dointvec(table, write, buffer, lenp, ppos); - if (write && (valp[0] < 0 || valp[1] < 0 || - (valp[0] >= valp[1] && valp[1]))) { - /* Restore the correct value */ - memcpy(valp, val, sizeof(val)); - } - return rc; -} - -static int -proc_do_sync_mode(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - int *valp = table->data; - int val = *valp; - int rc; - - rc = proc_dointvec(table, write, buffer, lenp, ppos); - if (write && (*valp != val)) { - if ((*valp < 0) || (*valp > 1)) { - /* Restore the correct value */ - *valp = val; - } + rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); + if (write) { + if (val[0] < 0 || val[1] < 0 || + (val[0] >= val[1] && val[1])) + rc = -EINVAL; + else + memcpy(valp, val, sizeof(val)); } + mutex_unlock(&ipvs->sync_mutex); return rc; } @@ -1725,12 +1722,18 @@ proc_do_sync_ports(struct ctl_table *table, int write, int val = *valp; int rc; - rc = proc_dointvec(table, write, buffer, lenp, ppos); + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(int), + .mode = table->mode, + }; + + rc = proc_dointvec(&tmp, write, buffer, lenp, ppos); if (write && (*valp != val)) { - if (*valp < 1 || !is_power_of_2(*valp)) { - /* Restore the correct value */ + if (val < 1 || !is_power_of_2(val)) + rc = -EINVAL; + else *valp = val; - } } return rc; } @@ -1790,7 +1793,9 @@ static struct ctl_table vs_vars[] = { .procname = "sync_version", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_do_sync_mode, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, }, { .procname = "sync_ports", @@ -2393,6 +2398,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Set timeout values for (tcp tcpfin udp) */ ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg); goto out_unlock; + } else if (!len) { + /* No more commands with len == 0 below */ + ret = -EINVAL; + goto out_unlock; } usvc_compat = (struct ip_vs_service_user *)arg; @@ -2469,9 +2478,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) break; case IP_VS_SO_SET_DELDEST: ret = ip_vs_del_dest(svc, &udest); - break; - default: - ret = -EINVAL; } out_unlock: @@ -3941,6 +3947,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD; ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD; tbl[idx].data = &ipvs->sysctl_sync_threshold; + tbl[idx].extra2 = ipvs; tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); ipvs->sysctl_sync_refresh_period = DEFAULT_SYNC_REFRESH_PERIOD; tbl[idx++].data = &ipvs->sysctl_sync_refresh_period; @@ -3954,6 +3961,11 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; +#ifdef CONFIG_IP_VS_DEBUG + /* Global sysctls must be ro in non-init netns */ + if (!net_eq(net, &init_net)) + tbl[idx++].mode = 0444; +#endif ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index f6af13c16cf5..c133ce825c2d 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1444,7 +1444,7 @@ static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) sin.sin_addr.s_addr = addr; sin.sin_port = 0; - return sock->ops->bind(sock, (struct sockaddr*)&sin, sizeof(sin)); + return kernel_bind(sock, (struct sockaddr *)&sin, sizeof(sin)); } static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, @@ -1510,8 +1510,8 @@ static int make_send_sock(struct netns_ipvs *ipvs, int id, } get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); - result = sock->ops->connect(sock, (struct sockaddr *) &mcast_addr, - salen, 0); + result = kernel_connect(sock, (struct sockaddr *)&mcast_addr, + salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); goto error; @@ -1551,7 +1551,7 @@ static int make_receive_sock(struct netns_ipvs *ipvs, int id, get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); sock->sk->sk_bound_dev_if = dev->ifindex; - result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); + result = kernel_bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); goto error; diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 3f75cd947045..e47d1a29c140 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -272,7 +272,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return false; } @@ -287,7 +287,7 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, { if (ip_hdr(skb)->ttl <= 1) { /* Tell the sender its packet died... */ - __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); return false; } @@ -586,6 +586,8 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (ret == NF_ACCEPT) { nf_reset(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; } return ret; } @@ -626,6 +628,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, if (!local) { skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else @@ -646,6 +650,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, if (!local) { ip_vs_drop_early_demux_sk(skb); skb_forward_csum(skb); + if (skb->dev) + skb->tstamp = 0; NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, NULL, skb_dst(skb)->dev, dst_output); } else diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ad1da6b2fb60..a38caf317dbb 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -70,10 +70,9 @@ EXPORT_SYMBOL_GPL(nf_conntrack_hash); struct conntrack_gc_work { struct delayed_work dwork; - u32 last_bucket; + u32 next_bucket; bool exiting; bool early_drop; - long next_gc_run; }; static __read_mostly struct kmem_cache *nf_conntrack_cachep; @@ -81,12 +80,8 @@ static __read_mostly spinlock_t nf_conntrack_locks_all_lock; static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock); static __read_mostly bool nf_conntrack_locks_all; -/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */ -#define GC_MAX_BUCKETS_DIV 128u -/* upper bound of full table scan */ -#define GC_MAX_SCAN_JIFFIES (16u * HZ) -/* desired ratio of entries found to be expired */ -#define GC_EVICT_RATIO 50u +#define GC_SCAN_INTERVAL (120u * HZ) +#define GC_SCAN_MAX_DURATION msecs_to_jiffies(10) static struct conntrack_gc_work conntrack_gc_work; @@ -630,8 +625,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) return false; tstamp = nf_conn_tstamp_find(ct); - if (tstamp && tstamp->stop == 0) + if (tstamp) { + s32 timeout = ct->timeout - nfct_time_stamp; + tstamp->stop = ktime_get_real_ns(); + if (timeout < 0) + tstamp->stop -= jiffies_to_nsecs(-timeout); + } if (nf_conntrack_event_report(IPCT_DESTROY, ct, portid, report) < 0) { @@ -1063,7 +1063,8 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, * Let nf_ct_resolve_clash() deal with this later. */ if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) && + nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) continue; NF_CT_STAT_INC_ATOMIC(net, found); @@ -1192,17 +1193,13 @@ static void nf_ct_offload_timeout(struct nf_conn *ct) static void gc_worker(struct work_struct *work) { - unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u); - unsigned int i, goal, buckets = 0, expired_count = 0; - unsigned int nf_conntrack_max95 = 0; + unsigned long end_time = jiffies + GC_SCAN_MAX_DURATION; + unsigned int i, hashsz, nf_conntrack_max95 = 0; + unsigned long next_run = GC_SCAN_INTERVAL; struct conntrack_gc_work *gc_work; - unsigned int ratio, scanned = 0; - unsigned long next_run; - gc_work = container_of(work, struct conntrack_gc_work, dwork.work); - goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV; - i = gc_work->last_bucket; + i = gc_work->next_bucket; if (gc_work->early_drop) nf_conntrack_max95 = nf_conntrack_max / 100u * 95u; @@ -1210,22 +1207,21 @@ static void gc_worker(struct work_struct *work) struct nf_conntrack_tuple_hash *h; struct hlist_nulls_head *ct_hash; struct hlist_nulls_node *n; - unsigned int hashsz; struct nf_conn *tmp; - i++; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hashsz); - if (i >= hashsz) - i = 0; + if (i >= hashsz) { + rcu_read_unlock(); + break; + } hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) { struct net *net; tmp = nf_ct_tuplehash_to_ctrack(h); - scanned++; if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) { nf_ct_offload_timeout(tmp); continue; @@ -1233,7 +1229,6 @@ static void gc_worker(struct work_struct *work) if (nf_ct_is_expired(tmp)) { nf_ct_gc_expired(tmp); - expired_count++; continue; } @@ -1265,7 +1260,14 @@ static void gc_worker(struct work_struct *work) */ rcu_read_unlock(); cond_resched(); - } while (++buckets < goal); + i++; + + if (time_after(jiffies, end_time) && i < hashsz) { + gc_work->next_bucket = i; + next_run = 0; + break; + } + } while (i < hashsz); if (gc_work->exiting) return; @@ -1276,40 +1278,17 @@ static void gc_worker(struct work_struct *work) * * This worker is only here to reap expired entries when system went * idle after a busy period. - * - * The heuristics below are supposed to balance conflicting goals: - * - * 1. Minimize time until we notice a stale entry - * 2. Maximize scan intervals to not waste cycles - * - * Normally, expire ratio will be close to 0. - * - * As soon as a sizeable fraction of the entries have expired - * increase scan frequency. */ - ratio = scanned ? expired_count * 100 / scanned : 0; - if (ratio > GC_EVICT_RATIO) { - gc_work->next_gc_run = min_interval; - } else { - unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV; - - BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0); - - gc_work->next_gc_run += min_interval; - if (gc_work->next_gc_run > max) - gc_work->next_gc_run = max; + if (next_run) { + gc_work->early_drop = false; + gc_work->next_bucket = 0; } - - next_run = gc_work->next_gc_run; - gc_work->last_bucket = i; - gc_work->early_drop = false; queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run); } static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work) { INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker); - gc_work->next_gc_run = HZ; gc_work->exiting = false; } diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index efc14c7b4f8e..c2fece0593ea 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -383,7 +383,7 @@ static int help(struct sk_buff *skb, int ret; u32 seq; int dir = CTINFO2DIR(ctinfo); - unsigned int uninitialized_var(matchlen), uninitialized_var(matchoff); + unsigned int matchlen, matchoff; struct nf_ct_ftp_master *ct_ftp_info = nfct_help_data(ct); struct nf_conntrack_expect *exp; union nf_inet_addr *daddr; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index e24b762ffa1d..06c70d4584cf 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -400,6 +400,9 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); + if (!nf_ct_helper_hash) + return -ENOENT; + if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; @@ -570,4 +573,5 @@ void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); kvfree(nf_ct_helper_hash); + nf_ct_helper_hash = NULL; } diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 4099f4d79bae..23ead02c6aa5 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -150,15 +150,37 @@ static int help(struct sk_buff *skb, unsigned int protoff, data = ib_ptr; data_limit = ib_ptr + skb->len - dataoff; - /* strlen("\1DCC SENT t AAAAAAAA P\1\n")=24 - * 5+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=14 */ - while (data < data_limit - (19 + MINMATCHLEN)) { - if (memcmp(data, "\1DCC ", 5)) { + /* Skip any whitespace */ + while (data < data_limit - 10) { + if (*data == ' ' || *data == '\r' || *data == '\n') + data++; + else + break; + } + + /* strlen("PRIVMSG x ")=10 */ + if (data < data_limit - 10) { + if (strncasecmp("PRIVMSG ", data, 8)) + goto out; + data += 8; + } + + /* strlen(" :\1DCC SENT t AAAAAAAA P\1\n")=26 + * 7+MINMATCHLEN+strlen("t AAAAAAAA P\1\n")=26 + */ + while (data < data_limit - (21 + MINMATCHLEN)) { + /* Find first " :", the start of message */ + if (memcmp(data, " :", 2)) { data++; continue; } + data += 2; + + /* then check that place only for the DCC command */ + if (memcmp(data, "\1DCC ", 5)) + goto out; data += 5; - /* we have at least (19+MINMATCHLEN)-5 bytes valid data left */ + /* we have at least (21+MINMATCHLEN)-(2+5) bytes valid data left */ iph = ip_hdr(skb); pr_debug("DCC found in master %pI4:%u %pI4:%u\n", @@ -174,7 +196,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, pr_debug("DCC %s detected\n", dccprotos[i]); /* we have at least - * (19+MINMATCHLEN)-5-dccprotos[i].matchlen bytes valid + * (21+MINMATCHLEN)-7-dccprotos[i].matchlen bytes valid * data left (== 14/13 bytes) */ if (parse_dcc(data, data_limit, &dcc_ip, &dcc_port, &addr_beg_p, &addr_end_p)) { @@ -187,8 +209,9 @@ static int help(struct sk_buff *skb, unsigned int protoff, /* dcc_ip can be the internal OR external (NAT'ed) IP */ tuple = &ct->tuplehash[dir].tuple; - if (tuple->src.u3.ip != dcc_ip && - tuple->dst.u3.ip != dcc_ip) { + if ((tuple->src.u3.ip != dcc_ip && + ct->tuplehash[!dir].tuple.dst.u3.ip != dcc_ip) || + dcc_port == 0) { net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n", &tuple->src.u3.ip, &dcc_ip, dcc_port); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 0b89609a6e9d..83e8566ec3f0 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -213,6 +213,7 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, if (!help) return 0; + rcu_read_lock(); helper = rcu_dereference(help->helper); if (!helper) goto out; @@ -228,9 +229,11 @@ static int ctnetlink_dump_helpinfo(struct sk_buff *skb, nla_nest_end(skb, nest_helper); out: + rcu_read_unlock(); return 0; nla_put_failure: + rcu_read_unlock(); return -1; } @@ -514,20 +517,15 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, { const struct nf_conntrack_zone *zone; struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct nlattr *nest_parms; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_NEW); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, nf_ct_l3num(ct), + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = nf_ct_l3num(ct); - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); @@ -684,7 +682,6 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) const struct nf_conntrack_zone *zone; struct net *net; struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct nlattr *nest_parms; struct nf_conn *ct = item->ct; struct sk_buff *skb; @@ -714,15 +711,11 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, type); - nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, nf_ct_l3num(ct), + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = nf_ct_l3num(ct); - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - zone = nf_ct_zone(ct); nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED); @@ -1213,9 +1206,6 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) { - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) - return 0; - return ctnetlink_filter_match(ct, data); } @@ -1277,11 +1267,6 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl, ct = nf_ct_tuplehash_to_ctrack(h); - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) { - nf_ct_put(ct); - return -EBUSY; - } - if (cda[CTA_ID]) { __be32 id = nla_get_be32(cda[CTA_ID]); @@ -2053,12 +2038,15 @@ ctnetlink_create_conntrack(struct net *net, err = nf_conntrack_hash_check_insert(ct); if (err < 0) - goto err2; + goto err3; rcu_read_unlock(); return ct; +err3: + if (ct->master) + nf_ct_put(ct->master); err2: rcu_read_unlock(); err1: @@ -2172,20 +2160,15 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS_CPU); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, htons(cpu)); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(cpu); - if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) || nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) || nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) || @@ -2256,20 +2239,15 @@ ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; unsigned int nr_conntracks = atomic_read(&net->ct.count); event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_CT_GET_STATS); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; @@ -2656,6 +2634,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, memset(&m, 0xFF, sizeof(m)); memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); m.src.u.all = mask->src.u.all; + m.src.l3num = tuple->src.l3num; m.dst.protonum = tuple->dst.protonum; nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK | NLA_F_NESTED); @@ -2682,7 +2661,9 @@ nla_put_failure: return -1; } +#if IS_ENABLED(CONFIG_NF_NAT) static const union nf_inet_addr any_addr; +#endif static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { @@ -2779,19 +2760,14 @@ ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, + exp->tuple.src.l3num, NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = exp->tuple.src.l3num; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; @@ -2811,7 +2787,6 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) struct nf_conntrack_expect *exp = item->exp; struct net *net = nf_ct_exp_net(exp); struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct sk_buff *skb; unsigned int type, group; int flags = 0; @@ -2834,15 +2809,11 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) goto errout; type = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_EXP, type); - nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, item->portid, 0, type, flags, + exp->tuple.src.l3num, NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = exp->tuple.src.l3num; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (ctnetlink_exp_dump_expect(skb, exp) < 0) goto nla_put_failure; @@ -3182,10 +3153,12 @@ ctnetlink_change_expect(struct nf_conntrack_expect *x, return 0; } +#if IS_ENABLED(CONFIG_NF_NAT) static const struct nla_policy exp_nat_nla_policy[CTA_EXPECT_NAT_MAX+1] = { [CTA_EXPECT_NAT_DIR] = { .type = NLA_U32 }, [CTA_EXPECT_NAT_TUPLE] = { .type = NLA_NESTED }, }; +#endif static int ctnetlink_parse_expect_nat(const struct nlattr *attr, @@ -3410,20 +3383,15 @@ ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK, IPCTNL_MSG_EXP_GET_STATS_CPU); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, htons(cpu)); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(cpu); - if (nla_put_be32(skb, CTA_STATS_EXP_NEW, htonl(st->expect_new)) || nla_put_be32(skb, CTA_STATS_EXP_CREATE, htonl(st->expect_create)) || nla_put_be32(skb, CTA_STATS_EXP_DELETE, htonl(st->expect_delete))) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index a937d4f75613..8453e92936ac 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -58,8 +58,8 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS, - [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, - [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, + [SCTP_CONNTRACK_SHUTDOWN_SENT] = 3 SECS, + [SCTP_CONNTRACK_SHUTDOWN_RECD] = 3 SECS, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, @@ -119,7 +119,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, +/* init */ {sCW, sCW, sCW, sCE, sES, sCL, sCL, sSA, sCW, sHA}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, @@ -317,22 +317,29 @@ static int sctp_packet(struct nf_conn *ct, for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { - /* Sec 8.5.1 (A) */ + /* (A) vtag MUST be zero */ if (sh->vtag != 0) goto out_unlock; } else if (sch->type == SCTP_CID_ABORT) { - /* Sec 8.5.1 (B) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir]) + /* (B) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { - /* Sec 8.5.1 (C) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir] && - sch->flags & SCTP_CHUNK_FLAG_T) + /* (C) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_COOKIE_ECHO) { - /* Sec 8.5.1 (D) */ + /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; } else if (sch->type == SCTP_CID_HEARTBEAT) { @@ -394,6 +401,15 @@ static int sctp_packet(struct nf_conn *ct, pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; + + /* don't renew timeout on init retransmit so + * port reuse by client or NAT middlebox cannot + * keep entry alive indefinitely (incl. nat info). + */ + if (new_state == SCTP_CONNTRACK_CLOSED && + old_state == SCTP_CONNTRACK_CLOSED && + nf_ct_is_confirmed(ct)) + ignore = true; } ct->proto.sctp.state = new_state; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 7011ab27c437..955b73a9a05e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -362,8 +362,8 @@ static void tcp_options(const struct sk_buff *skb, length, buff); BUG_ON(ptr == NULL); - state->td_scale = - state->flags = 0; + state->td_scale = 0; + state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL; while (length > 0) { int opcode=*ptr++; @@ -549,13 +549,20 @@ static bool tcp_in_window(const struct nf_conn *ct, swin = win << sender->td_scale; sender->td_maxwin = (swin == 0 ? 1 : swin); sender->td_maxend = end + sender->td_maxwin; - /* - * We haven't seen traffic in the other direction yet - * but we have to tweak window tracking to pass III - * and IV until that happens. - */ - if (receiver->td_maxwin == 0) + if (receiver->td_maxwin == 0) { + /* We haven't seen traffic in the other + * direction yet but we have to tweak window + * tracking to pass III and IV until that + * happens. + */ receiver->td_end = receiver->td_maxend = sack; + } else if (sack == receiver->td_end + 1) { + /* Likely a reply to a keepalive. + * Needed for III. + */ + receiver->td_end++; + } + } } else if (((state->state == TCP_CONNTRACK_SYN_SENT && dir == IP_CT_DIR_ORIGINAL) @@ -777,6 +784,16 @@ static bool nf_conntrack_tcp_established(const struct nf_conn *ct) test_bit(IPS_ASSURED_BIT, &ct->status); } +static void nf_ct_tcp_state_reset(struct ip_ct_tcp_state *state) +{ + state->td_end = 0; + state->td_maxend = 0; + state->td_maxwin = 0; + state->td_maxack = 0; + state->td_scale = 0; + state->flags &= IP_CT_TCP_FLAG_BE_LIBERAL; +} + /* Returns verdict for packet, or -1 for invalid. */ static int tcp_packet(struct nf_conn *ct, const struct sk_buff *skb, @@ -875,8 +892,7 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags = ct->proto.tcp.last_flags; - memset(&ct->proto.tcp.seen[dir], 0, - sizeof(struct ip_ct_tcp_state)); + nf_ct_tcp_state_reset(&ct->proto.tcp.seen[dir]); break; } ct->proto.tcp.last_index = index; @@ -1078,6 +1094,16 @@ static int tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + + if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { + /* do not renew timeout on SYN retransmit. + * + * Else port reuse by client or NAT middlebox can keep + * entry alive indefinitely (including nat info). + */ + return NF_ACCEPT; + } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index c8d2b6688a2a..d16aa43ebd4d 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -471,7 +471,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr, return ret; if (ret == 0) break; - dataoff += *matchoff; + dataoff = *matchoff; } *in_header = 0; } @@ -483,7 +483,7 @@ static int ct_sip_walk_headers(const struct nf_conn *ct, const char *dptr, break; if (ret == 0) return ret; - dataoff += *matchoff; + dataoff = *matchoff; } if (in_header) @@ -605,7 +605,7 @@ int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, start += strlen(name); *val = simple_strtoul(start, &end, 0); if (start == end) - return 0; + return -1; if (matchoff && matchlen) { *matchoff = start - dptr; *matchlen = end - start; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4c94f3ba2ae4..da0c9fa381d2 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -262,6 +262,7 @@ static const char* l4proto_name(u16 proto) case IPPROTO_GRE: return "gre"; case IPPROTO_SCTP: return "sctp"; case IPPROTO_UDPLITE: return "udplite"; + case IPPROTO_ICMPV6: return "icmpv6"; } return "unknown"; @@ -500,6 +501,9 @@ nf_conntrack_hash_sysctl(struct ctl_table *table, int write, { int ret; + /* module_param hashsize could have changed value */ + nf_conntrack_htable_size_user = nf_conntrack_htable_size; + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret < 0 || !write) return ret; @@ -590,8 +594,11 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) if (net->user_ns != &init_user_ns) table[0].procname = NULL; - if (!net_eq(&init_net, net)) + if (!net_eq(&init_net, net)) { + table[0].mode = 0444; table[2].mode = 0444; + table[5].mode = 0444; + } net->ct.sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.sysctl_header) diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index f4a566e67213..98d117f3340c 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -21,6 +21,7 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) skb_push(skb, skb->mac_len); skb->dev = dev; + skb->tstamp = 0; dev_queue_xmit(skb); } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 890799c16aa4..b3957fe7eced 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -360,7 +360,7 @@ static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, return -1; tcph = (void *)(skb_network_header(skb) + thoff); - inet_proto_csum_replace2(&tcph->check, skb, port, new_port, true); + inet_proto_csum_replace2(&tcph->check, skb, port, new_port, false); return 0; } @@ -377,7 +377,7 @@ static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff, udph = (void *)(skb_network_header(skb) + thoff); if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { inet_proto_csum_replace2(&udph->check, skb, port, - new_port, true); + new_port, false); if (!udph->check) udph->check = CSUM_MANGLED_0; } diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c index a8c5c846aec1..b164a0e1e053 100644 --- a/net/netfilter/nf_log_common.c +++ b/net/netfilter/nf_log_common.c @@ -176,6 +176,18 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf, } EXPORT_SYMBOL_GPL(nf_log_dump_packet_common); +void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb) +{ + u16 vid; + + if (!skb_vlan_tag_present(skb)) + return; + + vid = skb_vlan_tag_get(skb); + nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid); +} +EXPORT_SYMBOL_GPL(nf_log_dump_vlan); + /* bridge and netdev logging families share this code. */ void nf_log_l2packet(struct net *net, u_int8_t pf, __be16 protocol, diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 2268b10a9dcf..c31df6a76504 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1068,6 +1068,7 @@ static int __init nf_nat_init(void) ret = register_pernet_subsys(&nat_net_ops); if (ret < 0) { nf_ct_extend_unregister(&nat_extend); + kvfree(nf_nat_bysource); return ret; } diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c index 5d849d835561..234f535d350e 100644 --- a/net/netfilter/nf_nat_proto_common.c +++ b/net/netfilter/nf_nat_proto_common.c @@ -38,12 +38,12 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, - const struct nf_conn *ct, - u16 *rover) + const struct nf_conn *ct) { - unsigned int range_size, min, max, i; + unsigned int range_size, min, max, i, attempts; __be16 *portptr; - u_int16_t off; + u16 off; + static const unsigned int max_attempts = 128; if (maniptype == NF_NAT_MANIP_SRC) portptr = &tuple->src.u.all; @@ -86,18 +86,31 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, } else if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) { off = (ntohs(*portptr) - ntohs(range->base_proto.all)); } else { - off = *rover; + off = prandom_u32(); } - for (i = 0; ; ++off) { + attempts = range_size; + if (attempts > max_attempts) + attempts = max_attempts; + + /* We are in softirq; doing a search of the entire range risks + * soft lockup when all tuples are already used. + * + * If we can't find any free port from first offset, pick a new + * one and try again, with ever smaller search window. + */ +another_round: + for (i = 0; i < attempts; i++, off++) { *portptr = htons(min + off % range_size); - if (++i != range_size && nf_nat_used_tuple(tuple, ct)) - continue; - if (!(range->flags & (NF_NAT_RANGE_PROTO_RANDOM_ALL| - NF_NAT_RANGE_PROTO_OFFSET))) - *rover = off; - return; + if (!nf_nat_used_tuple(tuple, ct)) + return; } + + if (attempts >= range_size || attempts < 16) + return; + attempts /= 2; + off = prandom_u32(); + goto another_round; } EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c index 67ea0d83aa5a..7d4d2c124990 100644 --- a/net/netfilter/nf_nat_proto_dccp.c +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -18,8 +18,6 @@ #include <net/netfilter/nf_nat_l3proto.h> #include <net/netfilter/nf_nat_l4proto.h> -static u_int16_t dccp_port_rover; - static void dccp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, @@ -27,8 +25,7 @@ dccp_unique_tuple(const struct nf_nat_l3proto *l3proto, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { - nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, - &dccp_port_rover); + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct); } static bool diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index 1c5d9b65fbba..f05ad8fa7b20 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -12,8 +12,6 @@ #include <net/netfilter/nf_nat_l4proto.h> -static u_int16_t nf_sctp_port_rover; - static void sctp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, @@ -21,8 +19,7 @@ sctp_unique_tuple(const struct nf_nat_l3proto *l3proto, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { - nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, - &nf_sctp_port_rover); + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct); } static bool diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c index f15fcd475f98..c312e6b3e2ea 100644 --- a/net/netfilter/nf_nat_proto_tcp.c +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -18,8 +18,6 @@ #include <net/netfilter/nf_nat_l4proto.h> #include <net/netfilter/nf_nat_core.h> -static u16 tcp_port_rover; - static void tcp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, @@ -27,8 +25,7 @@ tcp_unique_tuple(const struct nf_nat_l3proto *l3proto, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { - nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, - &tcp_port_rover); + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct); } static bool diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c index d85c31c2433c..357539d15849 100644 --- a/net/netfilter/nf_nat_proto_udp.c +++ b/net/netfilter/nf_nat_proto_udp.c @@ -17,8 +17,6 @@ #include <net/netfilter/nf_nat_l3proto.h> #include <net/netfilter/nf_nat_l4proto.h> -static u16 udp_port_rover; - static void udp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, @@ -26,8 +24,7 @@ udp_unique_tuple(const struct nf_nat_l3proto *l3proto, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { - nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, - &udp_port_rover); + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct); } static void @@ -78,8 +75,6 @@ static bool udp_manip_pkt(struct sk_buff *skb, } #ifdef CONFIG_NF_NAT_PROTO_UDPLITE -static u16 udplite_port_rover; - static bool udplite_manip_pkt(struct sk_buff *skb, const struct nf_nat_l3proto *l3proto, unsigned int iphdroff, unsigned int hdroff, @@ -103,8 +98,7 @@ udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { - nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, - &udplite_port_rover); + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct); } const struct nf_nat_l4proto nf_nat_l4proto_udplite = { diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index ee6d98355081..b3a0385290a1 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -46,6 +46,15 @@ void nf_unregister_queue_handler(struct net *net) } EXPORT_SYMBOL(nf_unregister_queue_handler); +static void nf_queue_sock_put(struct sock *sk) +{ +#ifdef CONFIG_INET + sock_gen_put(sk); +#else + sock_put(sk); +#endif +} + void nf_queue_entry_release_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; @@ -56,7 +65,7 @@ void nf_queue_entry_release_refs(struct nf_queue_entry *entry) if (state->out) dev_put(state->out); if (state->sk) - sock_put(state->sk); + nf_queue_sock_put(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (entry->skb->nf_bridge) { struct net_device *physdev; @@ -73,16 +82,17 @@ void nf_queue_entry_release_refs(struct nf_queue_entry *entry) EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs); /* Bump dev refs so they don't vanish while packet is out */ -void nf_queue_entry_get_refs(struct nf_queue_entry *entry) +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; + if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt)) + return false; + if (state->in) dev_hold(state->in); if (state->out) dev_hold(state->out); - if (state->sk) - sock_hold(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (entry->skb->nf_bridge) { struct net_device *physdev; @@ -95,6 +105,7 @@ void nf_queue_entry_get_refs(struct nf_queue_entry *entry) dev_hold(physdev); } #endif + return true; } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); @@ -186,7 +197,10 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, .size = sizeof(*entry) + route_key_size, }; - nf_queue_entry_get_refs(entry); + if (!nf_queue_entry_get_refs(entry)) { + kfree(entry); + return -ENOTCONN; + } switch (entry->state.pf) { case AF_INET: diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 353a2aa80c3c..04b07b63c540 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -34,6 +34,9 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, int length = (th->doff * 4) - sizeof(*th); u8 buf[40], *ptr; + if (unlikely(length < 0)) + return false; + ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); if (ptr == NULL) return false; @@ -50,6 +53,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length--; continue; default: + if (length < 2) + return true; opsize = *ptr++; if (opsize < 2) return true; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5b4632826dc6..e0c224dea316 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -22,10 +22,13 @@ #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/net_namespace.h> +#include <net/netns/generic.h> #include <net/sock.h> #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +unsigned int nf_tables_net_id __read_mostly; + static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); @@ -53,7 +56,9 @@ static const struct rhashtable_params nft_chain_ht_params = { static void nft_validate_state_update(struct net *net, u8 new_validate_state) { - switch (net->nft.validate_state) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; @@ -64,7 +69,7 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) return; } - net->nft.validate_state = new_validate_state; + nft_net->validate_state = new_validate_state; } static void nft_ctx_init(struct nft_ctx *ctx, @@ -96,6 +101,8 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, if (trans == NULL) return NULL; + INIT_LIST_HEAD(&trans->list); + INIT_LIST_HEAD(&trans->binding_list); trans->msg_type = msg_type; trans->ctx = *ctx; @@ -108,34 +115,68 @@ static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx, return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL); } -static void nft_trans_destroy(struct nft_trans *trans) +static void nft_trans_list_del(struct nft_trans *trans) { list_del(&trans->list); + list_del(&trans->binding_list); +} + +static void nft_trans_destroy(struct nft_trans *trans) +{ + nft_trans_list_del(trans); kfree(trans); } -static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set, + bool bind) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_set_is_anonymous(set)) return; - list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) - nft_trans_set_bound(trans) = true; + nft_trans_set_bound(trans) = bind; break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set(trans) == set) - nft_trans_elem_set_bound(trans) = true; + nft_trans_elem_set_bound(trans) = bind; break; } } } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, true); +} + +static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, false); +} + +static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) +{ + struct nftables_pernet *nft_net; + + nft_net = net_generic(net, nf_tables_net_id); + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_set_is_anonymous(nft_trans_set(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; + } + + list_add_tail(&trans->list, &nft_net->commit_list); +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -186,7 +227,7 @@ static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) if (msg_type == NFT_MSG_NEWTABLE) nft_activate_next(ctx->net, ctx->table); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -213,7 +254,7 @@ static int nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) if (msg_type == NFT_MSG_NEWCHAIN) nft_activate_next(ctx->net, ctx->chain); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -225,7 +266,7 @@ static int nft_delchain(struct nft_ctx *ctx) if (err < 0) return err; - ctx->table->use--; + nft_use_dec(&ctx->table->use); nft_deactivate_next(ctx->net, ctx->chain); return err; @@ -266,7 +307,7 @@ nf_tables_delrule_deactivate(struct nft_ctx *ctx, struct nft_rule *rule) /* You cannot delete the same rule twice */ if (nft_is_active_next(ctx->net, rule)) { nft_deactivate_next(ctx->net, rule); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); return 0; } return -ENOENT; @@ -286,7 +327,7 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -341,7 +382,7 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -355,7 +396,7 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) return err; nft_deactivate_next(ctx->net, set); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -373,7 +414,7 @@ static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, obj); nft_trans_obj(trans) = obj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -387,7 +428,7 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; nft_deactivate_next(ctx->net, obj); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -406,7 +447,7 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, flowtable); nft_trans_flowtable(trans) = flowtable; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -421,7 +462,7 @@ static int nft_delflowtable(struct nft_ctx *ctx, return err; nft_deactivate_next(ctx->net, flowtable); - ctx->table->use--; + nft_use_dec(&ctx->table->use); return err; } @@ -434,12 +475,14 @@ static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, u8 family, u8 genmask) { + struct nftables_pernet *nft_net; struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) @@ -453,9 +496,11 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net; struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && nft_active_genmask(table, genmask)) return table; @@ -508,11 +553,13 @@ __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) static void nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; + struct nftables_pernet *nft_net; LIST_HEAD(commit_list); va_list args; int ret; - list_splice_init(&net->nft.commit_list, &commit_list); + nft_net = net_generic(net, nf_tables_net_id); + list_splice_init(&nft_net->commit_list, &commit_list); va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); @@ -520,19 +567,20 @@ static void nft_request_module(struct net *net, const char *fmt, ...) if (ret >= MODULE_NAME_LEN) return; - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); request_module("%s", module_name); - mutex_lock(&net->nft.commit_mutex); + mutex_lock(&nft_net->commit_mutex); - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_splice(&commit_list, &net->nft.commit_list); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + list_splice(&commit_list, &nft_net->commit_list); } #endif static void lockdep_nfnl_nft_mutex_not_held(void) { #ifdef CONFIG_PROVE_LOCKING - WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); + if (debug_locks) + WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES)); #endif } @@ -559,6 +607,13 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, return ERR_PTR(-ENOENT); } +static __be16 nft_base_seq(const struct net *net) +{ + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + return htons(nft_net->base_seq & 0xffff); +} + static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { [NFTA_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_TABLE_MAXNAMELEN - 1 }, @@ -571,18 +626,13 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, int family, const struct nft_table *table) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) || nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) || nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) || @@ -629,15 +679,17 @@ static int nf_tables_dump_tables(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -741,7 +793,7 @@ static void nft_table_disable(struct net *net, struct nft_table *table, u32 cnt) if (cnt && i++ == cnt) break; - nf_unregister_net_hook(net, &nft_base_chain(chain)->ops); + nf_tables_unregister_hook(net, table, chain); } } @@ -756,7 +808,7 @@ static int nf_tables_table_enable(struct net *net, struct nft_table *table) if (!nft_is_base_chain(chain)) continue; - err = nf_register_net_hook(net, &nft_base_chain(chain)->ops); + err = nf_tables_register_hook(net, table, chain); if (err < 0) goto err; @@ -800,17 +852,18 @@ static int nf_tables_updtable(struct nft_ctx *ctx) nft_trans_table_enable(trans) = false; } else if (!(flags & NFT_TABLE_F_DORMANT) && ctx->table->flags & NFT_TABLE_F_DORMANT) { + ctx->table->flags &= ~NFT_TABLE_F_DORMANT; ret = nf_tables_table_enable(ctx->net, ctx->table); - if (ret >= 0) { - ctx->table->flags &= ~NFT_TABLE_F_DORMANT; + if (ret >= 0) nft_trans_table_enable(trans) = true; - } + else + ctx->table->flags |= NFT_TABLE_F_DORMANT; } if (ret < 0) goto err; nft_trans_table_update(trans) = true; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: nft_trans_destroy(trans); @@ -840,11 +893,36 @@ static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg, return strcmp(chain->name, name); } +static bool nft_supported_family(u8 family) +{ + return false +#ifdef CONFIG_NF_TABLES_INET + || family == NFPROTO_INET +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + || family == NFPROTO_IPV4 +#endif +#ifdef CONFIG_NF_TABLES_ARP + || family == NFPROTO_ARP +#endif +#ifdef CONFIG_NF_TABLES_NETDEV + || family == NFPROTO_NETDEV +#endif +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) + || family == NFPROTO_BRIDGE +#endif +#ifdef CONFIG_NF_TABLES_IPV6 + || family == NFPROTO_IPV6 +#endif + ; +} + static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; @@ -854,7 +932,10 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct nft_ctx ctx; int err; - lockdep_assert_held(&net->nft.commit_mutex); + if (!nft_supported_family(family)) + return -EOPNOTSUPP; + + lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask); if (IS_ERR(table)) { @@ -904,7 +985,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (err < 0) goto err_trans; - list_add_tail_rcu(&table->list, &net->nft.tables); + list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: rhltable_destroy(&table->chains_ht); @@ -939,8 +1020,7 @@ static int nft_flush_table(struct nft_ctx *ctx) if (!nft_is_active_next(ctx->net, set)) continue; - if (nft_set_is_anonymous(set) && - !list_empty(&set->bindings)) + if (nft_set_is_anonymous(set)) continue; err = nft_delset(ctx, set); @@ -984,11 +1064,12 @@ out: static int nft_flush(struct nft_ctx *ctx, int family) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_table *table, *nt; const struct nlattr * const *nla = ctx->nla; int err = 0; - list_for_each_entry_safe(table, nt, &ctx->net->nft.tables, list) { + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (family != AF_UNSPEC && table->family != family) continue; @@ -1102,7 +1183,9 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) static bool lockdep_commit_lock_is_held(struct net *net) { #ifdef CONFIG_PROVE_LOCKING - return lockdep_is_held(&net->nft.commit_mutex); + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + return lockdep_is_held(&nft_net->commit_mutex); #else return true; #endif @@ -1205,18 +1288,13 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, const struct nft_chain *chain) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_CHAIN_TABLE, table->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_CHAIN_HANDLE, cpu_to_be64(chain->handle), @@ -1304,11 +1382,13 @@ static int nf_tables_dump_chains(struct sk_buff *skb, unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -1501,12 +1581,13 @@ static int nft_chain_parse_hook(struct net *net, struct nft_chain_hook *hook, u8 family, bool autoload) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; struct net_device *dev; int err; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK], @@ -1605,9 +1686,6 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_rule **rules; int err; - if (table->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_CHAIN_HOOK]) { struct nft_chain_hook hook; struct nf_hook_ops *ops; @@ -1679,6 +1757,11 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (err < 0) goto err1; + if (!nft_use_inc(&table->use)) { + err = -EMFILE; + goto err_use; + } + err = rhltable_insert_key(&table->chains_ht, chain->name, &chain->rhlhead, nft_chain_ht_params); if (err) @@ -1691,11 +1774,12 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, goto err2; } - table->use++; list_add_tail_rcu(&chain->list, &table->chains); return 0; err2: + nft_use_dec_restore(&table->use); +err_use: nf_tables_unregister_hook(net, table, chain); err1: nf_tables_chain_destroy(ctx); @@ -1775,6 +1859,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy) if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_trans *tmp; char *name; @@ -1784,7 +1869,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy) goto err; err = -EEXIST; - list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && tmp->ctx.table == table && nft_trans_chain_update(tmp) && @@ -1797,7 +1882,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy) nft_trans_chain_name(trans) = name; } - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: @@ -1811,6 +1896,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; @@ -1821,7 +1907,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct nft_ctx ctx; u64 handle = 0; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); if (IS_ERR(table)) { @@ -2166,27 +2252,31 @@ struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err = nf_tables_expr_parse(ctx, nla, &info); if (err < 0) - goto err1; + goto err_expr_parse; + + err = -EOPNOTSUPP; + if (!(info.ops->type->flags & NFT_EXPR_STATEFUL)) + goto err_expr_stateful; err = -ENOMEM; expr = kzalloc(info.ops->size, GFP_KERNEL); if (expr == NULL) - goto err2; + goto err_expr_stateful; err = nf_tables_newexpr(ctx, &info, expr); if (err < 0) - goto err3; + goto err_expr_new; return expr; -err3: +err_expr_new: kfree(expr); -err2: +err_expr_stateful: owner = info.ops->type->owner; if (info.ops->type->release_ops) info.ops->type->release_ops(info.ops); module_put(owner); -err1: +err_expr_parse: return ERR_PTR(err); } @@ -2245,21 +2335,16 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, const struct nft_rule *rule) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; const struct nft_expr *expr, *next; struct nlattr *list; const struct nft_rule *prule; u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, + nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_RULE_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_RULE_CHAIN, chain->name)) @@ -2345,11 +2430,13 @@ static int nf_tables_dump_rules(struct sk_buff *skb, unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -2502,7 +2589,6 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, { struct nft_expr *expr, *next; - lockdep_assert_held(&ctx->net->nft.commit_mutex); /* * Careful: some expressions might not be initialized in case this * is called on error from nf_tables_newrule(). @@ -2568,6 +2654,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) err = nft_chain_validate(&ctx, chain); if (err < 0) return err; + + cond_resched(); } return 0; @@ -2580,6 +2668,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); struct nft_expr_info *info = NULL; @@ -2596,7 +2685,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, int err, rem; u64 handle, pos_handle; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); if (IS_ERR(table)) { @@ -2632,9 +2721,6 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return -EINVAL; handle = nf_tables_alloc_handle(table); - if (chain->use == UINT_MAX) - return -EOVERFLOW; - if (nla[NFTA_RULE_POSITION]) { pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); old_rule = __nft_rule_lookup(chain, pos_handle); @@ -2710,23 +2796,28 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, expr = nft_expr_next(expr); } + if (!nft_use_inc(&chain->use)) { + err = -EMFILE; + goto err2; + } + if (nlh->nlmsg_flags & NLM_F_REPLACE) { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } err = nft_delrule(&ctx, old_rule); if (err < 0) { nft_trans_destroy(trans); - goto err2; + goto err_destroy_flow_rule; } list_add_tail_rcu(&rule->list, &old_rule->list); } else { if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } if (nlh->nlmsg_flags & NLM_F_APPEND) { @@ -2742,14 +2833,17 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } } kvfree(info); - chain->use++; - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); return 0; + +err_destroy_flow_rule: + nft_use_dec_restore(&chain->use); err2: - nf_tables_rule_release(&ctx, rule); + nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR); + nf_tables_rule_destroy(&ctx, rule); err1: for (i = 0; i < n; i++) { if (info[i].ops) { @@ -2763,15 +2857,18 @@ err1: } static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nft_chain *chain, const struct nlattr *nla) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_rule *rule = nft_trans_rule(trans); if (trans->msg_type == NFT_MSG_NEWRULE && + trans->ctx.chain == chain && id == nft_trans_rule_id(trans)) return rule; } @@ -2818,7 +2915,7 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, err = nft_delrule(&ctx, rule); } else if (nla[NFTA_RULE_ID]) { - rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]); + rule = nft_rule_lookup_byid(net, chain, nla[NFTA_RULE_ID]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]); return PTR_ERR(rule); @@ -2886,12 +2983,13 @@ nft_select_set_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, enum nft_set_policies policy) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; u32 flags = 0; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (list_empty(&nf_tables_set_types)) { @@ -3034,16 +3132,19 @@ static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table, } static struct nft_set *nft_set_lookup_byid(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWSET) { struct nft_set *set = nft_trans_set(trans); if (id == nft_trans_set_id(trans) && + set->table == table && nft_active_genmask(set, genmask)) return set; } @@ -3064,7 +3165,7 @@ struct nft_set *nft_set_lookup_global(const struct net *net, if (!nla_set_id) return set; - set = nft_set_lookup_byid(net, nla_set_id, genmask); + set = nft_set_lookup_byid(net, table, nla_set_id, genmask); } return set; } @@ -3090,7 +3191,7 @@ cont: list_for_each_entry(i, &ctx->table->sets, list) { int tmp; - if (!nft_is_active_next(ctx->net, set)) + if (!nft_is_active_next(ctx->net, i)) continue; if (!sscanf(i->name, name, &tmp)) continue; @@ -3148,23 +3249,17 @@ static __be64 nf_jiffies64_to_msecs(u64 input) static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct nlattr *desc; u32 portid = ctx->portid; u32 seq = ctx->seq; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, + NFNETLINK_V0, nft_base_seq(ctx->net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = ctx->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) @@ -3260,14 +3355,16 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); struct nft_ctx *ctx = cb->data, ctx_set; + struct nftables_pernet *nft_net; if (cb->args[1]) return skb->len; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && ctx->family != table->family) continue; @@ -3561,10 +3658,15 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (ops->privsize != NULL) size = ops->privsize(nla, &desc); + if (!nft_use_inc(&table->use)) { + err = -EMFILE; + goto err1; + } + set = kvzalloc(sizeof(*set) + size + udlen, GFP_KERNEL); if (!set) { err = -ENOMEM; - goto err1; + goto err_alloc; } name = nla_strdup(nla[NFTA_SET_NAME], GFP_KERNEL); @@ -3611,7 +3713,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, goto err4; list_add_tail_rcu(&set->list, &table->sets); - table->use++; + return 0; err4: @@ -3620,6 +3722,8 @@ err3: kfree(set->name); err2: kvfree(set); +err_alloc: + nft_use_dec_restore(&table->use); err1: module_put(to_set_type(ops)->owner); return err; @@ -3679,6 +3783,12 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, return nft_delset(&ctx, set); } +static int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, + unsigned int len); + static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, @@ -3700,9 +3810,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *i; struct nft_set_iter iter; - if (set->use == UINT_MAX) - return -EOVERFLOW; - if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -3727,10 +3834,12 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, return iter.err; } bind: + if (!nft_use_inc(&set->use)) + return -EMFILE; + binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); nft_set_trans_bind(ctx, set); - set->use++; return 0; } @@ -3750,17 +3859,38 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } EXPORT_SYMBOL_GPL(nf_tables_unbind_set); +void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) +{ + if (nft_set_is_anonymous(set)) + nft_clear(ctx->net, set); + + nft_use_inc_restore(&set->use); +} +EXPORT_SYMBOL_GPL(nf_tables_activate_set); + void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { switch (phase) { + case NFT_TRANS_PREPARE_ERROR: + nft_set_trans_unbind(ctx, set); + if (nft_set_is_anonymous(set)) + nft_deactivate_next(ctx->net, set); + else + list_del_rcu(&binding->list); + + nft_use_dec(&set->use); + break; case NFT_TRANS_PREPARE: - set->use--; + if (nft_set_is_anonymous(set)) + nft_deactivate_next(ctx->net, set); + + nft_use_dec(&set->use); return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: - set->use--; + nft_use_dec(&set->use); /* fall through */ default: nf_tables_unbind_set(ctx, set, binding, @@ -3956,18 +4086,19 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; struct net *net = sock_net(skb->sk); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; struct nft_set_dump_args args; bool set_found = false; - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct nlattr *nest; u32 portid, seq; int event; rcu_read_lock(); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) continue; @@ -3993,16 +4124,11 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - NLM_F_MULTI); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, + table->family, NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = table->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_ELEM_LIST_TABLE, table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_ELEM_LIST_SET, set->name)) @@ -4059,22 +4185,16 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_elem *elem) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct nlattr *nest; int err; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), - flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, + NFNETLINK_V0, nft_base_seq(ctx->net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = ctx->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(ctx->net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_SET_TABLE, ctx->table->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_SET_NAME, set->name)) @@ -4114,11 +4234,54 @@ static int nft_setelem_parse_flags(const struct nft_set *set, return 0; } +static int nft_setelem_parse_key(struct nft_ctx *ctx, struct nft_set *set, + struct nft_data *key, struct nlattr *attr) +{ + struct nft_data_desc desc; + int err; + + err = nft_data_init(ctx, key, NFT_DATA_VALUE_MAXLEN, &desc, attr); + if (err < 0) + return err; + + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(key, desc.type); + return -EINVAL; + } + + return 0; +} + +static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set, + struct nft_data_desc *desc, + struct nft_data *data, + struct nlattr *attr) +{ + u32 dtype; + int err; + + err = nft_data_init(ctx, data, NFT_DATA_VALUE_MAXLEN, desc, attr); + if (err < 0) + return err; + + if (set->dtype == NFT_DATA_VERDICT) + dtype = NFT_DATA_VERDICT; + else + dtype = NFT_DATA_VALUE; + + if (dtype != desc->type || + set->dlen != desc->len) { + nft_data_release(data, desc->type); + return -EINVAL; + } + + return 0; +} + static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, const struct nlattr *attr) { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; - struct nft_data_desc desc; struct nft_set_elem elem; struct sk_buff *skb; uint32_t flags = 0; @@ -4137,17 +4300,11 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc, - nla[NFTA_SET_ELEM_KEY]); + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) return err; - err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { - nft_data_release(&elem.key.val, desc.type); - return err; - } - priv = set->ops->get(ctx->net, set, &elem, flags); if (IS_ERR(priv)) return PTR_ERR(priv); @@ -4315,7 +4472,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } } if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); kfree(elem); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -4338,14 +4495,13 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; u8 genmask = nft_genmask_next(ctx->net); - struct nft_data_desc d1, d2; struct nft_set_ext_tmpl tmpl; struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; struct nft_object *obj = NULL; struct nft_userdata *udata; - struct nft_data data; + struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; u32 flags = 0; @@ -4378,6 +4534,15 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return -EINVAL; } + if (set->flags & NFT_SET_OBJECT) { + if (!nla[NFTA_SET_ELEM_OBJREF] && + !(flags & NFT_SET_ELEM_INTERVAL_END)) + return -EINVAL; + } else { + if (nla[NFTA_SET_ELEM_OBJREF]) + return -EINVAL; + } + if ((flags & NFT_SET_ELEM_INTERVAL_END) && (nla[NFTA_SET_ELEM_DATA] || nla[NFTA_SET_ELEM_OBJREF] || @@ -4399,15 +4564,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, timeout = set->timeout; } - err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &d1, - nla[NFTA_SET_ELEM_KEY]); + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) goto err1; - err = -EINVAL; - if (d1.type != NFT_DATA_VALUE || d1.len != set->klen) - goto err2; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, d1.len); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); if (timeout > 0) { nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); if (timeout != set->timeout) @@ -4415,29 +4577,29 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { - if (!(set->flags & NFT_SET_OBJECT)) { - err = -EINVAL; - goto err2; - } obj = nft_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); + obj = NULL; + goto err2; + } + + if (!nft_use_inc(&obj->use)) { + err = -EMFILE; + obj = NULL; goto err2; } + nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); } if (nla[NFTA_SET_ELEM_DATA] != NULL) { - err = nft_data_init(ctx, &data, sizeof(data), &d2, - nla[NFTA_SET_ELEM_DATA]); + err = nft_setelem_parse_data(ctx, set, &desc, &elem.data.val, + nla[NFTA_SET_ELEM_DATA]); if (err < 0) goto err2; - err = -EINVAL; - if (set->dtype != NFT_DATA_VERDICT && d2.len != set->dlen) - goto err3; - dreg = nft_type_to_reg(set->dtype); list_for_each_entry(binding, &set->bindings, list) { struct nft_ctx bind_ctx = { @@ -4451,19 +4613,19 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, continue; err = nft_validate_register_store(&bind_ctx, dreg, - &data, - d2.type, d2.len); + &elem.data.val, + desc.type, desc.len); if (err < 0) goto err3; - if (d2.type == NFT_DATA_VERDICT && - (data.verdict.code == NFT_GOTO || - data.verdict.code == NFT_JUMP)) + if (desc.type == NFT_DATA_VERDICT && + (elem.data.val.verdict.code == NFT_GOTO || + elem.data.val.verdict.code == NFT_JUMP)) nft_validate_state_update(ctx->net, NFT_VALIDATE_NEED); } - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, d2.len); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); } /* The full maximum length of userdata can exceed the maximum @@ -4479,7 +4641,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } err = -ENOMEM; - elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, data.data, + elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, + elem.data.val.data, timeout, GFP_KERNEL); if (elem.priv == NULL) goto err3; @@ -4492,10 +4655,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, udata->len = ulen - 1; nla_memcpy(&udata->data, nla[NFTA_SET_ELEM_USERDATA], ulen); } - if (obj) { + if (obj) *nft_set_ext_obj(ext) = obj; - obj->use++; - } trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) @@ -4533,7 +4694,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err6: @@ -4541,14 +4702,15 @@ err6: err5: kfree(trans); err4: - if (obj) - obj->use--; kfree(elem.priv); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) - nft_data_release(&data, d2.type); + nft_data_release(&elem.data.val, desc.type); err2: - nft_data_release(&elem.key.val, d1.type); + if (obj) + nft_use_dec_restore(&obj->use); + + nft_data_release(&elem.key.val, NFT_DATA_VALUE); err1: return err; } @@ -4558,6 +4720,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u8 genmask = nft_genmask_next(net); const struct nlattr *attr; struct nft_set *set; @@ -4577,7 +4740,8 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + if (!list_empty(&set->bindings) && + (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) return -EBUSY; nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { @@ -4586,7 +4750,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return err; } - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, ctx.table); return 0; @@ -4605,11 +4769,14 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, */ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { + struct nft_chain *chain; + if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - data->verdict.chain->use++; + chain = data->verdict.chain; + nft_use_inc_restore(&chain->use); break; } } @@ -4624,7 +4791,7 @@ static void nft_set_elem_activate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use++; + nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } static void nft_set_elem_deactivate(const struct net *net, @@ -4636,7 +4803,7 @@ static void nft_set_elem_deactivate(const struct net *net, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) - (*nft_set_ext_obj(ext))->use--; + nft_use_dec(&(*nft_set_ext_obj(ext))->use); } static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, @@ -4644,7 +4811,6 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, { struct nlattr *nla[NFTA_SET_ELEM_MAX + 1]; struct nft_set_ext_tmpl tmpl; - struct nft_data_desc desc; struct nft_set_elem elem; struct nft_set_ext *ext; struct nft_trans *trans; @@ -4655,11 +4821,10 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, err = nla_parse_nested(nla, NFTA_SET_ELEM_MAX, attr, nft_set_elem_policy, NULL); if (err < 0) - goto err1; + return err; - err = -EINVAL; if (nla[NFTA_SET_ELEM_KEY] == NULL) - goto err1; + return -EINVAL; nft_set_ext_prepare(&tmpl); @@ -4669,37 +4834,31 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (flags != 0) nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); - err = nft_data_init(ctx, &elem.key.val, sizeof(elem.key), &desc, - nla[NFTA_SET_ELEM_KEY]); + err = nft_setelem_parse_key(ctx, set, &elem.key.val, + nla[NFTA_SET_ELEM_KEY]); if (err < 0) - goto err1; - - err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) - goto err2; + return err; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, desc.len); + nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); err = -ENOMEM; elem.priv = nft_set_elem_init(set, &tmpl, elem.key.val.data, NULL, 0, GFP_KERNEL); if (elem.priv == NULL) - goto err2; + goto fail_elem; ext = nft_set_elem_ext(set, elem.priv); if (flags) *nft_set_ext_flags(ext) = flags; trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set); - if (trans == NULL) { - err = -ENOMEM; - goto err3; - } + if (trans == NULL) + goto fail_trans; priv = set->ops->deactivate(ctx->net, set, &elem); if (priv == NULL) { err = -ENOENT; - goto err4; + goto fail_ops; } kfree(elem.priv); elem.priv = priv; @@ -4707,16 +4866,15 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, nft_set_elem_deactivate(ctx->net, set, &elem); nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; -err4: +fail_ops: kfree(trans); -err3: +fail_trans: kfree(elem.priv); -err2: - nft_data_release(&elem.key.val, desc.type); -err1: +fail_elem: + nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; } @@ -4742,7 +4900,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, nft_set_elem_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err1: @@ -4769,7 +4927,11 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); - if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) + + if (nft_set_is_anonymous(set)) + return -EOPNOTSUPP; + + if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) return -EBUSY; if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) { @@ -5040,9 +5202,14 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + type = nft_obj_type_get(net, objtype); - if (IS_ERR(type)) - return PTR_ERR(type); + if (IS_ERR(type)) { + err = PTR_ERR(type); + goto err_type; + } obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]); if (IS_ERR(obj)) { @@ -5063,7 +5230,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, goto err3; list_add_tail_rcu(&obj->list, &table->objects); - table->use++; + return 0; err3: kfree(obj->name); @@ -5073,6 +5240,9 @@ err2: kfree(obj); err1: module_put(type->owner); +err_type: + nft_use_dec_restore(&table->use); + return err; } @@ -5081,19 +5251,14 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, int family, const struct nft_table *table, struct nft_object *obj, bool reset) { - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || nla_put_string(skb, NFTA_OBJ_NAME, obj->name) || nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || @@ -5124,6 +5289,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) struct nft_obj_filter *filter = cb->data; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; struct nft_object *obj; bool reset = false; @@ -5131,9 +5297,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) reset = true; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -5411,6 +5578,23 @@ struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, } EXPORT_SYMBOL_GPL(nft_flowtable_lookup); +void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, + struct nft_flowtable *flowtable, + enum nft_trans_phase phase) +{ + switch (phase) { + case NFT_TRANS_PREPARE_ERROR: + case NFT_TRANS_PREPARE: + case NFT_TRANS_ABORT: + case NFT_TRANS_RELEASE: + nft_use_dec(&flowtable->use); + /* fall through */ + default: + return; + } +} +EXPORT_SYMBOL_GPL(nf_tables_deactivate_flowtable); + static struct nft_flowtable * nft_flowtable_lookup_byhandle(const struct nft_table *table, const struct nlattr *nla, u8 genmask) @@ -5610,9 +5794,14 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); + if (!nft_use_inc(&table->use)) + return -EMFILE; + flowtable = kzalloc(sizeof(*flowtable), GFP_KERNEL); - if (!flowtable) - return -ENOMEM; + if (!flowtable) { + err = -ENOMEM; + goto flowtable_alloc; + } flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); @@ -5666,7 +5855,6 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, goto err6; list_add_tail_rcu(&flowtable->list, &table->flowtables); - table->use++; return 0; err6: @@ -5684,6 +5872,9 @@ err2: kfree(flowtable->name); err1: kfree(flowtable); +flowtable_alloc: + nft_use_dec_restore(&table->use); + return err; } @@ -5741,20 +5932,15 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, struct nft_flowtable *flowtable) { struct nlattr *nest, *nest_devs; - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; int i; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - if (nla_put_string(skb, NFTA_FLOWTABLE_TABLE, flowtable->table->name) || nla_put_string(skb, NFTA_FLOWTABLE_NAME, flowtable->name) || nla_put_be32(skb, NFTA_FLOWTABLE_USE, htonl(flowtable->use)) || @@ -5804,12 +5990,14 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; const struct nft_table *table; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -5979,21 +6167,17 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), 0); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, + NFNETLINK_V0, nft_base_seq(net)); + if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(net->nft.base_seq & 0xffff); - - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -6026,6 +6210,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; struct nft_table *table; struct net *net; @@ -6033,13 +6218,14 @@ static int nf_tables_flowtable_event(struct notifier_block *this, return 0; net = dev_net(dev); - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { nft_flowtable_event(event, dev, flowtable); } } - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } @@ -6220,19 +6406,22 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { static int nf_tables_validate(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_table *table; - switch (net->nft.validate_state) { + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: break; case NFT_VALIDATE_NEED: nft_validate_state_update(net, NFT_VALIDATE_DO); /* fall through */ case NFT_VALIDATE_DO: - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_validate(net, table) < 0) return -EAGAIN; } + + nft_validate_state_update(net, NFT_VALIDATE_SKIP); break; } @@ -6304,15 +6493,16 @@ static void nft_commit_release(struct nft_trans *trans) static void nf_tables_commit_release(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; - if (list_empty(&net->nft.commit_list)) + if (list_empty(&nft_net->commit_list)) return; synchronize_rcu(); - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { - list_del(&trans->list); + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { + nft_trans_list_del(trans); nft_commit_release(trans); } } @@ -6350,9 +6540,10 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha static void nf_tables_commit_chain_prepare_cancel(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWRULE || @@ -6444,17 +6635,30 @@ static void nft_chain_del(struct nft_chain *chain) static int nf_tables_commit(struct net *net, struct sk_buff *skb) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; + list_for_each_entry(trans, &nft_net->binding_list, binding_list) { + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_set_is_anonymous(nft_trans_set(trans)) && + !nft_trans_set_bound(trans)) { + pr_warn_once("nftables ruleset with unbound set\n"); + return -EINVAL; + } + break; + } + } + /* 0. Validate ruleset, otherwise roll back for error reporting. */ if (nf_tables_validate(net) < 0) return -EAGAIN; /* 1. Allocate space for next generation rules_gen_X[] */ - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { int ret; if (trans->msg_type == NFT_MSG_NEWRULE || @@ -6470,7 +6674,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } /* step 2. Make rules_gen_X visible to packet path */ - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_commit_chain(net, chain); } @@ -6479,12 +6683,13 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - while (++net->nft.base_seq == 0); + while (++nft_net->base_seq == 0) + ; /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { @@ -6544,7 +6749,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) - trans->ctx.table->use--; + nft_use_dec(&trans->ctx.table->use); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); @@ -6605,7 +6810,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_commit_release(net); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return 0; } @@ -6641,10 +6846,11 @@ static void nf_tables_abort_release(struct nft_trans *trans) static int __nf_tables_abort(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; struct nft_trans_elem *te; - list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, + list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: @@ -6669,7 +6875,7 @@ static int __nf_tables_abort(struct net *net) kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); nft_chain_del(trans->ctx.chain); nf_tables_unregister_hook(trans->ctx.net, trans->ctx.table, @@ -6677,25 +6883,25 @@ static int __nf_tables_abort(struct net *net) } break; case NFT_MSG_DELCHAIN: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, trans->ctx.chain); nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: - trans->ctx.chain->use--; + nft_use_dec_restore(&trans->ctx.chain->use); list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); break; case NFT_MSG_DELRULE: - trans->ctx.chain->use++; + nft_use_inc_restore(&trans->ctx.chain->use); nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; @@ -6703,7 +6909,7 @@ static int __nf_tables_abort(struct net *net) list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_set(trans)); nft_trans_destroy(trans); break; @@ -6726,22 +6932,22 @@ static int __nf_tables_abort(struct net *net) nft_trans_destroy(trans); break; case NFT_MSG_NEWOBJ: - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_obj(trans)->list); break; case NFT_MSG_DELOBJ: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWFLOWTABLE: - trans->ctx.table->use--; + nft_use_dec_restore(&trans->ctx.table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, nft_trans_flowtable(trans)); break; case NFT_MSG_DELFLOWTABLE: - trans->ctx.table->use++; + nft_use_inc_restore(&trans->ctx.table->use); nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); nft_trans_destroy(trans); break; @@ -6751,37 +6957,34 @@ static int __nf_tables_abort(struct net *net) synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, - &net->nft.commit_list, list) { - list_del(&trans->list); + &nft_net->commit_list, list) { + nft_trans_list_del(trans); nf_tables_abort_release(trans); } return 0; } -static void nf_tables_cleanup(struct net *net) -{ - nft_validate_state_update(net, NFT_VALIDATE_SKIP); -} - static int nf_tables_abort(struct net *net, struct sk_buff *skb) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); int ret = __nf_tables_abort(net); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); bool genid_ok; - mutex_lock(&net->nft.commit_mutex); + mutex_lock(&nft_net->commit_mutex); - genid_ok = genid == 0 || net->nft.base_seq == genid; + genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); /* else, commit mutex has to be released by commit or abort function */ return genid_ok; @@ -6794,7 +6997,6 @@ static const struct nfnetlink_subsystem nf_tables_subsys = { .cb = nf_tables_cb, .commit = nf_tables_commit, .abort = nf_tables_abort, - .cleanup = nf_tables_cleanup, .valid_genid = nf_tables_valid_genid, .owner = THIS_MODULE, }; @@ -6956,28 +7158,24 @@ int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest) } EXPORT_SYMBOL_GPL(nft_parse_u32_check); -/** - * nft_parse_register - parse a register value from a netlink attribute - * - * @attr: netlink attribute - * - * Parse and translate a register value from a netlink attribute. - * Registers used to be 128 bit wide, these register numbers will be - * mapped to the corresponding 32 bit register numbers. - */ -unsigned int nft_parse_register(const struct nlattr *attr) +static int nft_parse_register(const struct nlattr *attr, u32 *preg) { unsigned int reg; reg = ntohl(nla_get_be32(attr)); switch (reg) { case NFT_REG_VERDICT...NFT_REG_4: - return reg * NFT_REG_SIZE / NFT_REG32_SIZE; + *preg = reg * NFT_REG_SIZE / NFT_REG32_SIZE; + break; + case NFT_REG32_00...NFT_REG32_15: + *preg = reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; + break; default: - return reg + NFT_REG_SIZE / NFT_REG32_SIZE - NFT_REG32_00; + return -ERANGE; } + + return 0; } -EXPORT_SYMBOL_GPL(nft_parse_register); /** * nft_dump_register - dump a register value to a netlink attribute @@ -7010,7 +7208,7 @@ EXPORT_SYMBOL_GPL(nft_dump_register); * Validate that the input register is one of the general purpose * registers and that the length of the load is within the bounds. */ -int nft_validate_register_load(enum nft_registers reg, unsigned int len) +static int nft_validate_register_load(enum nft_registers reg, unsigned int len) { if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; @@ -7021,7 +7219,24 @@ int nft_validate_register_load(enum nft_registers reg, unsigned int len) return 0; } -EXPORT_SYMBOL_GPL(nft_validate_register_load); + +int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) +{ + u32 reg; + int err; + + err = nft_parse_register(attr, ®); + if (err < 0) + return err; + + err = nft_validate_register_load(reg, len); + if (err < 0) + return err; + + *sreg = reg; + return 0; +} +EXPORT_SYMBOL_GPL(nft_parse_register_load); /** * nft_validate_register_store - validate an expressions' register store @@ -7037,10 +7252,11 @@ EXPORT_SYMBOL_GPL(nft_validate_register_load); * A value of NULL for the data means that its runtime gathered * data. */ -int nft_validate_register_store(const struct nft_ctx *ctx, - enum nft_registers reg, - const struct nft_data *data, - enum nft_data_types type, unsigned int len) +static int nft_validate_register_store(const struct nft_ctx *ctx, + enum nft_registers reg, + const struct nft_data *data, + enum nft_data_types type, + unsigned int len) { int err; @@ -7072,7 +7288,27 @@ int nft_validate_register_store(const struct nft_ctx *ctx, return 0; } } -EXPORT_SYMBOL_GPL(nft_validate_register_store); + +int nft_parse_register_store(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *dreg, + const struct nft_data *data, + enum nft_data_types type, unsigned int len) +{ + int err; + u32 reg; + + err = nft_parse_register(attr, ®); + if (err < 0) + return err; + + err = nft_validate_register_store(ctx, reg, data, type, len); + if (err < 0) + return err; + + *dreg = reg; + return 0; +} +EXPORT_SYMBOL_GPL(nft_parse_register_store); static const struct nla_policy nft_verdict_policy[NFTA_VERDICT_MAX + 1] = { [NFTA_VERDICT_CODE] = { .type = NLA_U32 }, @@ -7095,6 +7331,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; + + /* zero padding hole for memcmp */ + memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { @@ -7122,8 +7361,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, return PTR_ERR(chain); if (nft_is_base_chain(chain)) return -EOPNOTSUPP; + if (!nft_use_inc(&chain->use)) + return -EMFILE; - chain->use++; data->verdict.chain = chain; break; } @@ -7135,10 +7375,13 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, static void nft_verdict_uninit(const struct nft_data *data) { + struct nft_chain *chain; + switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - data->verdict.chain->use--; + chain = data->verdict.chain; + nft_use_dec(&chain->use); break; } } @@ -7291,21 +7534,20 @@ int __nft_release_basechain(struct nft_ctx *ctx) nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - ctx->chain->use--; + nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } nft_chain_del(ctx->chain); - ctx->table->use--; + nft_use_dec(&ctx->table->use); nf_tables_chain_destroy(ctx); return 0; } EXPORT_SYMBOL_GPL(__nft_release_basechain); -static void __nft_release_tables(struct net *net) +static void __nft_release_table(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable, *nf; - struct nft_table *table, *nt; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_rule *rule, *nr; @@ -7315,71 +7557,85 @@ static void __nft_release_tables(struct net *net) .family = NFPROTO_NETDEV, }; - list_for_each_entry_safe(table, nt, &net->nft.tables, list) { - ctx.family = table->family; + ctx.family = table->family; - list_for_each_entry(chain, &table->chains, list) - nf_tables_unregister_hook(net, table, chain); - /* No packets are walking on these chains anymore. */ - ctx.table = table; - list_for_each_entry(chain, &table->chains, list) { - ctx.chain = chain; - list_for_each_entry_safe(rule, nr, &chain->rules, list) { - list_del(&rule->list); - chain->use--; - nf_tables_rule_release(&ctx, rule); - } - } - list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { - list_del(&flowtable->list); - table->use--; - nf_tables_flowtable_destroy(flowtable); - } - list_for_each_entry_safe(set, ns, &table->sets, list) { - list_del(&set->list); - table->use--; - nft_set_destroy(set); - } - list_for_each_entry_safe(obj, ne, &table->objects, list) { - list_del(&obj->list); - table->use--; - nft_obj_destroy(&ctx, obj); - } - list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; - nft_chain_del(chain); - table->use--; - nf_tables_chain_destroy(&ctx); + list_for_each_entry(chain, &table->chains, list) + nf_tables_unregister_hook(net, table, chain); + /* No packets are walking on these chains anymore. */ + ctx.table = table; + list_for_each_entry(chain, &table->chains, list) { + ctx.chain = chain; + list_for_each_entry_safe(rule, nr, &chain->rules, list) { + list_del(&rule->list); + nft_use_dec(&chain->use); + nf_tables_rule_release(&ctx, rule); } - list_del(&table->list); - nf_tables_table_destroy(&ctx); } + list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { + list_del(&flowtable->list); + nft_use_dec(&table->use); + nf_tables_flowtable_destroy(flowtable); + } + list_for_each_entry_safe(set, ns, &table->sets, list) { + list_del(&set->list); + nft_use_dec(&table->use); + nft_set_destroy(set); + } + list_for_each_entry_safe(obj, ne, &table->objects, list) { + list_del(&obj->list); + nft_use_dec(&table->use); + nft_obj_destroy(&ctx, obj); + } + list_for_each_entry_safe(chain, nc, &table->chains, list) { + ctx.chain = chain; + nft_chain_del(chain); + nft_use_dec(&table->use); + nf_tables_chain_destroy(&ctx); + } + list_del(&table->list); + nf_tables_table_destroy(&ctx); +} + +static void __nft_release_tables(struct net *net) +{ + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + struct nft_table *table, *nt; + + list_for_each_entry_safe(table, nt, &nft_net->tables, list) + __nft_release_table(net, table); } static int __net_init nf_tables_init_net(struct net *net) { - INIT_LIST_HEAD(&net->nft.tables); - INIT_LIST_HEAD(&net->nft.commit_list); - mutex_init(&net->nft.commit_mutex); - net->nft.base_seq = 1; - net->nft.validate_state = NFT_VALIDATE_SKIP; + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + INIT_LIST_HEAD(&nft_net->tables); + INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->binding_list); + mutex_init(&nft_net->commit_mutex); + nft_net->base_seq = 1; + nft_net->validate_state = NFT_VALIDATE_SKIP; return 0; } static void __net_exit nf_tables_exit_net(struct net *net) { - mutex_lock(&net->nft.commit_mutex); - if (!list_empty(&net->nft.commit_list)) + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nft_net->commit_list)) __nf_tables_abort(net); __nft_release_tables(net); - mutex_unlock(&net->nft.commit_mutex); - WARN_ON_ONCE(!list_empty(&net->nft.tables)); + mutex_unlock(&nft_net->commit_mutex); + WARN_ON_ONCE(!list_empty(&nft_net->tables)); } static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .exit = nf_tables_exit_net, + .id = &nf_tables_net_id, + .size = sizeof(struct nftables_pernet), }; static int __init nf_tables_module_init(void) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index a3850414dba2..7dfaad783cd5 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -144,7 +144,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) struct nft_rule *const *rules; const struct nft_rule *rule; const struct nft_expr *expr, *last; - struct nft_regs regs; + struct nft_regs regs = {}; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; bool genbit = READ_ONCE(net->nft.gencursor); diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index e1dc527a493b..7a19c517b191 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -186,7 +186,6 @@ static bool nft_trace_have_verdict_chain(struct nft_traceinfo *info) void nft_trace_notify(struct nft_traceinfo *info) { const struct nft_pktinfo *pkt = info->pkt; - struct nfgenmsg *nfmsg; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int size; @@ -222,15 +221,11 @@ void nft_trace_notify(struct nft_traceinfo *info) return; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_TRACE); - nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct nfgenmsg), 0); + nlh = nfnl_msg_put(skb, 0, 0, event, 0, info->basechain->type->family, + NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = info->basechain->type->family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(nft_pf(pkt)))) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 9bacddc761ba..0267be2e9cfe 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -452,7 +452,8 @@ ack: * processed, this avoids that the same error is * reported several times when replaying the batch. */ - if (nfnl_err_add(&err_list, nlh, err, &extack) < 0) { + if (err == -ENOMEM || + nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. @@ -495,8 +496,6 @@ done: } else { ss->abort(net, oskb); } - if (ss->cleanup) - ss->cleanup(net); nfnl_err_deliver(&err_list, oskb); kfree_skb(skb); diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 8fa8bf7c48e6..7c5f428dc5c9 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -135,21 +135,16 @@ nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_acct *acct) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; u64 pkts, bytes; u32 old_flags; event = nfnl_msg_type(NFNL_SUBSYS_ACCT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, NFACCT_NAME, acct->name)) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index ddcb1b607474..720177721e3c 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -381,10 +381,14 @@ static int nfnl_cthelper_update(const struct nlattr * const tb[], struct nf_conntrack_helper *helper) { + u32 size; int ret; - if (tb[NFCTH_PRIV_DATA_LEN]) - return -EBUSY; + if (tb[NFCTH_PRIV_DATA_LEN]) { + size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN])); + if (size != helper->data_len) + return -EBUSY; + } if (tb[NFCTH_POLICY]) { ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]); @@ -528,20 +532,15 @@ nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_conntrack_helper *helper) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; int status; event = nfnl_msg_type(NFNL_SUBSYS_CTHELPER, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, NFCTH_NAME, helper->name)) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 70a7382b9787..ae01e9ad5546 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -164,20 +164,15 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct ctnl_timeout *timeout) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; const struct nf_conntrack_l4proto *l4proto = timeout->timeout.l4proto; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) || nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->timeout.l3num)) || @@ -396,19 +391,14 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, const unsigned int *timeouts) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = AF_UNSPEC; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(l4proto->l3proto)) || nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto)) goto nla_put_failure; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 25298b3eb854..1735bcb07381 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -404,20 +404,15 @@ __build_packet_message(struct nfnl_log_net *log, { struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; sk_buff_data_t old_tail = inst->skb->tail; struct sock *sk; const unsigned char *hwhdrp; - nlh = nlmsg_put(inst->skb, 0, 0, - nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET), - sizeof(struct nfgenmsg), 0); + nlh = nfnl_msg_put(inst->skb, 0, 0, + nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET), + 0, pf, NFNETLINK_V0, htons(inst->group_num)); if (!nlh) return -1; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = pf; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(inst->group_num); memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; @@ -509,7 +504,8 @@ __build_packet_message(struct nfnl_log_net *log, goto nla_put_failure; if (indev && skb->dev && - skb->mac_header != skb->network_header) { + skb_mac_header_was_set(skb) && + skb_mac_header_len(skb) != 0) { struct nfulnl_msg_packet_hw phw; int len; @@ -635,8 +631,8 @@ nfulnl_log_packet(struct net *net, unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; + enum ip_conntrack_info ctinfo = 0; struct nf_conn *ct = NULL; - enum ip_conntrack_info uninitialized_var(ctinfo); if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 131f9f8c0b09..f3676238e64f 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -191,6 +191,8 @@ static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx, ctx->optp = skb_header_pointer(skb, ip_hdrlen(skb) + sizeof(struct tcphdr), ctx->optsize, opts); + if (!ctx->optp) + return NULL; } return tcp; @@ -316,6 +318,14 @@ static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl, f = nla_data(osf_attrs[OSF_ATTR_FINGER]); + if (f->opt_num > ARRAY_SIZE(f->opt)) + return -EINVAL; + + if (!memchr(f->genre, 0, MAXGENRELEN) || + !memchr(f->subtype, 0, MAXGENRELEN) || + !memchr(f->version, 0, MAXGENRELEN)) + return -EINVAL; + kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL); if (!kf) return -ENOMEM; @@ -440,3 +450,4 @@ module_init(nfnl_osf_init); module_exit(nfnl_osf_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f81a3ce0fe48..1aacc31a6bf9 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -387,12 +387,11 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; struct sk_buff *entskb = entry->skb; struct net_device *indev; struct net_device *outdev; struct nf_conn *ct = NULL; - enum ip_conntrack_info uninitialized_var(ctinfo); + enum ip_conntrack_info ctinfo; struct nfnl_ct_hook *nfnl_ct; bool csum_verify; char *secdata = NULL; @@ -473,18 +472,15 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, goto nlmsg_failure; } - nlh = nlmsg_put(skb, 0, 0, - nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET), - sizeof(struct nfgenmsg), 0); + nlh = nfnl_msg_put(skb, 0, 0, + nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET), + 0, entry->state.pf, NFNETLINK_V0, + htons(queue->queue_num)); if (!nlh) { skb_tx_error(entskb); kfree_skb(skb); goto nlmsg_failure; } - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = entry->state.pf; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = htons(queue->queue_num); nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg)); pmsg = nla_data(nla); @@ -566,7 +562,8 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, goto nla_put_failure; if (indev && entskb->dev && - entskb->mac_header != entskb->network_header) { + skb_mac_header_was_set(entskb) && + skb_mac_header_len(entskb) != 0) { struct nfqnl_msg_packet_hw phw; int len; @@ -715,9 +712,15 @@ static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); - if (entry) - nf_queue_entry_get_refs(entry); - return entry; + + if (!entry) + return NULL; + + if (nf_queue_entry_get_refs(entry)) + return entry; + + kfree(entry); + return NULL; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) @@ -843,11 +846,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) } static int -nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff) +nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; if (diff < 0) { + unsigned int min_len = skb_transport_offset(e->skb); + + if (data_len < min_len) + return -EINVAL; + if (pskb_trim(e->skb, data_len)) return -ENOMEM; } else if (diff > 0) { @@ -1179,7 +1187,7 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct nfqnl_instance *queue; unsigned int verdict; struct nf_queue_entry *entry; - enum ip_conntrack_info uninitialized_var(ctinfo); + enum ip_conntrack_info ctinfo; struct nfnl_ct_hook *nfnl_ct; struct nf_conn *ct = NULL; struct nfnl_queue_net *q = nfnl_queue_pernet(net); diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 058ee84ea531..c1055251ebde 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -18,8 +18,8 @@ #include <net/netfilter/nf_tables.h> struct nft_bitwise { - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; u8 len; struct nft_data mask; struct nft_data xor; @@ -68,14 +68,14 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, priv->len = len; - priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); - err = nft_validate_register_load(priv->sreg, priv->len); + err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + priv->len); if (err < 0) return err; - priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + err = nft_parse_register_store(ctx, tb[NFTA_BITWISE_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); if (err < 0) return err; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 13d4e421a6b3..dba16126c7ee 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -19,8 +19,8 @@ #include <net/netfilter/nf_tables.h> struct nft_byteorder { - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; enum nft_byteorder_ops op:8; u8 len; u8 size; @@ -33,11 +33,11 @@ static void nft_byteorder_eval(const struct nft_expr *expr, const struct nft_byteorder *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - union { u32 u32; u16 u16; } *s, *d; + u16 *s16, *d16; unsigned int i; - s = (void *)src; - d = (void *)dst; + s16 = (void *)src; + d16 = (void *)dst; switch (priv->size) { case 8: { @@ -63,11 +63,11 @@ static void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = ntohl((__force __be32)s[i].u32); + dst[i] = ntohl((__force __be32)src[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 4; i++) - d[i].u32 = (__force __u32)htonl(s[i].u32); + dst[i] = (__force __u32)htonl(src[i]); break; } break; @@ -75,11 +75,11 @@ static void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = ntohs((__force __be16)s[i].u16); + d16[i] = ntohs((__force __be16)s16[i]); break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 2; i++) - d[i].u16 = (__force __u16)htons(s[i].u16); + d16[i] = (__force __u16)htons(s16[i]); break; } break; @@ -133,20 +133,20 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, return -EINVAL; } - priv->sreg = nft_parse_register(tb[NFTA_BYTEORDER_SREG]); err = nft_parse_u32_check(tb[NFTA_BYTEORDER_LEN], U8_MAX, &len); if (err < 0) return err; priv->len = len; - err = nft_validate_register_load(priv->sreg, priv->len); + err = nft_parse_register_load(tb[NFTA_BYTEORDER_SREG], &priv->sreg, + priv->len); if (err < 0) return err; - priv->dreg = nft_parse_register(tb[NFTA_BYTEORDER_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + return nft_parse_register_store(ctx, tb[NFTA_BYTEORDER_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); } static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 3fd540b2c6ba..a308d45ee95e 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -2,6 +2,7 @@ #include <linux/kernel.h> #include <linux/netdevice.h> #include <net/net_namespace.h> +#include <net/netns/generic.h> #include <net/netfilter/nf_tables.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> @@ -10,6 +11,8 @@ #include <net/netfilter/nf_tables_ipv4.h> #include <net/netfilter/nf_tables_ipv6.h> +extern unsigned int nf_tables_net_id; + #ifdef CONFIG_NF_TABLES_IPV4 static unsigned int nft_do_chain_ipv4(void *priv, struct sk_buff *skb, @@ -315,6 +318,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_chain *chain, *nr; struct nft_ctx ctx = { @@ -325,8 +329,9 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; - mutex_lock(&ctx.net->nft.commit_mutex); - list_for_each_entry(table, &ctx.net->nft.tables, list) { + nft_net = net_generic(ctx.net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -340,7 +345,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_netdev_event(event, dev, &ctx); } } - mutex_unlock(&ctx.net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 7007045c0849..36bf64ebc892 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -19,7 +19,7 @@ struct nft_cmp_expr { struct nft_data data; - enum nft_registers sreg:8; + u8 sreg; u8 len; enum nft_cmp_ops op:8; }; @@ -88,8 +88,7 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return err; } - priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); - err = nft_validate_register_load(priv->sreg, desc.len); + err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -139,8 +138,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); - err = nft_validate_register_load(priv->sreg, desc.len); + err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 469f9da5073b..2846d64659f2 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -575,19 +575,14 @@ nfnl_compat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int rev, int target) { struct nlmsghdr *nlh; - struct nfgenmsg *nfmsg; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_NFT_COMPAT, event); - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); - if (nlh == NULL) + nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, + NFNETLINK_V0, 0); + if (!nlh) goto nlmsg_failure; - nfmsg = nlmsg_data(nlh); - nfmsg->nfgen_family = family; - nfmsg->version = NFNETLINK_V0; - nfmsg->res_id = 0; - if (nla_put_string(skb, NFTA_COMPAT_NAME, name) || nla_put_be32(skb, NFTA_COMPAT_REV, htonl(rev)) || nla_put_be32(skb, NFTA_COMPAT_TYPE, htonl(target))) diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 5dd87748afa8..f29f02805bcc 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -29,8 +29,8 @@ struct nft_ct { enum nft_ct_keys key:8; enum ip_conntrack_dir dir:8; union { - enum nft_registers dreg:8; - enum nft_registers sreg:8; + u8 dreg; + u8 sreg; }; }; @@ -486,9 +486,8 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, } } - priv->dreg = nft_parse_register(tb[NFTA_CT_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + err = nft_parse_register_store(ctx, tb[NFTA_CT_DREG], &priv->dreg, NULL, + NFT_DATA_VALUE, len); if (err < 0) return err; @@ -581,8 +580,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, } } - priv->sreg = nft_parse_register(tb[NFTA_CT_SREG]); - err = nft_validate_register_load(priv->sreg, len); + err = nft_parse_register_load(tb[NFTA_CT_SREG], &priv->sreg, len); if (err < 0) goto err1; diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index 2cc1e0ef56e8..e862f916efa0 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -16,7 +16,7 @@ #include <net/netfilter/nf_dup_netdev.h> struct nft_dup_netdev { - enum nft_registers sreg_dev:8; + u8 sreg_dev; }; static void nft_dup_netdev_eval(const struct nft_expr *expr, @@ -42,8 +42,8 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_DEV] == NULL) return -EINVAL; - priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); + return nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, + sizeof(int)); } static const struct nft_expr_ops nft_dup_netdev_ingress_ops; diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index eb7f9a5f2aeb..a4c6aba7da7e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -15,13 +15,16 @@ #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> +#include <net/netns/generic.h> + +extern unsigned int nf_tables_net_id; struct nft_dynset { struct nft_set *set; struct nft_set_ext_tmpl tmpl; enum nft_dynset_ops op:8; - enum nft_registers sreg_key:8; - enum nft_registers sreg_data:8; + u8 sreg_key; + u8 sreg_data; bool invert; u64 timeout; struct nft_expr *expr; @@ -112,13 +115,14 @@ static int nft_dynset_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_dynset *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; u64 timeout; int err; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); if (tb[NFTA_DYNSET_SET_NAME] == NULL || tb[NFTA_DYNSET_OP] == NULL || @@ -140,6 +144,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); + if (set->flags & NFT_SET_OBJECT) + return -EOPNOTSUPP; + if (set->ops->update == NULL) return -EOPNOTSUPP; @@ -166,8 +173,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, tb[NFTA_DYNSET_TIMEOUT]))); } - priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]); - err = nft_validate_register_load(priv->sreg_key, set->klen); + err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, + set->klen); if (err < 0) return err; @@ -177,8 +184,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (set->dtype == NFT_DATA_VERDICT) return -EOPNOTSUPP; - priv->sreg_data = nft_parse_register(tb[NFTA_DYNSET_SREG_DATA]); - err = nft_validate_register_load(priv->sreg_data, set->dlen); + err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_DATA], + &priv->sreg_data, set->dlen); if (err < 0) return err; } else if (set->flags & NFT_SET_MAP) @@ -193,9 +200,6 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return PTR_ERR(priv->expr); err = -EOPNOTSUPP; - if (!(priv->expr->ops->type->flags & NFT_EXPR_STATEFUL)) - goto err1; - if (priv->expr->ops->type->flags & NFT_EXPR_GC) { if (set->flags & NFT_SET_TIMEOUT) goto err1; @@ -213,8 +217,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx, nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_EXPR, priv->expr->ops->size); if (set->flags & NFT_SET_TIMEOUT) { - if (timeout || set->timeout) + if (timeout || set->timeout) { + nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT); nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION); + } } priv->timeout = timeout; @@ -249,7 +255,7 @@ static void nft_dynset_activate(const struct nft_ctx *ctx, { struct nft_dynset *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_dynset_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a940c9fd9045..8d0f14cd7cc3 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -22,8 +22,8 @@ struct nft_exthdr { u8 offset; u8 len; u8 op; - enum nft_registers dreg:8; - enum nft_registers sreg:8; + u8 dreg; + u8 sreg; u8 flags; }; @@ -45,6 +45,9 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, unsigned int offset = 0; int err; + if (pkt->skb->protocol != htons(ETH_P_IPV6)) + goto err; + err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { *dest = (err >= 0); @@ -134,7 +137,6 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, unsigned int i, optl, tcphdr_len, offset; struct tcphdr *tcph; u8 *opt; - u32 src; tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); if (!tcph) @@ -143,7 +145,6 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, opt = (u8 *)tcph; for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { union { - u8 octet; __be16 v16; __be32 v32; } old, new; @@ -164,13 +165,13 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, if (!tcph) return; - src = regs->data[priv->sreg]; offset = i + priv->offset; switch (priv->len) { case 2: old.v16 = get_unaligned((u16 *)(opt + offset)); - new.v16 = src; + new.v16 = (__force __be16)nft_reg_load16( + ®s->data[priv->sreg]); switch (priv->type) { case TCPOPT_MSS: @@ -188,7 +189,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, old.v16, new.v16, false); break; case 4: - new.v32 = src; + new.v32 = regs->data[priv->sreg]; old.v32 = get_unaligned((u32 *)(opt + offset)); if (old.v32 == new.v32) @@ -257,12 +258,12 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; priv->len = len; - priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); priv->flags = flags; priv->op = op; - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + return nft_parse_register_store(ctx, tb[NFTA_EXTHDR_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); } static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, @@ -307,11 +308,11 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); priv->offset = offset; priv->len = len; - priv->sreg = nft_parse_register(tb[NFTA_EXTHDR_SREG]); priv->flags = flags; priv->op = op; - return nft_validate_register_load(priv->sreg, priv->len); + return nft_parse_register_load(tb[NFTA_EXTHDR_SREG], &priv->sreg, + priv->len); } static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv) diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 21df8cccea65..ce6891337304 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -88,7 +88,6 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; priv->result = ntohl(nla_get_be32(tb[NFTA_FIB_RESULT])); - priv->dreg = nft_parse_register(tb[NFTA_FIB_DREG]); switch (priv->result) { case NFT_FIB_RESULT_OIF: @@ -108,8 +107,8 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; } - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + err = nft_parse_register_store(ctx, tb[NFTA_FIB_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); if (err < 0) return err; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 166edea0e452..ec35a41c7262 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -169,18 +169,34 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (IS_ERR(flowtable)) return PTR_ERR(flowtable); + if (!nft_use_inc(&flowtable->use)) + return -EMFILE; + priv->flowtable = flowtable; - flowtable->use++; return nf_ct_netns_get(ctx->net, ctx->family); } -static void nft_flow_offload_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_flow_offload_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_flow_offload *priv = nft_expr_priv(expr); - priv->flowtable->use--; + nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase); +} + +static void nft_flow_offload_activate(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ + struct nft_flow_offload *priv = nft_expr_priv(expr); + + nft_use_inc_restore(&priv->flowtable->use); +} + +static void nft_flow_offload_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) +{ nf_ct_netns_put(ctx->net, ctx->family); } @@ -203,6 +219,8 @@ static const struct nft_expr_ops nft_flow_offload_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)), .eval = nft_flow_offload_eval, .init = nft_flow_offload_init, + .activate = nft_flow_offload_activate, + .deactivate = nft_flow_offload_deactivate, .destroy = nft_flow_offload_destroy, .validate = nft_flow_offload_validate, .dump = nft_flow_offload_dump, diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 649edbe77a20..2efbe78de3b2 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -20,7 +20,7 @@ #include <net/ip.h> struct nft_fwd_netdev { - enum nft_registers sreg_dev:8; + u8 sreg_dev; }; static void nft_fwd_netdev_eval(const struct nft_expr *expr, @@ -49,8 +49,8 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_FWD_SREG_DEV] == NULL) return -EINVAL; - priv->sreg_dev = nft_parse_register(tb[NFTA_FWD_SREG_DEV]); - return nft_validate_register_load(priv->sreg_dev, sizeof(int)); + return nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + sizeof(int)); } static const struct nft_expr_ops nft_fwd_netdev_ingress_ops; @@ -69,8 +69,8 @@ nla_put_failure: } struct nft_fwd_neigh { - enum nft_registers sreg_dev:8; - enum nft_registers sreg_addr:8; + u8 sreg_dev; + u8 sreg_addr; u8 nfproto; }; @@ -129,6 +129,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr, return; skb->dev = dev; + skb->tstamp = 0; neigh_xmit(neigh_table, dev, addr, skb); out: regs->verdict.code = verdict; @@ -147,8 +148,6 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, !tb[NFTA_FWD_NFPROTO]) return -EINVAL; - priv->sreg_dev = nft_parse_register(tb[NFTA_FWD_SREG_DEV]); - priv->sreg_addr = nft_parse_register(tb[NFTA_FWD_SREG_ADDR]); priv->nfproto = ntohl(nla_get_be32(tb[NFTA_FWD_NFPROTO])); switch (priv->nfproto) { @@ -162,11 +161,13 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nft_validate_register_load(priv->sreg_dev, sizeof(int)); + err = nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + sizeof(int)); if (err < 0) return err; - return nft_validate_register_load(priv->sreg_addr, addr_len); + return nft_parse_register_load(tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, + addr_len); } static const struct nft_expr_ops nft_fwd_netdev_ingress_ops; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index b8f23f75aea6..513419aca9c6 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -18,8 +18,8 @@ #include <linux/jhash.h> struct nft_jhash { - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; u8 len; bool autogen_seed:1; u32 modulus; @@ -65,7 +65,7 @@ static void nft_jhash_map_eval(const struct nft_expr *expr, } struct nft_symhash { - enum nft_registers dreg:8; + u8 dreg; u32 modulus; u32 offset; struct nft_set *map; @@ -136,9 +136,6 @@ static int nft_jhash_init(const struct nft_ctx *ctx, if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); - priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); - priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); if (err < 0) return err; @@ -147,6 +144,10 @@ static int nft_jhash_init(const struct nft_ctx *ctx, priv->len = len; + err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len); + if (err < 0) + return err; + priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; @@ -161,9 +162,8 @@ static int nft_jhash_init(const struct nft_ctx *ctx, get_random_bytes(&priv->seed, sizeof(priv->seed)); } - return nft_validate_register_load(priv->sreg, len) && - nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_jhash_map_init(const struct nft_ctx *ctx, @@ -193,8 +193,6 @@ static int nft_symhash_init(const struct nft_ctx *ctx, if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); - priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; @@ -202,8 +200,9 @@ static int nft_symhash_init(const struct nft_ctx *ctx, if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + sizeof(u32)); } static int nft_symhash_map_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 3f6d1d2a6281..af4e2a4bce93 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -50,9 +50,9 @@ static int nft_immediate_init(const struct nft_ctx *ctx, priv->dlen = desc.len; - priv->dreg = nft_parse_register(tb[NFTA_IMMEDIATE_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, &priv->data, - desc.type, desc.len); + err = nft_parse_register_store(ctx, tb[NFTA_IMMEDIATE_DREG], + &priv->dreg, &priv->data, desc.type, + desc.len); if (err < 0) goto err1; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 72f13a1144dd..a7bdc532479a 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -79,13 +79,13 @@ static int nft_limit_init(struct nft_limit *limit, return -EOVERFLOW; if (pkts) { - tokens = div_u64(limit->nsecs, limit->rate) * limit->burst; + tokens = div64_u64(limit->nsecs, limit->rate) * limit->burst; } else { /* The token bucket size limits the number of tokens can be * accumulated. tokens_max specifies the bucket size. * tokens_max = unit * (rate + burst) / rate. */ - tokens = div_u64(limit->nsecs * (limit->rate + limit->burst), + tokens = div64_u64(limit->nsecs * (limit->rate + limit->burst), limit->rate); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 55754d9939b5..3c380fb32651 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -20,8 +20,8 @@ struct nft_lookup { struct nft_set *set; - enum nft_registers sreg:8; - enum nft_registers dreg:8; + u8 sreg; + u8 dreg; bool invert; struct nft_set_binding binding; }; @@ -76,8 +76,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); - priv->sreg = nft_parse_register(tb[NFTA_LOOKUP_SREG]); - err = nft_validate_register_load(priv->sreg, set->klen); + err = nft_parse_register_load(tb[NFTA_LOOKUP_SREG], &priv->sreg, + set->klen); if (err < 0) return err; @@ -100,9 +100,9 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_MAP)) return -EINVAL; - priv->dreg = nft_parse_register(tb[NFTA_LOOKUP_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - set->dtype, set->dlen); + err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG], + &priv->dreg, NULL, set->dtype, + set->dlen); if (err < 0) return err; } else if (set->flags & NFT_SET_MAP) @@ -132,7 +132,7 @@ static void nft_lookup_activate(const struct nft_ctx *ctx, { struct nft_lookup *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_lookup_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 9d8655bc1bea..4ecfebc2fdc4 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -53,19 +53,15 @@ int nft_masq_init(const struct nft_ctx *ctx, } if (tb[NFTA_MASQ_REG_PROTO_MIN]) { - priv->sreg_proto_min = - nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MIN]); - - err = nft_validate_register_load(priv->sreg_proto_min, plen); + err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MIN], + &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_MASQ_REG_PROTO_MAX]) { - priv->sreg_proto_max = - nft_parse_register(tb[NFTA_MASQ_REG_PROTO_MAX]); - - err = nft_validate_register_load(priv->sreg_proto_max, - plen); + err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MAX], + &priv->sreg_proto_max, + plen); if (err < 0) return err; } else { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 297fe7d97c18..061a29bd3066 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -30,8 +30,8 @@ struct nft_meta { enum nft_meta_keys key:8; union { - enum nft_registers dreg:8; - enum nft_registers sreg:8; + u8 dreg; + u8 sreg; }; }; @@ -358,9 +358,8 @@ static int nft_meta_get_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_META_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static int nft_meta_get_validate(const struct nft_ctx *ctx, @@ -448,8 +447,7 @@ static int nft_meta_set_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->sreg = nft_parse_register(tb[NFTA_META_SREG]); - err = nft_validate_register_load(priv->sreg, len); + err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 3e82a7d0df2a..aa6149cc8c87 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -27,10 +27,10 @@ #include <net/ip.h> struct nft_nat { - enum nft_registers sreg_addr_min:8; - enum nft_registers sreg_addr_max:8; - enum nft_registers sreg_proto_min:8; - enum nft_registers sreg_proto_max:8; + u8 sreg_addr_min; + u8 sreg_addr_max; + u8 sreg_proto_min; + u8 sreg_proto_max; enum nf_nat_manip_type type:8; u8 family; u16 flags; @@ -153,23 +153,22 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, alen = FIELD_SIZEOF(struct nf_nat_range, min_addr.ip6); break; default: - return -EAFNOSUPPORT; + if (tb[NFTA_NAT_REG_ADDR_MIN]) + return -EAFNOSUPPORT; + break; } priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { - priv->sreg_addr_min = - nft_parse_register(tb[NFTA_NAT_REG_ADDR_MIN]); - err = nft_validate_register_load(priv->sreg_addr_min, alen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MIN], + &priv->sreg_addr_min, alen); if (err < 0) return err; if (tb[NFTA_NAT_REG_ADDR_MAX]) { - priv->sreg_addr_max = - nft_parse_register(tb[NFTA_NAT_REG_ADDR_MAX]); - - err = nft_validate_register_load(priv->sreg_addr_max, - alen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MAX], + &priv->sreg_addr_max, + alen); if (err < 0) return err; } else { @@ -179,19 +178,15 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { - priv->sreg_proto_min = - nft_parse_register(tb[NFTA_NAT_REG_PROTO_MIN]); - - err = nft_validate_register_load(priv->sreg_proto_min, plen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], + &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_NAT_REG_PROTO_MAX]) { - priv->sreg_proto_max = - nft_parse_register(tb[NFTA_NAT_REG_PROTO_MAX]); - - err = nft_validate_register_load(priv->sreg_proto_max, - plen); + err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MAX], + &priv->sreg_proto_max, + plen); if (err < 0) return err; } else { diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 3cc1b3dc3c3c..8ff82f17ecba 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -20,7 +20,7 @@ static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state); struct nft_ng_inc { - enum nft_registers dreg:8; + u8 dreg; u32 modulus; atomic_t counter; u32 offset; @@ -70,11 +70,10 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; - priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); atomic_set(&priv->counter, priv->modulus - 1); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_NG_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, @@ -104,7 +103,7 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) } struct nft_ng_random { - enum nft_registers dreg:8; + u8 dreg; u32 modulus; u32 offset; }; @@ -144,10 +143,8 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, prandom_init_once(&nft_numgen_prandom_state); - priv->dreg = nft_parse_register(tb[NFTA_NG_DREG]); - - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, sizeof(u32)); + return nft_parse_register_store(ctx, tb[NFTA_NG_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index bf92a40dd1b2..2401e9fa17c4 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -43,8 +43,10 @@ static int nft_objref_init(const struct nft_ctx *ctx, if (IS_ERR(obj)) return -ENOENT; + if (!nft_use_inc(&obj->use)) + return -EMFILE; + nft_objref_priv(expr) = obj; - obj->use++; return 0; } @@ -73,7 +75,7 @@ static void nft_objref_deactivate(const struct nft_ctx *ctx, if (phase == NFT_TRANS_COMMIT) return; - obj->use--; + nft_use_dec(&obj->use); } static void nft_objref_activate(const struct nft_ctx *ctx, @@ -81,7 +83,7 @@ static void nft_objref_activate(const struct nft_ctx *ctx, { struct nft_object *obj = nft_objref_priv(expr); - obj->use++; + nft_use_inc_restore(&obj->use); } static struct nft_expr_type nft_objref_type; @@ -97,7 +99,7 @@ static const struct nft_expr_ops nft_objref_ops = { struct nft_objref_map { struct nft_set *set; - enum nft_registers sreg:8; + u8 sreg; struct nft_set_binding binding; }; @@ -139,8 +141,8 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; - priv->sreg = nft_parse_register(tb[NFTA_OBJREF_SET_SREG]); - err = nft_validate_register_load(priv->sreg, set->klen); + err = nft_parse_register_load(tb[NFTA_OBJREF_SET_SREG], &priv->sreg, + set->klen); if (err < 0) return err; @@ -182,7 +184,7 @@ static void nft_objref_map_activate(const struct nft_ctx *ctx, { struct nft_objref_map *priv = nft_expr_priv(expr); - priv->set->use++; + nf_tables_activate_set(ctx, priv->set); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index a003533ff4d9..af2ce7a8c587 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -5,7 +5,7 @@ #include <linux/netfilter/nfnetlink_osf.h> struct nft_osf { - enum nft_registers dreg:8; + u8 dreg; }; static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = { @@ -22,6 +22,11 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, struct tcphdr _tcph; const char *os_name; + if (pkt->tprot != IPPROTO_TCP) { + regs->verdict.code = NFT_BREAK; + return; + } + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); if (!tcp) { @@ -50,9 +55,9 @@ static int nft_osf_init(const struct nft_ctx *ctx, if (!tb[NFTA_OSF_DREG]) return -EINVAL; - priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN); + err = nft_parse_register_store(ctx, tb[NFTA_OSF_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, + NFT_OSF_MAXGENRELEN); if (err < 0) return err; @@ -76,9 +81,21 @@ static int nft_osf_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { - return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_FORWARD)); + unsigned int hooks; + + switch (ctx->family) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + hooks = (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_FORWARD); + break; + default: + return -EOPNOTSUPP; + } + + return nft_chain_validate_hooks(ctx->chain, hooks); } static struct nft_expr_type nft_osf_type; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index b1a9f330a51f..0ef51c81ec94 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -84,7 +84,7 @@ static void nft_payload_eval(const struct nft_expr *expr, switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: - if (!skb_mac_header_was_set(skb)) + if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0) goto err; if (skb_vlan_tag_present(skb)) { @@ -135,10 +135,10 @@ static int nft_payload_init(const struct nft_ctx *ctx, priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); - priv->dreg = nft_parse_register(tb[NFTA_PAYLOAD_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); + return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); } static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -194,6 +194,9 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, struct sk_buff *skb, unsigned int *l4csum_offset) { + if (pkt->xt.fragoff) + return -1; + switch (pkt->tprot) { case IPPROTO_TCP: *l4csum_offset = offsetof(struct tcphdr, check); @@ -329,18 +332,23 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_payload_set *priv = nft_expr_priv(expr); + u32 csum_offset, csum_type = NFT_PAYLOAD_CSUM_NONE; + int err; priv->base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); - priv->sreg = nft_parse_register(tb[NFTA_PAYLOAD_SREG]); if (tb[NFTA_PAYLOAD_CSUM_TYPE]) - priv->csum_type = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); - if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) - priv->csum_offset = - ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_OFFSET])); + csum_type = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_CSUM_TYPE])); + if (tb[NFTA_PAYLOAD_CSUM_OFFSET]) { + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_CSUM_OFFSET], U8_MAX, + &csum_offset); + if (err < 0) + return err; + + priv->csum_offset = csum_offset; + } if (tb[NFTA_PAYLOAD_CSUM_FLAGS]) { u32 flags; @@ -351,15 +359,17 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->csum_flags = flags; } - switch (priv->csum_type) { + switch (csum_type) { case NFT_PAYLOAD_CSUM_NONE: case NFT_PAYLOAD_CSUM_INET: break; default: return -EOPNOTSUPP; } + priv->csum_type = csum_type; - return nft_validate_register_load(priv->sreg, priv->len); + return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg, + priv->len); } static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *expr) @@ -395,6 +405,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, { enum nft_payload_bases base; unsigned int offset, len; + int err; if (tb[NFTA_PAYLOAD_BASE] == NULL || tb[NFTA_PAYLOAD_OFFSET] == NULL || @@ -420,8 +431,13 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_PAYLOAD_DREG] == NULL) return ERR_PTR(-EINVAL); - offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); - len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_OFFSET], U8_MAX, &offset); + if (err < 0) + return ERR_PTR(err); + + err = nft_parse_u32_check(tb[NFTA_PAYLOAD_LEN], U8_MAX, &len); + if (err < 0) + return ERR_PTR(err); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER) diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 98613658d4ac..de5f1bda9d6f 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -22,10 +22,10 @@ static u32 jhash_initval __read_mostly; struct nft_queue { - enum nft_registers sreg_qnum:8; - u16 queuenum; - u16 queues_total; - u16 flags; + u8 sreg_qnum; + u16 queuenum; + u16 queues_total; + u16 flags; }; static void nft_queue_eval(const struct nft_expr *expr, @@ -114,8 +114,8 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx, struct nft_queue *priv = nft_expr_priv(expr); int err; - priv->sreg_qnum = nft_parse_register(tb[NFTA_QUEUE_SREG_QNUM]); - err = nft_validate_register_load(priv->sreg_qnum, sizeof(u32)); + err = nft_parse_register_load(tb[NFTA_QUEUE_SREG_QNUM], + &priv->sreg_qnum, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 2e1d2ec2f52a..a5f74e5b8184 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -18,7 +18,7 @@ struct nft_range_expr { struct nft_data data_from; struct nft_data data_to; - enum nft_registers sreg:8; + u8 sreg; u8 len; enum nft_range_ops op:8; }; @@ -90,8 +90,8 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr goto err2; } - priv->sreg = nft_parse_register(tb[NFTA_RANGE_SREG]); - err = nft_validate_register_load(priv->sreg, desc_from.len); + err = nft_parse_register_load(tb[NFTA_RANGE_SREG], &priv->sreg, + desc_from.len); if (err < 0) goto err2; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index c64cbe78dee7..08a05bd1e817 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -49,19 +49,15 @@ int nft_redir_init(const struct nft_ctx *ctx, plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { - priv->sreg_proto_min = - nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MIN]); - - err = nft_validate_register_load(priv->sreg_proto_min, plen); + err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], + &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_REDIR_REG_PROTO_MAX]) { - priv->sreg_proto_max = - nft_parse_register(tb[NFTA_REDIR_REG_PROTO_MAX]); - - err = nft_validate_register_load(priv->sreg_proto_max, - plen); + err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MAX], + &priv->sreg_proto_max, + plen); if (err < 0) return err; } else { diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 76dba9f6b6f6..edce109ef4b0 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -18,7 +18,7 @@ struct nft_rt { enum nft_rt_keys key:8; - enum nft_registers dreg:8; + u8 dreg; }; static u16 get_tcpmss(const struct nft_pktinfo *pkt, const struct dst_entry *skbdst) @@ -134,9 +134,8 @@ static int nft_rt_get_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_RT_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_RT_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static int nft_rt_get_dump(struct sk_buff *skb, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 05118e03c3e4..0b8510a4185d 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -145,6 +145,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, /* Another cpu may race to insert the element with the same key */ if (prev) { nft_set_elem_destroy(set, he, true); + atomic_dec(&set->nelems); he = prev; } @@ -154,6 +155,7 @@ out: err2: nft_set_elem_destroy(set, he, true); + atomic_dec(&set->nelems); err1: return false; } @@ -392,9 +394,17 @@ static void nft_rhash_destroy(const struct nft_set *set) (void *)set); } +/* Number of buckets is stored in u32, so cap our result to 1U<<31 */ +#define NFT_MAX_BUCKETS (1U << 31) + static u32 nft_hash_buckets(u32 size) { - return roundup_pow_of_two(size * 4 / 3); + u64 val = div_u64((u64)size * 4, 3); + + if (val >= NFT_MAX_BUCKETS) + return NFT_MAX_BUCKETS; + + return roundup_pow_of_two(val); } static bool nft_rhash_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 84d317418d18..9c7ec2ec1fcf 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -326,6 +326,8 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; + } else if (nft_set_elem_expired(&rbe->ext)) { + break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; @@ -375,23 +377,37 @@ static void nft_rbtree_gc(struct work_struct *work) struct nft_rbtree *priv; struct rb_node *node; struct nft_set *set; + struct net *net; + u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + genmask = nft_genmask_cur(net); write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* elements are reversed in the rbtree for historical reasons, + * from highest to lowest value, that is why end element is + * always visited before the start element. + */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) + + if (nft_set_elem_mark_busy(&rbe->ext)) { + rbe_end = NULL; continue; + } if (rbe_prev) { rb_erase(&rbe_prev->node, &priv->root); diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 637ce3e8c575..7e4f7063f481 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -10,10 +10,36 @@ struct nft_socket { enum nft_socket_keys key:8; union { - enum nft_registers dreg:8; + u8 dreg; }; }; +static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) +{ + const struct net_device *indev = nft_in(pkt); + const struct sk_buff *skb = pkt->skb; + struct sock *sk = NULL; + + if (!indev) + return NULL; + + switch (nft_pf(pkt)) { + case NFPROTO_IPV4: + sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev); + break; +#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) + case NFPROTO_IPV6: + sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev); + break; +#endif + default: + WARN_ON_ONCE(1); + break; + } + + return sk; +} + static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -27,20 +53,7 @@ static void nft_socket_eval(const struct nft_expr *expr, sk = NULL; if (!sk) - switch(nft_pf(pkt)) { - case NFPROTO_IPV4: - sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt)); - break; -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - case NFPROTO_IPV6: - sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt)); - break; -#endif - default: - WARN_ON_ONCE(1); - regs->verdict.code = NFT_BREAK; - return; - } + sk = nft_socket_do_lookup(pkt); if (!sk) { regs->verdict.code = NFT_BREAK; @@ -106,9 +119,8 @@ static int nft_socket_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_SOCKET_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_SOCKET_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static int nft_socket_dump(struct sk_buff *skb, @@ -123,6 +135,16 @@ static int nft_socket_dump(struct sk_buff *skb, return 0; } +static int nft_socket_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_LOCAL_OUT)); +} + static struct nft_expr_type nft_socket_type; static const struct nft_expr_ops nft_socket_ops = { .type = &nft_socket_type, @@ -130,6 +152,7 @@ static const struct nft_expr_ops nft_socket_ops = { .eval = nft_socket_eval, .init = nft_socket_init, .dump = nft_socket_dump, + .validate = nft_socket_validate, }; static struct nft_expr_type nft_socket_type __read_mostly = { diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 95980154ef02..db780b5985ab 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -13,9 +13,9 @@ #endif struct nft_tproxy { - enum nft_registers sreg_addr:8; - enum nft_registers sreg_port:8; - u8 family; + u8 sreg_addr; + u8 sreg_port; + u8 family; }; static void nft_tproxy_eval_v4(const struct nft_expr *expr, @@ -30,6 +30,12 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, __be16 tport = 0; struct sock *sk; + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { + regs->verdict.code = NFT_BREAK; + return; + } + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (!hp) { regs->verdict.code = NFT_BREAK; @@ -91,7 +97,8 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, memset(&taddr, 0, sizeof(taddr)); - if (!pkt->tprot_set) { + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { regs->verdict.code = NFT_BREAK; return; } @@ -247,15 +254,15 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, } if (tb[NFTA_TPROXY_REG_ADDR]) { - priv->sreg_addr = nft_parse_register(tb[NFTA_TPROXY_REG_ADDR]); - err = nft_validate_register_load(priv->sreg_addr, alen); + err = nft_parse_register_load(tb[NFTA_TPROXY_REG_ADDR], + &priv->sreg_addr, alen); if (err < 0) return err; } if (tb[NFTA_TPROXY_REG_PORT]) { - priv->sreg_port = nft_parse_register(tb[NFTA_TPROXY_REG_PORT]); - err = nft_validate_register_load(priv->sreg_port, sizeof(u16)); + err = nft_parse_register_load(tb[NFTA_TPROXY_REG_PORT], + &priv->sreg_port, sizeof(u16)); if (err < 0) return err; } @@ -282,6 +289,13 @@ static int nft_tproxy_dump(struct sk_buff *skb, return 0; } +static int nft_tproxy_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); +} + static struct nft_expr_type nft_tproxy_type; static const struct nft_expr_ops nft_tproxy_ops = { .type = &nft_tproxy_type, @@ -289,6 +303,7 @@ static const struct nft_expr_ops nft_tproxy_ops = { .eval = nft_tproxy_eval, .init = nft_tproxy_init, .dump = nft_tproxy_dump, + .validate = nft_tproxy_validate, }; static struct nft_expr_type nft_tproxy_type __read_mostly = { diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 8ae948fd9dcf..ab69a34210a8 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -14,7 +14,7 @@ struct nft_tunnel { enum nft_tunnel_keys key:8; - enum nft_registers dreg:8; + u8 dreg; }; static void nft_tunnel_get_eval(const struct nft_expr *expr, @@ -72,10 +72,8 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - priv->dreg = nft_parse_register(tb[NFTA_TUNNEL_DREG]); - - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); + return nft_parse_register_store(ctx, tb[NFTA_TUNNEL_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); } static int nft_tunnel_get_dump(struct sk_buff *skb, @@ -104,6 +102,7 @@ static const struct nft_expr_ops nft_tunnel_get_ops = { static struct nft_expr_type nft_tunnel_type __read_mostly = { .name = "tunnel", + .family = NFPROTO_NETDEV, .ops = &nft_tunnel_get_ops, .policy = nft_tunnel_policy, .maxattr = NFTA_TUNNEL_MAX, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 3bab89dbc371..5dd6f6ce92e6 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -335,6 +335,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) const struct xt_match *m; int have_rev = 0; + mutex_lock(&xt[af].mutex); list_for_each_entry(m, &xt[af].match, list) { if (strcmp(m->name, name) == 0) { if (m->revision > *bestp) @@ -343,6 +344,7 @@ static int match_revfn(u8 af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return match_revfn(NFPROTO_UNSPEC, name, revision, bestp); @@ -355,6 +357,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) const struct xt_target *t; int have_rev = 0; + mutex_lock(&xt[af].mutex); list_for_each_entry(t, &xt[af].target, list) { if (strcmp(t->name, name) == 0) { if (t->revision > *bestp) @@ -363,6 +366,7 @@ static int target_revfn(u8 af, const char *name, u8 revision, int *bestp) have_rev = 1; } } + mutex_unlock(&xt[af].mutex); if (af != NFPROTO_UNSPEC && !have_rev) return target_revfn(NFPROTO_UNSPEC, name, revision, bestp); @@ -376,12 +380,10 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, { int have_rev, best = -1; - mutex_lock(&xt[af].mutex); if (target == 1) have_rev = target_revfn(af, name, revision, &best); else have_rev = match_revfn(af, name, revision, &best); - mutex_unlock(&xt[af].mutex); /* Nothing at all? Return 0 to try loading module. */ if (best == -1) { @@ -736,7 +738,7 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; - int pad, off = xt_compat_match_offset(match); + int off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; char name[sizeof(m->u.user.name)]; @@ -746,9 +748,6 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, match->compat_from_user(m->data, cm->data); else memcpy(m->data, cm->data, msize - sizeof(*cm)); - pad = XT_ALIGN(match->matchsize) - match->matchsize; - if (pad > 0) - memset(m->data + match->matchsize, 0, pad); msize += off; m->u.user.match_size = msize; @@ -1119,7 +1118,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; - int pad, off = xt_compat_target_offset(target); + int off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; char name[sizeof(t->u.user.name)]; @@ -1129,9 +1128,6 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, target->compat_from_user(t->data, ct->data); else memcpy(t->data, ct->data, tsize - sizeof(*ct)); - pad = XT_ALIGN(target->targetsize) - target->targetsize; - if (pad > 0) - memset(t->data + target->targetsize, 0, pad); tsize += off; t->u.user.target_size = tsize; @@ -1392,7 +1388,7 @@ xt_replace_table(struct xt_table *table, table->private = newinfo; /* make sure all cpus see new ->private value */ - smp_wmb(); + smp_mb(); /* * Even though table entries have now been swapped, other CPU's diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 9e05c86ba5c4..932c0ae99bdc 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -118,6 +118,9 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) } cfg; int ret; + if (strnlen(info->name, sizeof(est->name)) >= sizeof(est->name)) + return -ENAMETOOLONG; + net_get_random_once(&jhash_rnd, sizeof(jhash_rnd)); mutex_lock(&xn->hash_lock); diff --git a/net/netfilter/xt_SECMARK.c b/net/netfilter/xt_SECMARK.c index 4ad5fe27e08b..097534dbc622 100644 --- a/net/netfilter/xt_SECMARK.c +++ b/net/netfilter/xt_SECMARK.c @@ -30,10 +30,9 @@ MODULE_ALIAS("ip6t_SECMARK"); static u8 mode; static unsigned int -secmark_tg(struct sk_buff *skb, const struct xt_action_param *par) +secmark_tg(struct sk_buff *skb, const struct xt_secmark_target_info_v1 *info) { u32 secmark = 0; - const struct xt_secmark_target_info *info = par->targinfo; BUG_ON(info->mode != mode); @@ -49,7 +48,7 @@ secmark_tg(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static int checkentry_lsm(struct xt_secmark_target_info *info) +static int checkentry_lsm(struct xt_secmark_target_info_v1 *info) { int err; @@ -81,15 +80,15 @@ static int checkentry_lsm(struct xt_secmark_target_info *info) return 0; } -static int secmark_tg_check(const struct xt_tgchk_param *par) +static int +secmark_tg_check(const char *table, struct xt_secmark_target_info_v1 *info) { - struct xt_secmark_target_info *info = par->targinfo; int err; - if (strcmp(par->table, "mangle") != 0 && - strcmp(par->table, "security") != 0) { + if (strcmp(table, "mangle") != 0 && + strcmp(table, "security") != 0) { pr_info_ratelimited("only valid in \'mangle\' or \'security\' table, not \'%s\'\n", - par->table); + table); return -EINVAL; } @@ -124,25 +123,76 @@ static void secmark_tg_destroy(const struct xt_tgdtor_param *par) } } -static struct xt_target secmark_tg_reg __read_mostly = { - .name = "SECMARK", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = secmark_tg_check, - .destroy = secmark_tg_destroy, - .target = secmark_tg, - .targetsize = sizeof(struct xt_secmark_target_info), - .me = THIS_MODULE, +static int secmark_tg_check_v0(const struct xt_tgchk_param *par) +{ + struct xt_secmark_target_info *info = par->targinfo; + struct xt_secmark_target_info_v1 newinfo = { + .mode = info->mode, + }; + int ret; + + memcpy(newinfo.secctx, info->secctx, SECMARK_SECCTX_MAX); + + ret = secmark_tg_check(par->table, &newinfo); + info->secid = newinfo.secid; + + return ret; +} + +static unsigned int +secmark_tg_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_secmark_target_info *info = par->targinfo; + struct xt_secmark_target_info_v1 newinfo = { + .secid = info->secid, + }; + + return secmark_tg(skb, &newinfo); +} + +static int secmark_tg_check_v1(const struct xt_tgchk_param *par) +{ + return secmark_tg_check(par->table, par->targinfo); +} + +static unsigned int +secmark_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + return secmark_tg(skb, par->targinfo); +} + +static struct xt_target secmark_tg_reg[] __read_mostly = { + { + .name = "SECMARK", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = secmark_tg_check_v0, + .destroy = secmark_tg_destroy, + .target = secmark_tg_v0, + .targetsize = sizeof(struct xt_secmark_target_info), + .me = THIS_MODULE, + }, + { + .name = "SECMARK", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = secmark_tg_check_v1, + .destroy = secmark_tg_destroy, + .target = secmark_tg_v1, + .targetsize = sizeof(struct xt_secmark_target_info_v1), + .usersize = offsetof(struct xt_secmark_target_info_v1, secid), + .me = THIS_MODULE, + }, }; static int __init secmark_tg_init(void) { - return xt_register_target(&secmark_tg_reg); + return xt_register_targets(secmark_tg_reg, ARRAY_SIZE(secmark_tg_reg)); } static void __exit secmark_tg_exit(void) { - xt_unregister_target(&secmark_tg_reg); + xt_unregister_targets(secmark_tg_reg, ARRAY_SIZE(secmark_tg_reg)); } module_init(secmark_tg_init); diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index bf7bba80e24c..226a317d52a0 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -90,4 +90,3 @@ MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>"); MODULE_DESCRIPTION("Passive OS fingerprint matching."); MODULE_ALIAS("ipt_osf"); MODULE_ALIAS("ip6t_osf"); -MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF); diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index 46686fb73784..0c101b25cacf 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -76,29 +76,54 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) */ return false; - filp = sk->sk_socket->file; - if (filp == NULL) + read_lock_bh(&sk->sk_callback_lock); + filp = sk->sk_socket ? sk->sk_socket->file : NULL; + if (filp == NULL) { + read_unlock_bh(&sk->sk_callback_lock); return ((info->match ^ info->invert) & (XT_OWNER_UID | XT_OWNER_GID)) == 0; + } if (info->match & XT_OWNER_UID) { kuid_t uid_min = make_kuid(net->user_ns, info->uid_min); kuid_t uid_max = make_kuid(net->user_ns, info->uid_max); if ((uid_gte(filp->f_cred->fsuid, uid_min) && uid_lte(filp->f_cred->fsuid, uid_max)) ^ - !(info->invert & XT_OWNER_UID)) + !(info->invert & XT_OWNER_UID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } if (info->match & XT_OWNER_GID) { + unsigned int i, match = false; kgid_t gid_min = make_kgid(net->user_ns, info->gid_min); kgid_t gid_max = make_kgid(net->user_ns, info->gid_max); - if ((gid_gte(filp->f_cred->fsgid, gid_min) && - gid_lte(filp->f_cred->fsgid, gid_max)) ^ - !(info->invert & XT_OWNER_GID)) + struct group_info *gi = filp->f_cred->group_info; + + if (gid_gte(filp->f_cred->fsgid, gid_min) && + gid_lte(filp->f_cred->fsgid, gid_max)) + match = true; + + if (!match && (info->match & XT_OWNER_SUPPL_GROUPS) && gi) { + for (i = 0; i < gi->ngroups; ++i) { + kgid_t group = gi->gid[i]; + + if (gid_gte(group, gid_min) && + gid_lte(group, gid_max)) { + match = true; + break; + } + } + } + + if (match ^ !(info->invert & XT_OWNER_GID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } + read_unlock_bh(&sk->sk_callback_lock); return true; } diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 570144507df1..2dbf92346a7e 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -155,7 +155,8 @@ static void recent_entry_remove(struct recent_table *t, struct recent_entry *e) /* * Drop entries with timestamps older then 'time'. */ -static void recent_entry_reap(struct recent_table *t, unsigned long time) +static void recent_entry_reap(struct recent_table *t, unsigned long time, + struct recent_entry *working, bool update) { struct recent_entry *e; @@ -165,6 +166,12 @@ static void recent_entry_reap(struct recent_table *t, unsigned long time) e = list_entry(t->lru_list.next, struct recent_entry, lru_list); /* + * Do not reap the entry which are going to be updated. + */ + if (e == working && update) + return; + + /* * The last time stamp is the most recent. */ if (time_after(time, e->stamps[e->index-1])) @@ -306,7 +313,8 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par) /* info->seconds must be non-zero */ if (info->check_set & XT_RECENT_REAP) - recent_entry_reap(t, time); + recent_entry_reap(t, time, e, + info->check_set & XT_RECENT_UPDATE && ret); } if (info->check_set & XT_RECENT_SET || @@ -558,7 +566,7 @@ recent_mt_proc_write(struct file *file, const char __user *input, { struct recent_table *t = PDE_DATA(file_inode(file)); struct recent_entry *e; - char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")]; + char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:255.255.255.255")]; const char *c = buf; union nf_inet_addr addr = {}; u_int16_t family; diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 2d2fa1d53ea6..05495d3f47b8 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -149,6 +149,8 @@ static int sctp_mt_check(const struct xt_mtchk_param *par) { const struct xt_sctp_info *info = par->matchinfo; + if (info->flag_count > ARRAY_SIZE(info->flag_info)) + return -EINVAL; if (info->flags & ~XT_SCTP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~XT_SCTP_VALID_FLAGS) diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c index a95b50342dbb..58ba402bc0b0 100644 --- a/net/netfilter/xt_u32.c +++ b/net/netfilter/xt_u32.c @@ -95,11 +95,32 @@ static bool u32_mt(const struct sk_buff *skb, struct xt_action_param *par) return ret ^ data->invert; } +static int u32_mt_checkentry(const struct xt_mtchk_param *par) +{ + const struct xt_u32 *data = par->matchinfo; + const struct xt_u32_test *ct; + unsigned int i; + + if (data->ntests > ARRAY_SIZE(data->tests)) + return -EINVAL; + + for (i = 0; i < data->ntests; ++i) { + ct = &data->tests[i]; + + if (ct->nnums > ARRAY_SIZE(ct->location) || + ct->nvalues > ARRAY_SIZE(ct->value)) + return -EINVAL; + } + + return 0; +} + static struct xt_match xt_u32_mt_reg __read_mostly = { .name = "u32", .revision = 0, .family = NFPROTO_UNSPEC, .match = u32_mt, + .checkentry = u32_mt_checkentry, .matchsize = sizeof(struct xt_u32), .me = THIS_MODULE, }; diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index 4d748975117d..a0b7269cf190 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -68,6 +68,28 @@ static const struct nla_policy calipso_genl_policy[NLBL_CALIPSO_A_MAX + 1] = { [NLBL_CALIPSO_A_MTYPE] = { .type = NLA_U32 }, }; +static const struct netlbl_calipso_ops *calipso_ops; + +/** + * netlbl_calipso_ops_register - Register the CALIPSO operations + * @ops: ops to register + * + * Description: + * Register the CALIPSO packet engine operations. + * + */ +const struct netlbl_calipso_ops * +netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) +{ + return xchg(&calipso_ops, ops); +} +EXPORT_SYMBOL(netlbl_calipso_ops_register); + +static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) +{ + return READ_ONCE(calipso_ops); +} + /* NetLabel Command Handlers */ /** @@ -110,16 +132,19 @@ static int netlbl_calipso_add_pass(struct genl_info *info, * */ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) - { int ret_val = -EINVAL; struct netlbl_audit audit_info; + const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (!info->attrs[NLBL_CALIPSO_A_DOI] || !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + if (!ops) + return -EOPNOTSUPP; + + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: ret_val = netlbl_calipso_add_pass(info, &audit_info); @@ -301,7 +326,7 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_CALIPSO_A_DOI]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, @@ -375,27 +400,6 @@ int __init netlbl_calipso_genl_init(void) return genl_register_family(&netlbl_calipso_gnl_family); } -static const struct netlbl_calipso_ops *calipso_ops; - -/** - * netlbl_calipso_ops_register - Register the CALIPSO operations - * - * Description: - * Register the CALIPSO packet engine operations. - * - */ -const struct netlbl_calipso_ops * -netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) -{ - return xchg(&calipso_ops, ops); -} -EXPORT_SYMBOL(netlbl_calipso_ops_register); - -static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) -{ - return READ_ONCE(calipso_ops); -} - /** * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine * @doi_def: the DOI structure diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 9aacf2da3d98..a0a145db3fc7 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -156,8 +156,8 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, return -ENOMEM; doi_def->map.std = kzalloc(sizeof(*doi_def->map.std), GFP_KERNEL); if (doi_def->map.std == NULL) { - ret_val = -ENOMEM; - goto add_std_failure; + kfree(doi_def); + return -ENOMEM; } doi_def->type = CIPSO_V4_MAP_TRANS; @@ -198,14 +198,14 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, } doi_def->map.std->lvl.local = kcalloc(doi_def->map.std->lvl.local_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->lvl.local == NULL) { ret_val = -ENOMEM; goto add_std_failure; } doi_def->map.std->lvl.cipso = kcalloc(doi_def->map.std->lvl.cipso_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->lvl.cipso == NULL) { ret_val = -ENOMEM; goto add_std_failure; @@ -273,7 +273,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, doi_def->map.std->cat.local = kcalloc( doi_def->map.std->cat.local_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->cat.local == NULL) { ret_val = -ENOMEM; goto add_std_failure; @@ -281,7 +281,7 @@ static int netlbl_cipsov4_add_std(struct genl_info *info, doi_def->map.std->cat.cipso = kcalloc( doi_def->map.std->cat.cipso_size, sizeof(u32), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (doi_def->map.std->cat.cipso == NULL) { ret_val = -ENOMEM; goto add_std_failure; @@ -420,7 +420,7 @@ static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info) !info->attrs[NLBL_CIPSOV4_A_MTYPE]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CIPSOV4_A_MTYPE])) { case CIPSO_V4_MAP_TRANS: ret_val = netlbl_cipsov4_add_std(info, &audit_info); @@ -581,6 +581,7 @@ list_start: break; } + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); genlmsg_end(ans_skb, data); @@ -589,12 +590,14 @@ list_start: list_retry: /* XXX - this limit is a guesstimate */ if (nlsze_mult < 4) { + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); kfree_skb(ans_skb); nlsze_mult *= 2; goto list_start; } list_failure_lock: + cipso_v4_doi_putdef(doi_def); rcu_read_unlock(); list_failure: kfree_skb(ans_skb); @@ -712,7 +715,7 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_CIPSOV4_A_DOI]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 15fe2120b310..14c3d640f94b 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -871,7 +871,8 @@ int netlbl_catmap_setlong(struct netlbl_lsm_catmap **catmap, offset -= iter->startbit; idx = offset / NETLBL_CATMAP_MAPSIZE; - iter->bitmap[idx] |= bitmap << (offset % NETLBL_CATMAP_MAPSIZE); + iter->bitmap[idx] |= (NETLBL_CATMAP_MAPTYPE)bitmap + << (offset % NETLBL_CATMAP_MAPSIZE); return 0; } diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 21e0095b1d14..43c51242dcd2 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -90,6 +90,7 @@ static const struct nla_policy netlbl_mgmt_genl_policy[NLBL_MGMT_A_MAX + 1] = { static int netlbl_mgmt_add_common(struct genl_info *info, struct netlbl_audit *audit_info) { + void *pmap = NULL; int ret_val = -EINVAL; struct netlbl_domaddr_map *addrmap = NULL; struct cipso_v4_doi *cipsov4 = NULL; @@ -189,6 +190,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_free_addrmap; } + pmap = map; map->list.addr = addr->s_addr & mask->s_addr; map->list.mask = mask->s_addr; map->list.valid = 1; @@ -197,10 +199,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->def.cipso = cipsov4; ret_val = netlbl_af4list_add(&map->list, &addrmap->list4); - if (ret_val != 0) { - kfree(map); - goto add_free_addrmap; - } + if (ret_val != 0) + goto add_free_map; entry->family = AF_INET; entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -237,6 +237,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_free_addrmap; } + pmap = map; map->list.addr = *addr; map->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; map->list.addr.s6_addr32[1] &= mask->s6_addr32[1]; @@ -249,10 +250,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->def.calipso = calipso; ret_val = netlbl_af6list_add(&map->list, &addrmap->list6); - if (ret_val != 0) { - kfree(map); - goto add_free_addrmap; - } + if (ret_val != 0) + goto add_free_map; entry->family = AF_INET6; entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -262,10 +261,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = netlbl_domhsh_add(entry, audit_info); if (ret_val != 0) - goto add_free_addrmap; + goto add_free_map; return 0; +add_free_map: + kfree(pmap); add_free_addrmap: kfree(addrmap); add_doi_put_def: @@ -446,7 +447,7 @@ static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info) (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_mgmt_add_common(info, &audit_info); } @@ -469,7 +470,7 @@ static int netlbl_mgmt_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_MGMT_A_DOMAIN]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); domain = nla_data(info->attrs[NLBL_MGMT_A_DOMAIN]); return netlbl_domhsh_remove(domain, AF_UNSPEC, &audit_info); @@ -569,7 +570,7 @@ static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info) (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_mgmt_add_common(info, &audit_info); } @@ -588,7 +589,7 @@ static int netlbl_mgmt_removedef(struct sk_buff *skb, struct genl_info *info) { struct netlbl_audit audit_info; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_domhsh_remove_default(AF_UNSPEC, &audit_info); } diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index c92894c3e40a..ff52ff2278ed 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -827,7 +827,7 @@ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) { value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]); if (value == 1 || value == 0) { - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); netlbl_unlabel_acceptflg_set(value, &audit_info); return 0; } @@ -910,7 +910,7 @@ static int netlbl_unlabel_staticadd(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -960,7 +960,7 @@ static int netlbl_unlabel_staticadddef(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -1007,7 +1007,7 @@ static int netlbl_unlabel_staticremove(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -1047,7 +1047,7 @@ static int netlbl_unlabel_staticremovedef(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -1179,12 +1179,13 @@ 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 iter_bkt; - u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; + u32 skip_addr4 = cb->args[2]; + u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; struct list_head *iter_list; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) + u32 skip_addr6 = cb->args[3]; struct netlbl_af6list *addr6; #endif @@ -1195,7 +1196,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, rcu_read_lock(); for (iter_bkt = skip_bkt; iter_bkt < rcu_dereference(netlbl_unlhsh)->size; - iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) { + iter_bkt++) { iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt]; list_for_each_entry_rcu(iface, iter_list, list) { if (!iface->valid || @@ -1203,7 +1204,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < cb->args[2]) + if (iter_addr4++ < skip_addr4) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1216,10 +1217,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr4 = 0; + skip_addr4 = 0; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < cb->args[3]) + if (iter_addr6++ < skip_addr6) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1232,8 +1235,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr6 = 0; + skip_addr6 = 0; #endif /* IPv6 */ } + iter_chain = 0; + skip_chain = 0; } unlabel_staticlist_return: diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index 4a397cde1a48..2c608677b43b 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -42,11 +42,9 @@ /** * netlbl_netlink_auditinfo - Fetch the audit information from a NETLINK msg - * @skb: the packet * @audit_info: NetLabel audit information */ -static inline void netlbl_netlink_auditinfo(struct sk_buff *skb, - struct netlbl_audit *audit_info) +static inline void netlbl_netlink_auditinfo(struct netlbl_audit *audit_info) { security_task_getsecid(current, &audit_info->secid); audit_info->loginuid = audit_get_loginuid(current); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 1bb9f219f07d..e91489b3274c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -152,6 +152,8 @@ static const struct rhashtable_params netlink_rhashtable_params; static inline u32 netlink_group_mask(u32 group) { + if (group > 32) + return 0; return group ? 1 << (group - 1) : 0; } @@ -461,11 +463,13 @@ void netlink_table_ungrab(void) static inline void netlink_lock_table(void) { + unsigned long flags; + /* read_lock() synchronizes us to netlink_table_grab */ - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); atomic_inc(&nl_table_users); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); } static inline void @@ -574,12 +578,9 @@ static int netlink_insert(struct sock *sk, u32 portid) if (nlk_sk(sk)->bound) goto err; - err = -ENOMEM; - if (BITS_PER_LONG > 32 && - unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX)) - goto err; + /* portid can be read locklessly from netlink_getname(). */ + WRITE_ONCE(nlk_sk(sk)->portid, portid); - nlk_sk(sk)->portid = portid; sock_hold(sk); err = __netlink_insert(table, sk); @@ -597,7 +598,10 @@ static int netlink_insert(struct sock *sk, u32 portid) /* We need to ensure that the socket is hashed and visible. */ smp_wmb(); - nlk_sk(sk)->bound = portid; + /* Paired with lockless reads from netlink_bind(), + * netlink_connect() and netlink_sendmsg(). + */ + WRITE_ONCE(nlk_sk(sk)->bound, portid); err: release_sock(sk); @@ -1016,7 +1020,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, else if (nlk->ngroups < 8*sizeof(groups)) groups &= (1UL << nlk->ngroups) - 1; - bound = nlk->bound; + /* Paired with WRITE_ONCE() in netlink_insert() */ + bound = READ_ONCE(nlk->bound); if (bound) { /* Ensure nlk->portid is up-to-date. */ smp_rmb(); @@ -1025,7 +1030,6 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return -EINVAL; } - netlink_lock_table(); if (nlk->netlink_bind && groups) { int group; @@ -1037,13 +1041,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (!err) continue; netlink_undo_bind(group, groups, sk); - goto unlock; + return err; } } /* No need for barriers here as we return to user-space without * using any of the bound attributes. */ + netlink_lock_table(); if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : @@ -1085,9 +1090,11 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if (addr->sa_family == AF_UNSPEC) { - sk->sk_state = NETLINK_UNCONNECTED; - nlk->dst_portid = 0; - nlk->dst_group = 0; + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, 0); + WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) @@ -1102,14 +1109,17 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, /* No need for barriers here as we return to user-space without * using any of the bound attributes. + * Paired with WRITE_ONCE() in netlink_insert(). */ - if (!nlk->bound) + if (!READ_ONCE(nlk->bound)) err = netlink_autobind(sock); if (err == 0) { - sk->sk_state = NETLINK_CONNECTED; - nlk->dst_portid = nladdr->nl_pid; - nlk->dst_group = ffs(nladdr->nl_groups); + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); + WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; @@ -1126,10 +1136,12 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_pad = 0; if (peer) { - nladdr->nl_pid = nlk->dst_portid; - nladdr->nl_groups = netlink_group_mask(nlk->dst_group); + /* Paired with WRITE_ONCE() in netlink_connect() */ + nladdr->nl_pid = READ_ONCE(nlk->dst_portid); + nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { - nladdr->nl_pid = nlk->portid; + /* Paired with WRITE_ONCE() in netlink_insert() */ + nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); @@ -1156,8 +1168,9 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); - if (sock->sk_state == NETLINK_CONNECTED && - nlk->dst_portid != nlk_sk(ssk)->portid) { + /* dst_portid and sk_state can be changed in netlink_connect() */ + if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && + READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } @@ -1590,6 +1603,7 @@ out: int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; + unsigned long flags; struct sock *sk; int ret = 0; @@ -1599,12 +1613,12 @@ int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) /* sk->sk_err wants a positive error value */ info.code = -code; - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &nl_table[ssk->sk_protocol].mc_list) ret += do_one_set_err(sk, &info); - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); return ret; } EXPORT_SYMBOL(netlink_set_err); @@ -1725,7 +1739,8 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); - int len, val, err; + unsigned int flag; + int len, val; if (level != SOL_NETLINK) return -ENOPROTOOPT; @@ -1737,39 +1752,17 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, switch (optname) { case NETLINK_PKTINFO: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_RECV_PKTINFO ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_RECV_PKTINFO; break; case NETLINK_BROADCAST_ERROR: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_BROADCAST_SEND_ERROR ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_BROADCAST_SEND_ERROR; break; case NETLINK_NO_ENOBUFS: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_RECV_NO_ENOBUFS ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_RECV_NO_ENOBUFS; break; case NETLINK_LIST_MEMBERSHIPS: { - int pos, idx, shift; + int pos, idx, shift, err = 0; - err = 0; netlink_lock_table(); for (pos = 0; pos * 8 < nlk->ngroups; pos += sizeof(u32)) { if (len - pos < sizeof(u32)) @@ -1783,34 +1776,32 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, break; } } - if (put_user(ALIGN(nlk->ngroups / 8, sizeof(u32)), optlen)) + if (put_user(ALIGN(BITS_TO_BYTES(nlk->ngroups), sizeof(u32)), optlen)) err = -EFAULT; netlink_unlock_table(); - break; + return err; } case NETLINK_CAP_ACK: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_CAP_ACK ? 1 : 0; - if (put_user(len, optlen) || - put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_CAP_ACK; break; case NETLINK_EXT_ACK: - if (len < sizeof(int)) - return -EINVAL; - len = sizeof(int); - val = nlk->flags & NETLINK_F_EXT_ACK ? 1 : 0; - if (put_user(len, optlen) || put_user(val, optval)) - return -EFAULT; - err = 0; + flag = NETLINK_F_EXT_ACK; break; default: - err = -ENOPROTOOPT; + return -ENOPROTOOPT; } - return err; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + val = nlk->flags & flag ? 1 : 0; + + if (put_user(len, optlen) || + copy_to_user(optval, &val, len)) + return -EFAULT; + + return 0; } static void netlink_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) @@ -1846,6 +1837,11 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP; + if (len == 0) { + pr_warn_once("Zero length message leads to an empty skb\n"); + return -ENODATA; + } + err = scm_send(sock, msg, &scm, true); if (err < 0) return err; @@ -1864,11 +1860,13 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { - dst_portid = nlk->dst_portid; - dst_group = nlk->dst_group; + /* Paired with WRITE_ONCE() in netlink_connect() */ + dst_portid = READ_ONCE(nlk->dst_portid); + dst_group = READ_ONCE(nlk->dst_group); } - if (!nlk->bound) { + /* Paired with WRITE_ONCE() in netlink_insert() */ + if (!READ_ONCE(nlk->bound)) { err = netlink_autobind(sock); if (err) goto out; @@ -1963,7 +1961,6 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, copied = len; } - skb_reset_transport_header(data_skb); err = skb_copy_datagram_msg(data_skb, 0, msg, copied); if (msg->msg_name) { @@ -1987,7 +1984,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - if (nlk->cb_running && + if (READ_ONCE(nlk->cb_running) && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) { ret = netlink_dump(sk); if (ret) { @@ -2228,6 +2225,13 @@ static int netlink_dump(struct sock *sk) * single netdev. The outcome is MSG_TRUNC error. */ skb_reserve(skb, skb_tailroom(skb) - alloc_size); + + /* Make sure malicious BPF programs can not read unitialized memory + * from skb->head -> skb->data + */ + skb_reset_network_header(skb); + skb_reset_mac_header(skb); + netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) @@ -2262,7 +2266,7 @@ static int netlink_dump(struct sock *sk) if (cb->done) cb->done(cb); - nlk->cb_running = false; + WRITE_ONCE(nlk->cb_running, false); module = cb->module; skb = cb->skb; mutex_unlock(nlk->cb_mutex); @@ -2322,7 +2326,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, goto error_put; } - nlk->cb_running = true; + WRITE_ONCE(nlk->cb_running, true); nlk->dump_done_errno = INT_MAX; mutex_unlock(nlk->cb_mutex); @@ -2496,13 +2500,15 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); + if (err == -ESRCH) + err = 0; } if (report) { int err2; err2 = nlmsg_unicast(sk, skb, portid); - if (!err || err == -ESRCH) + if (!err) err = err2; } @@ -2626,7 +2632,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v) nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), - nlk->cb_running, + READ_ONCE(nlk->cb_running), refcount_read(&s->sk_refcnt), atomic_read(&s->sk_drops), sock_i_ino(s) diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 7dda33b9b784..85ee4891c2c7 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -93,6 +93,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net *net = sock_net(skb->sk); struct netlink_diag_req *req; struct netlink_sock *nlsk; + unsigned long flags; struct sock *sk; int num = 2; int ret = 0; @@ -151,7 +152,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, num++; mc_list: - read_lock(&nl_table_lock); + read_lock_irqsave(&nl_table_lock, flags); sk_for_each_bound(sk, &tbl->mc_list) { if (sk_hashed(sk)) continue; @@ -166,13 +167,13 @@ mc_list: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - sock_i_ino(sk)) < 0) { + __sock_i_ino(sk)) < 0) { ret = 1; break; } num++; } - read_unlock(&nl_table_lock); + read_unlock_irqrestore(&nl_table_lock, flags); done: cb->args[0] = num; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index ede73ecfb1f5..f449be93b375 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -961,11 +961,46 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; +static int genl_bind(struct net *net, int group) +{ + const struct genl_family *family; + unsigned int id; + int ret = 0; + + genl_lock_all(); + + idr_for_each_entry(&genl_fam_idr, family, id) { + const struct genl_multicast_group *grp; + int i; + + if (family->n_mcgrps == 0) + continue; + + i = group - family->mcgrp_offset; + if (i < 0 || i >= family->n_mcgrps) + continue; + + grp = &family->mcgrps[i]; + if ((grp->flags & GENL_UNS_ADMIN_PERM) && + !ns_capable(net->user_ns, CAP_NET_ADMIN)) + ret = -EPERM; + if (grp->cap_sys_admin && + !ns_capable(net->user_ns, CAP_SYS_ADMIN)) + ret = -EPERM; + + break; + } + + genl_unlock_all(); + return ret; +} + static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, + .bind = genl_bind, }; /* we'll bump the group number right afterwards */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 43910e50752c..146550ce0ac6 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -403,6 +403,11 @@ static int nr_listen(struct socket *sock, int backlog) struct sock *sk = sock->sk; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; @@ -658,6 +663,11 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, goto out_release; } + if (sock->state == SS_CONNECTING) { + err = -EALREADY; + goto out_release; + } + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index 029c8bb90f4c..a7d3a265befb 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -126,7 +126,7 @@ void nr_write_internal(struct sock *sk, int frametype) unsigned char *dptr; int len, timeout; - len = NR_NETWORK_LEN + NR_TRANSPORT_LEN; + len = NR_TRANSPORT_LEN; switch (frametype & 0x0F) { case NR_CONNREQ: @@ -144,7 +144,8 @@ void nr_write_internal(struct sock *sk, int frametype) return; } - if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) + skb = alloc_skb(NR_NETWORK_LEN + len, GFP_ATOMIC); + if (!skb) return; /* @@ -152,7 +153,7 @@ void nr_write_internal(struct sock *sk, int frametype) */ skb_reserve(skb, NR_NETWORK_LEN); - dptr = skb_put(skb, skb_tailroom(skb)); + dptr = skb_put(skb, len); switch (frametype & 0x0F) { case NR_CONNREQ: diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 908e53ab47a4..2bf99bd5be58 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -127,8 +127,7 @@ static void nr_heartbeat_expiry(struct timer_list *t) sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); - sock_put(sk); - return; + goto out; } break; @@ -149,6 +148,8 @@ static void nr_heartbeat_expiry(struct timer_list *t) nr_start_heartbeat(sk); bh_unlock_sock(sk); +out: + sock_put(sk); } static void nr_t2timer_expiry(struct timer_list *t) @@ -162,6 +163,7 @@ static void nr_t2timer_expiry(struct timer_list *t) nr_enquiry_response(sk); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t4timer_expiry(struct timer_list *t) @@ -172,6 +174,7 @@ static void nr_t4timer_expiry(struct timer_list *t) bh_lock_sock(sk); nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY; bh_unlock_sock(sk); + sock_put(sk); } static void nr_idletimer_expiry(struct timer_list *t) @@ -200,6 +203,7 @@ static void nr_idletimer_expiry(struct timer_list *t) sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); } static void nr_t1timer_expiry(struct timer_list *t) @@ -212,8 +216,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_1: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_CONNREQ); @@ -223,8 +226,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_2: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_write_internal(sk, NR_DISCREQ); @@ -234,8 +236,7 @@ static void nr_t1timer_expiry(struct timer_list *t) case NR_STATE_3: if (nr->n2count == nr->n2) { nr_disconnect(sk, ETIMEDOUT); - bh_unlock_sock(sk); - return; + goto out; } else { nr->n2count++; nr_requeue_frames(sk); @@ -244,5 +245,7 @@ static void nr_t1timer_expiry(struct timer_list *t) } nr_start_t1timer(sk); +out: bh_unlock_sock(sk); + sock_put(sk); } diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c index d3e594eb36d0..adf16ff007cc 100644 --- a/net/nfc/af_nfc.c +++ b/net/nfc/af_nfc.c @@ -72,6 +72,9 @@ int nfc_proto_register(const struct nfc_protocol *nfc_proto) proto_tab[nfc_proto->id] = nfc_proto; write_unlock(&proto_tab_lock); + if (rc) + proto_unregister(nfc_proto->proto); + return rc; } EXPORT_SYMBOL(nfc_proto_register); diff --git a/net/nfc/core.c b/net/nfc/core.c index 947a470f929d..dd12ee46ac73 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -50,7 +50,7 @@ int nfc_fw_download(struct nfc_dev *dev, const char *firmware_name) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -106,13 +106,13 @@ int nfc_dev_up(struct nfc_dev *dev) device_lock(&dev->dev); - if (dev->rfkill && rfkill_blocked(dev->rfkill)) { - rc = -ERFKILL; + if (dev->shutting_down) { + rc = -ENODEV; goto error; } - if (!device_is_registered(&dev->dev)) { - rc = -ENODEV; + if (dev->rfkill && rfkill_blocked(dev->rfkill)) { + rc = -ERFKILL; goto error; } @@ -154,7 +154,7 @@ int nfc_dev_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -218,7 +218,7 @@ int nfc_start_poll(struct nfc_dev *dev, u32 im_protocols, u32 tm_protocols) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -257,7 +257,7 @@ int nfc_stop_poll(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -302,7 +302,7 @@ int nfc_dep_link_up(struct nfc_dev *dev, int target_index, u8 comm_mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -346,7 +346,7 @@ int nfc_dep_link_down(struct nfc_dev *dev) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -412,7 +412,7 @@ int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -458,7 +458,7 @@ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -505,7 +505,7 @@ int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, struct sk_buff *skb, device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; kfree_skb(skb); goto error; @@ -562,7 +562,7 @@ int nfc_enable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -611,7 +611,7 @@ int nfc_disable_se(struct nfc_dev *dev, u32 se_idx) device_lock(&dev->dev); - if (!device_is_registered(&dev->dev)) { + if (dev->shutting_down) { rc = -ENODEV; goto error; } @@ -646,7 +646,7 @@ error: return rc; } -int nfc_set_remote_general_bytes(struct nfc_dev *dev, u8 *gb, u8 gb_len) +int nfc_set_remote_general_bytes(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { pr_debug("dev_name=%s gb_len=%d\n", dev_name(&dev->dev), gb_len); @@ -675,7 +675,7 @@ int nfc_tm_data_received(struct nfc_dev *dev, struct sk_buff *skb) EXPORT_SYMBOL(nfc_tm_data_received); int nfc_tm_activated(struct nfc_dev *dev, u32 protocol, u8 comm_mode, - u8 *gb, size_t gb_len) + const u8 *gb, size_t gb_len) { int rc; @@ -1130,11 +1130,7 @@ int nfc_register_device(struct nfc_dev *dev) if (rc) pr_err("Could not register llcp device\n"); - rc = nfc_genl_device_added(dev); - if (rc) - pr_debug("The userspace won't be notified that the device %s was added\n", - dev_name(&dev->dev)); - + device_lock(&dev->dev); dev->rfkill = rfkill_alloc(dev_name(&dev->dev), &dev->dev, RFKILL_TYPE_NFC, &nfc_rfkill_ops, dev); if (dev->rfkill) { @@ -1143,6 +1139,13 @@ int nfc_register_device(struct nfc_dev *dev) dev->rfkill = NULL; } } + dev->shutting_down = false; + device_unlock(&dev->dev); + + rc = nfc_genl_device_added(dev); + if (rc) + pr_debug("The userspace won't be notified that the device %s was added\n", + dev_name(&dev->dev)); return 0; } @@ -1159,24 +1162,25 @@ void nfc_unregister_device(struct nfc_dev *dev) pr_debug("dev_name=%s\n", dev_name(&dev->dev)); + rc = nfc_genl_device_removed(dev); + if (rc) + pr_debug("The userspace won't be notified that the device %s " + "was removed\n", dev_name(&dev->dev)); + + device_lock(&dev->dev); if (dev->rfkill) { rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); + dev->rfkill = NULL; } + dev->shutting_down = true; + device_unlock(&dev->dev); if (dev->ops->check_presence) { - device_lock(&dev->dev); - dev->shutting_down = true; - device_unlock(&dev->dev); del_timer_sync(&dev->check_pres_timer); cancel_work_sync(&dev->check_pres_work); } - rc = nfc_genl_device_removed(dev); - if (rc) - pr_debug("The userspace won't be notified that the device %s " - "was removed\n", dev_name(&dev->dev)); - nfc_llcp_unregister_device(dev); mutex_lock(&nfc_devlist_mutex); diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index ec0a8998e52d..d6258638a07a 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -286,6 +286,7 @@ int digital_tg_configure_hw(struct nfc_digital_dev *ddev, int type, int param) static int digital_tg_listen_mdaa(struct nfc_digital_dev *ddev, u8 rf_tech) { struct digital_tg_mdaa_params *params; + int rc; params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) @@ -300,8 +301,12 @@ static int digital_tg_listen_mdaa(struct nfc_digital_dev *ddev, u8 rf_tech) get_random_bytes(params->nfcid2 + 2, NFC_NFCID2_MAXSIZE - 2); params->sc = DIGITAL_SENSF_FELICA_SC; - return digital_send_cmd(ddev, DIGITAL_CMD_TG_LISTEN_MDAA, NULL, params, - 500, digital_tg_recv_atr_req, NULL); + rc = digital_send_cmd(ddev, DIGITAL_CMD_TG_LISTEN_MDAA, NULL, params, + 500, digital_tg_recv_atr_req, NULL); + if (rc) + kfree(params); + + return rc; } static int digital_tg_listen_md(struct nfc_digital_dev *ddev, u8 rf_tech) diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index 4f9a973988b2..1eed0cf59190 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -1285,6 +1285,8 @@ static void digital_tg_recv_dep_req(struct nfc_digital_dev *ddev, void *arg, } rc = nfc_tm_data_received(ddev->nfc_dev, resp); + if (rc) + resp = NULL; exit: kfree_skb(ddev->chaining_skb); diff --git a/net/nfc/digital_technology.c b/net/nfc/digital_technology.c index 2021d1d58a75..c092b02fde8a 100644 --- a/net/nfc/digital_technology.c +++ b/net/nfc/digital_technology.c @@ -474,8 +474,12 @@ static int digital_in_send_sdd_req(struct nfc_digital_dev *ddev, skb_put_u8(skb, sel_cmd); skb_put_u8(skb, DIGITAL_SDD_REQ_SEL_PAR); - return digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sdd_res, - target); + rc = digital_in_send_cmd(ddev, skb, 30, digital_in_recv_sdd_res, + target); + if (rc) + kfree_skb(skb); + + return rc; } static void digital_in_recv_sens_res(struct nfc_digital_dev *ddev, void *arg, diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index fe988936ad92..e6863c71f566 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -134,7 +134,7 @@ static bool llc_shdlc_x_lteq_y_lt_z(int x, int y, int z) return ((y >= x) || (y < z)) ? true : false; } -static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc, +static struct sk_buff *llc_shdlc_alloc_skb(const struct llc_shdlc *shdlc, int payload_len) { struct sk_buff *skb; @@ -148,7 +148,7 @@ static struct sk_buff *llc_shdlc_alloc_skb(struct llc_shdlc *shdlc, } /* immediately sends an S frame. */ -static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc, +static int llc_shdlc_send_s_frame(const struct llc_shdlc *shdlc, enum sframe_type sframe_type, int nr) { int r; @@ -170,7 +170,7 @@ static int llc_shdlc_send_s_frame(struct llc_shdlc *shdlc, } /* immediately sends an U frame. skb may contain optional payload */ -static int llc_shdlc_send_u_frame(struct llc_shdlc *shdlc, +static int llc_shdlc_send_u_frame(const struct llc_shdlc *shdlc, struct sk_buff *skb, enum uframe_modifier uframe_modifier) { @@ -372,7 +372,7 @@ static void llc_shdlc_connect_complete(struct llc_shdlc *shdlc, int r) wake_up(shdlc->connect_wq); } -static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc) +static int llc_shdlc_connect_initiate(const struct llc_shdlc *shdlc) { struct sk_buff *skb; @@ -388,7 +388,7 @@ static int llc_shdlc_connect_initiate(struct llc_shdlc *shdlc) return llc_shdlc_send_u_frame(shdlc, skb, U_FRAME_RSET); } -static int llc_shdlc_connect_send_ua(struct llc_shdlc *shdlc) +static int llc_shdlc_connect_send_ua(const struct llc_shdlc *shdlc) { struct sk_buff *skb; diff --git a/net/nfc/llcp.h b/net/nfc/llcp.h index 1f68724d44d3..a070a57fc151 100644 --- a/net/nfc/llcp.h +++ b/net/nfc/llcp.h @@ -233,15 +233,15 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *sk, struct socket *newsock); /* TLV API */ int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len); + const u8 *tlv_array, u16 tlv_array_len); int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, - u8 *tlv_array, u16 tlv_array_len); + const u8 *tlv_array, u16 tlv_array_len); /* Commands API */ void nfc_llcp_recv(void *data, struct sk_buff *skb, int err); -u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length); +u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length); struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap); -struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri, +struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len); void nfc_llcp_free_sdp_tlv(struct nfc_llcp_sdp_tlv *sdp); void nfc_llcp_free_sdp_tlv_list(struct hlist_head *sdp_head); diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index d1fc019e932e..737c7aa384f4 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -27,7 +27,7 @@ #include "nfc.h" #include "llcp.h" -static u8 llcp_tlv_length[LLCP_TLV_MAX] = { +static const u8 llcp_tlv_length[LLCP_TLV_MAX] = { 0, 1, /* VERSION */ 2, /* MIUX */ @@ -41,7 +41,7 @@ static u8 llcp_tlv_length[LLCP_TLV_MAX] = { }; -static u8 llcp_tlv8(u8 *tlv, u8 type) +static u8 llcp_tlv8(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; @@ -49,7 +49,7 @@ static u8 llcp_tlv8(u8 *tlv, u8 type) return tlv[2]; } -static u16 llcp_tlv16(u8 *tlv, u8 type) +static u16 llcp_tlv16(const u8 *tlv, u8 type) { if (tlv[0] != type || tlv[1] != llcp_tlv_length[tlv[0]]) return 0; @@ -58,37 +58,37 @@ static u16 llcp_tlv16(u8 *tlv, u8 type) } -static u8 llcp_tlv_version(u8 *tlv) +static u8 llcp_tlv_version(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_VERSION); } -static u16 llcp_tlv_miux(u8 *tlv) +static u16 llcp_tlv_miux(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_MIUX) & 0x7ff; } -static u16 llcp_tlv_wks(u8 *tlv) +static u16 llcp_tlv_wks(const u8 *tlv) { return llcp_tlv16(tlv, LLCP_TLV_WKS); } -static u16 llcp_tlv_lto(u8 *tlv) +static u16 llcp_tlv_lto(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_LTO); } -static u8 llcp_tlv_opt(u8 *tlv) +static u8 llcp_tlv_opt(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_OPT); } -static u8 llcp_tlv_rw(u8 *tlv) +static u8 llcp_tlv_rw(const u8 *tlv) { return llcp_tlv8(tlv, LLCP_TLV_RW) & 0xf; } -u8 *nfc_llcp_build_tlv(u8 type, u8 *value, u8 value_length, u8 *tlv_length) +u8 *nfc_llcp_build_tlv(u8 type, const u8 *value, u8 value_length, u8 *tlv_length) { u8 *tlv, length; @@ -142,7 +142,7 @@ struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdres_tlv(u8 tid, u8 sap) return sdres; } -struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, char *uri, +struct nfc_llcp_sdp_tlv *nfc_llcp_build_sdreq_tlv(u8 tid, const char *uri, size_t uri_len) { struct nfc_llcp_sdp_tlv *sdreq; @@ -202,9 +202,10 @@ void nfc_llcp_free_sdp_tlv_list(struct hlist_head *head) } int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, - u8 *tlv_array, u16 tlv_array_len) + const u8 *tlv_array, u16 tlv_array_len) { - u8 *tlv = tlv_array, type, length, offset = 0; + const u8 *tlv = tlv_array; + u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); @@ -251,9 +252,10 @@ int nfc_llcp_parse_gb_tlv(struct nfc_llcp_local *local, } int nfc_llcp_parse_connection_tlv(struct nfc_llcp_sock *sock, - u8 *tlv_array, u16 tlv_array_len) + const u8 *tlv_array, u16 tlv_array_len) { - u8 *tlv = tlv_array, type, length, offset = 0; + const u8 *tlv = tlv_array; + u8 type, length, offset = 0; pr_debug("TLV array length %d\n", tlv_array_len); @@ -307,7 +309,7 @@ static struct sk_buff *llcp_add_header(struct sk_buff *pdu, return pdu; } -static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, u8 *tlv, +static struct sk_buff *llcp_add_tlv(struct sk_buff *pdu, const u8 *tlv, u8 tlv_length) { /* XXX Add an skb length check */ @@ -401,9 +403,11 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; - u8 *service_name_tlv = NULL, service_name_tlv_length; - u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; + const u8 *service_name_tlv = NULL; + const u8 *miux_tlv = NULL; + const u8 *rw_tlv = NULL; + u8 service_name_tlv_length = 0; + u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; @@ -477,8 +481,9 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) { struct nfc_llcp_local *local; struct sk_buff *skb; - u8 *miux_tlv = NULL, miux_tlv_length; - u8 *rw_tlv = NULL, rw_tlv_length, rw; + const u8 *miux_tlv = NULL; + const u8 *rw_tlv = NULL; + u8 miux_tlv_length, rw_tlv_length, rw; int err; u16 size = 0; __be16 miux; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 4fa015208aab..a217830f0f34 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -157,6 +157,13 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { + /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever + * we hold a reference to local, we also need to hold a reference to + * the device to avoid UAF. + */ + if (!nfc_get_device(local->dev->idx)) + return NULL; + kref_get(&local->ref); return local; @@ -171,6 +178,7 @@ static void local_cleanup(struct nfc_llcp_local *local) cancel_work_sync(&local->rx_work); cancel_work_sync(&local->timeout_work); kfree_skb(local->rx_pending); + local->rx_pending = NULL; del_timer_sync(&local->sdreq_timer); cancel_work_sync(&local->sdreq_timeout_work); nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs); @@ -189,10 +197,18 @@ static void local_release(struct kref *ref) int nfc_llcp_local_put(struct nfc_llcp_local *local) { + struct nfc_dev *dev; + int ret; + if (local == NULL) return 0; - return kref_put(&local->ref, local_release); + dev = local->dev; + + ret = kref_put(&local->ref, local_release); + nfc_put_device(dev); + + return ret; } static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, @@ -215,17 +231,13 @@ static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, if (tmp_sock->ssap == ssap && tmp_sock->dsap == dsap) { llcp_sock = tmp_sock; + sock_hold(&llcp_sock->sk); break; } } read_unlock(&local->sockets.lock); - if (llcp_sock == NULL) - return NULL; - - sock_hold(&llcp_sock->sk); - return llcp_sock; } @@ -313,7 +325,7 @@ static char *wks[] = { "urn:nfc:sn:snep", }; -static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len) +static int nfc_llcp_wks_sap(const char *service_name, size_t service_name_len) { int sap, num_wks; @@ -337,7 +349,8 @@ static int nfc_llcp_wks_sap(char *service_name, size_t service_name_len) static struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, - u8 *sn, size_t sn_len) + const u8 *sn, size_t sn_len, + bool needref) { struct sock *sk; struct nfc_llcp_sock *llcp_sock, *tmp_sock; @@ -373,6 +386,8 @@ struct nfc_llcp_sock *nfc_llcp_sock_from_sn(struct nfc_llcp_local *local, if (memcmp(sn, tmp_sock->service_name, sn_len) == 0) { llcp_sock = tmp_sock; + if (needref) + sock_hold(&llcp_sock->sk); break; } } @@ -414,7 +429,8 @@ u8 nfc_llcp_get_sdp_ssap(struct nfc_llcp_local *local, * to this service name. */ if (nfc_llcp_sock_from_sn(local, sock->service_name, - sock->service_name_len) != NULL) { + sock->service_name_len, + false) != NULL) { mutex_unlock(&local->sdp_lock); return LLCP_SAP_MAX; @@ -534,7 +550,7 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { u8 *gb_cur, version, version_length; u8 lto_length, wks_length, miux_length; - u8 *version_tlv = NULL, *lto_tlv = NULL, + const u8 *version_tlv = NULL, *lto_tlv = NULL, *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; @@ -624,7 +640,7 @@ u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len) return local->gb; } -int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) +int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len) { struct nfc_llcp_local *local; @@ -651,27 +667,27 @@ int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len) local->remote_gb_len - 3); } -static u8 nfc_llcp_dsap(struct sk_buff *pdu) +static u8 nfc_llcp_dsap(const struct sk_buff *pdu) { return (pdu->data[0] & 0xfc) >> 2; } -static u8 nfc_llcp_ptype(struct sk_buff *pdu) +static u8 nfc_llcp_ptype(const struct sk_buff *pdu) { return ((pdu->data[0] & 0x03) << 2) | ((pdu->data[1] & 0xc0) >> 6); } -static u8 nfc_llcp_ssap(struct sk_buff *pdu) +static u8 nfc_llcp_ssap(const struct sk_buff *pdu) { return pdu->data[1] & 0x3f; } -static u8 nfc_llcp_ns(struct sk_buff *pdu) +static u8 nfc_llcp_ns(const struct sk_buff *pdu) { return pdu->data[2] >> 4; } -static u8 nfc_llcp_nr(struct sk_buff *pdu) +static u8 nfc_llcp_nr(const struct sk_buff *pdu) { return pdu->data[2] & 0xf; } @@ -813,23 +829,15 @@ out: } static struct nfc_llcp_sock *nfc_llcp_sock_get_sn(struct nfc_llcp_local *local, - u8 *sn, size_t sn_len) + const u8 *sn, size_t sn_len) { - struct nfc_llcp_sock *llcp_sock; - - llcp_sock = nfc_llcp_sock_from_sn(local, sn, sn_len); - - if (llcp_sock == NULL) - return NULL; - - sock_hold(&llcp_sock->sk); - - return llcp_sock; + return nfc_llcp_sock_from_sn(local, sn, sn_len, true); } -static u8 *nfc_llcp_connect_sn(struct sk_buff *skb, size_t *sn_len) +static const u8 *nfc_llcp_connect_sn(const struct sk_buff *skb, size_t *sn_len) { - u8 *tlv = &skb->data[2], type, length; + u8 type, length; + const u8 *tlv = &skb->data[2]; size_t tlv_array_len = skb->len - LLCP_HEADER_SIZE, offset = 0; while (offset < tlv_array_len) { @@ -887,7 +895,7 @@ static void nfc_llcp_recv_ui(struct nfc_llcp_local *local, } static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct sock *new_sk, *parent; struct nfc_llcp_sock *sock, *new_sock; @@ -905,7 +913,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, goto fail; } } else { - u8 *sn; + const u8 *sn; size_t sn_len; sn = nfc_llcp_connect_sn(skb, &sn_len); @@ -958,8 +966,17 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, } new_sock = nfc_llcp_sock(new_sk); - new_sock->dev = local->dev; + new_sock->local = nfc_llcp_local_get(local); + if (!new_sock->local) { + reason = LLCP_DM_REJ; + sock_put(&new_sock->sk); + release_sock(&sock->sk); + sock_put(&sock->sk); + goto fail; + } + + new_sock->dev = local->dev; new_sock->rw = sock->rw; new_sock->miux = sock->miux; new_sock->nfc_protocol = sock->nfc_protocol; @@ -1124,7 +1141,7 @@ static void nfc_llcp_recv_hdlc(struct nfc_llcp_local *local, } static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1167,7 +1184,8 @@ static void nfc_llcp_recv_disc(struct nfc_llcp_local *local, nfc_llcp_sock_put(llcp_sock); } -static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) +static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1200,7 +1218,8 @@ static void nfc_llcp_recv_cc(struct nfc_llcp_local *local, struct sk_buff *skb) nfc_llcp_sock_put(llcp_sock); } -static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) +static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; struct sock *sk; @@ -1238,12 +1257,13 @@ static void nfc_llcp_recv_dm(struct nfc_llcp_local *local, struct sk_buff *skb) } static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, - struct sk_buff *skb) + const struct sk_buff *skb) { struct nfc_llcp_sock *llcp_sock; - u8 dsap, ssap, *tlv, type, length, tid, sap; + u8 dsap, ssap, type, length, tid, sap; + const u8 *tlv; u16 tlv_len, offset; - char *service_name; + const char *service_name; size_t service_name_len; struct nfc_llcp_sdp_tlv *sdp; HLIST_HEAD(llc_sdres_list); @@ -1285,7 +1305,8 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, } llcp_sock = nfc_llcp_sock_from_sn(local, service_name, - service_name_len); + service_name_len, + true); if (!llcp_sock) { sap = 0; goto add_snl; @@ -1305,6 +1326,7 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, if (sap == LLCP_SAP_MAX) { sap = 0; + nfc_llcp_sock_put(llcp_sock); goto add_snl; } @@ -1322,6 +1344,7 @@ static void nfc_llcp_recv_snl(struct nfc_llcp_local *local, pr_debug("%p %d\n", llcp_sock, sap); + nfc_llcp_sock_put(llcp_sock); add_snl: sdp = nfc_llcp_build_sdres_tlv(tid, sap); if (sdp == NULL) @@ -1585,7 +1608,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) if (local == NULL) return -ENOMEM; - local->dev = ndev; + /* As we are going to initialize local's refcount, we need to get the + * nfc_dev to avoid UAF, otherwise there is no point in continuing. + * See nfc_llcp_local_get(). + */ + local->dev = nfc_get_device(ndev->idx); + if (!local->dev) { + kfree(local); + return -ENODEV; + } + INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 7d766350c08e..605d7448c3de 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -120,13 +120,19 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) llcp_sock->service_name_len, GFP_KERNEL); if (!llcp_sock->service_name) { + nfc_llcp_local_put(llcp_sock->local); + llcp_sock->local = NULL; + llcp_sock->dev = NULL; ret = -ENOMEM; goto put_dev; } llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock); if (llcp_sock->ssap == LLCP_SAP_MAX) { + nfc_llcp_local_put(llcp_sock->local); + llcp_sock->local = NULL; kfree(llcp_sock->service_name); llcp_sock->service_name = NULL; + llcp_sock->dev = NULL; ret = -EADDRINUSE; goto put_dev; } @@ -683,6 +689,10 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, ret = -EISCONN; goto error; } + if (sk->sk_state == LLCP_CONNECTING) { + ret = -EINPROGRESS; + goto error; + } dev = nfc_get_device(addr->dev_idx); if (dev == NULL) { @@ -714,6 +724,8 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, llcp_sock->local = nfc_llcp_local_get(local); llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { + nfc_llcp_local_put(llcp_sock->local); + llcp_sock->local = NULL; ret = -ENOMEM; goto put_dev; } @@ -751,8 +763,12 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, sock_unlink: nfc_llcp_put_ssap(local, llcp_sock->ssap); + nfc_llcp_local_put(llcp_sock->local); + llcp_sock->local = NULL; nfc_llcp_sock_unlink(&local->connecting_sockets, sk); + kfree(llcp_sock->service_name); + llcp_sock->service_name = NULL; put_dev: nfc_put_device(dev); @@ -780,6 +796,11 @@ static int llcp_sock_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); + if (!llcp_sock->local) { + release_sock(sk); + return -ENODEV; + } + if (sk->sk_type == SOCK_DGRAM) { DECLARE_SOCKADDR(struct sockaddr_nfc_llcp *, addr, msg->msg_name); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 074960154993..33723d843e47 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -156,12 +156,15 @@ inline int nci_request(struct nci_dev *ndev, { int rc; - if (!test_bit(NCI_UP, &ndev->flags)) - return -ENETDOWN; - /* Serialize all requests */ mutex_lock(&ndev->req_lock); - rc = __nci_request(ndev, req, opt, timeout); + /* check the state after obtaing the lock against any races + * from nci_close_device when the device gets removed. + */ + if (test_bit(NCI_UP, &ndev->flags)) + rc = __nci_request(ndev, req, opt, timeout); + else + rc = -ENETDOWN; mutex_unlock(&ndev->req_lock); return rc; @@ -482,6 +485,11 @@ static int nci_open_device(struct nci_dev *ndev) mutex_lock(&ndev->req_lock); + if (test_bit(NCI_UNREG, &ndev->flags)) { + rc = -ENODEV; + goto done; + } + if (test_bit(NCI_UP, &ndev->flags)) { rc = -EALREADY; goto done; @@ -534,7 +542,7 @@ static int nci_open_device(struct nci_dev *ndev) skb_queue_purge(&ndev->tx_q); ndev->ops->close(ndev); - ndev->flags = 0; + ndev->flags &= BIT(NCI_UNREG); } done: @@ -545,9 +553,17 @@ done: static int nci_close_device(struct nci_dev *ndev) { nci_req_cancel(ndev, ENODEV); + + /* This mutex needs to be held as a barrier for + * caller nci_unregister_device + */ mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { + /* Need to flush the cmd wq in case + * there is a queued/running cmd_work + */ + flush_workqueue(ndev->cmd_wq); del_timer_sync(&ndev->cmd_timer); del_timer_sync(&ndev->data_timer); mutex_unlock(&ndev->req_lock); @@ -582,8 +598,8 @@ static int nci_close_device(struct nci_dev *ndev) /* Flush cmd wq */ flush_workqueue(ndev->cmd_wq); - /* Clear flags */ - ndev->flags = 0; + /* Clear flags except NCI_UNREG */ + ndev->flags &= BIT(NCI_UNREG); mutex_unlock(&ndev->req_lock); @@ -890,6 +906,11 @@ static int nci_activate_target(struct nfc_dev *nfc_dev, return -EINVAL; } + if (protocol >= NFC_PROTO_MAX) { + pr_err("the requested nfc protocol is invalid\n"); + return -EINVAL; + } + if (!(nci_target->supported_protocols & (1 << protocol))) { pr_err("target does not support the requested protocol 0x%x\n", protocol); @@ -1187,6 +1208,7 @@ EXPORT_SYMBOL(nci_allocate_device); void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); + nci_hci_deallocate(ndev); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); @@ -1264,6 +1286,12 @@ void nci_unregister_device(struct nci_dev *ndev) { struct nci_conn_info *conn_info, *n; + /* This set_bit is not protected with specialized barrier, + * However, it is fine because the mutex_lock(&ndev->req_lock); + * in nci_close_device() will help to emit one. + */ + set_bit(NCI_UNREG, &ndev->flags); + nci_close_device(ndev); destroy_workqueue(ndev->cmd_wq); diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 5405d073804c..5d46d8dfad72 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -130,7 +130,7 @@ static int nci_queue_tx_data_frags(struct nci_dev *ndev, skb_frag = nci_skb_alloc(ndev, (NCI_DATA_HDR_SIZE + frag_len), - GFP_KERNEL); + GFP_ATOMIC); if (skb_frag == NULL) { rc = -ENOMEM; goto free_exit; @@ -291,8 +291,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) nci_plen(skb->data)); conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data)); - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return; + } /* strip the nci data header */ skb_pull(skb, NCI_DATA_HDR_SIZE); diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index c0d323b58e73..e5c5cff33236 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -165,7 +165,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, i = 0; skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; @@ -198,7 +198,7 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, if (i < data_len) { skb = nci_skb_alloc(ndev, conn_info->max_pkt_payload_len + - NCI_DATA_HDR_SIZE, GFP_KERNEL); + NCI_DATA_HDR_SIZE, GFP_ATOMIC); if (!skb) return -ENOMEM; @@ -807,3 +807,8 @@ struct nci_hci_dev *nci_hci_allocate(struct nci_dev *ndev) return hdev; } + +void nci_hci_deallocate(struct nci_dev *ndev) +{ + kfree(ndev->hci_dev); +} diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 1e8c1a12aaec..4f75453c07aa 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -230,6 +230,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, target->sens_res = nfca_poll->sens_res; target->sel_res = nfca_poll->sel_res; target->nfcid1_len = nfca_poll->nfcid1_len; + if (target->nfcid1_len > ARRAY_SIZE(target->nfcid1)) + return -EPROTO; if (target->nfcid1_len > 0) { memcpy(target->nfcid1, nfca_poll->nfcid1, target->nfcid1_len); @@ -238,6 +240,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, nfcb_poll = (struct rf_tech_specific_params_nfcb_poll *)params; target->sensb_res_len = nfcb_poll->sensb_res_len; + if (target->sensb_res_len > ARRAY_SIZE(target->sensb_res)) + return -EPROTO; if (target->sensb_res_len > 0) { memcpy(target->sensb_res, nfcb_poll->sensb_res, target->sensb_res_len); @@ -246,6 +250,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, nfcf_poll = (struct rf_tech_specific_params_nfcf_poll *)params; target->sensf_res_len = nfcf_poll->sensf_res_len; + if (target->sensf_res_len > ARRAY_SIZE(target->sensf_res)) + return -EPROTO; if (target->sensf_res_len > 0) { memcpy(target->sensf_res, nfcf_poll->sensf_res, target->sensf_res_len); diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c index e3bbf1937d0e..7681f89dc312 100644 --- a/net/nfc/nci/rsp.c +++ b/net/nfc/nci/rsp.c @@ -289,6 +289,8 @@ static void nci_core_conn_close_rsp_packet(struct nci_dev *ndev, ndev->cur_conn_id); if (conn_info) { list_del(&conn_info->list); + if (conn_info == ndev->rf_conn_info) + ndev->rf_conn_info = NULL; devm_kfree(&ndev->nfc_dev->dev, conn_info); } } diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index 452f4c16b7a9..d2de7fc226f0 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -163,6 +163,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge) int ret; skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL); + if (!skb) + return -ENOMEM; /* add the NCI SPI header to the start of the buffer */ hdr = skb_push(skb, NCI_SPI_HDR_LEN); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index a65a5a5f434b..f705800b2248 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -655,8 +655,10 @@ static int nfc_genl_dump_devices_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; - nfc_device_iter_exit(iter); - kfree(iter); + if (iter) { + nfc_device_iter_exit(iter); + kfree(iter); + } return 0; } @@ -871,6 +873,7 @@ static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info) if (!dev->polling) { device_unlock(&dev->dev); + nfc_put_device(dev); return -EINVAL; } @@ -1235,7 +1238,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info) u32 idx; char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1]; - if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME]) return -EINVAL; idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); @@ -1259,7 +1262,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, struct sk_buff *msg; void *hdr; - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) return -ENOMEM; @@ -1275,7 +1278,7 @@ int nfc_genl_fw_download_done(struct nfc_dev *dev, const char *firmware_name, genlmsg_end(msg, hdr); - genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_KERNEL); + genlmsg_multicast(&nfc_genl_family, msg, 0, 0, GFP_ATOMIC); return 0; @@ -1409,8 +1412,10 @@ static int nfc_genl_dump_ses_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; - nfc_device_iter_exit(iter); - kfree(iter); + if (iter) { + nfc_device_iter_exit(iter); + kfree(iter); + } return 0; } @@ -1455,8 +1460,12 @@ static int nfc_se_io(struct nfc_dev *dev, u32 se_idx, rc = dev->ops->se_io(dev, se_idx, apdu, apdu_length, cb, cb_context); + device_unlock(&dev->dev); + return rc; + error: device_unlock(&dev->dev); + kfree(cb_context); return rc; } @@ -1510,6 +1519,7 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info) u32 dev_idx, se_idx; u8 *apdu; size_t apdu_len; + int rc; if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_SE_INDEX] || @@ -1523,25 +1533,37 @@ static int nfc_genl_se_io(struct sk_buff *skb, struct genl_info *info) if (!dev) return -ENODEV; - if (!dev->ops || !dev->ops->se_io) - return -ENOTSUPP; + if (!dev->ops || !dev->ops->se_io) { + rc = -EOPNOTSUPP; + goto put_dev; + } apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]); - if (apdu_len == 0) - return -EINVAL; + if (apdu_len == 0) { + rc = -EINVAL; + goto put_dev; + } apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]); - if (!apdu) - return -EINVAL; + if (!apdu) { + rc = -EINVAL; + goto put_dev; + } ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL); - if (!ctx) - return -ENOMEM; + if (!ctx) { + rc = -ENOMEM; + goto put_dev; + } ctx->dev_idx = dev_idx; ctx->se_idx = se_idx; - return nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx); + rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx); + +put_dev: + nfc_put_device(dev); + return rc; } static int nfc_genl_vendor_cmd(struct sk_buff *skb, @@ -1564,14 +1586,21 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]); dev = nfc_get_device(dev_idx); - if (!dev || !dev->vendor_cmds || !dev->n_vendor_cmds) + if (!dev) return -ENODEV; + if (!dev->vendor_cmds || !dev->n_vendor_cmds) { + err = -ENODEV; + goto put_dev; + } + if (info->attrs[NFC_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]); data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]); - if (data_len == 0) - return -EINVAL; + if (data_len == 0) { + err = -EINVAL; + goto put_dev; + } } else { data = NULL; data_len = 0; @@ -1586,10 +1615,14 @@ static int nfc_genl_vendor_cmd(struct sk_buff *skb, dev->cur_cmd_info = info; err = cmd->doit(dev, data, data_len); dev->cur_cmd_info = NULL; - return err; + goto put_dev; } - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + +put_dev: + nfc_put_device(dev); + return err; } /* message building helper */ diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h index 6c6f76b370b1..c792165f523f 100644 --- a/net/nfc/nfc.h +++ b/net/nfc/nfc.h @@ -60,7 +60,7 @@ void nfc_llcp_mac_is_up(struct nfc_dev *dev, u32 target_idx, u8 comm_mode, u8 rf_mode); int nfc_llcp_register_device(struct nfc_dev *dev); void nfc_llcp_unregister_device(struct nfc_dev *dev); -int nfc_llcp_set_remote_gb(struct nfc_dev *dev, u8 *gb, u8 gb_len); +int nfc_llcp_set_remote_gb(struct nfc_dev *dev, const u8 *gb, u8 gb_len); u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *general_bytes_len); int nfc_llcp_data_received(struct nfc_dev *dev, struct sk_buff *skb); struct nfc_llcp_local *nfc_llcp_find_local(struct nfc_dev *dev); diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index b927730d9ab0..bdc72737fe24 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -117,7 +117,7 @@ static int rawsock_connect(struct socket *sock, struct sockaddr *_addr, if (addr->target_idx > dev->target_next_idx - 1 || addr->target_idx < dev->target_next_idx - dev->n_targets) { rc = -EINVAL; - goto error; + goto put_dev; } rc = nfc_activate_target(dev, addr->target_idx, addr->nfc_protocol); @@ -345,7 +345,7 @@ static int rawsock_create(struct net *net, struct socket *sock, return -ESOCKTNOSUPPORT; if (sock->type == SOCK_RAW) { - if (!capable(CAP_NET_RAW)) + if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; sock->ops = &rawsock_raw_ops; } else { diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 1a30e165eeb4..a5fa25555d7e 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -80,13 +80,12 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; unsigned int nsh_len, mac_len; __be16 proto; - int nhoff; skb_reset_network_header(skb); - nhoff = skb->network_header - skb->mac_header; mac_len = skb->mac_len; if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) @@ -111,15 +110,14 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, segs = skb_mac_gso_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, htons(ETH_P_NSH), nsh_len, - skb->network_header - nhoff, - mac_len); + mac_offset, mac_len); goto out; } for (skb = segs; skb; skb = skb->next) { skb->protocol = htons(ETH_P_NSH); __skb_push(skb, nsh_len); - skb_set_mac_header(skb, -nhoff); + skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 8211e8e97c96..091202b84b6e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -443,6 +443,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh, update_ip_l4_checksum(skb, nh, *addr, new_addr); csum_replace4(&nh->check, *addr, new_addr); skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); *addr = new_addr; } @@ -490,15 +491,47 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, update_ipv6_checksum(skb, l4_proto, addr, new_addr); skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); memcpy(addr, new_addr, sizeof(__be32[4])); } -static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask) +static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask) { + u8 old_ipv6_tclass = ipv6_get_dsfield(nh); + + ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12), + (__force __wsum)(ipv6_tclass << 12)); + + ipv6_change_dsfield(nh, ~mask, ipv6_tclass); +} + +static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask) +{ + u32 ofl; + + ofl = nh->flow_lbl[0] << 16 | nh->flow_lbl[1] << 8 | nh->flow_lbl[2]; + fl = OVS_MASKED(ofl, fl, mask); + /* Bits 21-24 are always unmasked, so this retains their values. */ - OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16)); - OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8)); - OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask); + nh->flow_lbl[0] = (u8)(fl >> 16); + nh->flow_lbl[1] = (u8)(fl >> 8); + nh->flow_lbl[2] = (u8)fl; + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl)); +} + +static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask) +{ + new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8), + (__force __wsum)(new_ttl << 8)); + nh->hop_limit = new_ttl; } static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl, @@ -616,18 +649,17 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, } } if (mask->ipv6_tclass) { - ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass); + set_ipv6_dsfield(skb, nh, key->ipv6_tclass, mask->ipv6_tclass); flow_key->ip.tos = ipv6_get_dsfield(nh); } if (mask->ipv6_label) { - set_ipv6_fl(nh, ntohl(key->ipv6_label), + set_ipv6_fl(skb, nh, ntohl(key->ipv6_label), ntohl(mask->ipv6_label)); flow_key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); } if (mask->ipv6_hlimit) { - OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit, - mask->ipv6_hlimit); + set_ipv6_ttl(skb, nh, key->ipv6_hlimit, mask->ipv6_hlimit); flow_key->ip.ttl = nh->hop_limit; } return 0; @@ -700,6 +732,7 @@ static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) { + ovs_ct_clear(skb, NULL); inet_proto_csum_replace2(check, skb, *port, new_port, false); *port = new_port; } @@ -739,6 +772,7 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key, uh->dest = dst; flow_key->tp.src = src; flow_key->tp.dst = dst; + ovs_ct_clear(skb, NULL); } skb_clear_hash(skb); @@ -801,6 +835,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key, sh->checksum = old_csum ^ old_correct_csum ^ new_csum; skb_clear_hash(skb); + ovs_ct_clear(skb, NULL); + flow_key->tp.src = sh->source; flow_key->tp.dst = sh->dest; @@ -892,17 +928,17 @@ static void ovs_fragment(struct net *net, struct vport *vport, } if (key->eth.type == htons(ETH_P_IP)) { - struct dst_entry ovs_dst; + struct rtable ovs_rt = { 0 }; unsigned long orig_dst; prepare_frag(vport, skb, orig_network_offset, ovs_key_mac_proto(key)); - dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1, + dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1, DST_OBSOLETE_NONE, DST_NOCOUNT); - ovs_dst.dev = vport->dev; + ovs_rt.dst.dev = vport->dev; orig_dst = skb->_skb_refdst; - skb_dst_set_noref(skb, &ovs_dst); + skb_dst_set_noref(skb, &ovs_rt.dst); IPCB(skb)->frag_max_size = mru; ip_do_fragment(net, skb->sk, skb, ovs_vport_output); @@ -1068,7 +1104,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb, int rem = nla_len(attr); bool dont_clone_flow_key; - /* The first action is always 'OVS_CLONE_ATTR_ARG'. */ + /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */ clone_arg = nla_data(attr); dont_clone_flow_key = nla_get_u32(clone_arg); actions = nla_next(clone_arg, &rem); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index fb13fcfedaf4..0777c8d416f1 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1303,7 +1303,8 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) if (skb_nfct(skb)) { nf_conntrack_put(skb_nfct(skb)); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - ovs_ct_fill_key(skb, key); + if (key) + ovs_ct_fill_key(skb, key); } return 0; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f350faef044d..0551915519d9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -249,10 +249,17 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key) upcall.portid = ovs_vport_find_upcall_portid(p, skb); upcall.mru = OVS_CB(skb)->mru; error = ovs_dp_upcall(dp, skb, key, &upcall, 0); - if (unlikely(error)) - kfree_skb(skb); - else + switch (error) { + case 0: + case -EAGAIN: + case -ERESTARTSYS: + case -EINTR: consume_skb(skb); + break; + default: + kfree_skb(skb); + break; + } stats_counter = &stats->n_missed; goto out; } @@ -519,8 +526,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, out: if (err) skb_tx_error(skb); - kfree_skb(user_skb); - kfree_skb(nskb); + consume_skb(user_skb); + consume_skb(nskb); + return err; } @@ -895,6 +903,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) struct sw_flow_mask mask; struct sk_buff *reply; struct datapath *dp; + struct sw_flow_key *key; struct sw_flow_actions *acts; struct sw_flow_match match; u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); @@ -922,30 +931,32 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } /* Extract key. */ - ovs_match_init(&match, &new_flow->key, false, &mask); + key = kzalloc(sizeof(*key), GFP_KERNEL); + if (!key) { + error = -ENOMEM; + goto err_kfree_flow; + } + + ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) - goto err_kfree_flow; + goto err_kfree_key; + + ovs_flow_mask_key(&new_flow->key, key, true, &mask); /* Extract flow identifier. */ error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], - &new_flow->key, log); + key, log); if (error) - goto err_kfree_flow; - - /* unmasked key is needed to match when ufid is not used. */ - if (ovs_identifier_is_key(&new_flow->id)) - match.key = new_flow->id.unmasked_key; - - ovs_flow_mask_key(&new_flow->key, &new_flow->key, true, &mask); + goto err_kfree_key; /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); - goto err_kfree_flow; + goto err_kfree_key; } reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, @@ -966,7 +977,7 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (ovs_identifier_is_ufid(&new_flow->id)) flow = ovs_flow_tbl_lookup_ufid(&dp->table, &new_flow->id); if (!flow) - flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->key); + flow = ovs_flow_tbl_lookup(&dp->table, key); if (likely(!flow)) { rcu_assign_pointer(new_flow->sf_acts, acts); @@ -1036,6 +1047,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) if (reply) ovs_notify(&dp_flow_genl_family, reply, info); + + kfree(key); return 0; err_unlock_ovs: @@ -1043,6 +1056,8 @@ err_unlock_ovs: kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); +err_kfree_key: + kfree(key); err_kfree_flow: ovs_flow_free(new_flow, false); error: @@ -1543,7 +1558,8 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in if (IS_ERR(dp)) return; - WARN(dp->user_features, "Dropping previously announced user features\n"); + pr_warn("%s: Dropping previously announced user features\n", + ovs_dp_name(dp)); dp->user_features = 0; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index eab5e8eaddaa..eba94cf3d2d0 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2166,8 +2166,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, icmpv6_key->icmpv6_type = ntohs(output->tp.src); icmpv6_key->icmpv6_code = ntohs(output->tp.dst); - if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION || - icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) { + if (swkey->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || + swkey->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { struct ovs_key_nd *nd_key; nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key)); @@ -2253,6 +2253,36 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size) return sfa; } +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len); + +static void ovs_nla_free_clone_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_CLONE_ATTR_EXEC: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + +static void ovs_nla_free_sample_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_SAMPLE_ATTR_ARG: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + static void ovs_nla_free_set_action(const struct nlattr *a) { const struct nlattr *ovs_key = nla_data(a); @@ -2266,25 +2296,46 @@ static void ovs_nla_free_set_action(const struct nlattr *a) } } -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) { const struct nlattr *a; int rem; - if (!sf_acts) + /* Whenever new actions are added, the need to update this + * function should be considered. + */ + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 20); + + if (!actions) return; - nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + nla_for_each_attr(a, actions, len, rem) { switch (nla_type(a)) { - case OVS_ACTION_ATTR_SET: - ovs_nla_free_set_action(a); + case OVS_ACTION_ATTR_CLONE: + ovs_nla_free_clone_action(a); break; + case OVS_ACTION_ATTR_CT: ovs_ct_free_action(a); break; + + case OVS_ACTION_ATTR_SAMPLE: + ovs_nla_free_sample_action(a); + break; + + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; } } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + if (!sf_acts) + return; + ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len); kfree(sf_acts); } @@ -2316,7 +2367,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) { + if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { OVS_NLERR(log, "Flow action size exceeds max %u", MAX_ACTIONS_BUFSIZE); return ERR_PTR(-EMSGSIZE); @@ -3173,7 +3224,9 @@ static int clone_action_to_attr(const struct nlattr *attr, if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); + /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */ + attr = nla_next(nla_data(attr), &rem); + err = ovs_nla_put_actions(attr, rem, skb); if (err) nla_nest_cancel(skb, start); diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 5ea2471ffc03..9b0c54f0702c 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -464,6 +464,14 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb, spin_lock(&meter->lock); long_delta_ms = (now_ms - meter->used); /* ms */ + if (long_delta_ms < 0) { + /* This condition means that we have several threads fighting + * for a meter lock, and the one who received the packets a + * bit later wins. Assuming that all racing threads received + * packets at the same time to avoid overflow. + */ + long_delta_ms = 0; + } /* Make sure delta_ms will not be too large, so that bucket will not * wrap around below. diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 16b745d254fe..377832981178 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -370,18 +370,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -398,17 +400,19 @@ static int __packet_get_status(struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); @@ -1716,6 +1720,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; + match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; list_add(&match->list, &fanout_list); } @@ -1729,7 +1734,10 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags) err = -ENOSPC; if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) { __dev_remove_pack(&po->prot_hook); - po->fanout = match; + + /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ + WRITE_ONCE(po->fanout, match); + po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); @@ -1951,7 +1959,7 @@ retry: goto retry; } - if (!dev_validate_header(dev, skb->data, len)) { + if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } @@ -1974,7 +1982,7 @@ retry: skb->mark = sk->sk_mark; skb->tstamp = sockc.transmit_time; - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -2101,7 +2109,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; - if (unlikely(po->origdev)) + if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; @@ -2205,8 +2213,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (snaplen > res) @@ -2242,8 +2249,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, copy_skb = skb_get(skb); skb_head = skb->data; } - if (copy_skb) + if (copy_skb) { + memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, + sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); + } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { @@ -2365,7 +2375,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_hatype = dev->type; sll->sll_protocol = skb->protocol; sll->sll_pkttype = skb->pkt_type; - if (unlikely(po->origdev)) + if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; @@ -2494,7 +2504,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = po->sk.sk_priority; skb->mark = po->sk.sk_mark; skb->tstamp = sockc->transmit_time; - sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); @@ -2656,7 +2666,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2784,8 +2794,9 @@ tpacket_error: status = TP_STATUS_SEND_REQUEST; err = po->xmit(skb); - if (unlikely(err > 0)) { - err = net_xmit_errno(err); + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ @@ -2869,7 +2880,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2958,7 +2969,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { @@ -2986,8 +2997,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->no_fcs = 1; err = po->xmit(skb); - if (err > 0 && (err = net_xmit_errno(err)) != 0) - goto out_unlock; + if (unlikely(err != 0)) { + if (err > 0) + err = net_xmit_errno(err); + if (err) + goto out_unlock; + } dev_put(dev); @@ -3106,6 +3121,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, lock_sock(sk); spin_lock(&po->bind_lock); + if (!proto) + proto = po->num; + rcu_read_lock(); if (po->fanout) { @@ -3141,7 +3159,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, /* prevents packet_notifier() from calling * register_prot_hook() */ - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); dev_curr = po->prot_hook.dev; @@ -3151,17 +3169,17 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } BUG_ON(po->running); - po->num = proto; + WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } @@ -3208,7 +3226,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); name[sizeof(uaddr->sa_data)] = 0; - return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); + return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) @@ -3225,8 +3243,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len if (sll->sll_family != AF_PACKET) return -EINVAL; - return packet_do_bind(sk, NULL, sll->sll_ifindex, - sll->sll_protocol ? : pkt_sk(sk)->num); + return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { @@ -3294,6 +3311,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; + po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; @@ -3401,6 +3419,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { + const size_t max_len = min(sizeof(skb->cb), + sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled @@ -3423,18 +3443,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, msg->msg_namelen = sizeof(struct sockaddr_ll); } } + if (WARN_ON_ONCE(copy_len > max_len)) { + copy_len = max_len; + msg->msg_namelen = copy_len; + } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } - if (pkt_sk(sk)->auxdata) { + if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && - (skb->ip_summed == CHECKSUM_COMPLETE || - skb_csum_unnecessary(skb))) + skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; aux.tp_len = origlen; @@ -3476,7 +3499,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); @@ -3491,16 +3514,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex; if (peer) return -EOPNOTSUPP; + ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; - sll->sll_protocol = po->num; + sll->sll_ifindex = ifindex; + sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -3808,9 +3833,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - lock_sock(sk); - po->auxdata = !!val; - release_sock(sk); + packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: @@ -3822,9 +3845,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - lock_sock(sk); - po->origdev = !!val; - release_sock(sk); + packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: @@ -3873,7 +3894,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv } case PACKET_FANOUT_DATA: { - if (!po->fanout) + /* Paired with the WRITE_ONCE() in fanout_add() */ + if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); @@ -3953,10 +3975,10 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, break; case PACKET_AUXDATA: - val = po->auxdata; + val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: - val = po->origdev; + val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = po->has_vnet_hdr; @@ -4079,7 +4101,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -4192,7 +4214,7 @@ static void packet_mm_open(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_inc(&pkt_sk(sk)->mapped); + atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) @@ -4202,7 +4224,7 @@ static void packet_mm_close(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_dec(&pkt_sk(sk)->mapped); + atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { @@ -4297,7 +4319,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; if (!closing) { - if (atomic_read(&po->mapped)) + if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; @@ -4391,7 +4413,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, was_running = po->running; num = po->num; if (was_running) { - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); @@ -4400,7 +4422,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; mutex_lock(&po->pg_vec_lock); - if (closing || atomic_read(&po->mapped) == 0) { + if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); @@ -4418,15 +4440,15 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); - if (atomic_read(&po->mapped)) - pr_err("packet_mmap: vma is busy: %d\n", - atomic_read(&po->mapped)); + if (atomic_long_read(&po->mapped)) + pr_err("packet_mmap: vma is busy: %ld\n", + atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); if (was_running) { - po->num = num; + WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); @@ -4437,9 +4459,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } out_free_pg_vec: - bitmap_free(rx_owner_map); - if (pg_vec) + if (pg_vec) { + bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); + } out: return err; } @@ -4497,7 +4520,7 @@ static int packet_mmap(struct file *file, struct socket *sock, } } - atomic_inc(&po->mapped); + atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; @@ -4597,8 +4620,8 @@ static int packet_seq_show(struct seq_file *seq, void *v) s, refcount_read(&s->sk_refcnt), s->sk_type, - ntohs(po->num), - po->ifindex, + ntohs(READ_ONCE(po->num)), + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), diff --git a/net/packet/diag.c b/net/packet/diag.c index 7ef1c881ae74..ecabf78d29b8 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -22,9 +22,9 @@ static int pdiag_put_info(const struct packet_sock *po, struct sk_buff *nlskb) pinfo.pdi_flags = 0; if (po->running) pinfo.pdi_flags |= PDI_RUNNING; - if (po->auxdata) + if (packet_sock_flag(po, PACKET_SOCK_AUXDATA)) pinfo.pdi_flags |= PDI_AUXDATA; - if (po->origdev) + if (packet_sock_flag(po, PACKET_SOCK_ORIGDEV)) pinfo.pdi_flags |= PDI_ORIGDEV; if (po->has_vnet_hdr) pinfo.pdi_flags |= PDI_VNETHDR; @@ -142,7 +142,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, rp = nlmsg_data(nlh); rp->pdiag_family = AF_PACKET; rp->pdiag_type = sk->sk_type; - rp->pdiag_num = ntohs(po->num); + rp->pdiag_num = ntohs(READ_ONCE(po->num)); rp->pdiag_ino = sk_ino; sock_diag_save_cookie(sk, rp->pdiag_cookie); diff --git a/net/packet/internal.h b/net/packet/internal.h index f10294800aaf..7f2d5eed5e00 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -115,10 +115,9 @@ struct packet_sock { int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; + unsigned long flags; unsigned int running; /* bind_lock must be held */ - unsigned int auxdata:1, /* writer must hold sock lock */ - origdev:1, - has_vnet_hdr:1, + unsigned int has_vnet_hdr:1, /* writer must hold sock lock */ tp_loss:1, tp_tx_has_off:1; int pressure; @@ -126,7 +125,7 @@ struct packet_sock { __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; - atomic_t mapped; + atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; @@ -142,4 +141,25 @@ static struct packet_sock *pkt_sk(struct sock *sk) return (struct packet_sock *)sk; } +enum packet_sock_flags { + PACKET_SOCK_ORIGDEV, + PACKET_SOCK_AUXDATA, +}; + +static inline void packet_sock_flag_set(struct packet_sock *po, + enum packet_sock_flags flag, + bool val) +{ + if (val) + set_bit(flag, &po->flags); + else + clear_bit(flag, &po->flags); +} + +static inline bool packet_sock_flag(const struct packet_sock *po, + enum packet_sock_flags flag) +{ + return test_bit(flag, &po->flags); +} + #endif diff --git a/net/phonet/pep.c b/net/phonet/pep.c index db3473540303..fe01cc788448 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -881,6 +881,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, err = pep_accept_conn(newsk, skb); if (err) { + __sock_put(sk); sock_put(newsk); newsk = NULL; goto drop; @@ -959,6 +960,8 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) ret = -EBUSY; else if (sk->sk_state == TCP_ESTABLISHED) ret = -EISCONN; + else if (!pn->pn_sk.sobject) + ret = -EADDRNOTAVAIL; else ret = pep_sock_enable(sk, NULL, 0); release_sock(sk); diff --git a/net/psample/psample.c b/net/psample/psample.c index 30e8239bd774..196fbf674dc1 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -31,7 +31,8 @@ enum psample_nl_multicast_groups { static const struct genl_multicast_group psample_nl_mcgrps[] = { [PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME }, - [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME }, + [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME, + .flags = GENL_UNS_ADMIN_PERM }, }; static struct genl_family psample_nl_family __ro_after_init; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index a05c5cb3429c..128d0a48478d 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -194,7 +194,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->src_port_id = cpu_to_le32(from->sq_port); if (to->sq_port == QRTR_PORT_CTRL) { hdr->dst_node_id = cpu_to_le32(node->nid); - hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST); + hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL); } else { hdr->dst_node_id = cpu_to_le32(to->sq_node); hdr->dst_port_id = cpu_to_le32(to->sq_port); @@ -264,14 +264,14 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) const struct qrtr_hdr_v2 *v2; struct sk_buff *skb; struct qrtr_cb *cb; - unsigned int size; + size_t size; unsigned int ver; size_t hdrlen; if (len == 0 || len & 3) return -EINVAL; - skb = netdev_alloc_skb(NULL, len); + skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN); if (!skb) return -ENOMEM; @@ -321,7 +321,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) goto err; } - if (len != ALIGN(size, 4) + hdrlen) + if (!size || len != ALIGN(size, 4) + hdrlen) goto err; if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA) @@ -797,8 +797,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) plen = (len + 3) & ~3; skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE, msg->msg_flags & MSG_DONTWAIT, &rc); - if (!skb) + if (!skb) { + rc = -ENOMEM; goto out_node; + } skb_reserve(skb, QRTR_HDR_MAX_SIZE); @@ -866,6 +868,11 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, rc = copied; if (addr) { + /* There is an anonymous 2-byte hole after sq_family, + * make sure to clear it. + */ + memset(addr, 0, sizeof(*addr)); + cb = (struct qrtr_cb *)skb->cb; addr->sq_family = AF_QIPCRTR; addr->sq_node = cb->src_node; diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c index e35869e81766..cb425e216d46 100644 --- a/net/qrtr/tun.c +++ b/net/qrtr/tun.c @@ -31,6 +31,7 @@ static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb) static int qrtr_tun_open(struct inode *inode, struct file *filp) { struct qrtr_tun *tun; + int ret; tun = kzalloc(sizeof(*tun), GFP_KERNEL); if (!tun) @@ -43,7 +44,16 @@ static int qrtr_tun_open(struct inode *inode, struct file *filp) filp->private_data = tun; - return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + ret = qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); + if (ret) + goto out; + + return 0; + +out: + filp->private_data = NULL; + kfree(tun); + return ret; } static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to) @@ -80,6 +90,12 @@ static ssize_t qrtr_tun_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t ret; void *kbuf; + if (!len) + return -EINVAL; + + if (len > KMALLOC_MAX_SIZE) + return -ENOMEM; + kbuf = kzalloc(len, GFP_KERNEL); if (!kbuf) return -ENOMEM; diff --git a/net/rds/connection.c b/net/rds/connection.c index 3bd2f4a5a30d..af9f7d184003 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -237,12 +237,24 @@ static struct rds_connection *__rds_conn_create(struct net *net, if (loop_trans) { rds_trans_put(loop_trans); conn->c_loopback = 1; - if (is_outgoing && trans->t_prefer_loopback) { - /* "outgoing" connection - and the transport - * says it wants the connection handled by the - * loopback transport. This is what TCP does. - */ - trans = &rds_loop_transport; + if (trans->t_prefer_loopback) { + if (likely(is_outgoing)) { + /* "outgoing" connection to local address. + * Protocol says it wants the connection + * handled by the loopback transport. + * This is what TCP does. + */ + trans = &rds_loop_transport; + } else { + /* No transport currently in use + * should end up here, but if it + * does, reset/destroy the connection. + */ + kfree(conn->c_path); + kmem_cache_free(rds_conn_slab, conn); + conn = ERR_PTR(-EOPNOTSUPP); + goto out; + } } } diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 6431a023ac89..46988c009a3e 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -111,9 +111,9 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) cpu_relax(); } - ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len, + ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len, &off, PAGE_SIZE); - if (unlikely(ret != ibmr->sg_len)) + if (unlikely(ret != ibmr->sg_dma_len)) return ret < 0 ? ret : -EINVAL; /* Perform a WR for the fast_reg_mr. Each individual page diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 2f16146e4ec9..18e0e3cba1ac 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -362,6 +362,7 @@ static int acquire_refill(struct rds_connection *conn) static void release_refill(struct rds_connection *conn) { clear_bit(RDS_RECV_REFILL, &conn->c_flags); + smp_mb__after_atomic(); /* We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk diff --git a/net/rds/message.c b/net/rds/message.c index 4b00b1152a5f..29f67ad483ea 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ @@ -118,7 +118,7 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, ck = &info->zcookies; memset(ck, 0, sizeof(*ck)); WARN_ON(!rds_zcookie_add(info, cookie)); - list_add_tail(&q->zcookie_head, &info->rs_zcookie_next); + list_add_tail(&info->rs_zcookie_next, &q->zcookie_head); spin_unlock_irqrestore(&q->lock, flags); /* caller invokes rds_wake_sk_sleep() */ diff --git a/net/rds/rdma.c b/net/rds/rdma.c index e1965d9cbcf8..9882cebfcad6 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -531,6 +531,9 @@ int rds_rdma_extra_size(struct rds_rdma_args *args, if (args->nr_local == 0) return -EINVAL; + if (args->nr_local > UIO_MAXIOV) + return -EMSGSIZE; + iov->iov = kcalloc(args->nr_local, sizeof(struct rds_iovec), GFP_KERNEL); diff --git a/net/rds/recv.c b/net/rds/recv.c index 3ca278988b52..ccf0bf283002 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -705,7 +705,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (rds_cmsg_recv(inc, msg, rs)) { ret = -EFAULT; - goto out; + break; } rds_recvmsg_zcookie(rs, msg); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 18bb522df282..645cbb17c13a 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -176,10 +176,10 @@ void rds_tcp_reset_callbacks(struct socket *sock, */ atomic_set(&cp->cp_state, RDS_CONN_RESETTING); wait_event(cp->cp_waitq, !test_bit(RDS_IN_XMIT, &cp->cp_flags)); - lock_sock(osock->sk); /* reset receive side state for rds_tcp_data_recv() for osock */ cancel_delayed_work_sync(&cp->cp_send_w); cancel_delayed_work_sync(&cp->cp_recv_w); + lock_sock(osock->sk); if (tc->t_tinc) { rds_inc_put(&tc->t_tinc->ti_inc); tc->t_tinc = NULL; @@ -322,8 +322,8 @@ out: } #endif -static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, - __u32 scope_id) +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id) { struct net_device *dev = NULL; #if IS_ENABLED(CONFIG_IPV6) @@ -502,7 +502,7 @@ void rds_tcp_tune(struct socket *sock) sk->sk_userlocks |= SOCK_SNDBUF_LOCK; } if (rtn->rcvbuf_size > 0) { - sk->sk_sndbuf = rtn->rcvbuf_size; + sk->sk_rcvbuf = rtn->rcvbuf_size; sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 3c69361d21c7..4620549ecbeb 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -60,7 +60,8 @@ u32 rds_tcp_snd_una(struct rds_tcp_connection *tc); u64 rds_tcp_map_seq(struct rds_tcp_connection *tc, u32 seq); extern struct rds_transport rds_tcp_transport; void rds_tcp_accept_work(struct sock *sk); - +int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr, + __u32 scope_id); /* tcp_connect.c */ int rds_tcp_conn_path_connect(struct rds_conn_path *cp); void rds_tcp_conn_path_shutdown(struct rds_conn_path *conn); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 008f50fb25dd..63efe60fda1f 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -141,7 +141,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) addrlen = sizeof(sin); } - ret = sock->ops->bind(sock, addr, addrlen); + ret = kernel_bind(sock, addr, addrlen); if (ret) { rdsdebug("bind failed with %d at address %pI6c\n", ret, &conn->c_laddr); @@ -169,7 +169,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) * own the socket */ rds_tcp_set_callbacks(sock, cp); - ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK); + ret = kernel_connect(sock, addr, addrlen, O_NONBLOCK); rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c12203f646da..37f4a8ca3ac8 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -198,6 +198,12 @@ int rds_tcp_accept_one(struct socket *sock) } #endif + if (!rds_tcp_laddr_check(sock_net(sock->sk), peer_addr, dev_if)) { + /* local address connection is only allowed via loopback */ + ret = -EOPNOTSUPP; + goto out; + } + conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, &rds_tcp_transport, GFP_KERNEL, dev_if); @@ -326,7 +332,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6) addr_len = sizeof(*sin); } - ret = sock->ops->bind(sock, (struct sockaddr *)&ss, addr_len); + ret = kernel_bind(sock, (struct sockaddr *)&ss, addr_len); if (ret < 0) { rdsdebug("could not bind %s listener socket: %d\n", isv6 ? "IPv6" : "IPv4", ret); diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 0f8465852254..7524544a965f 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -112,13 +112,13 @@ static int rfkill_gpio_probe(struct platform_device *pdev) rfkill->clk = devm_clk_get(&pdev->dev, NULL); - gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); rfkill->reset_gpio = gpio; - gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); @@ -130,6 +130,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev) return -EINVAL; } + ret = gpiod_direction_output(rfkill->reset_gpio, true); + if (ret) + return ret; + + ret = gpiod_direction_output(rfkill->shutdown_gpio, true); + if (ret) + return ret; + rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev, rfkill->type, &rfkill_gpio_ops, rfkill); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index d00a0ef39a56..015e475f5554 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -184,20 +184,47 @@ void rose_kill_by_neigh(struct rose_neigh *neigh) */ static void rose_kill_by_device(struct net_device *dev) { - struct sock *s; + struct sock *sk, *array[16]; + struct rose_sock *rose; + bool rescan; + int i, cnt; +start: + rescan = false; + cnt = 0; spin_lock_bh(&rose_list_lock); - sk_for_each(s, &rose_list) { - struct rose_sock *rose = rose_sk(s); + sk_for_each(sk, &rose_list) { + rose = rose_sk(sk); + if (rose->device == dev) { + if (cnt == ARRAY_SIZE(array)) { + rescan = true; + break; + } + sock_hold(sk); + array[cnt++] = sk; + } + } + spin_unlock_bh(&rose_list_lock); + for (i = 0; i < cnt; i++) { + sk = array[cnt]; + rose = rose_sk(sk); + lock_sock(sk); + spin_lock_bh(&rose_list_lock); if (rose->device == dev) { - rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); + rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); if (rose->neighbour) rose->neighbour->use--; + dev_put(rose->device); rose->device = NULL; } + spin_unlock_bh(&rose_list_lock); + release_sock(sk); + sock_put(sk); + cond_resched(); } - spin_unlock_bh(&rose_list_lock); + if (rescan) + goto start; } /* @@ -489,6 +516,12 @@ static int rose_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; + lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { struct rose_sock *rose = rose_sk(sk); @@ -498,8 +531,10 @@ static int rose_listen(struct socket *sock, int backlog) memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; + release_sock(sk); return 0; } + release_sock(sk); return -EOPNOTSUPP; } @@ -594,6 +629,8 @@ static struct sock *rose_make_new(struct sock *osk) rose->idle = orose->idle; rose->defer = orose->defer; rose->device = orose->device; + if (rose->device) + dev_hold(rose->device); rose->qbitincl = orose->qbitincl; return sk; @@ -647,6 +684,10 @@ static int rose_release(struct socket *sock) break; } + spin_lock_bh(&rose_list_lock); + dev_put(rose->device); + rose->device = NULL; + spin_unlock_bh(&rose_list_lock); sock->sk = NULL; release_sock(sk); sock_put(sk); @@ -721,7 +762,6 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le struct rose_sock *rose = rose_sk(sk); struct sockaddr_rose *addr = (struct sockaddr_rose *)uaddr; unsigned char cause, diagnostic; - struct net_device *dev; ax25_uid_assoc *user; int n, err = 0; @@ -778,9 +818,12 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le } if (sock_flag(sk, SOCK_ZAPPED)) { /* Must bind first - autobinding in this may or may not work */ + struct net_device *dev; + sock_reset_flag(sk, SOCK_ZAPPED); - if ((dev = rose_dev_first()) == NULL) { + dev = rose_dev_first(); + if (!dev) { err = -ENETUNREACH; goto out_release; } @@ -788,6 +831,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le user = ax25_findbyuid(current_euid()); if (!user) { err = -EINVAL; + dev_put(dev); goto out_release; } @@ -1293,9 +1337,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: { struct sk_buff *skb; long amount = 0L; - /* These two are safe on a single CPU system as only user tasks fiddle here */ + + spin_lock_irq(&sk->sk_receive_queue.lock); if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) amount = skb->len; + spin_unlock_irq(&sk->sk_receive_queue.lock); return put_user(amount, (unsigned int __user *) argp); } diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index 62055d3069d2..f3d7105c6cdd 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -239,6 +239,9 @@ void rose_transmit_clear_request(struct rose_neigh *neigh, unsigned int lci, uns unsigned char *dptr; int len; + if (!neigh->dev) + return; + len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 3; if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c index 094a6621f8e8..56eea298b8ef 100644 --- a/net/rose/rose_loopback.c +++ b/net/rose/rose_loopback.c @@ -99,10 +99,20 @@ static void rose_loopback_timer(struct timer_list *unused) } if (frametype == ROSE_CALL_REQUEST) { - if ((dev = rose_dev_get(dest)) != NULL) { - if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) - kfree_skb(skb); - } else { + if (!rose_loopback_neigh->dev && + !rose_loopback_neigh->loopback) { + kfree_skb(skb); + continue; + } + + dev = rose_dev_get(dest); + if (!dev) { + kfree_skb(skb); + continue; + } + + if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) { + dev_put(dev); kfree_skb(skb); } } else { diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index f2ff21d7df08..5671853bef83 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -230,8 +230,8 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh) { struct rose_neigh *s; - rose_stop_ftimer(rose_neigh); - rose_stop_t0timer(rose_neigh); + del_timer_sync(&rose_neigh->ftimer); + del_timer_sync(&rose_neigh->t0timer); skb_queue_purge(&rose_neigh->queue); @@ -616,6 +616,8 @@ struct net_device *rose_dev_first(void) if (first == NULL || strncmp(dev->name, first->name, 3) < 0) first = dev; } + if (first) + dev_hold(first); rcu_read_unlock(); return first; diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index 74555fb95615..cede9d0ceff8 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -34,89 +34,89 @@ static void rose_idletimer_expiry(struct timer_list *); void rose_start_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); sk->sk_timer.function = rose_heartbeat_expiry; sk->sk_timer.expires = jiffies + 5 * HZ; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires); } void rose_start_t1timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t1; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_t2timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t2; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_t3timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t3; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_hbtimer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->hb; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_idletimer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->idletimer); + sk_stop_timer(sk, &rose->idletimer); if (rose->idle > 0) { rose->idletimer.function = rose_idletimer_expiry; rose->idletimer.expires = jiffies + rose->idle; - add_timer(&rose->idletimer); + sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires); } } void rose_stop_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } void rose_stop_timer(struct sock *sk) { - del_timer(&rose_sk(sk)->timer); + sk_stop_timer(sk, &rose_sk(sk)->timer); } void rose_stop_idletimer(struct sock *sk) { - del_timer(&rose_sk(sk)->idletimer); + sk_stop_timer(sk, &rose_sk(sk)->idletimer); } static void rose_heartbeat_expiry(struct timer_list *t) @@ -133,6 +133,7 @@ static void rose_heartbeat_expiry(struct timer_list *t) (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); rose_destroy_socket(sk); + sock_put(sk); return; } break; @@ -155,6 +156,7 @@ static void rose_heartbeat_expiry(struct timer_list *t) rose_start_heartbeat(sk); bh_unlock_sock(sk); + sock_put(sk); } static void rose_timer_expiry(struct timer_list *t) @@ -184,6 +186,7 @@ static void rose_timer_expiry(struct timer_list *t) break; } bh_unlock_sock(sk); + sock_put(sk); } static void rose_idletimer_expiry(struct timer_list *t) @@ -208,4 +211,5 @@ static void rose_idletimer_expiry(struct timer_list *t) sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); } diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 57f835d2442e..fb7e3fffcb5e 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -1010,7 +1010,7 @@ static int __init af_rxrpc_init(void) goto error_security; } - ret = register_pernet_subsys(&rxrpc_net_ops); + ret = register_pernet_device(&rxrpc_net_ops); if (ret) goto error_pernet; @@ -1055,7 +1055,7 @@ error_key_type: error_sock: proto_unregister(&rxrpc_proto); error_proto: - unregister_pernet_subsys(&rxrpc_net_ops); + unregister_pernet_device(&rxrpc_net_ops); error_pernet: rxrpc_exit_security(); error_security: @@ -1077,7 +1077,7 @@ static void __exit af_rxrpc_exit(void) unregister_key_type(&key_type_rxrpc); sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); - unregister_pernet_subsys(&rxrpc_net_ops); + unregister_pernet_device(&rxrpc_net_ops); ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 7778f0fb48cf..7ecfbff1f0d0 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -211,6 +211,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->peer_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_peer *peer = b->peer_backlog[tail]; + rxrpc_put_local(peer->local); kfree(peer); tail = (tail + 1) & (size - 1); } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 468efc3660c0..12f5c1870103 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -429,7 +429,8 @@ recheck_state: goto recheck_state; } - if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events)) { + if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) && + call->state != RXRPC_CALL_CLIENT_RECV_REPLY) { rxrpc_resend(call, now); goto recheck_state; } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 58bd558a277a..40711f410828 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -446,7 +446,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, if (state >= RXRPC_CALL_COMPLETE) return; - if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) { + if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 2fe2add62a8e..9be6b35fd9b2 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -1112,7 +1112,7 @@ static long rxrpc_read(const struct key *key, default: /* we have a ticket we can't encode */ pr_err("Unsupported key token type (%u)\n", token->security_index); - continue; + return -ENOPKG; } _debug("token[%u]: toksize=%u", ntoks, toksize); @@ -1227,7 +1227,9 @@ static long rxrpc_read(const struct key *key, break; default: - break; + pr_err("Unsupported key token type (%u)\n", + token->security_index); + return -ENOPKG; } ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==, diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index fe190a691872..5a01479aae3f 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -452,6 +452,9 @@ static void rxrpc_local_processor(struct work_struct *work) container_of(work, struct rxrpc_local, processor); bool again; + if (local->dead) + return; + trace_rxrpc_local(local->debug_id, rxrpc_local_processing, atomic_read(&local->usage), NULL); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 417d80867c4f..39579cfcf9b8 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -119,6 +119,8 @@ static __net_exit void rxrpc_exit_net(struct net *net) rxnet->live = false; del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + /* Remove the timer again as the worker may have restarted it. */ + del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); rxrpc_destroy_all_peers(rxnet); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index b91b090217cd..d0a1ebecc6fb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -299,6 +299,12 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, return peer; } +static void rxrpc_free_peer(struct rxrpc_peer *peer) +{ + rxrpc_put_local(peer->local); + kfree_rcu(peer, rcu); +} + /* * Set up a new incoming peer. There shouldn't be any other matching peers * since we've already done a search in the list from the non-reentrant context @@ -365,7 +371,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, spin_unlock_bh(&rxnet->peer_hash_lock); if (peer) - kfree(candidate); + rxrpc_free_peer(candidate); else peer = candidate; } @@ -420,8 +426,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); - rxrpc_put_local(peer->local); - kfree_rcu(peer, rcu); + rxrpc_free_peer(peer); } /* @@ -457,8 +462,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer) if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); - rxrpc_put_local(peer->local); - kfree_rcu(peer, rcu); + rxrpc_free_peer(peer); } } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index edd76c41765f..eaa032c498c9 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -440,6 +440,12 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, success: ret = copied; + if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) { + read_lock_bh(&call->state_lock); + if (call->error < 0) + ret = call->error; + read_unlock_bh(&call->state_lock); + } out: call->tx_pending = skb; _leave(" = %d", ret); @@ -683,7 +689,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (call->tx_total_len != -1 || call->tx_pending || call->tx_top != 0) - goto error_put; + goto out_put_unlock; call->tx_total_len = p.call.tx_total_len; } } @@ -703,7 +709,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) /* Fall through */ case 1: if (p.call.timeouts.hard > 0) { - j = msecs_to_jiffies(p.call.timeouts.hard); + j = p.call.timeouts.hard * HZ; now = jiffies; j += now; WRITE_ONCE(call->expect_term_by, j); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index d75bd15151e6..50f825f55c21 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -17,7 +17,7 @@ static struct ctl_table_header *rxrpc_sysctl_reg_table; static const unsigned int one = 1; static const unsigned int four = 4; -static const unsigned int thirtytwo = 32; +static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1; static const unsigned long one_jiffy = 1; @@ -111,7 +111,7 @@ static struct ctl_table rxrpc_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = (void *)&four, - .extra2 = (void *)&thirtytwo, + .extra2 = (void *)&max_backlog, }, { .procname = "rx_window_size", diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e95741388311..7698a8974a47 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -458,17 +458,6 @@ config NET_CLS_BASIC To compile this code as a module, choose M here: the module will be called cls_basic. -config NET_CLS_TCINDEX - tristate "Traffic-Control Index (TCINDEX)" - select NET_CLS - ---help--- - Say Y here if you want to be able to classify packets based on - traffic control indices. You will want this feature if you want - to implement Differentiated Services together with DSMARK. - - To compile this code as a module, choose M here: the - module will be called cls_tcindex. - config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" depends on INET @@ -514,34 +503,6 @@ config CLS_U32_MARK ---help--- Say Y here to be able to use netfilter marks as u32 key. -config NET_CLS_RSVP - tristate "IPv4 Resource Reservation Protocol (RSVP)" - select NET_CLS - ---help--- - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp. - -config NET_CLS_RSVP6 - tristate "IPv6 Resource Reservation Protocol (RSVP6)" - select NET_CLS - ---help--- - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests and you are using the IPv6 protocol. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp6. - config NET_CLS_FLOW tristate "Flow classifier" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index f0403f49edcb..3139c32e1947 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -61,9 +61,6 @@ obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o -obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_TCINDEX) += cls_tcindex.o -obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f2c4bfc79663..ad0773b20d83 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -609,15 +609,24 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, restart_act_graph: for (i = 0; i < nr_actions; i++) { const struct tc_action *a = actions[i]; + int repeat_ttl; if (jmp_prgcnt > 0) { jmp_prgcnt -= 1; continue; } + + repeat_ttl = 32; repeat: ret = a->ops->act(skb, a, res); - if (ret == TC_ACT_REPEAT) - goto repeat; /* we need a ttl - JHS */ + + if (unlikely(ret == TC_ACT_REPEAT)) { + if (--repeat_ttl != 0) + goto repeat; + /* suspicious opcode, stop pipeline */ + net_warn_ratelimited("TC_ACT_REPEAT abuse ?\n"); + return TC_ACT_OK; + } if (TC_ACT_EXT_CMP(ret, TC_ACT_JUMP)) { jmp_prgcnt = ret & TCA_ACT_MAX_PRIO_MASK; @@ -900,6 +909,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, return ERR_PTR(-EINVAL); } + if (!bind && ovr && err == ACT_P_CREATED) + refcount_set(&a->tcfa_refcnt, 2); + return a; err_mod: diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index a30c17a28281..9aad86e4a0fb 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -220,7 +220,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - if (unlikely(!(dev->flags & IFF_UP))) { + if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto out; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index ce14fafb36a1..255d4ecf6252 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -29,6 +29,7 @@ static struct tc_action_ops act_pedit_ops; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, + [TCA_PEDIT_PARMS_EX] = { .len = sizeof(struct tc_pedit) }, [TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED }, }; @@ -148,7 +149,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct nlattr *pattr; struct tcf_pedit *p; int ret = 0, err; - int ksize; + int i, ksize; u32 index; if (!nla) { @@ -221,6 +222,22 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, p->tcfp_nkeys = parm->nkeys; } memcpy(p->tcfp_keys, parm->keys, ksize); + p->tcfp_off_max_hint = 0; + for (i = 0; i < p->tcfp_nkeys; ++i) { + u32 cur = p->tcfp_keys[i].off; + + /* sanitize the shift value for any later use */ + p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1, + p->tcfp_keys[i].shift); + + /* The AT option can read a single byte, we can bound the actual + * value with uchar max. + */ + cur += (0xff & p->tcfp_keys[i].offmask) >> p->tcfp_keys[i].shift; + + /* Each key touches 4 bytes starting from the computed offset */ + p->tcfp_off_max_hint = max(p->tcfp_off_max_hint, cur + 4); + } p->tcfp_flags = parm->flags; p->tcf_action = parm->action; @@ -298,13 +315,18 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_pedit *p = to_pedit(a); + u32 max_offset; int i; - if (skb_unclone(skb, GFP_ATOMIC)) - return p->tcf_action; - spin_lock(&p->tcf_lock); + max_offset = (skb_transport_header_was_set(skb) ? + skb_transport_offset(skb) : + skb_network_offset(skb)) + + p->tcfp_off_max_hint; + if (skb_ensure_writable(skb, min(skb->len, max_offset))) + goto unlock; + tcf_lastuse_update(&p->tcf_tm); if (p->tcfp_nkeys > 0) { @@ -393,6 +415,7 @@ bad: p->tcf_qstats.overlimits++; done: bstats_update(&p->tcf_bstats, skb); +unlock: spin_unlock(&p->tcf_lock); return p->tcf_action; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 21d195296121..03a272af664a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -10,6 +10,7 @@ */ #include <linux/module.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> @@ -36,6 +37,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&d->tcf_tm); bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb); + action = READ_ONCE(d->tcf_action); + if (unlikely(action == TC_ACT_SHOT)) + goto drop; + + if (!skb->dev || skb->dev->type != ARPHRD_ETHER) + return action; + /* XXX: if you are going to edit more fields beyond ethernet header * (example when you add IP header replacement or vlan swap) * then MAX_EDIT_LEN needs to change appropriately @@ -44,10 +52,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, if (unlikely(err)) /* best policy is to drop on the floor */ goto drop; - action = READ_ONCE(d->tcf_action); - if (unlikely(action == TC_ACT_SHOT)) - goto drop; - p = rcu_dereference_bh(d->skbmod_p); flags = p->flags; if (flags & SKBMOD_F_DMAC) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index e4fc6b2bc29d..f43234be5695 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -314,7 +314,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, - key_id, 0); + key_id, opts_len); } else { NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); ret = -EINVAL; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 184c20b86393..6166bbad9753 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -31,8 +31,6 @@ #include <net/pkt_sched.h> #include <net/pkt_cls.h> -extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; - /* The list of all installed classifier types */ static LIST_HEAD(tcf_proto_base); @@ -539,6 +537,7 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, struct netlink_ext_ack *extack) { struct tcf_block *block; + int err = 0; if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { block = tcf_block_lookup(net, block_index); @@ -550,55 +549,95 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, const struct Qdisc_class_ops *cops; struct net_device *dev; + rcu_read_lock(); + /* Find link */ - dev = __dev_get_by_index(net, ifindex); - if (!dev) + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); return ERR_PTR(-ENODEV); + } /* Find qdisc */ if (!*parent) { *q = dev->qdisc; *parent = (*q)->handle; } else { - *q = qdisc_lookup(dev, TC_H_MAJ(*parent)); + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); if (!*q) { NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto errout_rcu; } } + *q = qdisc_refcount_inc_nz(*q); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } + /* Is it classful? */ cops = (*q)->ops->cl_ops; if (!cops) { NL_SET_ERR_MSG(extack, "Qdisc not classful"); - return ERR_PTR(-EINVAL); + err = -EINVAL; + goto errout_rcu; } if (!cops->tcf_block) { NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); - return ERR_PTR(-EOPNOTSUPP); + err = -EOPNOTSUPP; + goto errout_rcu; } + /* At this point we know that qdisc is not noop_qdisc, + * which means that qdisc holds a reference to net_device + * and we hold a reference to qdisc, so it is safe to release + * rcu read lock. + */ + rcu_read_unlock(); + /* Do we search for filter, attached to class? */ if (TC_H_MIN(*parent)) { *cl = cops->find(*q, *parent); if (*cl == 0) { NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); - return ERR_PTR(-ENOENT); + err = -ENOENT; + goto errout_qdisc; } } /* And the last stroke */ block = cops->tcf_block(*q, *cl, extack); - if (!block) - return ERR_PTR(-EINVAL); + if (!block) { + err = -EINVAL; + goto errout_qdisc; + } if (tcf_block_shared(block)) { NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); - return ERR_PTR(-EOPNOTSUPP); + err = -EOPNOTSUPP; + goto errout_qdisc; } } return block; + +errout_rcu: + rcu_read_unlock(); +errout_qdisc: + if (*q) { + qdisc_put(*q); + *q = NULL; + } + return ERR_PTR(err); +} + +static void tcf_block_release(struct Qdisc *q, struct tcf_block *block) +{ + if (q) + qdisc_put(q); } struct tcf_block_owner_item { @@ -1336,6 +1375,7 @@ replay: errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); if (err == -EAGAIN) /* Replay the request. */ goto replay; @@ -1457,6 +1497,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); return err; } @@ -1542,6 +1583,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, errout: if (chain) tcf_chain_put(chain); + tcf_block_release(q, block); return err; } @@ -1796,6 +1838,7 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); + module_put(ops->owner); return -EOPNOTSUPP; } @@ -1858,7 +1901,8 @@ replay: chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit"); - return -EINVAL; + err = -EINVAL; + goto errout_block; } chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { @@ -1870,23 +1914,27 @@ replay: tcf_chain_hold(chain); } else { NL_SET_ERR_MSG(extack, "Filter chain already exists"); - return -EEXIST; + err = -EEXIST; + goto errout_block; } } else { if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); - return -ENOENT; + err = -ENOENT; + goto errout_block; } chain = tcf_chain_create(block, chain_index); if (!chain) { NL_SET_ERR_MSG(extack, "Failed to create filter chain"); - return -ENOMEM; + err = -ENOMEM; + goto errout_block; } } } else { if (!chain || tcf_chain_held_by_acts_only(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); - return -EINVAL; + err = -EINVAL; + goto errout_block; } tcf_chain_hold(chain); } @@ -1918,7 +1966,7 @@ replay: break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, - n->nlmsg_seq, n->nlmsg_type, true); + n->nlmsg_flags, n->nlmsg_type, true); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send chain notify message"); break; @@ -1930,6 +1978,8 @@ replay: errout: tcf_chain_put(chain); +errout_block: + tcf_block_release(q, block); if (err == -EAGAIN) /* Replay the request. */ goto replay; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 55bf75cb1f16..164049d20f4d 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -229,7 +229,7 @@ static u32 flow_get_skgid(const struct sk_buff *skb) static u32 flow_get_vlan_tag(const struct sk_buff *skb) { - u16 uninitialized_var(tag); + u16 tag; if (vlan_get_tag(skb, &tag) < 0) return 0; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 208436eb107c..7ffa28a98d74 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -554,6 +554,7 @@ static int fl_set_key_mpls(struct nlattr **tb, static void fl_set_key_vlan(struct nlattr **tb, __be16 ethertype, int vlan_id_key, int vlan_prio_key, + int vlan_next_eth_type_key, struct flow_dissector_key_vlan *key_val, struct flow_dissector_key_vlan *key_mask) { @@ -572,6 +573,11 @@ static void fl_set_key_vlan(struct nlattr **tb, } key_val->vlan_tpid = ethertype; key_mask->vlan_tpid = cpu_to_be16(~0); + if (tb[vlan_next_eth_type_key]) { + key_val->vlan_eth_type = + nla_get_be16(tb[vlan_next_eth_type_key]); + key_mask->vlan_eth_type = cpu_to_be16(~0); + } } static void fl_set_key_flag(u32 flower_key, u32 flower_mask, @@ -634,6 +640,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; @@ -801,8 +810,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (eth_type_vlan(ethertype)) { fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID, - TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, - &mask->vlan); + TCA_FLOWER_KEY_VLAN_PRIO, + TCA_FLOWER_KEY_VLAN_ETH_TYPE, + &key->vlan, &mask->vlan); if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) { ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]); @@ -810,6 +820,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb, fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_CVLAN_ID, TCA_FLOWER_KEY_CVLAN_PRIO, + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, &key->cvlan, &mask->cvlan); fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, @@ -1717,13 +1728,13 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, goto nla_put_failure; if (mask->basic.n_proto) { - if (mask->cvlan.vlan_tpid) { + if (mask->cvlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE, key->basic.n_proto)) goto nla_put_failure; - } else if (mask->vlan.vlan_tpid) { + } else if (mask->vlan.vlan_eth_type) { if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, - key->basic.n_proto)) + key->vlan.vlan_eth_type)) goto nla_put_failure; } } diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index cb2c62605fc7..f15089c24a32 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -221,11 +221,6 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, if (err < 0) return err; - if (tb[TCA_FW_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); - tcf_bind_filter(tp, &f->res, base); - } - #ifdef CONFIG_NET_CLS_IND if (tb[TCA_FW_INDEV]) { int ret; @@ -244,6 +239,11 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, } else if (head->mask != 0xFFFFFFFF) return err; + if (tb[TCA_FW_CLASSID]) { + f->res.classid = nla_get_u32(tb[TCA_FW_CLASSID]); + tcf_bind_filter(tp, &f->res, base); + } + return 0; } @@ -277,7 +277,6 @@ static int fw_change(struct net *net, struct sk_buff *in_skb, return -ENOBUFS; fnew->id = f->id; - fnew->res = f->res; #ifdef CONFIG_NET_CLS_IND fnew->ifindex = f->ifindex; #endif /* CONFIG_NET_CLS_IND */ diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 0256777b838e..a924292623ec 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -427,6 +427,11 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, return -EINVAL; } + if (!nhandle) { + NL_SET_ERR_MSG(extack, "Replacing with handle of 0 is invalid"); + return -EINVAL; + } + h1 = to_hash(nhandle); b = rtnl_dereference(head->table[h1]); if (!b) { @@ -480,6 +485,11 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, int err; bool new = true; + if (!handle) { + NL_SET_ERR_MSG(extack, "Creating with handle of 0 is invalid"); + return -EINVAL; + } + if (opt == NULL) return handle ? -EINVAL : 0; @@ -503,7 +513,6 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (fold) { f->id = fold->id; f->iif = fold->iif; - f->res = fold->res; f->handle = fold->handle; f->tp = fold->tp; @@ -528,7 +537,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, rcu_assign_pointer(f->next, f1); rcu_assign_pointer(*fp, f); - if (fold && fold->handle && f->handle != fold->handle) { + if (fold) { th = to_hash(fold->handle); h = from_hash(fold->handle >> 16); b = rtnl_dereference(head->table[th]); diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c deleted file mode 100644 index cbb5e0d600f3..000000000000 --- a/net/sched/cls_rsvp.c +++ /dev/null @@ -1,28 +0,0 @@ -/* - * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> - -#define RSVP_DST_LEN 1 -#define RSVP_ID "rsvp" -#define RSVP_OPS cls_rsvp_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h deleted file mode 100644 index eb1dd2afc5a1..000000000000 --- a/net/sched/cls_rsvp.h +++ /dev/null @@ -1,775 +0,0 @@ -/* - * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -/* - Comparing to general packet classification problem, - RSVP needs only sevaral relatively simple rules: - - * (dst, protocol) are always specified, - so that we are able to hash them. - * src may be exact, or may be wildcard, so that - we can keep a hash table plus one wildcard entry. - * source port (or flow label) is important only if src is given. - - IMPLEMENTATION. - - We use a two level hash table: The top level is keyed by - destination address and protocol ID, every bucket contains a list - of "rsvp sessions", identified by destination address, protocol and - DPI(="Destination Port ID"): triple (key, mask, offset). - - Every bucket has a smaller hash table keyed by source address - (cf. RSVP flowspec) and one wildcard entry for wildcard reservations. - Every bucket is again a list of "RSVP flows", selected by - source address and SPI(="Source Port ID" here rather than - "security parameter index"): triple (key, mask, offset). - - - NOTE 1. All the packets with IPv6 extension headers (but AH and ESP) - and all fragmented packets go to the best-effort traffic class. - - - NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires - only one "Generalized Port Identifier". So that for classic - ah, esp (and udp,tcp) both *pi should coincide or one of them - should be wildcard. - - At first sight, this redundancy is just a waste of CPU - resources. But DPI and SPI add the possibility to assign different - priorities to GPIs. Look also at note 4 about tunnels below. - - - NOTE 3. One complication is the case of tunneled packets. - We implement it as following: if the first lookup - matches a special session with "tunnelhdr" value not zero, - flowid doesn't contain the true flow ID, but the tunnel ID (1...255). - In this case, we pull tunnelhdr bytes and restart lookup - with tunnel ID added to the list of keys. Simple and stupid 8)8) - It's enough for PIMREG and IPIP. - - - NOTE 4. Two GPIs make it possible to parse even GRE packets. - F.e. DPI can select ETH_P_IP (and necessary flags to make - tunnelhdr correct) in GRE protocol field and SPI matches - GRE key. Is it not nice? 8)8) - - - Well, as result, despite its simplicity, we get a pretty - powerful classification engine. */ - - -struct rsvp_head { - u32 tmap[256/32]; - u32 hgenerator; - u8 tgenerator; - struct rsvp_session __rcu *ht[256]; - struct rcu_head rcu; -}; - -struct rsvp_session { - struct rsvp_session __rcu *next; - __be32 dst[RSVP_DST_LEN]; - struct tc_rsvp_gpi dpi; - u8 protocol; - u8 tunnelid; - /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter __rcu *ht[16 + 1]; - struct rcu_head rcu; -}; - - -struct rsvp_filter { - struct rsvp_filter __rcu *next; - __be32 src[RSVP_DST_LEN]; - struct tc_rsvp_gpi spi; - u8 tunnelhdr; - - struct tcf_result res; - struct tcf_exts exts; - - u32 handle; - struct rsvp_session *sess; - struct rcu_work rwork; -}; - -static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) -{ - unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; - - h ^= h>>16; - h ^= h>>8; - return (h ^ protocol ^ tunnelid) & 0xFF; -} - -static inline unsigned int hash_src(__be32 *src) -{ - unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; - - h ^= h>>16; - h ^= h>>8; - h ^= h>>4; - return h & 0xF; -} - -#define RSVP_APPLY_RESULT() \ -{ \ - int r = tcf_exts_exec(skb, &f->exts, res); \ - if (r < 0) \ - continue; \ - else if (r > 0) \ - return r; \ -} - -static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct rsvp_head *head = rcu_dereference_bh(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1, h2; - __be32 *dst, *src; - u8 protocol; - u8 tunnelid = 0; - u8 *xprt; -#if RSVP_DST_LEN == 4 - struct ipv6hdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ipv6_hdr(skb); -#else - struct iphdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ip_hdr(skb); -#endif -restart: - -#if RSVP_DST_LEN == 4 - src = &nhptr->saddr.s6_addr32[0]; - dst = &nhptr->daddr.s6_addr32[0]; - protocol = nhptr->nexthdr; - xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); -#else - src = &nhptr->saddr; - dst = &nhptr->daddr; - protocol = nhptr->protocol; - xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (ip_is_fragment(nhptr)) - return -1; -#endif - - h1 = hash_dst(dst, protocol, tunnelid); - h2 = hash_src(src); - - for (s = rcu_dereference_bh(head->ht[h1]); s; - s = rcu_dereference_bh(s->next)) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && - protocol == s->protocol && - !(s->dpi.mask & - (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - tunnelid == s->tunnelid) { - - for (f = rcu_dereference_bh(s->ht[h2]); f; - f = rcu_dereference_bh(f->next)) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && - !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) -#if RSVP_DST_LEN == 4 - && - src[0] == f->src[0] && - src[1] == f->src[1] && - src[2] == f->src[2] -#endif - ) { - *res = f->res; - RSVP_APPLY_RESULT(); - -matched: - if (f->tunnelhdr == 0) - return 0; - - tunnelid = f->res.classid; - nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); - goto restart; - } - } - - /* And wildcard bucket... */ - for (f = rcu_dereference_bh(s->ht[16]); f; - f = rcu_dereference_bh(f->next)) { - *res = f->res; - RSVP_APPLY_RESULT(); - goto matched; - } - return -1; - } - } - return -1; -} - -static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter __rcu **ins; - struct rsvp_filter *pins; - unsigned int h1 = h & 0xFF; - unsigned int h2 = (h >> 8) & 0xFF; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ; - ins = &pins->next, pins = rtnl_dereference(*ins)) { - if (pins->handle == h) { - RCU_INIT_POINTER(n->next, pins->next); - rcu_assign_pointer(*ins, n); - return; - } - } - } - - /* Something went wrong if we are trying to replace a non-existant - * node. Mind as well halt instead of silently failing. - */ - BUG_ON(1); -} - -static void *rsvp_get(struct tcf_proto *tp, u32 handle) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1 = handle & 0xFF; - unsigned int h2 = (handle >> 8) & 0xFF; - - if (h2 > 16) - return NULL; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->handle == handle) - return f; - } - } - return NULL; -} - -static int rsvp_init(struct tcf_proto *tp) -{ - struct rsvp_head *data; - - data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL); - if (data) { - rcu_assign_pointer(tp->root, data); - return 0; - } - return -ENOBUFS; -} - -static void __rsvp_delete_filter(struct rsvp_filter *f) -{ - tcf_exts_destroy(&f->exts); - tcf_exts_put_net(&f->exts); - kfree(f); -} - -static void rsvp_delete_filter_work(struct work_struct *work) -{ - struct rsvp_filter *f = container_of(to_rcu_work(work), - struct rsvp_filter, - rwork); - rtnl_lock(); - __rsvp_delete_filter(f); - rtnl_unlock(); -} - -static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) -{ - tcf_unbind_filter(tp, &f->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (tcf_exts_get_net(&f->exts)) - tcf_queue_work(&f->rwork, rsvp_delete_filter_work); - else - __rsvp_delete_filter(f); -} - -static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int h1, h2; - - if (data == NULL) - return; - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - - while ((s = rtnl_dereference(data->ht[h1])) != NULL) { - RCU_INIT_POINTER(data->ht[h1], s->next); - - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - while ((f = rtnl_dereference(s->ht[h2])) != NULL) { - rcu_assign_pointer(s->ht[h2], f->next); - rsvp_delete_filter(tp, f); - } - } - kfree_rcu(s, rcu); - } - } - kfree_rcu(data, rcu); -} - -static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_filter *nfp, *f = arg; - struct rsvp_filter __rcu **fp; - unsigned int h = f->handle; - struct rsvp_session __rcu **sp; - struct rsvp_session *nsp, *s = f->sess; - int i, h1; - - fp = &s->ht[(h >> 8) & 0xFF]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - if (nfp == f) { - RCU_INIT_POINTER(*fp, f->next); - rsvp_delete_filter(tp, f); - - /* Strip tree */ - - for (i = 0; i <= 16; i++) - if (s->ht[i]) - goto out; - - /* OK, session has no flows */ - sp = &head->ht[h & 0xFF]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if (nsp == s) { - RCU_INIT_POINTER(*sp, s->next); - kfree_rcu(s, rcu); - goto out; - } - } - - break; - } - } - -out: - *last = true; - for (h1 = 0; h1 < 256; h1++) { - if (rcu_access_pointer(head->ht[h1])) { - *last = false; - break; - } - } - - return 0; -} - -static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int i = 0xFFFF; - - while (i-- > 0) { - u32 h; - - if ((data->hgenerator += 0x10000) == 0) - data->hgenerator = 0x10000; - h = data->hgenerator|salt; - if (!rsvp_get(tp, h)) - return h; - } - return 0; -} - -static int tunnel_bts(struct rsvp_head *data) -{ - int n = data->tgenerator >> 5; - u32 b = 1 << (data->tgenerator & 0x1F); - - if (data->tmap[n] & b) - return 0; - data->tmap[n] |= b; - return 1; -} - -static void tunnel_recycle(struct rsvp_head *data) -{ - struct rsvp_session __rcu **sht = data->ht; - u32 tmap[256/32]; - int h1, h2; - - memset(tmap, 0, sizeof(tmap)); - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - for (s = rtnl_dereference(sht[h1]); s; - s = rtnl_dereference(s->next)) { - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->tunnelhdr == 0) - continue; - data->tgenerator = f->res.classid; - tunnel_bts(data); - } - } - } - } - - memcpy(data->tmap, tmap, sizeof(tmap)); -} - -static u32 gen_tunnel(struct rsvp_head *data) -{ - int i, k; - - for (k = 0; k < 2; k++) { - for (i = 255; i > 0; i--) { - if (++data->tgenerator == 0) - data->tgenerator = 1; - if (tunnel_bts(data)) - return data->tgenerator; - } - tunnel_recycle(data); - } - return 0; -} - -static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { - [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, -}; - -static int rsvp_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, - struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - struct rsvp_filter *f, *nfp; - struct rsvp_filter __rcu **fp; - struct rsvp_session *nsp, *s; - struct rsvp_session __rcu **sp; - struct tc_rsvp_pinfo *pinfo = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_RSVP_MAX + 1]; - struct tcf_exts e; - unsigned int h1, h2; - __be32 *dst; - int err; - - if (opt == NULL) - return handle ? -EINVAL : 0; - - err = nla_parse_nested(tb, TCA_RSVP_MAX, opt, rsvp_policy, NULL); - if (err < 0) - return err; - - err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, extack); - if (err < 0) - goto errout2; - - f = *arg; - if (f) { - /* Node exists: adjust only classid */ - struct rsvp_filter *n; - - if (f->handle != handle && handle) - goto errout2; - - n = kmemdup(f, sizeof(*f), GFP_KERNEL); - if (!n) { - err = -ENOMEM; - goto errout2; - } - - err = tcf_exts_init(&n->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) { - kfree(n); - goto errout2; - } - - if (tb[TCA_RSVP_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } - - tcf_exts_change(&n->exts, &e); - rsvp_replace(tp, n, handle); - return 0; - } - - /* Now more serious part... */ - err = -EINVAL; - if (handle) - goto errout2; - if (tb[TCA_RSVP_DST] == NULL) - goto errout2; - - err = -ENOBUFS; - f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL); - if (f == NULL) - goto errout2; - - err = tcf_exts_init(&f->exts, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - goto errout; - h2 = 16; - if (tb[TCA_RSVP_SRC]) { - memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); - h2 = hash_src(f->src); - } - if (tb[TCA_RSVP_PINFO]) { - pinfo = nla_data(tb[TCA_RSVP_PINFO]); - f->spi = pinfo->spi; - f->tunnelhdr = pinfo->tunnelhdr; - } - if (tb[TCA_RSVP_CLASSID]) - f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - - dst = nla_data(tb[TCA_RSVP_DST]); - h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0); - - err = -ENOMEM; - if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0) - goto errout; - - if (f->tunnelhdr) { - err = -EINVAL; - if (f->res.classid > 255) - goto errout; - - err = -ENOMEM; - if (f->res.classid == 0 && - (f->res.classid = gen_tunnel(data)) == 0) - goto errout; - } - - for (sp = &data->ht[h1]; - (s = rtnl_dereference(*sp)) != NULL; - sp = &s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && - pinfo && pinfo->protocol == s->protocol && - memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - pinfo->tunnelid == s->tunnelid) { - -insert: - /* OK, we found appropriate session */ - - fp = &s->ht[h2]; - - f->sess = s; - if (f->tunnelhdr == 0) - tcf_bind_filter(tp, &f->res, base); - - tcf_exts_change(&f->exts, &e); - - fp = &s->ht[h2]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - __u32 mask = nfp->spi.mask & f->spi.mask; - - if (mask != f->spi.mask) - break; - } - RCU_INIT_POINTER(f->next, nfp); - rcu_assign_pointer(*fp, f); - - *arg = f; - return 0; - } - } - - /* No session found. Create new one. */ - - err = -ENOBUFS; - s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL); - if (s == NULL) - goto errout; - memcpy(s->dst, dst, sizeof(s->dst)); - - if (pinfo) { - s->dpi = pinfo->dpi; - s->protocol = pinfo->protocol; - s->tunnelid = pinfo->tunnelid; - } - sp = &data->ht[h1]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask) - break; - } - RCU_INIT_POINTER(s->next, nsp); - rcu_assign_pointer(*sp, s); - - goto insert; - -errout: - tcf_exts_destroy(&f->exts); - kfree(f); -errout2: - tcf_exts_destroy(&e); - return err; -} - -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - unsigned int h, h1; - - if (arg->stop) - return; - - for (h = 0; h < 256; h++) { - struct rsvp_session *s; - - for (s = rtnl_dereference(head->ht[h]); s; - s = rtnl_dereference(s->next)) { - for (h1 = 0; h1 <= 16; h1++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h1]); f; - f = rtnl_dereference(f->next)) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(tp, f, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; - } - } - } - } -} - -static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) -{ - struct rsvp_filter *f = fh; - struct rsvp_session *s; - struct nlattr *nest; - struct tc_rsvp_pinfo pinfo; - - if (f == NULL) - return skb->len; - s = f->sess; - - t->tcm_handle = f->handle; - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst)) - goto nla_put_failure; - pinfo.dpi = s->dpi; - pinfo.spi = f->spi; - pinfo.protocol = s->protocol; - pinfo.tunnelid = s->tunnelid; - pinfo.tunnelhdr = f->tunnelhdr; - pinfo.pad = 0; - if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo)) - goto nla_put_failure; - if (f->res.classid && - nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid)) - goto nla_put_failure; - if (((f->handle >> 8) & 0xFF) != 16 && - nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &f->exts) < 0) - goto nla_put_failure; - - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &f->exts) < 0) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, - unsigned long base) -{ - struct rsvp_filter *f = fh; - - if (f && f->res.classid == classid) { - if (cl) - __tcf_bind_filter(q, &f->res, base); - else - __tcf_unbind_filter(q, &f->res); - } -} - -static struct tcf_proto_ops RSVP_OPS __read_mostly = { - .kind = RSVP_ID, - .classify = rsvp_classify, - .init = rsvp_init, - .destroy = rsvp_destroy, - .get = rsvp_get, - .change = rsvp_change, - .delete = rsvp_delete, - .walk = rsvp_walk, - .dump = rsvp_dump, - .bind_class = rsvp_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_rsvp(void) -{ - return register_tcf_proto_ops(&RSVP_OPS); -} - -static void __exit exit_rsvp(void) -{ - unregister_tcf_proto_ops(&RSVP_OPS); -} - -module_init(init_rsvp) -module_exit(exit_rsvp) diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c deleted file mode 100644 index dd08aea2aee5..000000000000 --- a/net/sched/cls_rsvp6.c +++ /dev/null @@ -1,28 +0,0 @@ -/* - * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/ipv6.h> -#include <linux/skbuff.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> -#include <net/netlink.h> - -#define RSVP_DST_LEN 4 -#define RSVP_ID "rsvp6" -#define RSVP_OPS cls_rsvp6_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c deleted file mode 100644 index 0d7a0aac8dbb..000000000000 --- a/net/sched/cls_tcindex.c +++ /dev/null @@ -1,694 +0,0 @@ -/* - * net/sched/cls_tcindex.c Packet classifier for skb->tc_index - * - * Written 1998,1999 by Werner Almesberger, EPFL ICA - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/skbuff.h> -#include <linux/errno.h> -#include <linux/slab.h> -#include <net/act_api.h> -#include <net/netlink.h> -#include <net/pkt_cls.h> -#include <net/sch_generic.h> - -/* - * Passing parameters to the root seems to be done more awkwardly than really - * necessary. At least, u32 doesn't seem to use such dirty hacks. To be - * verified. FIXME. - */ - -#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */ -#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ - - -struct tcindex_filter_result { - struct tcf_exts exts; - struct tcf_result res; - struct rcu_work rwork; -}; - -struct tcindex_filter { - u16 key; - struct tcindex_filter_result result; - struct tcindex_filter __rcu *next; - struct rcu_work rwork; -}; - - -struct tcindex_data { - struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */ - struct tcindex_filter __rcu **h; /* imperfect hash; */ - struct tcf_proto *tp; - u16 mask; /* AND key with mask */ - u32 shift; /* shift ANDed key to the right */ - u32 hash; /* hash table size; 0 if undefined */ - u32 alloc_hash; /* allocated size */ - u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_work rwork; -}; - -static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) -{ - return tcf_exts_has_actions(&r->exts) || r->res.classid; -} - -static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, - u16 key) -{ - if (p->perfect) { - struct tcindex_filter_result *f = p->perfect + key; - - return tcindex_filter_is_set(f) ? f : NULL; - } else if (p->h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *f; - - fp = &p->h[key % p->hash]; - for (f = rcu_dereference_bh_rtnl(*fp); - f; - fp = &f->next, f = rcu_dereference_bh_rtnl(*fp)) - if (f->key == key) - return &f->result; - } - - return NULL; -} - - -static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct tcindex_data *p = rcu_dereference_bh(tp->root); - struct tcindex_filter_result *f; - int key = (skb->tc_index & p->mask) >> p->shift; - - pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n", - skb, tp, res, p); - - f = tcindex_lookup(p, key); - if (!f) { - struct Qdisc *q = tcf_block_q(tp->chain->block); - - if (!p->fall_through) - return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); - res->class = 0; - pr_debug("alg 0x%x\n", res->classid); - return 0; - } - *res = f->res; - pr_debug("map 0x%x\n", res->classid); - - return tcf_exts_exec(skb, &f->exts, res); -} - - -static void *tcindex_get(struct tcf_proto *tp, u32 handle) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r; - - pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); - if (p->perfect && handle >= p->alloc_hash) - return NULL; - r = tcindex_lookup(p, handle); - return r && tcindex_filter_is_set(r) ? r : NULL; -} - -static int tcindex_init(struct tcf_proto *tp) -{ - struct tcindex_data *p; - - pr_debug("tcindex_init(tp %p)\n", tp); - p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL); - if (!p) - return -ENOMEM; - - p->mask = 0xffff; - p->hash = DEFAULT_HASH_SIZE; - p->fall_through = 1; - - rcu_assign_pointer(tp->root, p); - return 0; -} - -static void __tcindex_destroy_rexts(struct tcindex_filter_result *r) -{ - tcf_exts_destroy(&r->exts); - tcf_exts_put_net(&r->exts); -} - -static void tcindex_destroy_rexts_work(struct work_struct *work) -{ - struct tcindex_filter_result *r; - - r = container_of(to_rcu_work(work), - struct tcindex_filter_result, - rwork); - rtnl_lock(); - __tcindex_destroy_rexts(r); - rtnl_unlock(); -} - -static void __tcindex_destroy_fexts(struct tcindex_filter *f) -{ - tcf_exts_destroy(&f->result.exts); - tcf_exts_put_net(&f->result.exts); - kfree(f); -} - -static void tcindex_destroy_fexts_work(struct work_struct *work) -{ - struct tcindex_filter *f = container_of(to_rcu_work(work), - struct tcindex_filter, - rwork); - - rtnl_lock(); - __tcindex_destroy_fexts(f); - rtnl_unlock(); -} - -static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = arg; - struct tcindex_filter __rcu **walk; - struct tcindex_filter *f = NULL; - - pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p); - if (p->perfect) { - if (!r->res.class) - return -ENOENT; - } else { - int i; - - for (i = 0; i < p->hash; i++) { - walk = p->h + i; - for (f = rtnl_dereference(*walk); f; - walk = &f->next, f = rtnl_dereference(*walk)) { - if (&f->result == r) - goto found; - } - } - return -ENOENT; - -found: - rcu_assign_pointer(*walk, rtnl_dereference(f->next)); - } - tcf_unbind_filter(tp, &r->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (f) { - if (tcf_exts_get_net(&f->result.exts)) - tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work); - else - __tcindex_destroy_fexts(f); - } else { - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - - *last = false; - return 0; -} - -static void tcindex_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - kfree(p->perfect); - kfree(p->h); - kfree(p); -} - -static inline int -valid_perfect_hash(struct tcindex_data *p) -{ - return p->hash > (p->mask >> p->shift); -} - -static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { - [TCA_TCINDEX_HASH] = { .type = NLA_U32 }, - [TCA_TCINDEX_MASK] = { .type = NLA_U16 }, - [TCA_TCINDEX_SHIFT] = { .type = NLA_U32 }, - [TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 }, - [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, -}; - -static int tcindex_filter_result_init(struct tcindex_filter_result *r) -{ - memset(r, 0, sizeof(*r)); - return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); -} - -static void tcindex_partial_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - kfree(p->perfect); - kfree(p); -} - -static void tcindex_free_perfect_hash(struct tcindex_data *cp) -{ - int i; - - for (i = 0; i < cp->hash; i++) - tcf_exts_destroy(&cp->perfect[i].exts); - kfree(cp->perfect); -} - -static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) -{ - int i, err = 0; - - cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL); - if (!cp->perfect) - return -ENOMEM; - - for (i = 0; i < cp->hash; i++) { - err = tcf_exts_init(&cp->perfect[i].exts, - TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - goto errout; -#ifdef CONFIG_NET_CLS_ACT - cp->perfect[i].exts.net = net; -#endif - } - - return 0; - -errout: - tcindex_free_perfect_hash(cp); - return err; -} - -static int -tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, - u32 handle, struct tcindex_data *p, - struct tcindex_filter_result *r, struct nlattr **tb, - struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) -{ - struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_data *cp = NULL, *oldp; - struct tcindex_filter *f = NULL; /* make gcc behave */ - struct tcf_result cr = {}; - int err, balloc = 0; - struct tcf_exts e; - - err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr, extack); - if (err < 0) - goto errout; - - err = -ENOMEM; - /* tcindex_data attributes must look atomic to classifier/lookup so - * allocate new tcindex data and RCU assign it onto root. Keeping - * perfect hash and hash pointers from old data. - */ - cp = kzalloc(sizeof(*cp), GFP_KERNEL); - if (!cp) - goto errout; - - cp->mask = p->mask; - cp->shift = p->shift; - cp->hash = p->hash; - cp->alloc_hash = p->alloc_hash; - cp->fall_through = p->fall_through; - cp->tp = tp; - - if (tb[TCA_TCINDEX_HASH]) - cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); - - if (tb[TCA_TCINDEX_MASK]) - cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); - - if (tb[TCA_TCINDEX_SHIFT]) - cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); - - if (!cp->hash) { - /* Hash not specified, use perfect hash if the upper limit - * of the hashing index is below the threshold. - */ - if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) - cp->hash = (cp->mask >> cp->shift) + 1; - else - cp->hash = DEFAULT_HASH_SIZE; - } - - if (p->perfect) { - int i; - - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout; - cp->alloc_hash = cp->hash; - for (i = 0; i < min(cp->hash, p->hash); i++) - cp->perfect[i].res = p->perfect[i].res; - balloc = 1; - } - cp->h = p->h; - - err = tcindex_filter_result_init(&new_filter_result); - if (err < 0) - goto errout_alloc; - if (old_r) - cr = r->res; - - err = -EBUSY; - - /* Hash already allocated, make sure that we still meet the - * requirements for the allocated hash. - */ - if (cp->perfect) { - if (!valid_perfect_hash(cp) || - cp->hash > cp->alloc_hash) - goto errout_alloc; - } else if (cp->h && cp->hash != cp->alloc_hash) { - goto errout_alloc; - } - - err = -EINVAL; - if (tb[TCA_TCINDEX_FALL_THROUGH]) - cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - - if (!cp->perfect && !cp->h) - cp->alloc_hash = cp->hash; - - /* Note: this could be as restrictive as if (handle & ~(mask >> shift)) - * but then, we'd fail handles that may become valid after some future - * mask change. While this is extremely unlikely to ever matter, - * the check below is safer (and also more backwards-compatible). - */ - if (cp->perfect || valid_perfect_hash(cp)) - if (handle >= cp->alloc_hash) - goto errout_alloc; - - - err = -ENOMEM; - if (!cp->perfect && !cp->h) { - if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout_alloc; - balloc = 1; - } else { - struct tcindex_filter __rcu **hash; - - hash = kcalloc(cp->hash, - sizeof(struct tcindex_filter *), - GFP_KERNEL); - - if (!hash) - goto errout_alloc; - - cp->h = hash; - balloc = 2; - } - } - - if (cp->perfect) - r = cp->perfect + handle; - else - r = tcindex_lookup(cp, handle) ? : &new_filter_result; - - if (r == &new_filter_result) { - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (!f) - goto errout_alloc; - f->key = handle; - f->next = NULL; - err = tcindex_filter_result_init(&f->result); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - if (tb[TCA_TCINDEX_CLASSID]) { - cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr, base); - } - - if (old_r && old_r != r) { - err = tcindex_filter_result_init(old_r); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - oldp = p; - r->res = cr; - tcf_exts_change(&r->exts, &e); - - rcu_assign_pointer(tp->root, cp); - - if (r == &new_filter_result) { - struct tcindex_filter *nfp; - struct tcindex_filter __rcu **fp; - - f->result.res = r->res; - tcf_exts_change(&f->result.exts, &r->exts); - - fp = cp->h + (handle % cp->hash); - for (nfp = rtnl_dereference(*fp); - nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) - ; /* nothing */ - - rcu_assign_pointer(*fp, f); - } else { - tcf_exts_destroy(&new_filter_result.exts); - } - - if (oldp) - tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); - return 0; - -errout_alloc: - if (balloc == 1) - tcindex_free_perfect_hash(cp); - else if (balloc == 2) - kfree(cp->h); - tcf_exts_destroy(&new_filter_result.exts); -errout: - kfree(cp); - tcf_exts_destroy(&e); - return err; -} - -static int -tcindex_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) -{ - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = *arg; - int err; - - pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p," - "p %p,r %p,*arg %p\n", - tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL); - - if (!opt) - return 0; - - err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL); - if (err < 0) - return err; - - return tcindex_set_parms(net, tp, base, handle, p, r, tb, - tca[TCA_RATE], ovr, extack); -} - -static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter *f, *next; - int i; - - pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p); - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - if (!p->perfect[i].res.class) - continue; - if (walker->count >= walker->skip) { - if (walker->fn(tp, p->perfect + i, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } - if (!p->h) - return; - for (i = 0; i < p->hash; i++) { - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - if (walker->count >= walker->skip) { - if (walker->fn(tp, &f->result, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } -} - -static void tcindex_destroy(struct tcf_proto *tp, - struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - int i; - - pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - struct tcindex_filter_result *r = p->perfect + i; - - tcf_unbind_filter(tp, &r->res); - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, - tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - } - - for (i = 0; p->h && i < p->hash; i++) { - struct tcindex_filter *f, *next; - bool last; - - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - tcindex_delete(tp, &f->result, &last, NULL); - } - } - - tcf_queue_work(&p->rwork, tcindex_destroy_work); -} - - -static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = fh; - struct nlattr *nest; - - pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n", - tp, fh, skb, t, p, r); - pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h); - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (!fh) { - t->tcm_handle = ~0; /* whatever ... */ - if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) || - nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) || - nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) || - nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through)) - goto nla_put_failure; - nla_nest_end(skb, nest); - } else { - if (p->perfect) { - t->tcm_handle = r - p->perfect; - } else { - struct tcindex_filter *f; - struct tcindex_filter __rcu **fp; - int i; - - t->tcm_handle = 0; - for (i = 0; !t->tcm_handle && i < p->hash; i++) { - fp = &p->h[i]; - for (f = rtnl_dereference(*fp); - !t->tcm_handle && f; - fp = &f->next, f = rtnl_dereference(*fp)) { - if (&f->result == r) - t->tcm_handle = f->key; - } - } - } - pr_debug("handle = %d\n", t->tcm_handle); - if (r->res.class && - nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &r->exts) < 0) - goto nla_put_failure; - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &r->exts) < 0) - goto nla_put_failure; - } - - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl, - void *q, unsigned long base) -{ - struct tcindex_filter_result *r = fh; - - if (r && r->res.classid == classid) { - if (cl) - __tcf_bind_filter(q, &r->res, base); - else - __tcf_unbind_filter(q, &r->res); - } -} - -static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { - .kind = "tcindex", - .classify = tcindex_classify, - .init = tcindex_init, - .destroy = tcindex_destroy, - .get = tcindex_get, - .change = tcindex_change, - .delete = tcindex_delete, - .walk = tcindex_walk, - .dump = tcindex_dump, - .bind_class = tcindex_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_tcindex(void) -{ - return register_tcf_proto_ops(&cls_tcindex_ops); -} - -static void __exit exit_tcindex(void) -{ - unregister_tcf_proto_ops(&cls_tcindex_ops); -} - -module_init(init_tcindex) -module_exit(exit_tcindex) -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index fe246e03fcd9..1e71ff093c91 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -404,15 +404,20 @@ static int u32_init(struct tcf_proto *tp) return 0; } -static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, - bool free_pf) +static void __u32_destroy_key(struct tc_u_knode *n) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); tcf_exts_destroy(&n->exts); - tcf_exts_put_net(&n->exts); if (ht && --ht->refcnt == 0) kfree(ht); + kfree(n); +} + +static void u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, + bool free_pf) +{ + tcf_exts_put_net(&n->exts); #ifdef CONFIG_CLS_U32_PERF if (free_pf) free_percpu(n->pf); @@ -421,8 +426,7 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n, if (free_pf) free_percpu(n->pcpu_success); #endif - kfree(n); - return 0; + __u32_destroy_key(n); } /* u32_delete_key_rcu should be called when free'ing a copied @@ -774,11 +778,22 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, struct netlink_ext_ack *extack) { int err; +#ifdef CONFIG_NET_CLS_IND + int ifindex = -1; +#endif err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, extack); if (err < 0) return err; +#ifdef CONFIG_NET_CLS_IND + if (tb[TCA_U32_INDEV]) { + ifindex = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); + if (ifindex < 0) + return -EINVAL; + } +#endif + if (tb[TCA_U32_LINK]) { u32 handle = nla_get_u32(tb[TCA_U32_LINK]); struct tc_u_hnode *ht_down = NULL, *ht_old; @@ -810,13 +825,8 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, } #ifdef CONFIG_NET_CLS_IND - if (tb[TCA_U32_INDEV]) { - int ret; - ret = tcf_change_indev(net, tb[TCA_U32_INDEV], extack); - if (ret < 0) - return -EINVAL; - n->ifindex = ret; - } + if (ifindex >= 0) + n->ifindex = ifindex; #endif return 0; } @@ -869,14 +879,9 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, new->ifindex = n->ifindex; #endif new->fshift = n->fshift; - new->res = n->res; new->flags = n->flags; RCU_INIT_POINTER(new->ht_down, ht); - /* bump reference count as long as we hold pointer to structure */ - if (ht) - ht->refcnt++; - #ifdef CONFIG_CLS_U32_PERF /* Statistics may be incremented by readers during update * so we must keep them in tact. When the node is later destroyed @@ -899,6 +904,10 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, return NULL; } + /* bump reference count as long as we hold pointer to structure */ + if (ht) + ht->refcnt++; + return new; } @@ -965,13 +974,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, tca[TCA_RATE], ovr, extack); if (err) { - u32_destroy_key(tp, new, false); + __u32_destroy_key(new); return err; } err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { - u32_destroy_key(tp, new, false); + __u32_destroy_key(new); return err; } @@ -1057,18 +1066,62 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return -EINVAL; } + /* At this point, we need to derive the new handle that will be used to + * uniquely map the identity of this table match entry. The + * identity of the entry that we need to construct is 32 bits made of: + * htid(12b):bucketid(8b):node/entryid(12b) + * + * At this point _we have the table(ht)_ in which we will insert this + * entry. We carry the table's id in variable "htid". + * Note that earlier code picked the ht selection either by a) the user + * providing the htid specified via TCA_U32_HASH attribute or b) when + * no such attribute is passed then the root ht, is default to at ID + * 0x[800][00][000]. Rule: the root table has a single bucket with ID 0. + * If OTOH the user passed us the htid, they may also pass a bucketid of + * choice. 0 is fine. For example a user htid is 0x[600][01][000] it is + * indicating hash bucketid of 1. Rule: the entry/node ID _cannot_ be + * passed via the htid, so even if it was non-zero it will be ignored. + * + * We may also have a handle, if the user passed one. The handle also + * carries the same addressing of htid(12b):bucketid(8b):node/entryid(12b). + * Rule: the bucketid on the handle is ignored even if one was passed; + * rather the value on "htid" is always assumed to be the bucketid. + */ if (handle) { + /* Rule: The htid from handle and tableid from htid must match */ if (TC_U32_HTID(handle) && TC_U32_HTID(handle ^ htid)) { NL_SET_ERR_MSG_MOD(extack, "Handle specified hash table address mismatch"); return -EINVAL; } - handle = htid | TC_U32_NODE(handle); - err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, handle, - GFP_KERNEL); - if (err) - return err; - } else + /* Ok, so far we have a valid htid(12b):bucketid(8b) but we + * need to finalize the table entry identification with the last + * part - the node/entryid(12b)). Rule: Nodeid _cannot be 0_ for + * entries. Rule: nodeid of 0 is reserved only for tables(see + * earlier code which processes TC_U32_DIVISOR attribute). + * Rule: The nodeid can only be derived from the handle (and not + * htid). + * Rule: if the handle specified zero for the node id example + * 0x60000000, then pick a new nodeid from the pool of IDs + * this hash table has been allocating from. + * If OTOH it is specified (i.e for example the user passed a + * handle such as 0x60000123), then we use it generate our final + * handle which is used to uniquely identify the match entry. + */ + if (!TC_U32_NODE(handle)) { + handle = gen_new_kid(ht, htid); + } else { + handle = htid | TC_U32_NODE(handle); + err = idr_alloc_u32(&ht->handle_idr, NULL, &handle, + handle, GFP_KERNEL); + if (err) + return err; + } + } else { + /* The user did not give us a handle; lets just generate one + * from the table's pool of nodeids. + */ handle = gen_new_kid(ht, htid); + } if (tb[TCA_U32_SEL] == NULL) { NL_SET_ERR_MSG_MOD(extack, "Selector not specified"); diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 73e2ed576ceb..cbf44783024f 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -101,8 +101,10 @@ retry: static void em_text_destroy(struct tcf_ematch *m) { - if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) { textsearch_destroy(EM_TEXT_PRIV(m)->config); + kfree(EM_TEXT_PRIV(m)); + } } static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 113a133ee544..5ba3548d2eb7 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -259,6 +259,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * the value carried. */ if (em_hdr->flags & TCF_EM_SIMPLE) { + if (em->ops->datalen > 0) + goto errout; if (data_len < sizeof(u32)) goto errout; em->data = *(u32 *) data; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 39e319d04bb8..ab57c0ee9923 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -315,6 +315,24 @@ out: return q; } +struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) +{ + struct netdev_queue *nq; + struct Qdisc *q; + + if (!handle) + return NULL; + q = qdisc_match_from_root(dev->qdisc, handle); + if (q) + goto out; + + nq = dev_ingress_queue_rcu(dev); + if (nq) + q = qdisc_match_from_root(nq->qdisc_sleeping, handle); +out: + return q; +} + static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) { unsigned long cl; @@ -398,7 +416,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, { struct qdisc_rate_table *rtab; - if (tab == NULL || r->rate == 0 || r->cell_log == 0 || + if (tab == NULL || r->rate == 0 || + r->cell_log == 0 || r->cell_log >= 32 || nla_len(tab) != TC_RTAB_SIZE) { NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching"); return NULL; @@ -497,6 +516,12 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, return stab; } + if (s->size_log > STAB_SIZE_LOG_MAX || + s->cell_log > STAB_SIZE_LOG_MAX) { + NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); + return ERR_PTR(-EINVAL); + } + stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); @@ -921,7 +946,7 @@ static void notify_and_destroy(struct net *net, struct sk_buff *skb, qdisc_notify(net, skb, n, clid, old, new); if (old) - qdisc_destroy(old); + qdisc_put(old); } /* Graft qdisc "new" to class "classid" of qdisc "parent" or @@ -974,17 +999,18 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, qdisc_refcount_inc(new); if (!ingress) - qdisc_destroy(old); + qdisc_put(old); } skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - dev->qdisc, new); + old = dev->qdisc; if (new && !new->ops->attach) qdisc_refcount_inc(new); dev->qdisc = new ? : &noop_qdisc; + notify_and_destroy(net, skb, n, classid, old, new); + if (new && new->ops->attach) new->ops->attach(new); } else { @@ -1006,8 +1032,12 @@ skip: unsigned long cl = cops->find(parent, classid); if (cl) { - err = cops->graft(parent, cl, new, &old, - extack); + if (new && new->ops == &noqueue_qdisc_ops) { + NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); + err = -EINVAL; + } else { + err = cops->graft(parent, cl, new, &old, extack); + } } else { NL_SET_ERR_MSG(extack, "Specified class not found"); err = -ENOENT; @@ -1106,7 +1136,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, err = -ENOENT; if (!ops) { - NL_SET_ERR_MSG(extack, "Specified qdisc not found"); + NL_SET_ERR_MSG(extack, "Specified qdisc kind is unknown"); goto err_out; } @@ -1119,7 +1149,12 @@ static struct Qdisc *qdisc_create(struct net_device *dev, sch->parent = parent; if (handle == TC_H_INGRESS) { - sch->flags |= TCQ_F_INGRESS; + if (!(sch->flags & TCQ_F_INGRESS)) { + NL_SET_ERR_MSG(extack, + "Specified parent ID is reserved for ingress and clsact Qdiscs"); + err = -EINVAL; + goto err_out3; + } handle = TC_H_MAKE(TC_H_INGRESS, 0); lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { @@ -1404,10 +1439,28 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, return 0; } +static bool req_create_or_replace(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_REPLACE); +} + +static bool req_create_exclusive(struct nlmsghdr *n) +{ + return (n->nlmsg_flags & NLM_F_CREATE && + n->nlmsg_flags & NLM_F_EXCL); +} + +static bool req_change(struct nlmsghdr *n) +{ + return (!(n->nlmsg_flags & NLM_F_CREATE) && + !(n->nlmsg_flags & NLM_F_REPLACE) && + !(n->nlmsg_flags & NLM_F_EXCL)); +} + /* * Create/change qdisc. */ - static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -1480,11 +1533,20 @@ replay: NL_SET_ERR_MSG(extack, "Invalid qdisc name"); return -EINVAL; } + if (q->flags & TCQ_F_INGRESS) { + NL_SET_ERR_MSG(extack, + "Cannot regraft ingress or clsact Qdiscs"); + return -EINVAL; + } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } + if (clid == TC_H_INGRESS) { + NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); + return -EINVAL; + } qdisc_refcount_inc(q); goto graft; } else { @@ -1495,27 +1557,35 @@ replay: * * We know, that some child q is already * attached to this parent and have choice: - * either to change it or to create/graft new one. + * 1) change it or 2) create/graft new one. + * If the requested qdisc kind is different + * than the existing one, then we choose graft. + * If they are the same then this is "change" + * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only - * if CREATE and REPLACE flags are set. + * if the request is explicitly stating + * "please create if it doesn't exist". * - * 2. If EXCL is set, requestor wanted to say, - * that qdisc tcm_handle is not expected + * 2. If the request is to exclusive create + * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. + * This will happen when for example tc + * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. - * For now we select create/graft, if - * user gave KIND, which does not match existing. + * For now we select create/graft. */ - if ((n->nlmsg_flags & NLM_F_CREATE) && - (n->nlmsg_flags & NLM_F_REPLACE) && - ((n->nlmsg_flags & NLM_F_EXCL) || - (tca[TCA_KIND] && - nla_strcmp(tca[TCA_KIND], q->ops->id)))) - goto create_n_graft; + if (tca[TCA_KIND] && + nla_strcmp(tca[TCA_KIND], q->ops->id)) { + if (req_create_or_replace(n) || + req_create_exclusive(n)) + goto create_n_graft; + else if (req_change(n)) + goto create_n_graft2; + } } } } else { @@ -1549,6 +1619,7 @@ create_n_graft: NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } +create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), p, @@ -1582,7 +1653,7 @@ graft: err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) - qdisc_destroy(q); + qdisc_put(q); return err; } @@ -2047,7 +2118,7 @@ static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, - int *t_p, int s_t) + int *t_p, int s_t, bool recur) { struct Qdisc *q; int b; @@ -2058,7 +2129,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; - if (!qdisc_dev(root)) + if (!qdisc_dev(root) || !recur) return 0; if (tcm->tcm_parent) { @@ -2093,13 +2164,13 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; t = 0; - if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0) + if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, - &t, s_t) < 0) + &t, s_t, false) < 0) goto done; done: diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 91bd5c839303..ff825f40ea04 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -150,7 +150,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) pr_debug("atm_tc_put: destroying\n"); list_del_init(&flow->list); pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_destroy(flow->q); + qdisc_put(flow->q); tcf_block_put(flow->block); if (flow->sock) { pr_debug("atm_tc_put: f_count %ld\n", @@ -394,10 +394,13 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, result = tcf_classify(skb, fl, &res, true); if (result < 0) continue; + if (result == TC_ACT_SHOT) + goto done; + flow = (struct atm_flow_data *)res.class; if (!flow) flow = lookup_flow(sch, res.classid); - goto done; + goto drop; } } flow = NULL; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 32712e7dcbdc..d91665ea7b14 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -900,7 +900,7 @@ static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); - if (!tcph) + if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, @@ -924,6 +924,8 @@ static const void *cake_get_tcpopt(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -1061,6 +1063,8 @@ static bool cake_tcph_may_drop(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -1645,7 +1649,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct cake_sched_data *q = qdisc_priv(sch); int len = qdisc_pkt_len(skb); - int uninitialized_var(ret); + int ret; struct sk_buff *ack = NULL; ktime_t now = ktime_get(); struct cake_tin_data *b; @@ -2145,8 +2149,12 @@ retry: static void cake_reset(struct Qdisc *sch) { + struct cake_sched_data *q = qdisc_priv(sch); u32 c; + if (!q->tins) + return; + for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } @@ -2671,7 +2679,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) - goto nomem; + return -ENOMEM; for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; @@ -2701,10 +2709,6 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->min_netlen = ~0; q->min_adjlen = ~0; return 0; - -nomem: - cake_destroy(sch); - return -ENOMEM; } static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index ebc3c8c7e666..7f0a5d22deaf 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -236,6 +236,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) result = tcf_classify(skb, fl, &res, true); if (!fl || result < 0) goto fallback; + if (result == TC_ACT_SHOT) + return NULL; cl = (void *)res.class; if (!cl) { @@ -256,8 +258,6 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; /* fall through */ - case TC_ACT_SHOT: - return NULL; case TC_ACT_RECLASSIFY: return cbq_reclassify(skb, cl); } @@ -365,7 +365,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct cbq_sched_data *q = qdisc_priv(sch); - int uninitialized_var(ret); + int ret; struct cbq_class *cl = cbq_classify(skb, sch, &ret); #ifdef CONFIG_NET_CLS_ACT @@ -1439,7 +1439,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) WARN_ON(cl->filters); tcf_block_put(cl->block); - qdisc_destroy(cl->q); + qdisc_put(cl->q); qdisc_put_rtab(cl->R_tab); gen_kill_estimator(&cl->rate_est); if (cl != &q->link) @@ -1616,7 +1616,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); - return err; + goto failure; } if (tca[TCA_RATE]) { diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index d5e22452d597..f95dc899e989 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -452,7 +452,7 @@ static void cbs_destroy(struct Qdisc *sch) cbs_disable_offload(dev, q); if (q->qdisc) - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 63bfceeb8e3c..8b72aed77ed4 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -355,6 +355,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, struct sk_buff **old = NULL; unsigned int mask; u32 max_P; + u8 *stab; if (opt == NULL) return -EINVAL; @@ -370,8 +371,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; ctl = nla_data(tb[TCA_CHOKE_PARMS]); - - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + stab = nla_data(tb[TCA_CHOKE_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) @@ -421,7 +422,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_CHOKE_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index e0b0cf8a9939..cdebaed0f8cf 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -134,7 +134,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); return err; } @@ -153,7 +153,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl) { gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 1c2fce8c45b2..47a61689dadb 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -402,7 +402,8 @@ static void dsmark_reset(struct Qdisc *sch) struct dsmark_qdisc_data *p = qdisc_priv(sch); pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - qdisc_reset(p->q); + if (p->q) + qdisc_reset(p->q); sch->qstats.backlog = 0; sch->q.qlen = 0; } @@ -414,7 +415,7 @@ static void dsmark_destroy(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); tcf_block_put(p->block); - qdisc_destroy(p->q); + qdisc_put(p->q); if (p->mv != p->embedded) kfree(p->mv); } diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 24893d3b5d22..3697cd799767 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -152,6 +152,9 @@ int fifo_set_limit(struct Qdisc *q, unsigned int limit) if (strncmp(q->ops->id + 1, "fifo", 4) != 0) return 0; + if (!q->ops->change) + return 0; + nla = kmalloc(nla_attr_size(sizeof(struct tc_fifo_qopt)), GFP_KERNEL); if (nla) { nla->nla_type = RTM_NEWQDISC; @@ -177,7 +180,7 @@ struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, if (q) { err = fifo_set_limit(q, limit); if (err < 0) { - qdisc_destroy(q); + qdisc_put(q); q = NULL; } } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index a862d9990be7..7a4777ee0536 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -192,7 +192,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct fq_codel_sched_data *q = qdisc_priv(sch); unsigned int idx, prev_backlog, prev_qlen; struct fq_codel_flow *flow; - int uninitialized_var(ret); + int ret; unsigned int pkt_len; bool memory_limited; @@ -382,6 +382,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, { struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; + u32 quantum = 0; int err; if (!opt) @@ -399,6 +400,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->flows_cnt > 65536) return -EINVAL; } + if (tb[TCA_FQ_CODEL_QUANTUM]) { + quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); + if (quantum > FQ_CODEL_QUANTUM_MAX) { + NL_SET_ERR_MSG(extack, "Invalid quantum"); + return -EINVAL; + } + } sch_tree_lock(sch); if (tb[TCA_FQ_CODEL_TARGET]) { @@ -425,8 +433,8 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_CODEL_ECN]) q->cparams.ecn = !!nla_get_u32(tb[TCA_FQ_CODEL_ECN]); - if (tb[TCA_FQ_CODEL_QUANTUM]) - q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); + if (quantum) + q->quantum = quantum; if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index bd96fd261dba..c966dacf1130 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -397,7 +397,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = dev_tx_weight; + int quota = READ_ONCE(dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { @@ -918,7 +918,7 @@ struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, if (!ops->init || ops->init(sch, NULL, extack) == 0) return sch; - qdisc_destroy(sch); + qdisc_put(sch); return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); @@ -958,19 +958,20 @@ void qdisc_free(struct Qdisc *qdisc) kfree((char *) qdisc - qdisc->padded); } -void qdisc_destroy(struct Qdisc *qdisc) +static void qdisc_free_cb(struct rcu_head *head) +{ + struct Qdisc *q = container_of(head, struct Qdisc, rcu); + + qdisc_free(q); +} + +static void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops; struct sk_buff *skb, *tmp; - if (!qdisc) - return; ops = qdisc->ops; - if (qdisc->flags & TCQ_F_BUILTIN || - !refcount_dec_and_test(&qdisc->refcnt)) - return; - #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); @@ -995,9 +996,37 @@ void qdisc_destroy(struct Qdisc *qdisc) kfree_skb_list(skb); } - qdisc_free(qdisc); + call_rcu(&qdisc->rcu, qdisc_free_cb); } -EXPORT_SYMBOL(qdisc_destroy); + +void qdisc_put(struct Qdisc *qdisc) +{ + if (!qdisc) + return; + + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_test(&qdisc->refcnt)) + return; + + qdisc_destroy(qdisc); +} +EXPORT_SYMBOL(qdisc_put); + +/* Version of qdisc_put() that is called with rtnl mutex unlocked. + * Intended to be used as optimization, this function only takes rtnl lock if + * qdisc reference counter reached zero. + */ + +void qdisc_put_unlocked(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN || + !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) + return; + + qdisc_destroy(qdisc); + rtnl_unlock(); +} +EXPORT_SYMBOL(qdisc_put_unlocked); /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, @@ -1116,10 +1145,13 @@ static void dev_deactivate_queue(struct net_device *dev, void *_qdisc_default) { struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc); + struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { if (!(qdisc->flags & TCQ_F_BUILTIN)) set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); + + rcu_assign_pointer(dev_queue->qdisc, qdisc_default); } } @@ -1253,6 +1285,15 @@ static int qdisc_change_tx_queue_len(struct net_device *dev, return 0; } +void dev_qdisc_change_real_num_tx(struct net_device *dev, + unsigned int new_real_tx) +{ + struct Qdisc *qdisc = dev->qdisc; + + if (qdisc->ops->change_real_num_tx) + qdisc->ops->change_real_num_tx(qdisc, new_real_tx); +} + int dev_qdisc_change_tx_queue_len(struct net_device *dev) { bool up = dev->flags & IFF_UP; @@ -1306,7 +1347,7 @@ static void shutdown_scheduler_queue(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, qdisc_default); dev_queue->qdisc_sleeping = qdisc_default; - qdisc_destroy(qdisc); + qdisc_put(qdisc); } } @@ -1315,7 +1356,7 @@ void dev_shutdown(struct net_device *dev) netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); - qdisc_destroy(dev->qdisc); + qdisc_put(dev->qdisc); dev->qdisc = &noop_qdisc; WARN_ON(timer_pending(&dev->watchdog_timer)); @@ -1327,6 +1368,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, { memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; + r->mpu = conf->mpu; r->rate_bytes_ps = max_t(u64, conf->rate, rate64); r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); r->mult = 1; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 4a042abf844c..db7a91a29b59 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -357,7 +357,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; if (!q) { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3278a76f6861..e71443623d67 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -913,6 +913,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc, cl->cl_flags |= HFSC_USC; } +static void +hfsc_upgrade_rt(struct hfsc_class *cl) +{ + cl->cl_fsc = cl->cl_rsc; + rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); + cl->cl_flags |= HFSC_FSC; +} + static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { [TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) }, @@ -1073,6 +1081,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->cf_tree = RB_ROOT; sch_tree_lock(sch); + /* Check if the inner class is a misconfigured 'rt' */ + if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { + NL_SET_ERR_MSG(extack, + "Forced curve change on parent 'rt' to 'sc'"); + hfsc_upgrade_rt(parent); + } qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) @@ -1092,7 +1106,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) struct hfsc_sched *q = qdisc_priv(sch); tcf_block_put(cl->block); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); gen_kill_estimator(&cl->rate_est); if (cl != &q->root) kfree(cl); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 43c4bfe625a9..862a33b9e2e0 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1224,7 +1224,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { WARN_ON(!cl->un.leaf.q); - qdisc_destroy(cl->un.leaf.q); + qdisc_put(cl->un.leaf.q); } gen_kill_estimator(&cl->rate_est); tcf_block_put(cl->block); @@ -1425,7 +1425,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* turn parent into inner node */ qdisc_reset(parent->un.leaf.q); qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); - qdisc_destroy(parent->un.leaf.q); + qdisc_put(parent->un.leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index ce3f55259d0d..834960cc755e 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -83,6 +83,9 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + if (sch->parent != TC_H_INGRESS) + return -EOPNOTSUPP; + net_inc_ingress_queue(); mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress); @@ -98,6 +101,9 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_INGRESS) + return; + tcf_block_put_ext(q->block, sch, &q->block_info); net_dec_ingress_queue(); } @@ -130,7 +136,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -215,6 +221,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, struct net_device *dev = qdisc_dev(sch); int err; + if (sch->parent != TC_H_CLSACT) + return -EOPNOTSUPP; + net_inc_ingress_queue(); net_inc_egress_queue(); @@ -242,6 +251,9 @@ static void clsact_destroy(struct Qdisc *sch) { struct clsact_sched_data *q = qdisc_priv(sch); + if (sch->parent != TC_H_CLSACT) + return; + tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); tcf_block_put_ext(q->ingress_block, sch, &q->ingress_block_info); @@ -262,7 +274,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), - .static_flags = TCQ_F_CPUSTATS, + .static_flags = TCQ_F_INGRESS | TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index c008a316e943..0ab13a495af9 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -65,7 +65,7 @@ static void mq_destroy(struct Qdisc *sch) if (!priv->qdiscs) return; for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } @@ -119,7 +119,7 @@ static void mq_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); #ifdef CONFIG_NET_SCHED if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); @@ -130,6 +130,29 @@ static void mq_attach(struct Qdisc *sch) priv->qdiscs = NULL; } +static void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) +{ +#ifdef CONFIG_NET_SCHED + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *qdisc; + unsigned int i; + + for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + /* Only update the default qdiscs we created, + * qdiscs with handles are always hashed. + */ + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_del(qdisc); + } + for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_add(qdisc, false); + } +#endif +} + static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) { struct net_device *dev = qdisc_dev(sch); @@ -285,6 +308,7 @@ struct Qdisc_ops mq_qdisc_ops __read_mostly = { .init = mq_init, .destroy = mq_destroy, .attach = mq_attach, + .change_real_num_tx = mq_change_real_num_tx, .dump = mq_dump, .owner = THIS_MODULE, }; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 008db8d59ace..c0ab1e38e80c 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -40,7 +40,7 @@ static void mqprio_destroy(struct Qdisc *sch) for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) - qdisc_destroy(priv->qdiscs[ntx]); + qdisc_put(priv->qdiscs[ntx]); kfree(priv->qdiscs); } @@ -132,6 +132,97 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, return 0; } +static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt, + struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct mqprio_sched *priv = qdisc_priv(sch); + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int i, rem, err; + + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) { + NL_SET_ERR_MSG(extack, + "mqprio TCA_OPTIONS can only contain netlink attributes in hardware mode"); + return -EINVAL; + } + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MIN_RATE64], + "min_rate accepted only when shaper is in bw_rlimit mode"); + return -EINVAL; + } + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute type expected to be TCA_MQPRIO_MIN_RATE64"); + return -EINVAL; + } + + if (nla_len(attr) != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute TCA_MQPRIO_MIN_RATE64 expected to have 8 bytes length"); + return -EINVAL; + } + + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) { + NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MAX_RATE64], + "max_rate accepted only when shaper is in bw_rlimit mode"); + return -EINVAL; + } + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute type expected to be TCA_MQPRIO_MAX_RATE64"); + return -EINVAL; + } + + if (nla_len(attr) != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Attribute TCA_MQPRIO_MAX_RATE64 expected to have 8 bytes length"); + return -EINVAL; + } + + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -141,9 +232,6 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; - struct nlattr *tb[TCA_MQPRIO_MAX + 1]; - struct nlattr *attr; - int rem; int len; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); @@ -168,55 +256,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); if (len > 0) { - err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, - sizeof(*qopt)); - if (err < 0) + err = mqprio_parse_nlattr(sch, qopt, opt, extack); + if (err) return err; - - if (!qopt->hw) - return -EINVAL; - - if (tb[TCA_MQPRIO_MODE]) { - priv->flags |= TC_MQPRIO_F_MODE; - priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); - } - - if (tb[TCA_MQPRIO_SHAPER]) { - priv->flags |= TC_MQPRIO_F_SHAPER; - priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); - } - - if (tb[TCA_MQPRIO_MIN_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->min_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MIN_RATE; - } - - if (tb[TCA_MQPRIO_MAX_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->max_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MAX_RATE; - } } /* pre-allocate qdisc, attachment can't fail */ @@ -300,7 +342,7 @@ static void mqprio_attach(struct Qdisc *sch) qdisc = priv->qdiscs[ntx]; old = dev_graft_qdisc(qdisc->dev_queue, qdisc); if (old) - qdisc_destroy(old); + qdisc_put(old); if (ntx < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); } @@ -308,6 +350,28 @@ static void mqprio_attach(struct Qdisc *sch) priv->qdiscs = NULL; } +static void mqprio_change_real_num_tx(struct Qdisc *sch, + unsigned int new_real_tx) +{ + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *qdisc; + unsigned int i; + + for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + /* Only update the default qdiscs we created, + * qdiscs with handles are always hashed. + */ + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_del(qdisc); + } + for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_add(qdisc, false); + } +} + static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, unsigned long cl) { @@ -531,22 +595,28 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, for (i = tc.offset; i < tc.offset + tc.count; i++) { struct netdev_queue *q = netdev_get_tx_queue(dev, i); struct Qdisc *qdisc = rtnl_dereference(q->qdisc); - struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL; - struct gnet_stats_queue __percpu *cpu_qstats = NULL; spin_lock_bh(qdisc_lock(qdisc)); + if (qdisc_is_percpu_stats(qdisc)) { - cpu_bstats = qdisc->cpu_bstats; - cpu_qstats = qdisc->cpu_qstats; + qlen = qdisc_qlen_sum(qdisc); + + __gnet_stats_copy_basic(NULL, &bstats, + qdisc->cpu_bstats, + &qdisc->bstats); + __gnet_stats_copy_queue(&qstats, + qdisc->cpu_qstats, + &qdisc->qstats, + qlen); + } else { + qlen += qdisc->q.qlen; + bstats.bytes += qdisc->bstats.bytes; + bstats.packets += qdisc->bstats.packets; + qstats.backlog += qdisc->qstats.backlog; + qstats.drops += qdisc->qstats.drops; + qstats.requeues += qdisc->qstats.requeues; + qstats.overlimits += qdisc->qstats.overlimits; } - - qlen = qdisc_qlen_sum(qdisc); - __gnet_stats_copy_basic(NULL, &sch->bstats, - cpu_bstats, &qdisc->bstats); - __gnet_stats_copy_queue(&sch->qstats, - cpu_qstats, - &qdisc->qstats, - qlen); spin_unlock_bh(qdisc_lock(qdisc)); } @@ -626,6 +696,7 @@ static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { .init = mqprio_init, .destroy = mqprio_destroy, .attach = mqprio_attach, + .change_real_num_tx = mqprio_change_real_num_tx, .dump = mqprio_dump, .owner = THIS_MODULE, }; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 1df78e361ef9..1c2f9a3ab1ca 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -175,7 +175,7 @@ multiq_destroy(struct Qdisc *sch) tcf_block_put(q->block); for (band = 0; band < q->bands; band++) - qdisc_destroy(q->queues[band]); + qdisc_put(q->queues[band]); kfree(q->queues); } @@ -204,7 +204,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, q->queues[i] = &noop_qdisc; qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); - qdisc_destroy(child); + qdisc_put(child); } } @@ -228,7 +228,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog); - qdisc_destroy(old); + qdisc_put(old); } sch_tree_unlock(sch); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 014a28d8dd4f..cf93dbe3d040 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -330,7 +330,7 @@ static s64 tabledist(s64 mu, s32 sigma, /* default uniform distribution */ if (dist == NULL) - return ((rnd % (2 * sigma)) + mu) - sigma; + return ((rnd % (2 * (u32)sigma)) + mu) - sigma; t = dist->table[rnd % dist->size]; x = (sigma % NETEM_DIST_SCALE) * t; @@ -748,12 +748,10 @@ static void dist_free(struct disttable *d) * signed 16 bit values. */ -static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, - const struct nlattr *attr) +static int get_dist_table(struct disttable **tbl, const struct nlattr *attr) { size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); - spinlock_t *root_lock; struct disttable *d; int i; @@ -768,13 +766,7 @@ static int get_dist_table(struct Qdisc *sch, struct disttable **tbl, for (i = 0; i < n; i++) d->table[i] = data[i]; - root_lock = qdisc_root_sleeping_lock(sch); - - spin_lock_bh(root_lock); - swap(*tbl, d); - spin_unlock_bh(root_lock); - - dist_free(d); + *tbl = d; return 0; } @@ -787,6 +779,10 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr) q->slot_config.max_packets = INT_MAX; if (q->slot_config.max_bytes == 0) q->slot_config.max_bytes = INT_MAX; + + /* capping dist_jitter to the range acceptable by tabledist() */ + q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter)); + q->slot.packets_left = q->slot_config.max_packets; q->slot.bytes_left = q->slot_config.max_bytes; if (q->slot_config.min_delay | q->slot_config.max_delay | @@ -926,6 +922,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, { struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; + struct disttable *delay_dist = NULL; + struct disttable *slot_dist = NULL; struct tc_netem_qopt *qopt; struct clgstate old_clg; int old_loss_model = CLG_RANDOM; @@ -939,6 +937,19 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (ret < 0) return ret; + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(&delay_dist, tb[TCA_NETEM_DELAY_DIST]); + if (ret) + goto table_free; + } + + if (tb[TCA_NETEM_SLOT_DIST]) { + ret = get_dist_table(&slot_dist, tb[TCA_NETEM_SLOT_DIST]); + if (ret) + goto table_free; + } + + sch_tree_lock(sch); /* backup q->clg and q->loss_model */ old_clg = q->clg; old_loss_model = q->loss_model; @@ -947,26 +958,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); if (ret) { q->loss_model = old_loss_model; - return ret; + q->clg = old_clg; + goto unlock; } } else { q->loss_model = CLG_RANDOM; } - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, &q->delay_dist, - tb[TCA_NETEM_DELAY_DIST]); - if (ret) - goto get_table_failure; - } - - if (tb[TCA_NETEM_SLOT_DIST]) { - ret = get_dist_table(sch, &q->slot_dist, - tb[TCA_NETEM_SLOT_DIST]); - if (ret) - goto get_table_failure; - } - + if (delay_dist) + swap(q->delay_dist, delay_dist); + if (slot_dist) + swap(q->slot_dist, slot_dist); sch->limit = qopt->limit; q->latency = PSCHED_TICKS2NS(qopt->latency); @@ -1011,15 +1013,15 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_NETEM_SLOT]) get_slot(q, tb[TCA_NETEM_SLOT]); - return ret; + /* capping jitter to the range acceptable by tabledist() */ + q->jitter = min_t(s64, abs(q->jitter), INT_MAX); -get_table_failure: - /* recover clg and loss_model, in case of - * q->clg and q->loss_model were modified - * in get_loss_clg() - */ - q->clg = old_clg; - q->loss_model = old_loss_model; +unlock: + sch_tree_unlock(sch); + +table_free: + dist_free(delay_dist); + dist_free(slot_dist); return ret; } @@ -1047,7 +1049,7 @@ static void netem_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); if (q->qdisc) - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); dist_free(q->delay_dist); dist_free(q->slot_dist); } @@ -1113,9 +1115,9 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_netem_rate rate; struct tc_netem_slot slot; - qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency), + qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency), UINT_MAX); - qopt.jitter = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->jitter), + qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter), UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 5619d2eb17b6..4ddb4af61d10 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -214,7 +214,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = { .priv_size = sizeof(struct plug_sched_data), .enqueue = plug_enqueue, .dequeue = plug_dequeue, - .peek = qdisc_peek_head, + .peek = qdisc_peek_dequeued, .init = plug_init, .change = plug_change, .reset = qdisc_reset_queue, diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 1cbbd8c31405..0e6f34bd9a68 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -175,7 +175,7 @@ prio_destroy(struct Qdisc *sch) tcf_block_put(q->block); prio_offload(sch, NULL); for (prio = 0; prio < q->bands; prio++) - qdisc_destroy(q->queues[prio]); + qdisc_put(q->queues[prio]); } static int prio_tune(struct Qdisc *sch, struct nlattr *opt, @@ -205,7 +205,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, extack); if (!queues[i]) { while (i > oldbands) - qdisc_destroy(queues[--i]); + qdisc_put(queues[--i]); return -ENOMEM; } } @@ -220,7 +220,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); - qdisc_destroy(child); + qdisc_put(child); } for (i = oldbands; i < q->bands; i++) { diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index bb1a9c11fc54..4f246599734e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -387,8 +387,13 @@ static int qfq_change_agg(struct Qdisc *sch, struct qfq_class *cl, u32 weight, u32 lmax) { struct qfq_sched *q = qdisc_priv(sch); - struct qfq_aggregate *new_agg = qfq_find_agg(q, lmax, weight); + struct qfq_aggregate *new_agg; + /* 'lmax' can range from [QFQ_MIN_LMAX, pktlen + stab overhead] */ + if (lmax > (1UL << QFQ_MTU_SHIFT)) + return -EINVAL; + + new_agg = qfq_find_agg(q, lmax, weight); if (new_agg == NULL) { /* create new aggregate */ new_agg = kzalloc(sizeof(*new_agg), GFP_ATOMIC); if (new_agg == NULL) @@ -433,15 +438,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } else weight = 1; - if (tb[TCA_QFQ_LMAX]) { + if (tb[TCA_QFQ_LMAX]) lmax = nla_get_u32(tb[TCA_QFQ_LMAX]); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - } else + else lmax = psched_mtu(qdisc_dev(sch)); + if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { + pr_notice("qfq: invalid max length %u\n", lmax); + return -EINVAL; + } + inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; @@ -497,11 +503,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl->qdisc != &noop_qdisc) qdisc_hash_add(cl->qdisc, true); - sch_tree_lock(sch); - qdisc_class_hash_insert(&q->clhash, &cl->common); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); set_change_agg: sch_tree_lock(sch); @@ -519,14 +520,17 @@ set_change_agg: } if (existing) qfq_deact_rm_from_agg(q, cl); + else + qdisc_class_hash_insert(&q->clhash, &cl->common); qfq_add_to_agg(q, new_agg, cl); sch_tree_unlock(sch); + qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; destroy_class: - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); return err; } @@ -537,7 +541,7 @@ static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); - qdisc_destroy(cl->qdisc); + qdisc_put(cl->qdisc); kfree(cl); } @@ -984,10 +988,13 @@ static void qfq_update_eligible(struct qfq_sched *q) } /* Dequeue head packet of the head class in the DRR queue of the aggregate. */ -static void agg_dequeue(struct qfq_aggregate *agg, - struct qfq_class *cl, unsigned int len) +static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, + struct qfq_class *cl, unsigned int len) { - qdisc_dequeue_peeked(cl->qdisc); + struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc); + + if (!skb) + return NULL; cl->deficit -= (int) len; @@ -997,6 +1004,8 @@ static void agg_dequeue(struct qfq_aggregate *agg, cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); } + + return skb; } static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, @@ -1142,11 +1151,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) if (!skb) return NULL; - qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; + + skb = agg_dequeue(in_serv_agg, cl, len); + + if (!skb) { + sch->q.qlen++; + return NULL; + } + + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); - agg_dequeue(in_serv_agg, cl, 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. @@ -1432,10 +1448,8 @@ static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt, if (err < 0) return err; - if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES) - max_classes = QFQ_MAX_AGG_CLASSES; - else - max_classes = qdisc_dev(sch)->tx_queue_len + 1; + max_classes = min_t(u64, (u64)qdisc_dev(sch)->tx_queue_len + 1, + QFQ_MAX_AGG_CLASSES); /* max_cl_shift = floor(log_2(max_classes)) */ max_cl_shift = __fls(max_classes); q->max_agg_classes = 1<<max_cl_shift; diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 56c181c3feeb..afe0c2d689b1 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -63,6 +63,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; + unsigned int len; int ret; q->vars.qavg = red_calc_qavg(&q->parms, @@ -98,9 +99,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; } + len = qdisc_pkt_len(skb); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; @@ -181,7 +183,7 @@ static void red_destroy(struct Qdisc *sch) del_timer_sync(&q->adapt_timer); red_offload(sch, false); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static const struct nla_policy red_policy[TCA_RED_MAX + 1] = { @@ -199,6 +201,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *child = NULL; int err; u32 max_P; + u8 *stab; if (opt == NULL) return -EINVAL; @@ -214,7 +217,9 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; ctl = nla_data(tb[TCA_RED_PARMS]); - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + stab = nla_data(tb[TCA_RED_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Scell_log, stab)) return -EINVAL; if (ctl->limit > 0) { @@ -233,14 +238,14 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt, if (child) { qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; } red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_RED_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 1aa95e761671..a8ef8efa62fc 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -139,15 +139,15 @@ static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) } } -static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) +static void increment_qlen(const struct sfb_skb_cb *cb, struct sfb_sched_data *q) { u32 sfbhash; - sfbhash = sfb_hash(skb, 0); + sfbhash = cb->hashes[0]; if (sfbhash) increment_one_qlen(sfbhash, 0, q); - sfbhash = sfb_hash(skb, 1); + sfbhash = cb->hashes[1]; if (sfbhash) increment_one_qlen(sfbhash, 1, q); } @@ -285,8 +285,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct sfb_sched_data *q = qdisc_priv(sch); + unsigned int len = qdisc_pkt_len(skb); struct Qdisc *child = q->qdisc; struct tcf_proto *fl; + struct sfb_skb_cb cb; int i; u32 p_min = ~0; u32 minqlen = ~0; @@ -403,11 +405,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, } enqueue: + memcpy(&cb, sfb_skb_cb(skb), sizeof(cb)); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; - increment_qlen(skb, q); + increment_qlen(&cb, q); } else if (net_xmit_drop_count(ret)) { q->stats.childdrop++; qdisc_qstats_drop(sch); @@ -470,7 +473,7 @@ static void sfb_destroy(struct Qdisc *sch) struct sfb_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = { @@ -524,7 +527,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b89cf0971d3d..07721a1e98d8 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -353,7 +353,7 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) unsigned int hash, dropped; sfq_index x, qlen; struct sfq_slot *slot; - int uninitialized_var(ret); + int ret; struct sk_buff *head; int delta; @@ -651,7 +651,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) } if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, - ctl_v1->Wlog)) + ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6f74a426f159..dd29de1418b7 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -392,7 +392,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, if (child) { qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, q->qdisc->qstats.backlog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); q->qdisc = child; } q->limit = qopt->limit; @@ -438,7 +438,7 @@ static void tbf_destroy(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); - qdisc_destroy(q->qdisc); + qdisc_put(q->qdisc); } static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 7ed53124069c..163364124691 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -138,6 +138,9 @@ teql_destroy(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); struct teql_master *master = dat->m; + if (!master) + return; + prev = master->slaves; if (prev) { do { diff --git a/net/sctp/associola.c b/net/sctp/associola.c index d17708800652..78c1429d1301 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1181,8 +1181,7 @@ int sctp_assoc_update(struct sctp_association *asoc, /* Add any peer addresses from the new association. */ list_for_each_entry(trans, &new->peer.transport_addr_list, transports) - if (!sctp_assoc_lookup_paddr(asoc, &trans->ipaddr) && - !sctp_assoc_add_peer(asoc, &trans->ipaddr, + if (!sctp_assoc_add_peer(asoc, &trans->ipaddr, GFP_ATOMIC, trans->state)) return -ENOMEM; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 2bd8c80bd85f..9cf61a18098a 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -880,12 +880,23 @@ int sctp_auth_set_key(struct sctp_endpoint *ep, memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength); cur_key->key = key; - if (replace) { - list_del_init(&shkey->key_list); - sctp_auth_shkey_release(shkey); + if (!replace) { + list_add(&cur_key->key_list, sh_keys); + return 0; } + + list_del_init(&shkey->key_list); list_add(&cur_key->key_list, sh_keys); + if (asoc && asoc->active_key_id == auth_key->sca_keynumber && + sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) { + list_del_init(&cur_key->key_list); + sctp_auth_shkey_release(cur_key); + list_add(&shkey->key_list, sh_keys); + return -ENOMEM; + } + + sctp_auth_shkey_release(shkey); return 0; } @@ -914,8 +925,13 @@ int sctp_auth_set_active_key(struct sctp_endpoint *ep, return -EINVAL; if (asoc) { + __u16 active_key_id = asoc->active_key_id; + asoc->active_key_id = key_id; - sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL); + if (sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL)) { + asoc->active_key_id = active_key_id; + return -ENOMEM; + } } else ep->active_key_id = key_id; diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 38d01cfb313e..d723942e5e65 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -88,6 +88,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, } } + /* If somehow no addresses were found that can be used with this + * scope, it's an error. + */ + if (list_empty(&dest->address_list)) + error = -ENETUNREACH; + out: if (error) sctp_bind_addr_clean(dest); @@ -285,22 +291,19 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list, rawaddr = (union sctp_addr_param *)raw_addr_list; af = sctp_get_af_specific(param_type2af(param->type)); - if (unlikely(!af)) { + if (unlikely(!af) || + !af->from_addr_param(&addr, rawaddr, htons(port), 0)) { retval = -EINVAL; - sctp_bind_addr_clean(bp); - break; + goto out_err; } - af->from_addr_param(&addr, rawaddr, htons(port), 0); if (sctp_bind_addr_state(bp, &addr) != -1) goto next; retval = sctp_add_bind_addr(bp, &addr, sizeof(addr), SCTP_ADDR_SRC, gfp); - if (retval) { + if (retval) /* Can't finish building the list, clean up. */ - sctp_bind_addr_clean(bp); - break; - } + goto out_err; next: len = ntohs(param->length); @@ -309,6 +312,12 @@ next: } return retval; + +out_err: + if (retval) + sctp_bind_addr_clean(bp); + + return retval; } /******************************************************************** diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 8767405de9fa..5f10984bf0f5 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -76,10 +76,6 @@ static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r, r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX; r->idiag_retrans = asoc->rtx_data_chunks; r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies); - } else { - r->idiag_timer = 0; - r->idiag_retrans = 0; - r->idiag_expires = 0; } } @@ -159,13 +155,14 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, r = nlmsg_data(nlh); BUG_ON(!sk_fullsock(sk)); + r->idiag_timer = 0; + r->idiag_retrans = 0; + r->idiag_expires = 0; if (asoc) { inet_diag_msg_sctpasoc_fill(r, sk, asoc); } else { inet_diag_msg_common_fill(r, sk); r->idiag_state = sk->sk_state; - r->idiag_timer = 0; - r->idiag_retrans = 0; } if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) @@ -307,9 +304,8 @@ out: return err; } -static int sctp_sock_dump(struct sctp_transport *tsp, void *p) +static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p) { - struct sctp_endpoint *ep = tsp->asoc->ep; struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; struct sk_buff *skb = commp->skb; @@ -319,6 +315,8 @@ static int sctp_sock_dump(struct sctp_transport *tsp, void *p) int err = 0; lock_sock(sk); + if (ep != tsp->asoc->ep) + goto release; list_for_each_entry(assoc, &ep->asocs, asocs) { if (cb->args[4] < cb->args[1]) goto next; @@ -361,9 +359,8 @@ release: return err; } -static int sctp_sock_filter(struct sctp_transport *tsp, void *p) +static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p) { - struct sctp_endpoint *ep = tsp->asoc->ep; struct sctp_comm_param *commp = p; struct sock *sk = ep->base.sk; const struct inet_diag_req_v2 *r = commp->r; @@ -521,8 +518,8 @@ skip: if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE))) goto done; - sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump, - net, &pos, &commp); + sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump, + net, &pos, &commp); cb->args[2] = pos; done: diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 8640dedcf64f..c4068451b9c7 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -242,6 +242,18 @@ void sctp_endpoint_free(struct sctp_endpoint *ep) } /* Final destructor for endpoint. */ +static void sctp_endpoint_destroy_rcu(struct rcu_head *head) +{ + struct sctp_endpoint *ep = container_of(head, struct sctp_endpoint, rcu); + struct sock *sk = ep->base.sk; + + sctp_sk(sk)->ep = NULL; + sock_put(sk); + + kfree(ep); + SCTP_DBG_OBJCNT_DEC(ep); +} + static void sctp_endpoint_destroy(struct sctp_endpoint *ep) { struct sock *sk; @@ -275,18 +287,13 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) if (sctp_sk(sk)->bind_hash) sctp_put_port(sk); - sctp_sk(sk)->ep = NULL; - /* Give up our hold on the sock */ - sock_put(sk); - - kfree(ep); - SCTP_DBG_OBJCNT_DEC(ep); + call_rcu(&ep->rcu, sctp_endpoint_destroy_rcu); } /* Hold a reference to an endpoint. */ -void sctp_endpoint_hold(struct sctp_endpoint *ep) +int sctp_endpoint_hold(struct sctp_endpoint *ep) { - refcount_inc(&ep->base.refcnt); + return refcount_inc_not_zero(&ep->base.refcnt); } /* Release a reference to an endpoint and clean up if there are diff --git a/net/sctp/input.c b/net/sctp/input.c index f64d882c8698..0e2503e536ed 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -104,6 +104,7 @@ int sctp_rcv(struct sk_buff *skb) struct sctp_chunk *chunk; union sctp_addr src; union sctp_addr dest; + int bound_dev_if; int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); @@ -181,7 +182,8 @@ int sctp_rcv(struct sk_buff *skb) * If a frame arrives on an interface and the receiving socket is * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB */ - if (sk->sk_bound_dev_if && (sk->sk_bound_dev_if != af->skb_iif(skb))) { + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + if (bound_dev_if && (bound_dev_if != af->skb_iif(skb))) { if (transport) { sctp_transport_put(transport); asoc = NULL; @@ -461,7 +463,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, else { if (!mod_timer(&t->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(t); } } else { struct net *net = sock_net(sk); @@ -470,7 +472,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, "encountered!\n", __func__); if (del_timer(&t->proto_unreach_timer)) - sctp_association_put(asoc); + sctp_transport_put(t); sctp_do_sm(net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), @@ -687,7 +689,7 @@ static int sctp_rcv_ootb(struct sk_buff *skb) ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); /* Break out if chunk length is less then minimal. */ - if (ntohs(ch->length) < sizeof(_ch)) + if (!ch || ntohs(ch->length) < sizeof(_ch)) break; ch_end = offset + SCTP_PAD4(ntohs(ch->length)); @@ -1088,7 +1090,8 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, if (!af) continue; - af->from_addr_param(paddr, params.addr, sh->source, 0); + if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) + continue; asoc = __sctp_lookup_association(net, laddr, paddr, transportp); if (asoc) @@ -1124,6 +1127,9 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( union sctp_addr_param *param; union sctp_addr paddr; + if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr)) + return NULL; + /* Skip over the ADDIP header and find the Address parameter */ param = (union sctp_addr_param *)(asconf + 1); @@ -1131,7 +1137,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - af->from_addr_param(&paddr, param, peer_port, 0); + if (!af->from_addr_param(&paddr, param, peer_port, 0)) + return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); } @@ -1202,7 +1209,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; - } while (ch_end < skb_tail_pointer(skb)); + } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb)); return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 736d8ca9821b..fc82617b6076 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -542,15 +542,20 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v6_from_addr_param(union sctp_addr *addr, +static bool sctp_v6_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param)) + return false; + addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = port; addr->v6.sin6_flowinfo = 0; /* BUG */ addr->v6.sin6_addr = param->v6.addr; addr->v6.sin6_scope_id = iif; + + return true; } /* Initialize an address parameter from a sctp_addr and return the length @@ -655,8 +660,8 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (!(type & IPV6_ADDR_UNICAST)) return 0; - return sp->inet.freebind || net->ipv6.sysctl.ip_nonlocal_bind || - ipv6_chk_addr(net, in6, NULL, 0); + return ipv6_can_nonlocal_bind(net, &sp->inet) || + ipv6_chk_addr(net, in6, NULL, 0); } /* This function checks if the address is a valid address to be used for @@ -945,8 +950,7 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) net = sock_net(&opt->inet.sk); rcu_read_lock(); dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id); - if (!dev || !(opt->inet.freebind || - net->ipv6.sysctl.ip_nonlocal_bind || + if (!dev || !(ipv6_can_nonlocal_bind(net, &opt->inet) || ipv6_chk_addr(net, &addr->v6.sin6_addr, dev, 0))) { rcu_read_unlock(); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index a644292f9faf..84f79ac4b984 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -230,6 +230,12 @@ static void sctp_transport_seq_stop(struct seq_file *seq, void *v) { struct sctp_ht_iter *iter = seq->private; + if (v && v != SEQ_START_TOKEN) { + struct sctp_transport *transport = v; + + sctp_transport_put(transport); + } + sctp_transport_walk_stop(&iter->hti); } @@ -237,6 +243,12 @@ static void *sctp_transport_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sctp_ht_iter *iter = seq->private; + if (v && v != SEQ_START_TOKEN) { + struct sctp_transport *transport = v; + + sctp_transport_put(transport); + } + ++*pos; return sctp_transport_get_next(seq_file_net(seq), &iter->hti); @@ -292,8 +304,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) sk->sk_rcvbuf); seq_printf(seq, "\n"); - sctp_transport_put(transport); - return 0; } @@ -369,8 +379,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } - sctp_transport_put(transport); - return 0; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index af054f38341b..8db8209c5b61 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -268,14 +268,19 @@ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v4_from_addr_param(union sctp_addr *addr, +static bool sctp_v4_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param)) + return false; + addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); + + return true; } /* Initialize an address parameter from a sctp_addr and return the length @@ -368,7 +373,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && - !net->ipv4.sysctl_ip_nonlocal_bind) + !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; if (ipv6_only_sock(sctp_opt2sk(sp))) @@ -407,7 +412,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr) retval = SCTP_SCOPE_LINK; } else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) || ipv4_is_private_172(addr->v4.sin_addr.s_addr) || - ipv4_is_private_192(addr->v4.sin_addr.s_addr)) { + ipv4_is_private_192(addr->v4.sin_addr.s_addr) || + ipv4_is_test_198(addr->v4.sin_addr.s_addr)) { retval = SCTP_SCOPE_PRIVATE; } else { retval = SCTP_SCOPE_GLOBAL; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index ce6053be60bc..35e1fb708f4a 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2172,9 +2172,16 @@ static enum sctp_ierror sctp_verify_param(struct net *net, break; case SCTP_PARAM_SET_PRIMARY: - if (net->sctp.addip_enable) - break; - goto fallthrough; + if (!net->sctp.addip_enable) + goto fallthrough; + + if (ntohs(param.p->length) < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_paramhdr)) { + sctp_process_inv_paramlength(asoc, param.p, + chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } + break; case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ @@ -2352,11 +2359,13 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* Process the initialization parameters. */ sctp_walk_params(param, peer_init, init_hdr.params) { - if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS || - param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { + if (!src_match && + (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, - chunk->sctp_hdr->source, 0); + if (!af->from_addr_param(&addr, param.addr, + chunk->sctp_hdr->source, 0)) + continue; if (sctp_cmp_addr_exact(sctp_source(chunk), &addr)) src_match = 1; } @@ -2537,7 +2546,8 @@ static int sctp_process_param(struct sctp_association *asoc, break; do_addr_param: af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0)) + break; scope = sctp_scope(peer_addr); if (sctp_in_scope(net, &addr, scope)) if (!sctp_assoc_add_peer(asoc, &addr, gfp, SCTP_UNCONFIRMED)) @@ -2634,15 +2644,13 @@ do_addr_param: addr_param = param.v + sizeof(struct sctp_addip_param); af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - if (af == NULL) + if (!af) break; - af->from_addr_param(&addr, addr_param, - htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, + htons(asoc->peer.port), 0)) + break; - /* if the address is invalid, we can't process it. - * XXX: see spec for what to do. - */ if (!af->addr_valid(&addr, NULL, NULL)) break; @@ -3059,7 +3067,8 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, if (unlikely(!af)) return SCTP_ERROR_DNS_FAILED; - af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0)) + return SCTP_ERROR_DNS_FAILED; /* ADDIP 4.2.1 This parameter MUST NOT contain a broadcast * or multicast address. @@ -3148,7 +3157,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, * primary. */ if (af->is_any(&addr)) - memcpy(&addr.v4, sctp_source(asconf), sizeof(addr)); + memcpy(&addr, sctp_source(asconf), sizeof(addr)); if (security_sctp_bind_connect(asoc->ep->base.sk, SCTP_PARAM_SET_PRIMARY, @@ -3336,7 +3345,8 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, /* We have checked the packet before, so we do not check again. */ af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - af->from_addr_param(&addr, addr_param, htons(bp->port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(bp->port), 0)) + return; switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: @@ -3663,7 +3673,7 @@ struct sctp_chunk *sctp_make_strreset_req( outlen = (sizeof(outreq) + stream_len) * out; inlen = (sizeof(inreq) + stream_len) * in; - retval = sctp_make_reconf(asoc, outlen + inlen); + retval = sctp_make_reconf(asoc, SCTP_PAD4(outlen) + SCTP_PAD4(inlen)); if (!retval) return NULL; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 567517e44811..c4a2d647e6cc 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -434,7 +434,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) /* Try again later. */ if (!mod_timer(&transport->proto_unreach_timer, jiffies + (HZ/20))) - sctp_association_hold(asoc); + sctp_transport_hold(transport); goto out_unlock; } @@ -450,7 +450,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t) out_unlock: bh_unlock_sock(sk); - sctp_association_put(asoc); + sctp_transport_put(transport); } /* Handle the timeout of the RE-CONFIG timer. */ @@ -473,6 +473,10 @@ void sctp_generate_reconf_event(struct timer_list *t) goto out_unlock; } + /* This happens when the response arrives after the timer is triggered. */ + if (!asoc->strreset_chunk) + goto out_unlock; + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF), asoc->state, asoc->ep, asoc, @@ -1251,7 +1255,10 @@ static int sctp_side_effects(enum sctp_event event_type, default: pr_err("impossible disposition %d in state %d, event_type %d, event_id %d\n", status, state, event_type, subtype.chunk); - BUG(); + error = status; + if (error >= 0) + error = -EINVAL; + WARN_ON_ONCE(1); break; } @@ -1615,12 +1622,12 @@ static int sctp_cmd_interpreter(enum sctp_event event_type, break; case SCTP_CMD_INIT_FAILED: - sctp_cmd_init_failed(commands, asoc, cmd->obj.u32); + sctp_cmd_init_failed(commands, asoc, cmd->obj.u16); break; case SCTP_CMD_ASSOC_FAILED: sctp_cmd_assoc_failed(commands, asoc, event_type, - subtype, chunk, cmd->obj.u32); + subtype, chunk, cmd->obj.u16); break; case SCTP_CMD_INIT_COUNTER_INC: diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index a3033b74df54..8298f27e8de0 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -164,6 +164,12 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( void *arg, struct sctp_cmd_seq *commands); +static enum sctp_disposition +__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands); + /* Small helper function that checks if the chunk length * is of the appropriate length. The 'required_length' argument * is set to be the size of a specific chunk we are testing. @@ -345,6 +351,14 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the INIT chunk has a valid length. + * Normally, this would cause an ABORT with a Protocol Violation + * error, but since we don't have an association, we'll + * just discard the packet. + */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ @@ -359,14 +373,6 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); - /* Make sure that the INIT chunk has a valid length. - * Normally, this would cause an ABORT with a Protocol Violation - * error, but since we don't have an association, we'll - * just discard the packet. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* If the INIT is coming toward a closing socket, we'll send back * and ABORT. Essentially, this catches the race of INIT being * backloged to the socket at the same time as the user isses close(). @@ -712,6 +718,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, struct sock *sk; int error = 0; + if (asoc && !sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* If the packet is an OOTB packet which is temporarily on the * control endpoint, respond with an ABORT. */ @@ -726,7 +735,8 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, * in sctp_unpack_cookie(). */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); /* If the endpoint is not listening or if the number of associations * on the TCP-style socket exceed the max backlog, respond with an @@ -1495,19 +1505,16 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( if (!chunk->singleton) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the INIT chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* 3.1 A packet containing an INIT chunk MUST have a zero Verification * Tag. */ if (chunk->sctp_hdr->vtag != 0) return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); - /* Make sure that the INIT chunk has a valid length. - * In this case, we generate a protocol violation since we have - * an association established. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); /* Grab the INIT header. */ chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; @@ -1825,9 +1832,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( * its peer. */ if (sctp_state(asoc, SHUTDOWN_ACK_SENT)) { - disposition = sctp_sf_do_9_2_reshutack(net, ep, asoc, - SCTP_ST_CHUNK(chunk->chunk_hdr->type), - chunk, commands); + disposition = __sctp_sf_do_9_2_reshutack(net, ep, asoc, + SCTP_ST_CHUNK(chunk->chunk_hdr->type), + chunk, commands); if (SCTP_DISPOSITION_NOMEM == disposition) goto nomem; @@ -1856,20 +1863,35 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL()); - repl = sctp_make_cookie_ack(new_asoc, chunk); + /* Update the content of current association. */ + if (sctp_assoc_update((struct sctp_association *)asoc, new_asoc)) { + struct sctp_chunk *abort; + + abort = sctp_make_abort(asoc, NULL, sizeof(struct sctp_errhdr)); + if (abort) { + sctp_init_cause(abort, SCTP_ERROR_RSRC_LOW, 0); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + } + sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNABORTED)); + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, + SCTP_PERR(SCTP_ERROR_RSRC_LOW)); + SCTP_INC_STATS(net, SCTP_MIB_ABORTEDS); + SCTP_DEC_STATS(net, SCTP_MIB_CURRESTAB); + goto nomem; + } + + repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem; /* Report association restart to upper layer. */ ev = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_RESTART, 0, - new_asoc->c.sinit_num_ostreams, - new_asoc->c.sinit_max_instreams, + asoc->c.sinit_num_ostreams, + asoc->c.sinit_max_instreams, NULL, GFP_ATOMIC); if (!ev) goto nomem_ev; - /* Update the content of current association. */ - sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); if ((sctp_state(asoc, SHUTDOWN_PENDING) || sctp_state(asoc, SHUTDOWN_SENT)) && @@ -1933,7 +1955,8 @@ static enum sctp_disposition sctp_sf_do_dupcook_b( sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_ESTABLISHED)); - SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); + if (asoc->state < SCTP_STATE_ESTABLISHED) + SCTP_INC_STATS(net, SCTP_MIB_CURRESTAB); sctp_add_cmd_sf(commands, SCTP_CMD_HB_TIMERS_START, SCTP_NULL()); repl = sctp_make_cookie_ack(new_asoc, chunk); @@ -2140,9 +2163,11 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( * enough for the chunk header. Cookie length verification is * done later. */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) { + if (!sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); + } /* "Decode" the chunk. We have no optional parameters so we * are in good shape. @@ -2279,7 +2304,7 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2325,7 +2350,7 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2595,7 +2620,7 @@ enum sctp_disposition sctp_sf_do_9_1_abort( */ if (SCTP_ADDR_DEL == sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); if (!sctp_err_chunk_valid(chunk)) return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -2908,13 +2933,11 @@ enum sctp_disposition sctp_sf_do_9_2_shut_ctsn( * that belong to this association, it should discard the INIT chunk and * retransmit the SHUTDOWN ACK chunk. */ -enum sctp_disposition sctp_sf_do_9_2_reshutack( - struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const union sctp_subtype type, - void *arg, - struct sctp_cmd_seq *commands) +static enum sctp_disposition +__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands) { struct sctp_chunk *chunk = arg; struct sctp_chunk *reply; @@ -2948,6 +2971,26 @@ nomem: return SCTP_DISPOSITION_NOMEM; } +enum sctp_disposition +sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, void *arg, + struct sctp_cmd_seq *commands) +{ + struct sctp_chunk *chunk = arg; + + if (!chunk->singleton) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + + if (chunk->sctp_hdr->vtag != 0) + return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands); + + return __sctp_sf_do_9_2_reshutack(net, ep, asoc, type, arg, commands); +} + /* * sctp_sf_do_ecn_cwr * @@ -3561,6 +3604,9 @@ enum sctp_disposition sctp_sf_ootb(struct net *net, SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES); + if (asoc && !sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + ch = (struct sctp_chunkhdr *)chunk->chunk_hdr; do { /* Report violation if the chunk is less then minimal */ @@ -3676,12 +3722,6 @@ static enum sctp_disposition sctp_sf_shut_8_4_5( SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); - /* If the chunk length is invalid, we don't want to process - * the reset of the packet. - */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* We need to discard the rest of the packet to prevent * potential bomming attacks from additional bundled chunks. * This is documented in SCTP Threats ID. @@ -3709,6 +3749,9 @@ enum sctp_disposition sctp_sf_do_8_5_1_E_sa(struct net *net, { struct sctp_chunk *chunk = arg; + if (!sctp_vtag_verify(chunk, asoc)) + asoc = NULL; + /* Make sure that the SHUTDOWN_ACK chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, @@ -3744,6 +3787,11 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } + /* Make sure that the ASCONF ADDIP chunk has a valid length. */ + if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); + /* ADD-IP: Section 4.1.1 * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk @@ -3751,13 +3799,7 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net, * described in [I-D.ietf-tsvwg-sctp-auth]. */ if (!net->sctp.addip_noauth && !chunk->auth) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, - commands); - - /* Make sure that the ASCONF ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); hdr = (struct sctp_addiphdr *)chunk->skb->data; serial = ntohl(hdr->serial); @@ -3886,6 +3928,12 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } + /* Make sure that the ADDIP chunk has a valid length. */ + if (!sctp_chunk_length_valid(asconf_ack, + sizeof(struct sctp_addip_chunk))) + return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, + commands); + /* ADD-IP, Section 4.1.2: * This chunk MUST be sent in an authenticated way by using * the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk @@ -3893,14 +3941,7 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net, * described in [I-D.ietf-tsvwg-sctp-auth]. */ if (!net->sctp.addip_noauth && !asconf_ack->auth) - return sctp_sf_discard_chunk(net, ep, asoc, type, arg, - commands); - - /* Make sure that the ADDIP chunk has a valid length. */ - if (!sctp_chunk_length_valid(asconf_ack, - sizeof(struct sctp_addip_chunk))) - return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, - commands); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data; rcvd_serial = ntohl(addip_hdr->serial); @@ -4351,7 +4392,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, SCTP_AUTH_NEW_KEY, GFP_ATOMIC); if (!ev) - return -ENOMEM; + return SCTP_DISPOSITION_NOMEM; sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); @@ -4472,6 +4513,9 @@ enum sctp_disposition sctp_sf_discard_chunk(struct net *net, { struct sctp_chunk *chunk = arg; + if (asoc && !sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the chunk has a valid length. * Since we don't know the chunk type, we use a general * chunkhdr structure to make a comparison. @@ -4539,6 +4583,9 @@ enum sctp_disposition sctp_sf_violation(struct net *net, { struct sctp_chunk *chunk = arg; + if (!sctp_vtag_verify(chunk, asoc)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Make sure that the chunk has a valid length. */ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, @@ -6245,6 +6292,7 @@ static struct sctp_packet *sctp_ootb_pkt_new( * yet. */ switch (chunk->chunk_hdr->type) { + case SCTP_CID_INIT: case SCTP_CID_INIT_ACK: { struct sctp_initack_chunk *initack; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 4a2873f70b37..f954d3c8876d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -112,7 +112,7 @@ struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { - sctp_memory_pressure = 1; + WRITE_ONCE(sctp_memory_pressure, 1); } @@ -375,6 +375,18 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, return af; } +static void sctp_auto_asconf_init(struct sctp_sock *sp) +{ + struct net *net = sock_net(&sp->inet.sk); + + if (net->sctp.default_auto_asconf) { + spin_lock_bh(&net->sctp.addr_wq_lock); + list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); + spin_unlock_bh(&net->sctp.addr_wq_lock); + sp->do_auto_asconf = 1; + } +} + /* Bind a local address either to an endpoint or to an association. */ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) { @@ -437,8 +449,10 @@ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) } /* Refresh ephemeral port. */ - if (!bp->port) + if (!bp->port) { bp->port = inet_sk(sk)->inet_num; + sctp_auto_asconf_init(sp); + } /* Add the address to the bind address list. * Use GFP_ATOMIC since BHs will be disabled. @@ -1939,6 +1953,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) goto err; + if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { + err = -EINVAL; + goto err; + } } if (sctp_state(asoc, CLOSED)) { @@ -2560,6 +2578,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, if (trans) { trans->hbinterval = msecs_to_jiffies(params->spp_hbinterval); + sctp_transport_reset_hb_timer(trans); } else if (asoc) { asoc->hbinterval = msecs_to_jiffies(params->spp_hbinterval); @@ -4776,19 +4795,6 @@ static int sctp_init_sock(struct sock *sk) sk_sockets_allocated_inc(sk); sock_prot_inuse_add(net, sk->sk_prot, 1); - /* Nothing can fail after this block, otherwise - * sctp_destroy_sock() will be called without addr_wq_lock held - */ - if (net->sctp.default_auto_asconf) { - spin_lock(&sock_net(sk)->sctp.addr_wq_lock); - list_add_tail(&sp->auto_asconf_list, - &net->sctp.auto_asconf_splist); - sp->do_auto_asconf = 1; - spin_unlock(&sock_net(sk)->sctp.addr_wq_lock); - } else { - sp->do_auto_asconf = 0; - } - local_bh_enable(); return 0; @@ -4823,13 +4829,17 @@ static void sctp_destroy_sock(struct sock *sk) } /* Triggered when there are no references on the socket anymore */ -static void sctp_destruct_sock(struct sock *sk) +static void sctp_destruct_common(struct sock *sk) { struct sctp_sock *sp = sctp_sk(sk); /* Free up the HMAC transform. */ crypto_free_shash(sp->hmac); +} +static void sctp_destruct_sock(struct sock *sk) +{ + sctp_destruct_common(sk); inet_sock_destruct(sk); } @@ -5055,11 +5065,12 @@ int sctp_transport_lookup_process(int (*cb)(struct sctp_transport *, void *), } EXPORT_SYMBOL_GPL(sctp_transport_lookup_process); -int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *), - int (*cb_done)(struct sctp_transport *, void *), - struct net *net, int *pos, void *p) { +int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, + struct net *net, int *pos, void *p) +{ struct rhashtable_iter hti; struct sctp_transport *tsp; + struct sctp_endpoint *ep; int ret; again: @@ -5068,26 +5079,32 @@ again: tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { - ret = cb(tsp, p); - if (ret) - break; + ep = tsp->asoc->ep; + if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */ + ret = cb(ep, tsp, p); + if (ret) + break; + sctp_endpoint_put(ep); + } (*pos)++; sctp_transport_put(tsp); } sctp_transport_walk_stop(&hti); if (ret) { - if (cb_done && !cb_done(tsp, p)) { + if (cb_done && !cb_done(ep, tsp, p)) { (*pos)++; + sctp_endpoint_put(ep); sctp_transport_put(tsp); goto again; } + sctp_endpoint_put(ep); sctp_transport_put(tsp); } return ret; } -EXPORT_SYMBOL_GPL(sctp_for_each_transport); +EXPORT_SYMBOL_GPL(sctp_transport_traverse_process); /* 7.2.1 Association Status (SCTP_STATUS) @@ -5325,7 +5342,7 @@ int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, struct socket **sockp) * Set the daddr and initialize id to something more random and also * copy over any ip options. */ - sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sk); + sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); sp->pf->copy_ip_options(sk, sock->sk); /* Populate the fields of the newsk from the oldsk and migrate the @@ -8752,7 +8769,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, sctp_sk(newsk)->reuse = sp->reuse; newsk->sk_shutdown = sk->sk_shutdown; - newsk->sk_destruct = sctp_destruct_sock; + newsk->sk_destruct = sk->sk_destruct; newsk->sk_family = sk->sk_family; newsk->sk_protocol = IPPROTO_SCTP; newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; @@ -8848,6 +8865,8 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, sctp_bind_addr_dup(&newsp->ep->base.bind_addr, &oldsp->ep->base.bind_addr, GFP_KERNEL); + sctp_auto_asconf_init(newsp); + /* Move any messages in the old socket's receive queue that are for the * peeled off association to the new socket's receive queue. */ @@ -8970,11 +8989,20 @@ struct proto sctp_prot = { #if IS_ENABLED(CONFIG_IPV6) -#include <net/transp_v6.h> -static void sctp_v6_destroy_sock(struct sock *sk) +static void sctp_v6_destruct_sock(struct sock *sk) +{ + sctp_destruct_common(sk); + inet6_sock_destruct(sk); +} + +static int sctp_v6_init_sock(struct sock *sk) { - sctp_destroy_sock(sk); - inet6_destroy_sock(sk); + int ret = sctp_init_sock(sk); + + if (!ret) + sk->sk_destruct = sctp_v6_destruct_sock; + + return ret; } struct proto sctpv6_prot = { @@ -8984,8 +9012,8 @@ struct proto sctpv6_prot = { .disconnect = sctp_disconnect, .accept = sctp_accept, .ioctl = sctp_ioctl, - .init = sctp_init_sock, - .destroy = sctp_v6_destroy_sock, + .init = sctp_v6_init_sock, + .destroy = sctp_destroy_sock, .shutdown = sctp_shutdown, .setsockopt = sctp_setsockopt, .getsockopt = sctp_getsockopt, diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 0a78cdf86463..3290e6f5b6c6 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1151,7 +1151,8 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + (void *)pos <= (void *)chunk->subh.ifwdtsn_hdr->skip + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index a6c04a94b08f..3a5c0d00e96c 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -178,7 +178,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc, if (!SCTP_SO(&asoc->stream, i)->ext) continue; - ret = n->init_sid(&asoc->stream, i, GFP_KERNEL); + ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC); if (ret) goto err; } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index c0d55ed62d2e..78302e547b2b 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -148,7 +148,7 @@ void sctp_transport_free(struct sctp_transport *transport) /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) - sctp_association_put(transport->asoc); + sctp_transport_put(transport); sctp_transport_put(transport); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 26dcd02b2d0c..ad0ac657fe12 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -141,34 +141,34 @@ static int smc_release(struct socket *sock) if (!smc->use_fallback) { rc = smc_close_active(smc); - sock_set_flag(sk, SOCK_DEAD); + smc_sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; - } - - sk->sk_prot->unhash(sk); - - if (smc->clcsock) { - if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { + } else { + if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) + sock_put(sk); /* passive closing */ + if (sk->sk_state == SMC_LISTEN) { /* wake up clcsock accept */ rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } - mutex_lock(&smc->clcsock_release_lock); - sock_release(smc->clcsock); - smc->clcsock = NULL; - mutex_unlock(&smc->clcsock_release_lock); - } - if (smc->use_fallback) { - if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) - sock_put(sk); /* passive closing */ sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); } + sk->sk_prot->unhash(sk); + + if (sk->sk_state == SMC_CLOSED) { + if (smc->clcsock) { + release_sock(sk); + smc_clcsock_release(smc); + lock_sock(sk); + } + if (!smc->use_fallback) + smc_conn_free(&smc->conn); + } + /* detach socket */ sock_orphan(sk); sock->sk = NULL; - if (!smc->use_fallback && sk->sk_state == SMC_CLOSED) - smc_conn_free(&smc->conn); release_sock(sk); sock_put(sk); /* final sock_put */ @@ -852,7 +852,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) if (new_clcsock) sock_release(new_clcsock); new_sk->sk_state = SMC_CLOSED; - sock_set_flag(new_sk, SOCK_DEAD); + smc_sock_set_flag(new_sk, SOCK_DEAD); sock_put(new_sk); /* final */ *new_smc = NULL; goto out; @@ -1013,13 +1013,13 @@ static void smc_listen_out(struct smc_sock *new_smc) struct smc_sock *lsmc = new_smc->listen_smc; struct sock *newsmcsk = &new_smc->sk; - lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); if (lsmc->sk.sk_state == SMC_LISTEN) { + lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING); smc_accept_enqueue(&lsmc->sk, newsmcsk); + release_sock(&lsmc->sk); } else { /* no longer listening */ smc_close_non_accepted(newsmcsk); } - release_sock(&lsmc->sk); /* Wake up accept */ lsmc->sk.sk_data_ready(&lsmc->sk); @@ -1031,7 +1031,6 @@ static void smc_listen_out_connected(struct smc_sock *new_smc) { struct sock *newsmcsk = &new_smc->sk; - sk_refcnt_debug_inc(newsmcsk); if (newsmcsk->sk_state == SMC_INIT) newsmcsk->sk_state = SMC_ACTIVE; @@ -1216,6 +1215,9 @@ static void smc_listen_work(struct work_struct *work) int rc = 0; u8 ibport; + if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN) + return smc_listen_out_err(new_smc); + if (new_smc->use_fallback) { smc_listen_out_connected(new_smc); return; @@ -1589,8 +1591,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, static int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; + bool do_shutdown = true; struct smc_sock *smc; int rc = -EINVAL; + int old_state; int rc1 = 0; smc = smc_sk(sk); @@ -1617,7 +1621,11 @@ static int smc_shutdown(struct socket *sock, int how) } switch (how) { case SHUT_RDWR: /* shutdown in both directions */ + old_state = sk->sk_state; rc = smc_close_active(smc); + if (old_state == SMC_ACTIVE && + sk->sk_state == SMC_PEERCLOSEWAIT1) + do_shutdown = false; break; case SHUT_WR: rc = smc_close_shutdown_write(smc); @@ -1627,7 +1635,7 @@ static int smc_shutdown(struct socket *sock, int how) /* nothing more to do because peer is not involved */ break; } - if (smc->clcsock) + if (do_shutdown && smc->clcsock) rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; @@ -1644,6 +1652,9 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, struct smc_sock *smc; int val, rc; + if (level == SOL_TCP && optname == TCP_ULP) + return -EOPNOTSUPP; + smc = smc_sk(sk); /* generic setsockopts reaching us here always apply to the @@ -1665,7 +1676,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, lock_sock(sk); switch (optname) { - case TCP_ULP: case TCP_FASTOPEN: case TCP_FASTOPEN_CONNECT: case TCP_FASTOPEN_KEY: diff --git a/net/smc/smc.h b/net/smc/smc.h index adbdf195eb08..c3b0e1e3f505 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -268,4 +268,9 @@ static inline bool using_ipsec(struct smc_sock *smc) struct sock *smc_accept_dequeue(struct sock *parent, struct socket *new_sock); void smc_close_non_accepted(struct sock *sk); +static inline void smc_sock_set_flag(struct sock *sk, enum sock_flags flag) +{ + set_bit(flag, &sk->sk_flags); +} + #endif /* __SMC_H */ diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 333e4353498f..c657fd29ff5d 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -304,7 +304,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, smc->sk.sk_shutdown |= RCV_SHUTDOWN; if (smc->clcsock && smc->clcsock->sk) smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN; - sock_set_flag(&smc->sk, SOCK_DONE); + smc_sock_set_flag(&smc->sk, SOCK_DONE); sock_hold(&smc->sk); /* sock_put in close_work */ if (!schedule_work(&conn->close_work)) sock_put(&smc->sk); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index aa9a17ac1f7b..063acfbdcd89 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -162,7 +162,8 @@ static int smc_clc_prfx_set(struct socket *clcsock, goto out_rel; } /* get address to which the internal TCP socket is bound */ - kernel_getsockname(clcsock, (struct sockaddr *)&addrs); + if (kernel_getsockname(clcsock, (struct sockaddr *)&addrs) < 0) + goto out_rel; /* analyze IP specific data of net_device belonging to TCP socket */ addr6 = (struct sockaddr_in6 *)&addrs; rcu_read_lock(); diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ea2b87f29469..4ea28ec7ad13 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -21,6 +21,22 @@ #define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME (5 * HZ) +/* release the clcsock that is assigned to the smc_sock */ +void smc_clcsock_release(struct smc_sock *smc) +{ + struct socket *tcp; + + if (smc->listen_smc && current_work() != &smc->smc_listen_work) + cancel_work_sync(&smc->smc_listen_work); + mutex_lock(&smc->clcsock_release_lock); + if (smc->clcsock) { + tcp = smc->clcsock; + smc->clcsock = NULL; + sock_release(tcp); + } + mutex_unlock(&smc->clcsock_release_lock); +} + static void smc_close_cleanup_listen(struct sock *parent) { struct sock *sk; @@ -148,7 +164,7 @@ static void smc_close_active_abort(struct smc_sock *smc) break; } - sock_set_flag(sk, SOCK_DEAD); + smc_sock_set_flag(sk, SOCK_DEAD); sk->sk_state_change(sk); } @@ -167,6 +183,7 @@ int smc_close_active(struct smc_sock *smc) int old_state; long timeout; int rc = 0; + int rc1 = 0; timeout = current->flags & PF_EXITING ? 0 : sock_flag(sk, SOCK_LINGER) ? @@ -202,6 +219,15 @@ again: if (rc) break; sk->sk_state = SMC_PEERCLOSEWAIT1; + + /* actively shutdown clcsock before peer close it, + * prevent peer from entering TIME_WAIT state. + */ + if (smc->clcsock && smc->clcsock->sk) { + rc1 = kernel_sock_shutdown(smc->clcsock, + SHUT_RDWR); + rc = rc ? rc : rc1; + } } else { /* peer event has changed the state */ goto again; @@ -321,6 +347,7 @@ static void smc_close_passive_work(struct work_struct *work) close_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_cdc_conn_state_flags *rxflags; + bool release_clcsock = false; struct sock *sk = &smc->sk; int old_state; @@ -405,10 +432,15 @@ wakeup: if (old_state != sk->sk_state) { sk->sk_state_change(sk); if ((sk->sk_state == SMC_CLOSED) && - (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) + (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { smc_conn_free(conn); + if (smc->clcsock) + release_clcsock = true; + } } release_sock(sk); + if (release_clcsock) + smc_clcsock_release(smc); sock_put(sk); /* sock_hold done by schedulers of close_work */ } diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h index 19eb6a211c23..e0e3b5df25d2 100644 --- a/net/smc/smc_close.h +++ b/net/smc/smc_close.h @@ -23,5 +23,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc); int smc_close_active(struct smc_sock *smc); int smc_close_shutdown_write(struct smc_sock *smc); void smc_close_init(struct smc_sock *smc); +void smc_clcsock_release(struct smc_sock *smc); #endif /* SMC_CLOSE_H */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2c9baf8bf118..4d421407d6fc 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -321,8 +321,8 @@ void smc_conn_free(struct smc_connection *conn) } else { smc_cdc_tx_dismiss_slots(conn); } - smc_lgr_unregister_conn(conn); /* unsets conn->lgr */ smc_buf_unuse(conn, lgr); /* allow buffer reuse */ + smc_lgr_unregister_conn(conn); /* unsets conn->lgr */ if (!lgr->conns_num) smc_lgr_schedule_free_work(lgr); @@ -609,7 +609,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, !lgr->sync_err && lgr->vlan_id == vlan_id && (role == SMC_CLNT || - lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { + (lgr->conns_num < SMC_RMBS_PER_LGR_MAX && + !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) { /* link group found */ local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; @@ -708,7 +709,7 @@ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, */ static inline int smc_rmb_wnd_update_limit(int rmbe_size) { - return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); + return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); } static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, @@ -770,7 +771,7 @@ static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, return buf_desc; } -#define SMCD_DMBE_SIZES 7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ +#define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 36340912df48..a7a4e3ce211a 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -349,12 +349,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, } break; } + if (!timeo) + return -EAGAIN; if (signal_pending(current)) { read_done = sock_intr_errno(timeo); break; } - if (!timeo) - return -EAGAIN; } if (!smc_rx_data_available(conn)) { diff --git a/net/socket.c b/net/socket.c index 29169045dcfe..49ac98cfda42 100644 --- a/net/socket.c +++ b/net/socket.c @@ -90,6 +90,7 @@ #include <linux/slab.h> #include <linux/xattr.h> #include <linux/nospec.h> +#include <linux/indirect_call_wrapper.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -108,6 +109,13 @@ #include <net/busy_poll.h> #include <linux/errqueue.h> +/* proto_ops for ipv4 and ipv6 use the same {recv,send}msg function */ +#if IS_ENABLED(CONFIG_INET) +#define INDIRECT_CALL_INET4(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) +#else +#define INDIRECT_CALL_INET4(f, f1, ...) f(__VA_ARGS__) +#endif + #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; @@ -384,6 +392,18 @@ static struct file_system_type sock_fs_type = { * but we take care of internal coherence yet. */ +/** + * sock_alloc_file - Bind a &socket to a &file + * @sock: socket + * @flags: file status flags + * @dname: protocol name + * + * Returns the &file bound with @sock, implicitly storing it + * in sock->file. If dname is %NULL, sets to "". + * On failure the return is a ERR pointer (see linux/err.h). + * This function uses GFP_KERNEL internally. + */ + struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { struct file *file; @@ -424,6 +444,14 @@ static int sock_map_fd(struct socket *sock, int flags) return PTR_ERR(newfile); } +/** + * sock_from_file - Return the &socket bounded to @file. + * @file: file + * @err: pointer to an error code return + * + * On failure returns %NULL and assigns -ENOTSOCK to @err. + */ + struct socket *sock_from_file(struct file *file, int *err) { if (file->f_op == &socket_file_ops) @@ -532,11 +560,11 @@ static const struct inode_operations sockfs_inode_ops = { }; /** - * sock_alloc - allocate a socket + * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes - * NULL is returned. + * NULL is returned. This functions uses GFP_KERNEL internally. */ struct socket *sock_alloc(void) @@ -561,7 +589,7 @@ struct socket *sock_alloc(void) EXPORT_SYMBOL(sock_alloc); /** - * sock_release - close a socket + * sock_release - close a socket * @sock: socket to close * * The socket is released from the protocol stack if it has a release @@ -617,22 +645,64 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) } EXPORT_SYMBOL(__sock_tx_timestamp); +INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, + size_t)); static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { - int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg)); + int ret = INDIRECT_CALL_INET4(sock->ops->sendmsg, inet_sendmsg, sock, + msg, msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); return ret; } -int sock_sendmsg(struct socket *sock, struct msghdr *msg) +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) { int err = security_socket_sendmsg(sock, msg, msg_data_left(msg)); return err ?: sock_sendmsg_nosec(sock, msg); } + +/** + * sock_sendmsg - send a message through @sock + * @sock: socket + * @msg: message to send + * + * Sends @msg through @sock, passing through LSM. + * Returns the number of bytes sent, or an error code. + */ +int sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int save_len = msg->msg_namelen; + int ret; + + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + msg->msg_namelen = save_len; + + return ret; +} EXPORT_SYMBOL(sock_sendmsg); +/** + * kernel_sendmsg - send a message through @sock (kernel-space) + * @sock: socket + * @msg: message header + * @vec: kernel vec + * @num: vec array length + * @size: total message data size + * + * Builds the message data with @vec and sends it through @sock. + * Returns the number of bytes sent, or an error code. + */ + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { @@ -641,6 +711,19 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_sendmsg); +/** + * kernel_sendmsg_locked - send a message through @sock (kernel-space) + * @sk: sock + * @msg: message header + * @vec: output s/g array + * @num: output s/g array length + * @size: total message data size + * + * Builds the message data with @vec and sends it through @sock. + * Returns the number of bytes sent, or an error code. + * Caller must hold @sk. + */ + int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { @@ -789,12 +872,24 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, } EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops); +INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, + size_t , int )); static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { - return sock->ops->recvmsg(sock, msg, msg_data_left(msg), flags); + return INDIRECT_CALL_INET4(sock->ops->recvmsg, inet_recvmsg, sock, msg, + msg_data_left(msg), flags); } +/** + * sock_recvmsg - receive a message from @sock + * @sock: socket + * @msg: message to receive + * @flags: message flags + * + * Receives @msg from @sock, passing through LSM. Returns the total number + * of bytes received, or an error. + */ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) { int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags); @@ -804,20 +899,21 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) EXPORT_SYMBOL(sock_recvmsg); /** - * kernel_recvmsg - Receive a message from a socket (kernel space) - * @sock: The socket to receive the message from - * @msg: Received message - * @vec: Input s/g array for message data - * @num: Size of input s/g array - * @size: Number of bytes to read - * @flags: Message flags (MSG_DONTWAIT, etc...) + * kernel_recvmsg - Receive a message from a socket (kernel space) + * @sock: The socket to receive the message from + * @msg: Received message + * @vec: Input s/g array for message data + * @num: Size of input s/g array + * @size: Number of bytes to read + * @flags: Message flags (MSG_DONTWAIT, etc...) * - * On return the msg structure contains the scatter/gather array passed in the - * vec argument. The array is modified so that it consists of the unfilled - * portion of the original array. + * On return the msg structure contains the scatter/gather array passed in the + * vec argument. The array is modified so that it consists of the unfilled + * portion of the original array. * - * The returned value is the total number of bytes received, or an error. + * The returned value is the total number of bytes received, or an error. */ + int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { @@ -898,7 +994,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -965,7 +1061,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, rtnl_unlock(); if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) err = -EFAULT; - } else { + } else if (is_socket_ioctl_cmd(cmd)) { struct ifreq ifr; bool need_copyout; if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) @@ -974,6 +1070,8 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (!err && need_copyout) if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; + } else { + err = -ENOTTY; } return err; } @@ -983,12 +1081,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} -EXPORT_SYMBOL_GPL(get_net_ns); - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; @@ -1077,6 +1169,19 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) return err; } +/** + * sock_create_lite - creates a socket + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * Creates a new socket and assigns it to @res, passing through LSM. + * The new socket initialization is not complete, see kernel_accept(). + * Returns 0 or an error. On failure @res is set to %NULL. + * This function internally uses GFP_KERNEL. + */ + int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; @@ -1202,6 +1307,21 @@ call_kill: } EXPORT_SYMBOL(sock_wake_async); +/** + * __sock_create - creates a socket + * @net: net namespace + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * @kern: boolean for kernel space sockets + * + * Creates a new socket and assigns it to @res, passing through LSM. + * Returns 0 or an error. On failure @res is set to %NULL. @kern must + * be set to true if the socket resides in kernel space. + * This function internally uses GFP_KERNEL. + */ + int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { @@ -1311,12 +1431,35 @@ out_release: } EXPORT_SYMBOL(__sock_create); +/** + * sock_create - creates a socket + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * A wrapper around __sock_create(). + * Returns 0 or an error. This function internally uses GFP_KERNEL. + */ + int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } EXPORT_SYMBOL(sock_create); +/** + * sock_create_kern - creates a socket (kernel space) + * @net: net namespace + * @family: protocol family (AF_INET, ...) + * @type: communication type (SOCK_STREAM, ...) + * @protocol: protocol (0, ...) + * @res: new socket + * + * A wrapper around __sock_create(). + * Returns 0 or an error. This function internally uses GFP_KERNEL. + */ + int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { return __sock_create(net, family, type, protocol, res, 1); @@ -1507,7 +1650,7 @@ int __sys_listen(int fd, int backlog) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; + somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; @@ -1784,7 +1927,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -2112,7 +2255,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. @@ -2443,7 +2586,7 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ - sock->sk->sk_err = -err; + WRITE_ONCE(sock->sk->sk_err, -err); } out_put: fput_light(sock->file, fput_needed); @@ -2954,6 +3097,8 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct ifreq ifreq; u32 data32; + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) return -EFAULT; if (get_user(data32, &u_ifreq32->ifr_data)) @@ -3273,18 +3418,50 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, } #endif +/** + * kernel_bind - bind an address to a socket (kernel space) + * @sock: socket + * @addr: address + * @addrlen: length of address + * + * Returns 0 or an error. + */ + int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { - return sock->ops->bind(sock, addr, addrlen); + struct sockaddr_storage address; + + memcpy(&address, addr, addrlen); + + return sock->ops->bind(sock, (struct sockaddr *)&address, addrlen); } EXPORT_SYMBOL(kernel_bind); +/** + * kernel_listen - move socket to listening state (kernel space) + * @sock: socket + * @backlog: pending connections queue size + * + * Returns 0 or an error. + */ + int kernel_listen(struct socket *sock, int backlog) { return sock->ops->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); +/** + * kernel_accept - accept a connection (kernel space) + * @sock: listening socket + * @newsock: new connected socket + * @flags: flags + * + * @flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. + * If it fails, @newsock is guaranteed to be %NULL. + * Returns 0 or an error. + */ + int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; @@ -3310,25 +3487,72 @@ done: } EXPORT_SYMBOL(kernel_accept); +/** + * kernel_connect - connect a socket (kernel space) + * @sock: socket + * @addr: address + * @addrlen: address length + * @flags: flags (O_NONBLOCK, ...) + * + * For datagram sockets, @addr is the addres to which datagrams are sent + * by default, and the only address from which datagrams are received. + * For stream sockets, attempts to connect to @addr. + * Returns 0 or an error code. + */ + int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { - return sock->ops->connect(sock, addr, addrlen, flags); + struct sockaddr_storage address; + + memcpy(&address, addr, addrlen); + + return sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); +/** + * kernel_getsockname - get the address which the socket is bound (kernel space) + * @sock: socket + * @addr: address holder + * + * Fills the @addr pointer with the address which the socket is bound. + * Returns 0 or an error code. + */ + int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { return sock->ops->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); +/** + * kernel_peername - get the address which the socket is connected (kernel space) + * @sock: socket + * @addr: address holder + * + * Fills the @addr pointer with the address which the socket is connected. + * Returns 0 or an error code. + */ + int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { return sock->ops->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); +/** + * kernel_getsockopt - get a socket option (kernel space) + * @sock: socket + * @level: API level (SOL_SOCKET, ...) + * @optname: option tag + * @optval: option value + * @optlen: option length + * + * Assigns the option length to @optlen. + * Returns 0 or an error. + */ + int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen) { @@ -3351,6 +3575,17 @@ int kernel_getsockopt(struct socket *sock, int level, int optname, } EXPORT_SYMBOL(kernel_getsockopt); +/** + * kernel_setsockopt - set a socket option (kernel space) + * @sock: socket + * @level: API level (SOL_SOCKET, ...) + * @optname: option tag + * @optval: option value + * @optlen: option length + * + * Returns 0 or an error. + */ + int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen) { @@ -3371,6 +3606,17 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, } EXPORT_SYMBOL(kernel_setsockopt); +/** + * kernel_sendpage - send a &page through a socket (kernel space) + * @sock: socket + * @page: page + * @offset: page offset + * @size: total size in bytes + * @flags: flags (MSG_DONTWAIT, ...) + * + * Returns the total amount sent in bytes or an error. + */ + int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -3381,6 +3627,18 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset, } EXPORT_SYMBOL(kernel_sendpage); +/** + * kernel_sendpage_locked - send a &page through the locked sock (kernel space) + * @sk: sock + * @page: page + * @offset: page offset + * @size: total size in bytes + * @flags: flags (MSG_DONTWAIT, ...) + * + * Returns the total amount sent in bytes or an error. + * Caller must hold @sk. + */ + int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -3394,17 +3652,30 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, } EXPORT_SYMBOL(kernel_sendpage_locked); +/** + * kernel_shutdown - shut down part of a full-duplex connection (kernel space) + * @sock: socket + * @how: connection part + * + * Returns 0 or an error. + */ + int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { return sock->ops->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); -/* This routine returns the IP overhead imposed by a socket i.e. - * the length of the underlying IP header, depending on whether - * this is an IPv4 or IPv6 socket and the length from IP options turned - * on at the socket. Assumes that the caller has a lock on the socket. +/** + * kernel_sock_ip_overhead - returns the IP overhead imposed by a socket + * @sk: socket + * + * This routine returns the IP overhead imposed by a socket i.e. + * the length of the underlying IP header, depending on whether + * this is an IPv4 or IPv6 socket and the length from IP options turned + * on at the socket. Assumes that the caller has a lock on the socket. */ + u32 kernel_sock_ip_overhead(struct sock *sk) { struct inet_sock *inet; diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index 8391c2785550..7404f02702a1 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -184,7 +184,7 @@ static int rpc_parse_scope_id(struct net *net, const char *buf, scope_id = dev->ifindex; dev_put(dev); } else { - if (kstrtou32(p, 10, &scope_id) == 0) { + if (kstrtou32(p, 10, &scope_id) != 0) { kfree(p); return 0; } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 8cb7d812ccb8..c11e68539602 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -53,6 +53,7 @@ #include <linux/uaccess.h> #include <linux/hashtable.h> +#include "auth_gss_internal.h" #include "../netns.h" static const struct rpc_authops authgss_ops; @@ -147,35 +148,6 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx) clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags); } -static const void * -simple_get_bytes(const void *p, const void *end, void *res, size_t len) -{ - const void *q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - memcpy(res, p, len); - return q; -} - -static inline const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) -{ - const void *q; - unsigned int len; - - p = simple_get_bytes(p, end, &len, sizeof(len)); - if (IS_ERR(p)) - return p; - q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - dest->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(dest->data == NULL)) - return ERR_PTR(-ENOMEM); - dest->len = len; - return q; -} - static struct gss_cl_ctx * gss_cred_get_ctx(struct rpc_cred *cred) { @@ -351,7 +323,7 @@ __gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; - if (auth && pos->auth->service != auth->service) + if (pos->auth->service != auth->service) continue; refcount_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); @@ -705,6 +677,21 @@ out: return err; } +static struct gss_upcall_msg * +gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid) +{ + struct gss_upcall_msg *pos; + list_for_each_entry(pos, &pipe->in_downcall, list) { + if (!uid_eq(pos->uid, uid)) + continue; + if (!rpc_msg_is_inflight(&pos->msg)) + continue; + refcount_inc(&pos->count); + return pos; + } + return NULL; +} + #define MSG_BUF_MAXSIZE 1024 static ssize_t @@ -751,7 +738,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid, NULL); + gss_msg = gss_find_downcall(pipe, uid); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h new file mode 100644 index 000000000000..f6d9631bd9d0 --- /dev/null +++ b/net/sunrpc/auth_gss/auth_gss_internal.h @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * linux/net/sunrpc/auth_gss/auth_gss_internal.h + * + * Internal definitions for RPCSEC_GSS client authentication + * + * Copyright (c) 2000 The Regents of the University of Michigan. + * All rights reserved. + * + */ +#include <linux/err.h> +#include <linux/string.h> +#include <linux/sunrpc/xdr.h> + +static inline const void * +simple_get_bytes(const void *p, const void *end, void *res, size_t len) +{ + const void *q = (const void *)((const char *)p + len); + if (unlikely(q > end || q < p)) + return ERR_PTR(-EFAULT); + memcpy(res, p, len); + return q; +} + +static inline const void * +simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) +{ + const void *q; + unsigned int len; + + p = simple_get_bytes(p, end, &len, sizeof(len)); + if (IS_ERR(p)) + return p; + q = (const void *)((const char *)p + len); + if (unlikely(q > end || q < p)) + return ERR_PTR(-EFAULT); + if (len) { + dest->data = kmemdup(p, len, GFP_NOFS); + if (unlikely(dest->data == NULL)) + return ERR_PTR(-ENOMEM); + } else + dest->data = NULL; + dest->len = len; + return q; +} diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 7bb2514aadd9..14f2823ad6c2 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -46,6 +46,8 @@ #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/gss_krb5_enctypes.h> +#include "auth_gss_internal.h" + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH #endif @@ -187,35 +189,6 @@ get_gss_krb5_enctype(int etype) return NULL; } -static const void * -simple_get_bytes(const void *p, const void *end, void *res, int len) -{ - const void *q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - memcpy(res, p, len); - return q; -} - -static const void * -simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res) -{ - const void *q; - unsigned int len; - - p = simple_get_bytes(p, end, &len, sizeof(len)); - if (IS_ERR(p)) - return p; - q = (const void *)((const char *)p + len); - if (unlikely(q > end || q < p)) - return ERR_PTR(-EFAULT); - res->data = kmemdup(p, len, GFP_NOFS); - if (unlikely(res->data == NULL)) - return ERR_PTR(-ENOMEM); - res->len = len; - return q; -} - static inline const void * get_key(const void *p, const void *end, struct krb5_ctx *ctx, struct crypto_skcipher **res) diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 68259eec6afd..ed6b2a155f44 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1079,27 +1079,32 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, struct gssp_in_token *in_token) { struct kvec *argv = &rqstp->rq_arg.head[0]; - unsigned int page_base, length; - int pages, i, res; - size_t inlen; + unsigned int length, pgto_offs, pgfrom_offs; + int pages, i, res, pgto, pgfrom; + size_t inlen, to_offs, from_offs; res = gss_read_common_verf(gc, argv, authp, in_handle); if (res) return res; inlen = svc_getnl(argv); - if (inlen > (argv->iov_len + rqstp->rq_arg.page_len)) + if (inlen > (argv->iov_len + rqstp->rq_arg.page_len)) { + kfree(in_handle->data); return SVC_DENIED; + } pages = DIV_ROUND_UP(inlen, PAGE_SIZE); in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL); - if (!in_token->pages) + if (!in_token->pages) { + kfree(in_handle->data); return SVC_DENIED; + } in_token->page_base = 0; in_token->page_len = inlen; for (i = 0; i < pages; i++) { in_token->pages[i] = alloc_page(GFP_KERNEL); if (!in_token->pages[i]) { + kfree(in_handle->data); gss_free_in_token_pages(in_token); return SVC_DENIED; } @@ -1109,17 +1114,24 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp, memcpy(page_address(in_token->pages[0]), argv->iov_base, length); inlen -= length; - i = 1; - page_base = rqstp->rq_arg.page_base; + to_offs = length; + from_offs = rqstp->rq_arg.page_base; while (inlen) { - length = min_t(unsigned int, inlen, PAGE_SIZE); - memcpy(page_address(in_token->pages[i]), - page_address(rqstp->rq_arg.pages[i]) + page_base, + pgto = to_offs >> PAGE_SHIFT; + pgfrom = from_offs >> PAGE_SHIFT; + pgto_offs = to_offs & ~PAGE_MASK; + pgfrom_offs = from_offs & ~PAGE_MASK; + + length = min_t(unsigned int, inlen, + min_t(unsigned int, PAGE_SIZE - pgto_offs, + PAGE_SIZE - pgfrom_offs)); + memcpy(page_address(in_token->pages[pgto]) + pgto_offs, + page_address(rqstp->rq_arg.pages[pgfrom]) + pgfrom_offs, length); + to_offs += length; + from_offs += length; inlen -= length; - page_base = 0; - i++; } return 0; } @@ -1759,11 +1771,14 @@ static int svcauth_gss_release(struct svc_rqst *rqstp) { struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data; - struct rpc_gss_wire_cred *gc = &gsd->clcred; + struct rpc_gss_wire_cred *gc; struct xdr_buf *resbuf = &rqstp->rq_res; int stat = -EINVAL; struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); + if (!gsd) + goto out; + gc = &gsd->clcred; if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; /* Release can be called twice, but we only wrap once. */ @@ -1804,10 +1819,10 @@ out_err: if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; - if (gsd->rsci) + if (gsd && gsd->rsci) { cache_put(&gsd->rsci->h, sn->rsc_cache); - gsd->rsci = NULL; - + gsd->rsci = NULL; + } return stat; } @@ -1904,7 +1919,7 @@ gss_svc_init_net(struct net *net) goto out2; return 0; out2: - destroy_use_gss_proxy_proc_entry(net); + rsi_cache_destroy_net(net); out1: rsc_cache_destroy_net(net); return rv; diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 3c15a99b9700..e41427e1740d 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -69,6 +69,17 @@ static void xprt_free_allocation(struct rpc_rqst *req) kfree(req); } +static void xprt_bc_reinit_xdr_buf(struct xdr_buf *buf) +{ + buf->head[0].iov_len = PAGE_SIZE; + buf->tail[0].iov_len = 0; + buf->pages = NULL; + buf->page_len = 0; + buf->flags = 0; + buf->len = 0; + buf->buflen = PAGE_SIZE; +} + static int xprt_alloc_xdr_buf(struct xdr_buf *buf, gfp_t gfp_flags) { struct page *page; @@ -291,6 +302,9 @@ void xprt_free_bc_rqst(struct rpc_rqst *req) */ spin_lock_bh(&xprt->bc_pa_lock); if (xprt_need_to_requeue(xprt)) { + xprt_bc_reinit_xdr_buf(&req->rq_snd_buf); + xprt_bc_reinit_xdr_buf(&req->rq_rcv_buf); + req->rq_rcv_buf.len = PAGE_SIZE; list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list); xprt->bc_alloc_count++; req = NULL; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 0d7d149b1b1b..e5498253ad93 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1267,7 +1267,7 @@ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, break; default: err = -EAFNOSUPPORT; - goto out; + goto out_release; } if (err < 0) { dprintk("RPC: can't bind UDP socket (%d)\n", err); @@ -1814,9 +1814,6 @@ call_bind_status(struct rpc_task *task) status = -EOPNOTSUPP; break; } - if (task->tk_rebind_retry == 0) - break; - task->tk_rebind_retry--; rpc_delay(task, 3*HZ); goto retry_timeout; case -ETIMEDOUT: diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index e2808586c9e6..9af919364a00 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -499,10 +499,20 @@ static struct rpc_task *__rpc_find_next_queued_priority(struct rpc_wait_queue *q struct rpc_task *task; /* + * Service the privileged queue. + */ + q = &queue->tasks[RPC_NR_PRIORITY - 1]; + if (queue->maxpriority > RPC_PRIORITY_PRIVILEGED && !list_empty(q)) { + task = list_first_entry(q, struct rpc_task, u.tk_wait.list); + goto out; + } + + /* * Service a batch of tasks from a single owner. */ q = &queue->tasks[queue->priority]; - if (!list_empty(q) && --queue->nr) { + if (!list_empty(q) && queue->nr) { + queue->nr--; task = list_first_entry(q, struct rpc_task, u.tk_wait.list); goto out; } @@ -699,7 +709,6 @@ rpc_init_task_statistics(struct rpc_task *task) /* Initialize retry counters */ task->tk_garb_retry = 2; task->tk_cred_retry = 2; - task->tk_rebind_retry = 2; /* starting timestamp */ task->tk_start = ktime_get(); @@ -883,8 +892,10 @@ int rpc_malloc(struct rpc_task *task) struct rpc_buffer *buf; gfp_t gfp = GFP_NOIO | __GFP_NOWARN; + if (RPC_IS_ASYNC(task)) + gfp = GFP_NOWAIT | __GFP_NOWARN; if (RPC_IS_SWAPPER(task)) - gfp = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN; + gfp |= __GFP_MEMALLOC; size += sizeof(struct rpc_buffer); if (size <= RPC_BUFFER_MAXSIZE) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d65f8d35de87..6a606af8de81 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1146,6 +1146,22 @@ static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, .. extern void svc_tcp_prep_reply_hdr(struct svc_rqst *); +__be32 +svc_return_autherr(struct svc_rqst *rqstp, __be32 auth_err) +{ + set_bit(RQ_AUTHERR, &rqstp->rq_flags); + return auth_err; +} +EXPORT_SYMBOL_GPL(svc_return_autherr); + +static __be32 +svc_get_autherr(struct svc_rqst *rqstp, __be32 *statp) +{ + if (test_and_clear_bit(RQ_AUTHERR, &rqstp->rq_flags)) + return *statp; + return rpc_auth_ok; +} + /* * Common routine for processing the RPC request. */ @@ -1296,11 +1312,9 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) procp->pc_release(rqstp); goto dropit; } - if (*statp == rpc_autherr_badcred) { - if (procp->pc_release) - procp->pc_release(rqstp); - goto err_bad_auth; - } + auth_stat = svc_get_autherr(rqstp, statp); + if (auth_stat != rpc_auth_ok) + goto err_release_bad_auth; if (*statp == rpc_success && procp->pc_encode && !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) { dprintk("svc: failed to encode reply\n"); @@ -1330,7 +1344,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) sendit: if (svc_authorise(rqstp)) - goto close; + goto close_xprt; return 1; /* Caller can now send it */ dropit: @@ -1339,6 +1353,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) return 0; close: + svc_authorise(rqstp); +close_xprt: if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) svc_close_xprt(rqstp->rq_xprt); dprintk("svc: svc_process close\n"); @@ -1347,7 +1363,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) err_short_len: svc_printk(rqstp, "short len %zd, dropping request\n", argv->iov_len); - goto close; + goto close_xprt; err_bad_rpc: serv->sv_stats->rpcbadfmt++; @@ -1357,6 +1373,9 @@ err_bad_rpc: svc_putnl(resv, 2); goto sendit; +err_release_bad_auth: + if (procp->pc_release) + procp->pc_release(rqstp); err_bad_auth: dprintk("svc: authentication failed (%d)\n", ntohl(auth_stat)); serv->sv_stats->rpcbadauth++; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 709c082dc905..4b56b949a463 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1052,7 +1052,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st struct svc_xprt *xprt; int ret = 0; - spin_lock(&serv->sv_lock); + spin_lock_bh(&serv->sv_lock); list_for_each_entry(xprt, xprt_list, xpt_list) { if (xprt->xpt_net != net) continue; @@ -1060,7 +1060,7 @@ static int svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, st set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); } - spin_unlock(&serv->sv_lock); + spin_unlock_bh(&serv->sv_lock); return ret; } diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index d0b5a1c47a32..b5ee21d5d1f3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -757,12 +757,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) dprintk("svc: socket %p TCP (listen) state change %d\n", sk, sk->sk_state); - if (svsk) { - /* Refer to svc_setup_socket() for details. */ - rmb(); - svsk->sk_odata(sk); - } - /* * This callback may called twice when a new connection * is established as a child socket inherits everything @@ -771,15 +765,20 @@ static void svc_tcp_listen_data_ready(struct sock *sk) * when one of child sockets become ESTABLISHED. * 2) data_ready method of the child socket may be called * when it receives data before the socket is accepted. - * In case of 2, we should ignore it silently. + * In case of 2, we should ignore it silently and DO NOT + * dereference svsk. */ - if (sk->sk_state == TCP_LISTEN) { - if (svsk) { - set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); - svc_xprt_enqueue(&svsk->sk_xprt); - } else - printk("svc: socket %p: no user data\n", sk); - } + if (sk->sk_state != TCP_LISTEN) + return; + + if (svsk) { + /* Refer to svc_setup_socket() for details. */ + rmb(); + svsk->sk_odata(sk); + set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); + svc_xprt_enqueue(&svsk->sk_xprt); + } else + printk("svc: socket %p: no user data\n", sk); } /* diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 540e340e2565..7459180e992b 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -544,7 +544,11 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, */ xdr->p = (void *)p + frag2bytes; space_left = xdr->buf->buflen - xdr->buf->len; - xdr->end = (void *)p + min_t(int, space_left, PAGE_SIZE); + if (space_left - frag1bytes >= PAGE_SIZE) + xdr->end = (void *)p + PAGE_SIZE; + else + xdr->end = (void *)p + space_left - frag1bytes; + xdr->buf->page_len += frag2bytes; xdr->buf->len += nbytes; return p; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 5e7c13aa66d0..b1abf4848bbc 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -143,31 +143,64 @@ out: } EXPORT_SYMBOL_GPL(xprt_unregister_transport); +static void +xprt_class_release(const struct xprt_class *t) +{ + module_put(t->owner); +} + +static const struct xprt_class * +xprt_class_find_by_netid_locked(const char *netid) +{ + const struct xprt_class *t; + unsigned int i; + + list_for_each_entry(t, &xprt_list, list) { + for (i = 0; t->netid[i][0] != '\0'; i++) { + if (strcmp(t->netid[i], netid) != 0) + continue; + if (!try_module_get(t->owner)) + continue; + return t; + } + } + return NULL; +} + +static const struct xprt_class * +xprt_class_find_by_netid(const char *netid) +{ + const struct xprt_class *t; + + spin_lock(&xprt_list_lock); + t = xprt_class_find_by_netid_locked(netid); + if (!t) { + spin_unlock(&xprt_list_lock); + request_module("rpc%s", netid); + spin_lock(&xprt_list_lock); + t = xprt_class_find_by_netid_locked(netid); + } + spin_unlock(&xprt_list_lock); + return t; +} + /** * xprt_load_transport - load a transport implementation - * @transport_name: transport to load + * @netid: transport to load * * Returns: * 0: transport successfully loaded * -ENOENT: transport module not available */ -int xprt_load_transport(const char *transport_name) +int xprt_load_transport(const char *netid) { - struct xprt_class *t; - int result; + const struct xprt_class *t; - result = 0; - spin_lock(&xprt_list_lock); - list_for_each_entry(t, &xprt_list, list) { - if (strcmp(t->name, transport_name) == 0) { - spin_unlock(&xprt_list_lock); - goto out; - } - } - spin_unlock(&xprt_list_lock); - result = request_module("xprt%s", transport_name); -out: - return result; + t = xprt_class_find_by_netid(netid); + if (!t) + return -ENOENT; + xprt_class_release(t); + return 0; } EXPORT_SYMBOL_GPL(xprt_load_transport); @@ -1512,7 +1545,14 @@ static void xprt_destroy(struct rpc_xprt *xprt) */ wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_UNINTERRUPTIBLE); + /* + * xprt_schedule_autodisconnect() can run after XPRT_LOCKED + * is cleared. We use ->transport_lock to ensure the mod_timer() + * can only run *before* del_time_sync(), never after. + */ + spin_lock_bh(&xprt->transport_lock); del_timer_sync(&xprt->timer); + spin_unlock_bh(&xprt->transport_lock); /* * Destroy sockets etc from the system workqueue so they can diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c index 620327c01302..45c5b41ac8dc 100644 --- a/net/sunrpc/xprtrdma/module.c +++ b/net/sunrpc/xprtrdma/module.c @@ -24,6 +24,7 @@ MODULE_DESCRIPTION("RPC/RDMA Transport"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("svcrdma"); MODULE_ALIAS("xprtrdma"); +MODULE_ALIAS("rpcrdma6"); static void __exit rpc_rdma_cleanup(void) { diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index f2eaf264726b..7f9d8365c932 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -72,7 +72,7 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) /* Maximum Read list size */ maxsegs += 2; /* segment for head and tail buffers */ - size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); + size += maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); /* Minimal Read chunk size */ size += sizeof(__be32); /* segment count */ @@ -98,7 +98,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) /* Maximum Write list size */ maxsegs += 2; /* segment for head and tail buffers */ - size = sizeof(__be32); /* segment count */ + size += sizeof(__be32); /* segment count */ size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ @@ -980,6 +980,7 @@ static bool rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep) #if defined(CONFIG_SUNRPC_BACKCHANNEL) { + struct rpc_xprt *xprt = &r_xprt->rx_xprt; struct xdr_stream *xdr = &rep->rr_stream; __be32 *p; @@ -1003,6 +1004,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep) if (*p != cpu_to_be32(RPC_CALL)) return false; + /* No bc service. */ + if (xprt->bc_serv == NULL) + return false; + /* Now that we are sure this is a backchannel call, * advance to the RPC header. */ diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index d183d4aee822..cf2272a90f13 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -308,9 +308,9 @@ xprt_setup_rdma_bc(struct xprt_create *args) xprt->timeout = &xprt_rdma_bc_timeout; xprt_set_bound(xprt); xprt_set_connected(xprt); - xprt->bind_timeout = RPCRDMA_BIND_TO; - xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO; - xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO; + xprt->bind_timeout = 0; + xprt->reestablish_timeout = 0; + xprt->idle_timeout = 0; xprt->prot = XPRT_TRANSPORT_BC_RDMA; xprt->tsh_size = 0; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index aa4d19a780d7..4062cd624b26 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -639,10 +639,11 @@ static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - pageoff, remaining); - memcpy(dst, page_address(*ppages), len); + memcpy(dst, page_address(*ppages) + pageoff, len); remaining -= len; dst += len; pageoff = 0; + ppages++; } } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index f56f36b4d742..e87a79be7ef0 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -665,8 +665,10 @@ xprt_rdma_allocate(struct rpc_task *task) gfp_t flags; flags = RPCRDMA_DEF_GFP; + if (RPC_IS_ASYNC(task)) + flags = GFP_NOWAIT | __GFP_NOWARN; if (RPC_IS_SWAPPER(task)) - flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN; + flags |= __GFP_MEMALLOC; if (!rpcrdma_get_sendbuf(r_xprt, req, rqst->rq_callsize, flags)) goto out_fail; @@ -854,6 +856,7 @@ static struct xprt_class xprt_rdma = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_RDMA, .setup = xprt_setup_rdma, + .netid = { "rdma", "rdma6", "" }, }; void xprt_rdma_cleanup(void) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9dc059dea689..a0a82d9a5900 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2974,9 +2974,6 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) } xprt_set_bound(xprt); xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL); - ret = ERR_PTR(xs_local_setup_socket(transport)); - if (ret) - goto out_err; break; default: ret = ERR_PTR(-EAFNOSUPPORT); @@ -3241,6 +3238,7 @@ static struct xprt_class xs_local_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_LOCAL, .setup = xs_setup_local, + .netid = { "" }, }; static struct xprt_class xs_udp_transport = { @@ -3249,6 +3247,7 @@ static struct xprt_class xs_udp_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_UDP, .setup = xs_setup_udp, + .netid = { "udp", "udp6", "" }, }; static struct xprt_class xs_tcp_transport = { @@ -3257,6 +3256,7 @@ static struct xprt_class xs_tcp_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_TCP, .setup = xs_setup_tcp, + .netid = { "tcp", "tcp6", "" }, }; static struct xprt_class xs_bc_tcp_transport = { @@ -3265,6 +3265,7 @@ static struct xprt_class xs_bc_tcp_transport = { .owner = THIS_MODULE, .ident = XPRT_TRANSPORT_BC_TCP, .setup = xs_setup_bc_tcp, + .netid = { "" }, }; /** diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 2649a0a0d45e..4353968bc5a5 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -231,7 +231,8 @@ void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest) */ static int tipc_enable_bearer(struct net *net, const char *name, u32 disc_domain, u32 prio, - struct nlattr *attr[]) + struct nlattr *attr[], + struct netlink_ext_ack *extack) { struct tipc_net *tn = tipc_net(net); struct tipc_bearer_names b_names; @@ -242,20 +243,23 @@ static int tipc_enable_bearer(struct net *net, const char *name, int bearer_id = 0; int res = -EINVAL; char *errstr = ""; + u32 i; if (!bearer_name_validate(name, &b_names)) { - errstr = "illegal name"; - goto rejected; + NL_SET_ERR_MSG(extack, "Illegal name"); + return res; } if (prio > TIPC_MAX_LINK_PRI && prio != TIPC_MEDIA_LINK_PRI) { errstr = "illegal priority"; + NL_SET_ERR_MSG(extack, "Illegal priority"); goto rejected; } m = tipc_media_find(b_names.media_name); if (!m) { errstr = "media not registered"; + NL_SET_ERR_MSG(extack, "Media not registered"); goto rejected; } @@ -263,33 +267,43 @@ static int tipc_enable_bearer(struct net *net, const char *name, prio = m->priority; /* Check new bearer vs existing ones and find free bearer id if any */ - while (bearer_id < MAX_BEARERS) { - b = rtnl_dereference(tn->bearer_list[bearer_id]); - if (!b) - break; + bearer_id = MAX_BEARERS; + i = MAX_BEARERS; + while (i-- != 0) { + b = rtnl_dereference(tn->bearer_list[i]); + if (!b) { + bearer_id = i; + continue; + } if (!strcmp(name, b->name)) { errstr = "already enabled"; + NL_SET_ERR_MSG(extack, "Already enabled"); goto rejected; } - bearer_id++; - if (b->priority != prio) - continue; - if (++with_this_prio <= 2) - continue; - pr_warn("Bearer <%s>: already 2 bearers with priority %u\n", - name, prio); - if (prio == TIPC_MIN_LINK_PRI) { - errstr = "cannot adjust to lower"; - goto rejected; + + if (b->priority == prio && + (++with_this_prio > 2)) { + pr_warn("Bearer <%s>: already 2 bearers with priority %u\n", + name, prio); + + if (prio == TIPC_MIN_LINK_PRI) { + errstr = "cannot adjust to lower"; + NL_SET_ERR_MSG(extack, "Cannot adjust to lower"); + goto rejected; + } + + pr_warn("Bearer <%s>: trying with adjusted priority\n", + name); + prio--; + bearer_id = MAX_BEARERS; + i = MAX_BEARERS; + with_this_prio = 1; } - pr_warn("Bearer <%s>: trying with adjusted priority\n", name); - prio--; - bearer_id = 0; - with_this_prio = 1; } if (bearer_id >= MAX_BEARERS) { errstr = "max 3 bearers permitted"; + NL_SET_ERR_MSG(extack, "Max 3 bearers permitted"); goto rejected; } @@ -303,6 +317,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, if (res) { kfree(b); errstr = "failed to enable media"; + NL_SET_ERR_MSG(extack, "Failed to enable media"); goto rejected; } @@ -318,6 +333,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, if (res) { bearer_disable(net, b); errstr = "failed to create discoverer"; + NL_SET_ERR_MSG(extack, "Failed to create discoverer"); goto rejected; } @@ -795,6 +811,7 @@ int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info) bearer = tipc_bearer_find(net, name); if (!bearer) { err = -EINVAL; + NL_SET_ERR_MSG(info->extack, "Bearer not found"); goto err_out; } @@ -834,8 +851,10 @@ int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); bearer = tipc_bearer_find(net, name); - if (!bearer) + if (!bearer) { + NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; + } bearer_disable(net, bearer); @@ -893,7 +912,8 @@ int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); } - return tipc_enable_bearer(net, bearer, domain, prio, attrs); + return tipc_enable_bearer(net, bearer, domain, prio, attrs, + info->extack); } int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info) @@ -932,6 +952,7 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) b = tipc_bearer_find(net, name); if (!b) { rtnl_unlock(); + NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; } @@ -972,8 +993,10 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_BEARER_NAME]); b = tipc_bearer_find(net, name); - if (!b) + if (!b) { + NL_SET_ERR_MSG(info->extack, "Bearer not found"); return -EINVAL; + } if (attrs[TIPC_NLA_BEARER_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; @@ -992,12 +1015,18 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_WIN]) b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { - if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { + NL_SET_ERR_MSG(info->extack, + "MTU property is unsupported"); return -EINVAL; + } #ifdef CONFIG_TIPC_MEDIA_UDP if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) + (props[TIPC_NLA_PROP_MTU]))) { + NL_SET_ERR_MSG(info->extack, + "MTU value is out-of-range"); return -EINVAL; + } b->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); tipc_node_apply_property(net, b, TIPC_NLA_PROP_MTU); #endif @@ -1099,7 +1128,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) struct tipc_nl_msg msg; struct tipc_media *media; struct sk_buff *rep; - struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; @@ -1125,6 +1154,7 @@ int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); media = tipc_media_find(name); if (!media) { + NL_SET_ERR_MSG(info->extack, "Media not found"); err = -EINVAL; goto err_out; } @@ -1147,7 +1177,7 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) int err; char *name; struct tipc_media *m; - struct nlattr *attrs[TIPC_NLA_BEARER_MAX + 1]; + struct nlattr *attrs[TIPC_NLA_MEDIA_MAX + 1]; if (!info->attrs[TIPC_NLA_MEDIA]) return -EINVAL; @@ -1161,9 +1191,10 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) name = nla_data(attrs[TIPC_NLA_MEDIA_NAME]); m = tipc_media_find(name); - if (!m) + if (!m) { + NL_SET_ERR_MSG(info->extack, "Media not found"); return -EINVAL; - + } if (attrs[TIPC_NLA_MEDIA_PROP]) { struct nlattr *props[TIPC_NLA_PROP_MAX + 1]; @@ -1179,12 +1210,18 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_WIN]) m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); if (props[TIPC_NLA_PROP_MTU]) { - if (m->type_id != TIPC_MEDIA_TYPE_UDP) + if (m->type_id != TIPC_MEDIA_TYPE_UDP) { + NL_SET_ERR_MSG(info->extack, + "MTU property is unsupported"); return -EINVAL; + } #ifdef CONFIG_TIPC_MEDIA_UDP if (tipc_udp_mtu_bad(nla_get_u32 - (props[TIPC_NLA_PROP_MTU]))) + (props[TIPC_NLA_PROP_MTU]))) { + NL_SET_ERR_MSG(info->extack, + "MTU value is out-of-range"); return -EINVAL; + } m->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); #endif } diff --git a/net/tipc/core.c b/net/tipc/core.c index 49bb9fc0aa06..ce0f067d0faf 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -93,6 +93,11 @@ out_sk_rht: static void __net_exit tipc_exit_net(struct net *net) { tipc_net_stop(net); + + /* Make sure the tipc_net_finalize_work stopped + * before releasing the resources. + */ + flush_scheduled_work(); tipc_bcast_stop(net); tipc_nametbl_stop(net); tipc_sk_rht_destroy(net); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index c138d68e8a69..0436c8f2967d 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -146,8 +146,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); - bool trial = time_before(jiffies, tn->addr_trial_end); u32 self = tipc_own_addr(net); + bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) @@ -208,7 +208,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err; - skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) diff --git a/net/tipc/link.c b/net/tipc/link.c index f756b721f93e..ee4aca974622 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -914,9 +914,7 @@ void tipc_link_reset(struct tipc_link *l) int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) { - struct tipc_msg *hdr = buf_msg(skb_peek(list)); unsigned int maxwin = l->window; - int imp = msg_importance(hdr); unsigned int mtu = l->mtu; u16 ack = l->rcv_nxt - 1; u16 seqno = l->snd_nxt; @@ -925,13 +923,20 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *backlogq = &l->backlogq; struct sk_buff *skb, *_skb, **tskb; int pkt_cnt = skb_queue_len(list); + struct tipc_msg *hdr; int rc = 0; + int imp; + + if (pkt_cnt <= 0) + return 0; + hdr = buf_msg(skb_peek(list)); if (unlikely(msg_size(hdr) > mtu)) { __skb_queue_purge(list); return -EMSGSIZE; } + imp = msg_importance(hdr); /* Allow oversubscription of one data msg per source at congestion */ if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) { if (imp == TIPC_SYSTEM_IMPORTANCE) { @@ -1574,20 +1579,25 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); u16 rcv_nxt = l->rcv_nxt; - u16 dlen = msg_data_sz(hdr); + u32 dlen = msg_data_sz(hdr); int mtyp = msg_type(hdr); bool reply = msg_probe(hdr); void *data; char *if_name; int rc = 0; + if (dlen > U16_MAX) + goto exit; + if (tipc_link_is_blocked(l) || !xmitq) goto exit; if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); - skb_linearize(skb); + if (skb_linearize(skb)) + goto exit; + hdr = buf_msg(skb); data = msg_data(hdr); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 23706ee16607..0268857a3cfe 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -130,7 +130,7 @@ static void map_set(u64 *up_map, int i, unsigned int v) static int map_get(u64 up_map, int i) { - return (up_map & (1 << i)) >> i; + return (up_map & (1ULL << i)) >> i; } static struct tipc_peer *peer_prev(struct tipc_peer *peer) @@ -457,6 +457,8 @@ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, state->probing = false; /* Sanity check received domain record */ + if (new_member_cnt > MAX_MON_DOMAIN) + return; if (dlen < dom_rec_len(arrv_dom, 0)) return; if (dlen != dom_rec_len(arrv_dom, new_member_cnt)) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index b078b77620f1..0ac270444974 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -140,19 +140,14 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; + *buf = NULL; + if (skb_has_frag_list(frag) && __skb_linearize(frag)) + goto err; frag = skb_unshare(frag, GFP_ATOMIC); if (unlikely(!frag)) goto err; head = *headbuf = frag; - *buf = NULL; TIPC_SKB_CB(head)->tail = NULL; - if (skb_is_nonlinear(head)) { - skb_walk_frags(head, tail) { - TIPC_SKB_CB(head)->tail = tail; - } - } else { - skb_frag_list_init(head); - } return 0; } diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 836e629e8f4a..661bc2551a0a 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -290,7 +290,7 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i, pr_warn_ratelimited("Failed to remove binding %u,%u from %x\n", type, lower, node); } else { - pr_warn("Unrecognized name table message received\n"); + pr_warn_ratelimited("Unknown name table message received\n"); } return false; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 89993afe0fbd..059ffb8b466a 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -812,7 +812,7 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, list_for_each_entry(p, &sr->all_publ, all_publ) if (p->key == *last_key) break; - if (p->key != *last_key) + if (list_entry_is_head(p, &sr->all_publ, all_publ)) return -EPIPE; } else { p = list_first_entry(&sr->all_publ, diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 9b36163d951e..bf11d57ef3ae 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -87,7 +87,7 @@ const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { [TIPC_NLA_LINK_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_LINK_NAME] = { .type = NLA_STRING, + [TIPC_NLA_LINK_NAME] = { .type = NLA_NUL_STRING, .len = TIPC_MAX_LINK_NAME }, [TIPC_NLA_LINK_MTU] = { .type = NLA_U32 }, [TIPC_NLA_LINK_BROADCAST] = { .type = NLA_FLAG }, @@ -116,7 +116,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { const struct nla_policy tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1] = { [TIPC_NLA_BEARER_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_BEARER_NAME] = { .type = NLA_STRING, + [TIPC_NLA_BEARER_NAME] = { .type = NLA_NUL_STRING, .len = TIPC_MAX_BEARER_NAME }, [TIPC_NLA_BEARER_PROP] = { .type = NLA_NESTED }, [TIPC_NLA_BEARER_DOMAIN] = { .type = NLA_U32 } diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index f8e111218a0e..2276a0704a63 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -101,6 +101,7 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len) return -EMSGSIZE; skb_put(skb, TLV_SPACE(len)); + memset(tlv, 0, TLV_SPACE(len)); tlv->tlv_type = htons(type); tlv->tlv_len = htons(TLV_LENGTH(len)); if (len && data) @@ -671,7 +672,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg, if (err) return err; - link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]); + link_info.dest = htonl(nla_get_flag(link[TIPC_NLA_LINK_DEST])); link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP])); nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME], TIPC_MAX_LINK_NAME); @@ -865,7 +866,7 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); - if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + if (TLV_GET_DATA_LEN(msg->req) < (int)sizeof(struct tipc_name_table_query)) return -EINVAL; depth = ntohl(ntq->depth); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 16e2af3a00cc..c83eaa718369 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -388,7 +388,7 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) rc_ = tipc_sk_sock_err((sock_), timeo_); \ if (rc_) \ break; \ - prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \ + add_wait_queue(sk_sleep(sk_), &wait_); \ release_sock(sk_); \ *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \ sched_annotate_sleep(); \ @@ -453,6 +453,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sock_init_data(sock, sk); tipc_set_sk_state(sk, TIPC_OPEN); if (tipc_sk_insert(tsk)) { + sk_free(sk); pr_warn("Socket create failed; port number exhausted\n"); return -EINVAL; } @@ -1187,6 +1188,9 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); + /* Decrease the skb's refcnt as increasing in the + * function tipc_skb_peek + */ kfree_skb(__skb_dequeue(arrvq)); } spin_unlock_bh(&inputq->lock); @@ -1713,6 +1717,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, bool connected = !tipc_sk_type_connectionless(sk); struct tipc_sock *tsk = tipc_sk(sk); int rc, err, hlen, dlen, copy; + struct tipc_skb_cb *skb_cb; struct sk_buff_head xmitq; struct tipc_msg *hdr; struct sk_buff *skb; @@ -1736,6 +1741,7 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, if (unlikely(rc)) goto exit; skb = skb_peek(&sk->sk_receive_queue); + skb_cb = TIPC_SKB_CB(skb); hdr = buf_msg(skb); dlen = msg_data_sz(hdr); hlen = msg_hdr_sz(hdr); @@ -1755,18 +1761,33 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, /* Capture data if non-error msg, otherwise just set return value */ if (likely(!err)) { - copy = min_t(int, dlen, buflen); - if (unlikely(copy != dlen)) - m->msg_flags |= MSG_TRUNC; - rc = skb_copy_datagram_msg(skb, hlen, m, copy); + int offset = skb_cb->bytes_read; + + copy = min_t(int, dlen - offset, buflen); + rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); + if (unlikely(rc)) + goto exit; + if (unlikely(offset + copy < dlen)) { + if (flags & MSG_EOR) { + if (!(flags & MSG_PEEK)) + skb_cb->bytes_read = offset + copy; + } else { + m->msg_flags |= MSG_TRUNC; + skb_cb->bytes_read = 0; + } + } else { + if (flags & MSG_EOR) + m->msg_flags |= MSG_EOR; + skb_cb->bytes_read = 0; + } } else { copy = 0; rc = 0; - if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control) + if (err != TIPC_CONN_SHUTDOWN && connected && !m->msg_control) { rc = -ECONNRESET; + goto exit; + } } - if (unlikely(rc)) - goto exit; /* Mark message as group event if applicable */ if (unlikely(grp_evt)) { @@ -1789,6 +1810,9 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m, tipc_node_distr_xmit(sock_net(sk), &xmitq); } + if (skb_cb->bytes_read) + goto exit; + tsk_advance_rx_queue(sk); if (likely(!connected)) @@ -2200,7 +2224,7 @@ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, u32 dport, struct sk_buff_head *xmitq) { - unsigned long time_limit = jiffies + 2; + unsigned long time_limit = jiffies + usecs_to_jiffies(20000); struct sk_buff *skb; unsigned int lim; atomic_t *dcnt; @@ -2437,7 +2461,7 @@ static int tipc_listen(struct socket *sock, int len) static int tipc_wait_for_accept(struct socket *sock, long timeo) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); int err; /* True wake-one mechanism for incoming connections: only @@ -2446,12 +2470,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) * anymore, the common case will execute the loop only once. */ for (;;) { - prepare_to_wait_exclusive(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -2463,7 +2487,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) if (signal_pending(current)) break; } - finish_wait(sk_sleep(sk), &wait); return err; } @@ -3465,7 +3488,7 @@ static int __tipc_nl_list_sk_publ(struct sk_buff *skb, if (p->key == *last_publ) break; } - if (p->key != *last_publ) { + if (list_entry_is_head(p, &tsk->publications, binding_sock)) { /* We never set seq or call nl_dump_check_consistent() * this means that setting prev_seq here will cause the * consistence check to fail in the netlink callback diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index ec9a7137d267..d3bb19cd0ec0 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -184,7 +184,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -210,10 +210,12 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + conn_get(con); + spin_unlock_bh(&s->idr_lock); return con; } @@ -457,17 +459,24 @@ static void tipc_conn_data_ready(struct sock *sk) static void tipc_topsrv_accept(struct work_struct *work) { struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork); - struct socket *lsock = srv->listener; - struct socket *newsock; + struct socket *newsock, *lsock; struct tipc_conn *con; struct sock *newsk; int ret; + spin_lock_bh(&srv->idr_lock); + if (!srv->listener) { + spin_unlock_bh(&srv->idr_lock); + return; + } + lsock = srv->listener; + spin_unlock_bh(&srv->idr_lock); + while (1) { ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -479,11 +488,11 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); + conn_put(con); } } @@ -496,7 +505,7 @@ static void tipc_topsrv_listener_data_ready(struct sock *sk) read_lock_bh(&sk->sk_callback_lock); srv = sk->sk_user_data; - if (srv->listener) + if (srv) queue_work(srv->rcv_wq, &srv->awork); read_unlock_bh(&sk->sk_callback_lock); } @@ -575,19 +584,19 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; - *(u32 *)&sub.usr_handle = port; + *(u64 *)&sub.usr_handle = (u64)port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); - if (rc >= 0) - return true; + if (rc) + conn_put(con); + conn_put(con); - return false; + return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) @@ -671,12 +680,18 @@ static int tipc_topsrv_start(struct net *net) ret = tipc_topsrv_work_start(srv); if (ret < 0) - return ret; + goto err_start; ret = tipc_topsrv_create_listener(srv); if (ret < 0) - tipc_topsrv_work_stop(srv); + goto err_create; + + return 0; +err_create: + tipc_topsrv_work_stop(srv); +err_start: + kfree(srv); return ret; } @@ -700,8 +715,9 @@ static void tipc_topsrv_stop(struct net *net) __module_get(lsock->sk->sk_prot_creator->owner); srv->listener = NULL; spin_unlock_bh(&srv->idr_lock); - sock_release(lsock); + tipc_topsrv_work_stop(srv); + sock_release(lsock); idr_destroy(&srv->conn_idr); kfree(srv); } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 575d62130578..b290eb3ae155 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -110,13 +110,16 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx) unsigned long flags; spin_lock_irqsave(&tls_device_lock, flags); + if (unlikely(!refcount_dec_and_test(&ctx->refcount))) + goto unlock; + list_move_tail(&ctx->list, &tls_device_gc_list); /* schedule_work inside the spinlock * to make sure tls_device_down waits for that work. */ schedule_work(&tls_device_gc_work); - +unlock: spin_unlock_irqrestore(&tls_device_lock, flags); } @@ -214,8 +217,7 @@ void tls_device_sk_destruct(struct sock *sk) clean_acked_data_disable(inet_csk(sk)); } - if (refcount_dec_and_test(&tls_ctx->refcount)) - tls_device_queue_ctx_destruction(tls_ctx); + tls_device_queue_ctx_destruction(tls_ctx); } EXPORT_SYMBOL(tls_device_sk_destruct); @@ -351,13 +353,13 @@ static int tls_push_data(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx); int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; - int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); struct tls_record_info *record = ctx->open_record; struct page_frag *pfrag; size_t orig_size = size; u32 max_open_record_len; - int copy, rc = 0; + bool more = false; bool done = false; + int copy, rc = 0; long timeo; if (flags & @@ -422,9 +424,8 @@ handle_error: if (!size) { last_record: tls_push_record_flags = flags; - if (more) { - tls_ctx->pending_open_record_frags = - record->num_frags; + if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) { + more = true; break; } @@ -445,6 +446,8 @@ last_record: } } while (!done); + tls_ctx->pending_open_record_frags = more; + if (orig_size - size > 0) rc = orig_size - size; @@ -954,6 +957,8 @@ void tls_device_offload_cleanup_rx(struct sock *sk) if (tls_ctx->tx_conf != TLS_HW) { dev_put(netdev); tls_ctx->netdev = NULL; + } else { + set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags); } out: up_read(&device_offload_lock); @@ -983,7 +988,8 @@ static int tls_device_down(struct net_device *netdev) if (ctx->tx_conf == TLS_HW) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_TX); - if (ctx->rx_conf == TLS_HW) + if (ctx->rx_conf == TLS_HW && + !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags)) netdev->tlsdev_ops->tls_dev_del(netdev, ctx, TLS_OFFLOAD_CTX_DIR_RX); WRITE_ONCE(ctx->netdev, NULL); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bbb2da70e870..7d761244a360 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -630,6 +630,12 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return NULL; } + if (!skb_queue_empty(&sk->sk_receive_queue)) { + __strp_unpause(&ctx->strp); + if (ctx->recv_pkt) + return ctx->recv_pkt; + } + if (sk->sk_shutdown & RCV_SHUTDOWN) return NULL; diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 8b31ab85d050..3b9e450656a4 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -19,6 +19,11 @@ config UNIX Say Y unless you know what you are doing. +config UNIX_SCM + bool + depends on UNIX + default y + config UNIX_DIAG tristate "UNIX: socket monitoring interface" depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index ffd0a275c3a7..54e58cc4f945 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -10,3 +10,5 @@ unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o + +obj-$(CONFIG_UNIX_SCM) += scm.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2020306468af..0632b494d329 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -119,6 +119,8 @@ #include <linux/freezer.h> #include <linux/file.h> +#include "scm.h" + struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; EXPORT_SYMBOL_GPL(unix_socket_table); DEFINE_SPINLOCK(unix_table_lock); @@ -443,7 +445,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other) * -ECONNREFUSED. Otherwise, if we haven't queued any skbs * to other and its full, we will hang waiting for POLLOUT. */ - if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD)) + if (unix_recvq_full_lockless(other) && !sock_flag(other, SOCK_DEAD)) return 1; if (connected) @@ -534,23 +536,25 @@ static void unix_release_sock(struct sock *sk, int embrion) /* Clear state */ unix_state_lock(sk); sock_orphan(sk); - sk->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); path = u->path; u->path.dentry = NULL; u->path.mnt = NULL; state = sk->sk_state; sk->sk_state = TCP_CLOSE; + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; + unix_state_unlock(sk); wake_up_interruptible_all(&u->peer_wait); - skpair = unix_peer(sk); - if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); /* No more writes */ - skpair->sk_shutdown = SHUTDOWN_MASK; + WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); if (!skb_queue_empty(&sk->sk_receive_queue) || embrion) skpair->sk_err = ECONNRESET; unix_state_unlock(skpair); @@ -560,7 +564,6 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ - unix_peer(sk) = NULL; } /* Try to flush out this socket. Throw out buffers at least */ @@ -591,26 +594,48 @@ static void unix_release_sock(struct sock *sk, int embrion) * What the above comment does talk about? --ANK(980817) */ - if (unix_tot_inflight) + if (READ_ONCE(unix_tot_inflight)) unix_gc(); /* Garbage collect fds */ } static void init_peercred(struct sock *sk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + spin_lock(&sk->sk_peer_lock); + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(task_tgid(current)); sk->sk_peer_cred = get_current_cred(); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static void copy_peercred(struct sock *sk, struct sock *peersk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + if (sk < peersk) { + spin_lock(&sk->sk_peer_lock); + spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&peersk->sk_peer_lock); + spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); + + spin_unlock(&sk->sk_peer_lock); + spin_unlock(&peersk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) @@ -681,7 +706,7 @@ static int unix_set_peek_off(struct sock *sk, int val) if (mutex_lock_interruptible(&u->iolock)) return -EINTR; - sk->sk_peek_off = val; + WRITE_ONCE(sk->sk_peek_off, val); mutex_unlock(&u->iolock); return 0; @@ -1207,7 +1232,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) sched = !sock_flag(other, SOCK_DEAD) && !(other->sk_shutdown & RCV_SHUTDOWN) && - unix_recvq_full(other); + unix_recvq_full_lockless(other); unix_state_unlock(other); @@ -1514,65 +1539,51 @@ out: return err; } -static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} - -static void unix_destruct_scm(struct sk_buff *skb) -{ - struct scm_cookie scm; - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; - if (UNIXCB(skb).fp) - unix_detach_fds(&scm, skb); - - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ - scm_destroy(&scm); - sock_wfree(skb); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) +static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { - struct user_struct *user = current_user(); - - if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; + scm->fp = scm_fp_dup(UNIXCB(skb).fp); /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. + * Garbage collection of unix sockets starts by selecting a set of + * candidate sockets which have reference only from being in flight + * (total_refs == inflight_refs). This condition is checked once during + * the candidate collection phase, and candidates are marked as such, so + * that non-candidates can later be ignored. While inflight_refs is + * protected by unix_gc_lock, total_refs (file count) is not, hence this + * is an instantaneous decision. + * + * Once a candidate, however, the socket must not be reinstalled into a + * file descriptor while the garbage collection is in progress. + * + * If the above conditions are met, then the directed graph of + * candidates (*) does not change while unix_gc_lock is held. + * + * Any operations that changes the file count through file descriptors + * (dup, close, sendmsg) does not change the graph since candidates are + * not installed in fds. + * + * Dequeing a candidate via recvmsg would install it into an fd, but + * that takes unix_gc_lock to decrement the inflight count, so it's + * serialized with garbage collection. + * + * MSG_PEEK is special in that it does not change the inflight count, + * yet does install the socket into an fd. The following lock/unlock + * pair is to ensure serialization with garbage collection. It must be + * done between incrementing the file count and installing the file into + * an fd. + * + * If garbage collection starts after the barrier provided by the + * lock/unlock, then it will see the elevated refcount and not mark this + * as a candidate. If a garbage collection is already in progress + * before the file count was incremented, then the lock/unlock pair will + * ensure that garbage collection is finished before progressing to + * installing the fd. + * + * (*) A -> B where B is on the queue of A or B is on the queue of C + * which is on the queue of listening socket A. */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return 0; + spin_lock(&unix_gc_lock); + spin_unlock(&unix_gc_lock); } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -1973,6 +1984,7 @@ static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, if (false) { alloc_skb: + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT, @@ -2012,6 +2024,7 @@ alloc_skb: init_scm = false; } + spin_lock(&other->sk_receive_queue.lock); skb = skb_peek_tail(&other->sk_receive_queue); if (tail && tail == skb) { skb = newskb; @@ -2042,14 +2055,11 @@ alloc_skb: refcount_add(size, &sk->sk_wmem_alloc); if (newskb) { - err = unix_scm_to_skb(&scm, skb, false); - if (err) - goto err_state_unlock; - spin_lock(&other->sk_receive_queue.lock); + unix_scm_to_skb(&scm, skb, false); __skb_queue_tail(&other->sk_receive_queue, newskb); - spin_unlock(&other->sk_receive_queue.lock); } + spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); mutex_unlock(&unix_sk(other)->iolock); @@ -2200,7 +2210,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, sk_peek_offset_fwd(sk, size); if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); } err = (flags & MSG_TRUNC) ? skb->len - skip : size; @@ -2441,7 +2451,7 @@ unlock: /* It is questionable, see note in unix_dgram_recvmsg. */ if (UNIXCB(skb).fp) - scm.fp = scm_fp_dup(UNIXCB(skb).fp); + unix_peek_fds(&scm, skb); sk_peek_offset_fwd(sk, chunk); @@ -2540,7 +2550,7 @@ static int unix_shutdown(struct socket *sock, int mode) ++mode; unix_state_lock(sk); - sk->sk_shutdown |= mode; + WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | mode); other = unix_peer(sk); if (other) sock_hold(other); @@ -2557,7 +2567,7 @@ static int unix_shutdown(struct socket *sock, int mode) if (mode&SEND_SHUTDOWN) peer_mode |= RCV_SHUTDOWN; unix_state_lock(other); - other->sk_shutdown |= peer_mode; + WRITE_ONCE(other->sk_shutdown, other->sk_shutdown | peer_mode); unix_state_unlock(other); other->sk_state_change(other); if (peer_mode == SHUTDOWN_MASK) @@ -2676,16 +2686,18 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa { struct sock *sk = sock->sk; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (sk->sk_err) mask |= EPOLLERR; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ @@ -2713,18 +2725,20 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk, *other; unsigned int writable; __poll_t mask; + u8 shutdown; sock_poll_wait(file, sock, wait); mask = 0; + shutdown = READ_ONCE(sk->sk_shutdown); /* exceptional events? */ if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (sk->sk_shutdown & RCV_SHUTDOWN) + if (shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; - if (sk->sk_shutdown == SHUTDOWN_MASK) + if (shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; /* readable? */ @@ -2750,7 +2764,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, other = unix_peer(sk); if (other && unix_peer(other) != sk && - unix_recvq_full(other) && + unix_recvq_full_lockless(other) && unix_dgram_peer_wake_me(sk, other)) writable = 0; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index c36757e72844..4d283e26d816 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -86,77 +86,13 @@ #include <net/scm.h> #include <net/tcp_states.h> +#include "scm.h" + /* Internal data structures and random procedures: */ -static LIST_HEAD(gc_inflight_list); static LIST_HEAD(gc_candidates); -static DEFINE_SPINLOCK(unix_gc_lock); static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); -unsigned int unix_tot_inflight; - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && sock->ops && sock->ops->family == PF_UNIX) - u_sock = s; - } - return u_sock; -} - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ - -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (atomic_long_inc_return(&u->inflight) == 1) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - unix_tot_inflight++; - } - user->unix_inflight++; - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!atomic_long_read(&u->inflight)); - BUG_ON(list_empty(&u->link)); - - if (atomic_long_dec_and_test(&u->inflight)) - list_del_init(&u->link); - unix_tot_inflight--; - } - user->unix_inflight--; - spin_unlock(&unix_gc_lock); -} - static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), struct sk_buff_head *hitlist) { @@ -261,8 +197,11 @@ void wait_for_unix_gc(void) { /* If number of inflight sockets is insane, * force a garbage collect right now. + * Paired with the WRITE_ONCE() in unix_inflight(), + * unix_notinflight() and gc_in_progress(). */ - if (unix_tot_inflight > UNIX_INFLIGHT_TRIGGER_GC && !gc_in_progress) + if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && + !READ_ONCE(gc_in_progress)) unix_gc(); wait_event(unix_gc_wait, gc_in_progress == false); } @@ -282,7 +221,9 @@ void unix_gc(void) if (gc_in_progress) goto out; - gc_in_progress = true; + /* Paired with READ_ONCE() in wait_for_unix_gc(). */ + WRITE_ONCE(gc_in_progress, true); + /* First, select candidates for garbage collection. Only * in-flight sockets are considered, and from those only ones * which don't have any external reference. @@ -368,7 +309,10 @@ void unix_gc(void) /* All candidates should have been detached by now. */ BUG_ON(!list_empty(&gc_candidates)); - gc_in_progress = false; + + /* Paired with READ_ONCE() in wait_for_unix_gc(). */ + WRITE_ONCE(gc_in_progress, false); + wake_up(&unix_gc_wait); out: diff --git a/net/unix/scm.c b/net/unix/scm.c new file mode 100644 index 000000000000..ac206bfdbbe3 --- /dev/null +++ b/net/unix/scm.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/socket.h> +#include <linux/net.h> +#include <linux/fs.h> +#include <net/af_unix.h> +#include <net/scm.h> +#include <linux/init.h> + +#include "scm.h" + +unsigned int unix_tot_inflight; +EXPORT_SYMBOL(unix_tot_inflight); + +LIST_HEAD(gc_inflight_list); +EXPORT_SYMBOL(gc_inflight_list); + +DEFINE_SPINLOCK(unix_gc_lock); +EXPORT_SYMBOL(unix_gc_lock); + +struct sock *unix_get_socket(struct file *filp) +{ + struct sock *u_sock = NULL; + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + struct sock *s = sock->sk; + + /* PF_UNIX ? */ + if (s && sock->ops && sock->ops->family == PF_UNIX) + u_sock = s; + } + return u_sock; +} +EXPORT_SYMBOL(unix_get_socket); + +/* Keep the number of times in flight count for the file + * descriptor if it is for an AF_UNIX socket. + */ +void unix_inflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + if (atomic_long_inc_return(&u->inflight) == 1) { + BUG_ON(!list_empty(&u->link)); + list_add_tail(&u->link, &gc_inflight_list); + } else { + BUG_ON(list_empty(&u->link)); + } + /* Paired with READ_ONCE() in wait_for_unix_gc() */ + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); + } + WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); + spin_unlock(&unix_gc_lock); +} + +void unix_notinflight(struct user_struct *user, struct file *fp) +{ + struct sock *s = unix_get_socket(fp); + + spin_lock(&unix_gc_lock); + + if (s) { + struct unix_sock *u = unix_sk(s); + + BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(list_empty(&u->link)); + + if (atomic_long_dec_and_test(&u->inflight)) + list_del_init(&u->link); + /* Paired with READ_ONCE() in wait_for_unix_gc() */ + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); + } + WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); + spin_unlock(&unix_gc_lock); +} + +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + /* + * Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); + return 0; +} +EXPORT_SYMBOL(unix_attach_fds); + +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + int i; + + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + for (i = scm->fp->count-1; i >= 0; i--) + unix_notinflight(scm->fp->user, scm->fp->fp[i]); +} +EXPORT_SYMBOL(unix_detach_fds); + +void unix_destruct_scm(struct sk_buff *skb) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); +} +EXPORT_SYMBOL(unix_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h new file mode 100644 index 000000000000..5a255a477f16 --- /dev/null +++ b/net/unix/scm.h @@ -0,0 +1,10 @@ +#ifndef NET_UNIX_SCM_H +#define NET_UNIX_SCM_H + +extern struct list_head gc_inflight_list; +extern spinlock_t unix_gc_lock; + +int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); +void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); + +#endif diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index c88dc8ee3144..0dfa2dfcb4bc 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -628,8 +628,9 @@ struct sock *__vsock_create(struct net *net, vsk->trusted = psk->trusted; vsk->owner = get_cred(psk->owner); vsk->connect_timeout = psk->connect_timeout; + security_sk_clone(parent, sk); } else { - vsk->trusted = capable(CAP_NET_ADMIN); + vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN); vsk->owner = get_current_cred(); vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; } @@ -816,10 +817,12 @@ static int vsock_shutdown(struct socket *sock, int mode) */ sk = sock->sk; + + lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; if (sk->sk_type == SOCK_STREAM) - return err; + goto out; } else { sock->state = SS_DISCONNECTING; err = 0; @@ -828,10 +831,8 @@ static int vsock_shutdown(struct socket *sock, int mode) /* Receive and send shutdowns are treated alike. */ mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN); if (mode) { - lock_sock(sk); sk->sk_shutdown |= mode; sk->sk_state_change(sk); - release_sock(sk); if (sk->sk_type == SOCK_STREAM) { sock_reset_flag(sk, SOCK_DONE); @@ -839,6 +840,8 @@ static int vsock_shutdown(struct socket *sock, int mode) } } +out: + release_sock(sk); return err; } @@ -1107,7 +1110,6 @@ static void vsock_connect_timeout(struct work_struct *work) { struct sock *sk; struct vsock_sock *vsk; - int cancel = 0; vsk = container_of(work, struct vsock_sock, connect_work.work); sk = sk_vsock(vsk); @@ -1116,13 +1118,12 @@ static void vsock_connect_timeout(struct work_struct *work) if (sk->sk_state == TCP_SYN_SENT && (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; + sk->sk_socket->state = SS_UNCONNECTED; sk->sk_err = ETIMEDOUT; sk->sk_error_report(sk); - cancel = 1; + vsock_transport_cancel_pkt(vsk); } release_sock(sk); - if (cancel) - vsock_transport_cancel_pkt(vsk); sock_put(sk); } @@ -1159,6 +1160,8 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, * non-blocking call. */ err = -EALREADY; + if (flags & O_NONBLOCK) + goto out; break; default: if ((sk->sk_state == TCP_LISTEN) || @@ -1213,7 +1216,14 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, * timeout fires. */ sock_hold(sk); - schedule_delayed_work(&vsk->connect_work, timeout); + + /* If the timeout function is already scheduled, + * reschedule it, then ungrab the socket refcount to + * keep it balanced. + */ + if (mod_delayed_work(system_wq, &vsk->connect_work, + timeout)) + sock_put(sk); /* Skip ahead to preserve error code set above. */ goto out_wait; @@ -1225,11 +1235,12 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - sk->sk_state = TCP_CLOSE; + sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); + vsock_remove_connected(vsk); goto out_wait; - } else if (timeout == 0) { + } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { err = -ETIMEDOUT; sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index db6ca51228d2..2bdf36845a5f 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -443,14 +443,10 @@ static void hvs_shutdown_lock_held(struct hvsock *hvs, int mode) static int hvs_shutdown(struct vsock_sock *vsk, int mode) { - struct sock *sk = sk_vsock(vsk); - if (!(mode & SEND_SHUTDOWN)) return 0; - lock_sock(sk); hvs_shutdown_lock_held(vsk->trans, mode); - release_sock(sk); return 0; } diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index cc70d651d13e..e34979fcefd2 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -373,11 +373,14 @@ static void virtio_vsock_event_fill(struct virtio_vsock *vsock) static void virtio_vsock_reset_sock(struct sock *sk) { - lock_sock(sk); + /* vmci_transport.c doesn't take sk_lock here either. At least we're + * under vsock_table_lock so the sock cannot disappear while we're + * executing. + */ + sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; sk->sk_error_report(sk); - release_sock(sk); } static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 5f8a72d34d31..187d0f7253a6 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -348,7 +348,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk) struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; @@ -1033,10 +1033,10 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, vsk = vsock_sk(sk); - space_available = virtio_transport_space_update(sk, pkt); - lock_sock(sk); + space_available = virtio_transport_space_update(sk, pkt); + /* Update CID in case it has changed after a transport reset event */ vsk->local_addr.svm_cid = dst.svm_cid; @@ -1079,7 +1079,7 @@ EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt); void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt) { - kfree(pkt->buf); + kvfree(pkt->buf); kfree(pkt); } EXPORT_SYMBOL_GPL(virtio_transport_free_pkt); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c3d5ab01fba7..2a8127f245e8 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -584,8 +584,7 @@ vmci_transport_queue_pair_alloc(struct vmci_qp **qpair, peer, flags, VMCI_NO_PRIVILEGE_FLAGS); out: if (err < 0) { - pr_err("Could not attach to queue pair with %d\n", - err); + pr_err_once("Could not attach to queue pair with %d\n", err); err = vmci_transport_error_to_vsock_error(err); } @@ -1734,7 +1733,11 @@ static int vmci_transport_dgram_enqueue( if (!dg) return -ENOMEM; - memcpy_from_msg(VMCI_DG_PAYLOAD(dg), msg, len); + err = memcpy_from_msg(VMCI_DG_PAYLOAD(dg), msg, len); + if (err) { + kfree(dg); + return err; + } dg->dst = vmci_make_handle(remote_addr->svm_cid, remote_addr->svm_port); diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 8158b375d170..4500ad5f2a61 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -27,7 +27,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" @(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ - cat $^ ; \ + echo | cat - $^ ; \ echo '};'; \ echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ ) > $@ diff --git a/net/wireless/certs/wens.hex b/net/wireless/certs/wens.hex new file mode 100644 index 000000000000..0d50369bede9 --- /dev/null +++ b/net/wireless/certs/wens.hex @@ -0,0 +1,87 @@ +/* Chen-Yu Tsai's regdb certificate */ +0x30, 0x82, 0x02, 0xa7, 0x30, 0x82, 0x01, 0x8f, +0x02, 0x14, 0x61, 0xc0, 0x38, 0x65, 0x1a, 0xab, +0xdc, 0xf9, 0x4b, 0xd0, 0xac, 0x7f, 0xf0, 0x6c, +0x72, 0x48, 0xdb, 0x18, 0xc6, 0x00, 0x30, 0x0d, +0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, +0x01, 0x01, 0x0b, 0x05, 0x00, 0x30, 0x0f, 0x31, +0x0d, 0x30, 0x0b, 0x06, 0x03, 0x55, 0x04, 0x03, +0x0c, 0x04, 0x77, 0x65, 0x6e, 0x73, 0x30, 0x20, +0x17, 0x0d, 0x32, 0x33, 0x31, 0x32, 0x30, 0x31, +0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, 0x18, +0x0f, 0x32, 0x31, 0x32, 0x33, 0x31, 0x31, 0x30, +0x37, 0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, +0x30, 0x0f, 0x31, 0x0d, 0x30, 0x0b, 0x06, 0x03, +0x55, 0x04, 0x03, 0x0c, 0x04, 0x77, 0x65, 0x6e, +0x73, 0x30, 0x82, 0x01, 0x22, 0x30, 0x0d, 0x06, +0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01, +0x01, 0x01, 0x05, 0x00, 0x03, 0x82, 0x01, 0x0f, +0x00, 0x30, 0x82, 0x01, 0x0a, 0x02, 0x82, 0x01, +0x01, 0x00, 0xa9, 0x7a, 0x2c, 0x78, 0x4d, 0xa7, +0x19, 0x2d, 0x32, 0x52, 0xa0, 0x2e, 0x6c, 0xef, +0x88, 0x7f, 0x15, 0xc5, 0xb6, 0x69, 0x54, 0x16, +0x43, 0x14, 0x79, 0x53, 0xb7, 0xae, 0x88, 0xfe, +0xc0, 0xb7, 0x5d, 0x47, 0x8e, 0x1a, 0xe1, 0xef, +0xb3, 0x90, 0x86, 0xda, 0xd3, 0x64, 0x81, 0x1f, +0xce, 0x5d, 0x9e, 0x4b, 0x6e, 0x58, 0x02, 0x3e, +0xb2, 0x6f, 0x5e, 0x42, 0x47, 0x41, 0xf4, 0x2c, +0xb8, 0xa8, 0xd4, 0xaa, 0xc0, 0x0e, 0xe6, 0x48, +0xf0, 0xa8, 0xce, 0xcb, 0x08, 0xae, 0x37, 0xaf, +0xf6, 0x40, 0x39, 0xcb, 0x55, 0x6f, 0x5b, 0x4f, +0x85, 0x34, 0xe6, 0x69, 0x10, 0x50, 0x72, 0x5e, +0x4e, 0x9d, 0x4c, 0xba, 0x38, 0x36, 0x0d, 0xce, +0x73, 0x38, 0xd7, 0x27, 0x02, 0x2a, 0x79, 0x03, +0xe1, 0xac, 0xcf, 0xb0, 0x27, 0x85, 0x86, 0x93, +0x17, 0xab, 0xec, 0x42, 0x77, 0x37, 0x65, 0x8a, +0x44, 0xcb, 0xd6, 0x42, 0x93, 0x92, 0x13, 0xe3, +0x39, 0x45, 0xc5, 0x6e, 0x00, 0x4a, 0x7f, 0xcb, +0x42, 0x17, 0x2b, 0x25, 0x8c, 0xb8, 0x17, 0x3b, +0x15, 0x36, 0x59, 0xde, 0x42, 0xce, 0x21, 0xe6, +0xb6, 0xc7, 0x6e, 0x5e, 0x26, 0x1f, 0xf7, 0x8a, +0x57, 0x9e, 0xa5, 0x96, 0x72, 0xb7, 0x02, 0x32, +0xeb, 0x07, 0x2b, 0x73, 0xe2, 0x4f, 0x66, 0x58, +0x9a, 0xeb, 0x0f, 0x07, 0xb6, 0xab, 0x50, 0x8b, +0xc3, 0x8f, 0x17, 0xfa, 0x0a, 0x99, 0xc2, 0x16, +0x25, 0xbf, 0x2d, 0x6b, 0x1a, 0xaa, 0xe6, 0x3e, +0x5f, 0xeb, 0x6d, 0x9b, 0x5d, 0x4d, 0x42, 0x83, +0x2d, 0x39, 0xb8, 0xc9, 0xac, 0xdb, 0x3a, 0x91, +0x50, 0xdf, 0xbb, 0xb1, 0x76, 0x6d, 0x15, 0x73, +0xfd, 0xc6, 0xe6, 0x6b, 0x71, 0x9e, 0x67, 0x36, +0x22, 0x83, 0x79, 0xb1, 0xd6, 0xb8, 0x84, 0x52, +0xaf, 0x96, 0x5b, 0xc3, 0x63, 0x02, 0x4e, 0x78, +0x70, 0x57, 0x02, 0x03, 0x01, 0x00, 0x01, 0x30, +0x0d, 0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, +0x0d, 0x01, 0x01, 0x0b, 0x05, 0x00, 0x03, 0x82, +0x01, 0x01, 0x00, 0x24, 0x28, 0xee, 0x22, 0x74, +0x7f, 0x7c, 0xfa, 0x6c, 0x1f, 0xb3, 0x18, 0xd1, +0xc2, 0x3d, 0x7d, 0x29, 0x42, 0x88, 0xad, 0x82, +0xa5, 0xb1, 0x8a, 0x05, 0xd0, 0xec, 0x5c, 0x91, +0x20, 0xf6, 0x82, 0xfd, 0xd5, 0x67, 0x60, 0x5f, +0x31, 0xf5, 0xbd, 0x88, 0x91, 0x70, 0xbd, 0xb8, +0xb9, 0x8c, 0x88, 0xfe, 0x53, 0xc9, 0x54, 0x9b, +0x43, 0xc4, 0x7a, 0x43, 0x74, 0x6b, 0xdd, 0xb0, +0xb1, 0x3b, 0x33, 0x45, 0x46, 0x78, 0xa3, 0x1c, +0xef, 0x54, 0x68, 0xf7, 0x85, 0x9c, 0xe4, 0x51, +0x6f, 0x06, 0xaf, 0x81, 0xdb, 0x2a, 0x7b, 0x7b, +0x6f, 0xa8, 0x9c, 0x67, 0xd8, 0xcb, 0xc9, 0x91, +0x40, 0x00, 0xae, 0xd9, 0xa1, 0x9f, 0xdd, 0xa6, +0x43, 0x0e, 0x28, 0x7b, 0xaa, 0x1b, 0xe9, 0x84, +0xdb, 0x76, 0x64, 0x42, 0x70, 0xc9, 0xc0, 0xeb, +0xae, 0x84, 0x11, 0x16, 0x68, 0x4e, 0x84, 0x9e, +0x7e, 0x92, 0x36, 0xee, 0x1c, 0x3b, 0x08, 0x63, +0xeb, 0x79, 0x84, 0x15, 0x08, 0x9d, 0xaf, 0xc8, +0x9a, 0xc7, 0x34, 0xd3, 0x94, 0x4b, 0xd1, 0x28, +0x97, 0xbe, 0xd1, 0x45, 0x75, 0xdc, 0x35, 0x62, +0xac, 0x1d, 0x1f, 0xb7, 0xb7, 0x15, 0x87, 0xc8, +0x98, 0xc0, 0x24, 0x31, 0x56, 0x8d, 0xed, 0xdb, +0x06, 0xc6, 0x46, 0xbf, 0x4b, 0x6d, 0xa6, 0xd5, +0xab, 0xcc, 0x60, 0xfc, 0xe5, 0x37, 0xb6, 0x53, +0x7d, 0x58, 0x95, 0xa9, 0x56, 0xc7, 0xf7, 0xee, +0xc3, 0xa0, 0x76, 0xf7, 0x65, 0x4d, 0x53, 0xfa, +0xff, 0x5f, 0x76, 0x33, 0x5a, 0x08, 0xfa, 0x86, +0x92, 0x5a, 0x13, 0xfa, 0x1a, 0xfc, 0xf2, 0x1b, +0x8c, 0x7f, 0x42, 0x6d, 0xb7, 0x7e, 0xb7, 0xb4, +0xf0, 0xc7, 0x83, 0xbb, 0xa2, 0x81, 0x03, 0x2d, +0xd4, 0x2a, 0x63, 0x3f, 0xf7, 0x31, 0x2e, 0x40, +0x33, 0x5c, 0x46, 0xbc, 0x9b, 0xc1, 0x05, 0xa5, +0x45, 0x4e, 0xc3, diff --git a/net/wireless/core.c b/net/wireless/core.c index 68660781aa51..7c66f99046ac 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -4,6 +4,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH + * Copyright (C) 2018-2021 Intel Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -835,9 +836,6 @@ int wiphy_register(struct wiphy *wiphy) return res; } - /* set up regulatory info */ - wiphy_regulatory_register(wiphy); - list_add_rcu(&rdev->list, &cfg80211_rdev_list); cfg80211_rdev_list_generation++; @@ -851,6 +849,9 @@ int wiphy_register(struct wiphy *wiphy) cfg80211_debugfs_rdev_add(rdev); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); + /* set up regulatory info */ + wiphy_regulatory_register(wiphy); + if (wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) { struct regulatory_request request; diff --git a/net/wireless/core.h b/net/wireless/core.h index f5d58652108d..5f177dad2fa8 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -404,6 +404,8 @@ void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev); /* internal helpers */ bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher); +bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev, + int key_idx, bool pairwise); int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr); diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c index 30fc6eb352bc..e6410487e25d 100644 --- a/net/wireless/debugfs.c +++ b/net/wireless/debugfs.c @@ -68,9 +68,10 @@ static ssize_t ht40allow_map_read(struct file *file, { struct wiphy *wiphy = file->private_data; char *buf; - unsigned int offset = 0, buf_size = PAGE_SIZE, i, r; + unsigned int offset = 0, buf_size = PAGE_SIZE, i; enum nl80211_band band; struct ieee80211_supported_band *sband; + ssize_t r; buf = kzalloc(buf_size, GFP_KERNEL); if (!buf) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4e4179209982..e33c1175b158 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1950,7 +1950,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, * case we'll continue with more data in the next round, * but break unconditionally so unsplit data stops here. */ - state->split_start++; + if (state->split) + state->split_start++; + else + state->split_start = 0; break; case 9: if (rdev->wiphy.extended_capabilities && @@ -2882,6 +2885,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag wdev_lock(wdev); switch (wdev->iftype) { case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: if (wdev->ssid_len && nla_put(msg, NL80211_ATTR_SSID, wdev->ssid_len, wdev->ssid)) goto nla_put_failure_locked; @@ -3621,9 +3625,6 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (key.idx < 0) - return -EINVAL; - if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3639,6 +3640,10 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) key.type != NL80211_KEYTYPE_GROUP) return -EINVAL; + if (!cfg80211_valid_key_idx(rdev, key.idx, + key.type == NL80211_KEYTYPE_PAIRWISE)) + return -EINVAL; + if (!rdev->ops->del_key) return -EOPNOTSUPP; @@ -6499,7 +6504,7 @@ static int nl80211_update_mesh_config(struct sk_buff *skb, struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; - struct mesh_config cfg; + struct mesh_config cfg = {}; u32 mask; int err; @@ -11499,7 +11504,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct nlattr *tb[NUM_NL80211_REKEY_DATA]; - struct cfg80211_gtk_rekey_data rekey_data; + struct cfg80211_gtk_rekey_data rekey_data = {}; int err; if (!info->attrs[NL80211_ATTR_REKEY_DATA]) @@ -11787,6 +11792,9 @@ static int handle_nan_filter(struct nlattr *attr_filter, i = 0; nla_for_each_nested(attr, attr_filter, rem) { filter[i].filter = nla_memdup(attr, GFP_KERNEL); + if (!filter[i].filter) + goto err; + filter[i].len = nla_len(attr); i++; } @@ -11799,6 +11807,15 @@ static int handle_nan_filter(struct nlattr *attr_filter, } return 0; + +err: + i = 0; + nla_for_each_nested(attr, attr_filter, rem) { + kfree(filter[i].filter); + i++; + } + kfree(filter); + return -ENOMEM; } static int nl80211_nan_add_func(struct sk_buff *skb, @@ -15502,7 +15519,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev, wdev->chandef = *chandef; wdev->preset_chandef = *chandef; - if (wdev->iftype == NL80211_IFTYPE_STATION && + if ((wdev->iftype == NL80211_IFTYPE_STATION || + wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) && !WARN_ON(!wdev->current_bss)) wdev->current_bss->pub.channel = chandef->chan; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 935aebf15010..beba41f8a178 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1050,6 +1050,8 @@ static void regdb_fw_cb(const struct firmware *fw, void *context) static int query_regdb_file(const char *alpha2) { + int err; + ASSERT_RTNL(); if (regdb) @@ -1059,9 +1061,13 @@ static int query_regdb_file(const char *alpha2) if (!alpha2) return -ENOMEM; - return request_firmware_nowait(THIS_MODULE, true, "regulatory.db", - ®_pdev->dev, GFP_KERNEL, - (void *)alpha2, regdb_fw_cb); + err = request_firmware_nowait(THIS_MODULE, true, "regulatory.db", + ®_pdev->dev, GFP_KERNEL, + (void *)alpha2, regdb_fw_cb); + if (err) + kfree(alpha2); + + return err; } int reg_reload_regdb(void) @@ -3374,7 +3380,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd) power_rule = ®_rule->power_rule; if (reg_rule->flags & NL80211_RRF_AUTO_BW) - snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO", + snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO", freq_range->max_bandwidth_khz, reg_get_max_bandwidth(rd, reg_rule)); else @@ -3756,6 +3762,7 @@ void wiphy_regulatory_register(struct wiphy *wiphy) wiphy_update_regulatory(wiphy, lr->initiator); wiphy_all_share_dfs_chan_state(wiphy); + reg_process_self_managed_hints(); } void wiphy_regulatory_deregister(struct wiphy *wiphy) @@ -3911,8 +3918,10 @@ static int __init regulatory_init_db(void) return -EINVAL; err = load_builtin_regdb_keys(); - if (err) + if (err) { + platform_device_unregister(reg_pdev); return err; + } /* We always try to get an update for the static regdomain */ err = regulatory_hint_core(cfg80211_world_regdom->alpha2); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index e5d61ba837ad..d871349036a5 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1029,14 +1029,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, * be grouped with this beacon for updates ... */ if (!cfg80211_combine_bsses(rdev, new)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } } if (rdev->bss_entries >= bss_entries_limit && !cfg80211_bss_expire_oldest(rdev)) { - kfree(new); + bss_ref_put(rdev, new); goto drop; } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f455b9af6815..ebc73faa8fb1 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -269,6 +269,15 @@ void cfg80211_conn_work(struct work_struct *work) rtnl_unlock(); } +static void cfg80211_step_auth_next(struct cfg80211_conn *conn, + struct cfg80211_bss *bss) +{ + memcpy(conn->bssid, bss->bssid, ETH_ALEN); + conn->params.bssid = conn->bssid; + conn->params.channel = bss->channel; + conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; +} + /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) { @@ -286,10 +295,7 @@ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) if (!bss) return NULL; - memcpy(wdev->conn->bssid, bss->bssid, ETH_ALEN); - wdev->conn->params.bssid = wdev->conn->bssid; - wdev->conn->params.channel = bss->channel; - wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; + cfg80211_step_auth_next(wdev->conn, bss); schedule_work(&rdev->conn_work); return bss; @@ -530,7 +536,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, cfg80211_sme_free(wdev); } - if (WARN_ON(wdev->conn)) + if (wdev->conn) return -EINPROGRESS; wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL); @@ -568,7 +574,12 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, wdev->conn->params.ssid_len = wdev->ssid_len; /* see if we have the bss already */ - bss = cfg80211_get_conn_bss(wdev); + bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, + wdev->conn->params.bssid, + wdev->conn->params.ssid, + wdev->conn->params.ssid_len, + wdev->conn_bss_type, + IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (prev_bssid) { memcpy(wdev->conn->prev_bssid, prev_bssid, ETH_ALEN); @@ -579,6 +590,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, if (bss) { enum nl80211_timeout_reason treason; + cfg80211_step_auth_next(wdev->conn, bss); err = cfg80211_conn_do_work(wdev, &treason); cfg80211_put_bss(wdev->wiphy, bss); } else { @@ -1207,6 +1219,13 @@ int cfg80211_connect(struct cfg80211_registered_device *rdev, } else { if (WARN_ON(connkeys)) return -EINVAL; + + /* connect can point to wdev->wext.connect which + * can hold key data from a previous connection + */ + connect->key = NULL; + connect->key_len = 0; + connect->key_idx = 0; } wdev->connect_keys = connkeys; diff --git a/net/wireless/util.c b/net/wireless/util.c index 1a878b84cbd0..82bf1339c28e 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -214,11 +214,48 @@ bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher) return false; } +static bool +cfg80211_igtk_cipher_supported(struct cfg80211_registered_device *rdev) +{ + struct wiphy *wiphy = &rdev->wiphy; + int i; + + for (i = 0; i < wiphy->n_cipher_suites; i++) { + switch (wiphy->cipher_suites[i]) { + case WLAN_CIPHER_SUITE_AES_CMAC: + case WLAN_CIPHER_SUITE_BIP_CMAC_256: + case WLAN_CIPHER_SUITE_BIP_GMAC_128: + case WLAN_CIPHER_SUITE_BIP_GMAC_256: + return true; + } + } + + return false; +} + +bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev, + int key_idx, bool pairwise) +{ + int max_key_idx; + + if (pairwise) + max_key_idx = 3; + else if (cfg80211_igtk_cipher_supported(rdev)) + max_key_idx = 5; + else + max_key_idx = 3; + + if (key_idx < 0 || key_idx > max_key_idx) + return false; + + return true; +} + int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { - if (key_idx < 0 || key_idx > 5) + if (!cfg80211_valid_key_idx(rdev, key_idx, pairwise)) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) @@ -422,7 +459,7 @@ EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, - u8 data_offset) + u8 data_offset, bool is_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { @@ -510,7 +547,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, skb_copy_bits(skb, hdrlen, &payload, sizeof(payload)); tmp.h_proto = payload.proto; - if (likely((ether_addr_equal(payload.hdr, rfc1042_header) && + if (likely((!is_amsdu && ether_addr_equal(payload.hdr, rfc1042_header) && tmp.h_proto != htons(ETH_P_AARP) && tmp.h_proto != htons(ETH_P_IPX)) || ether_addr_equal(payload.hdr, bridge_tunnel_header))) @@ -652,6 +689,9 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, remaining = skb->len - offset; if (subframe_len > remaining) goto purge; + /* mitigate A-MSDU aggregation injection attacks */ + if (ether_addr_equal(eth.h_dest, rfc1042_header)) + goto purge; offset += sizeof(struct ethhdr); last = remaining <= subframe_len + padding; @@ -910,6 +950,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, switch (otype) { case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, dev, true); break; case NL80211_IFTYPE_ADHOC: @@ -925,6 +966,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; + case NL80211_IFTYPE_OCB: + cfg80211_leave_ocb(rdev, dev); + break; default: break; } diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 69102fda9ebd..a57f54bc0e1a 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -796,6 +796,12 @@ static int ioctl_standard_iw_point(struct iw_point *iwp, unsigned int cmd, } } + /* Sanity-check to ensure we never end up _allocating_ zero + * bytes of data for extra. + */ + if (extra_size <= 0) + return -EFAULT; + /* kzalloc() ensures NULL-termination for essid_compat. */ extra = kzalloc(extra_size, GFP_KERNEL); if (!extra) @@ -896,8 +902,9 @@ out: int call_commit_handler(struct net_device *dev) { #ifdef CONFIG_WIRELESS_EXT - if ((netif_running(dev)) && - (dev->wireless_handlers->standard[0] != NULL)) + if (netif_running(dev) && + dev->wireless_handlers && + dev->wireless_handlers->standard[0]) /* Call the commit handler on the driver */ return dev->wireless_handlers->standard[0](dev, NULL, NULL, NULL); diff --git a/net/wireless/wext-spy.c b/net/wireless/wext-spy.c index 33bef22e44e9..b379a0371653 100644 --- a/net/wireless/wext-spy.c +++ b/net/wireless/wext-spy.c @@ -120,8 +120,8 @@ int iw_handler_set_thrspy(struct net_device * dev, return -EOPNOTSUPP; /* Just do it */ - memcpy(&(spydata->spy_thr_low), &(threshold->low), - 2 * sizeof(struct iw_quality)); + spydata->spy_thr_low = threshold->low; + spydata->spy_thr_high = threshold->high; /* Clear flag */ memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); @@ -147,8 +147,8 @@ int iw_handler_get_thrspy(struct net_device * dev, return -EOPNOTSUPP; /* Just do it */ - memcpy(&(threshold->low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); + threshold->low = spydata->spy_thr_low; + threshold->high = spydata->spy_thr_high; return 0; } @@ -173,10 +173,10 @@ static void iw_send_thrspy_event(struct net_device * dev, memcpy(threshold.addr.sa_data, address, ETH_ALEN); threshold.addr.sa_family = ARPHRD_ETHER; /* Copy stats */ - memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); + threshold.qual = *wstats; /* Copy also thresholds */ - memcpy(&(threshold.low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); + threshold.low = spydata->spy_thr_low; + threshold.high = spydata->spy_thr_high; /* Send event to user space */ wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index bd1cbbfe5924..9d0328bb30ca 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -497,6 +497,12 @@ static int x25_listen(struct socket *sock, int backlog) int rc = -EOPNOTSUPP; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + rc = -EINVAL; + release_sock(sk); + return rc; + } + if (sk->sk_state != TCP_LISTEN) { memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; @@ -551,7 +557,7 @@ static int x25_create(struct net *net, struct socket *sock, int protocol, if (protocol) goto out; - rc = -ENOBUFS; + rc = -ENOMEM; if ((sk = x25_alloc_socket(net, kern)) == NULL) goto out; @@ -680,7 +686,8 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) int len, i, rc = 0; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) { + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) { rc = -EINVAL; goto out; } @@ -774,7 +781,8 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, rc = -EINVAL; if (addr_len != sizeof(struct sockaddr_x25) || - addr->sx25_family != AF_X25) + addr->sx25_family != AF_X25 || + strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) goto out; rc = -ENETUNREACH; @@ -824,7 +832,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; rc = 0; out_put_neigh: - if (rc) { + if (rc && x25->neighbour) { read_lock_bh(&x25_list_lock); x25_neigh_put(x25->neighbour); x25->neighbour = NULL; @@ -1049,6 +1057,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, makex25->lci = lci; makex25->dest_addr = dest_addr; makex25->source_addr = source_addr; + x25_neigh_hold(nb); makex25->neighbour = nb; makex25->facilities = facilities; makex25->dte_facilities= dte_facilities; @@ -1794,10 +1803,15 @@ void x25_kill_by_neigh(struct x25_neigh *nb) write_lock_bh(&x25_list_lock); - sk_for_each(s, &x25_list) - if (x25_sk(s)->neighbour == nb) + sk_for_each(s, &x25_list) { + if (x25_sk(s)->neighbour == nb) { + write_unlock_bh(&x25_list_lock); + lock_sock(s); x25_disconnect(s, ENETUNREACH, 0, 0); - + release_sock(s); + write_lock_bh(&x25_list_lock); + } + } write_unlock_bh(&x25_list_lock); /* Remove any related forwards */ diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 30f71620d4e3..24f2676e3b66 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -122,7 +122,7 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, if (!pskb_may_pull(skb, 1)) { x25_neigh_put(nb); - return 0; + goto drop; } switch (skb->data[0]) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9ff2ab63e639..6bb0649c028c 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -289,17 +289,17 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len); } -static unsigned int xsk_poll(struct file *file, struct socket *sock, +static __poll_t xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { - unsigned int mask = datagram_poll(file, sock, wait); + __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); if (xs->rx && !xskq_empty_desc(xs->rx)) - mask |= POLLIN | POLLRDNORM; + mask |= EPOLLIN | EPOLLRDNORM; if (xs->tx && !xskq_full_desc(xs->tx)) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; return mask; } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index fe96c0d039f2..cf7cbb5dd918 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -245,12 +245,15 @@ static inline void xskq_produce_flush_desc(struct xsk_queue *q) static inline bool xskq_full_desc(struct xsk_queue *q) { - return xskq_nb_avail(q, q->nentries) == q->nentries; + /* No barriers needed since data is not accessed */ + return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer) == + q->nentries; } static inline bool xskq_empty_desc(struct xsk_queue *q) { - return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; + /* No barriers needed since data is not accessed */ + return READ_ONCE(q->ring->consumer) == READ_ONCE(q->ring->producer); } void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index fbc4552d17b8..6e5e307f985e 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -3,6 +3,8 @@ # Makefile for the XFRM subsystem. # +xfrm_interface-$(CONFIG_XFRM_INTERFACE) += xfrm_interface_core.o + obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ xfrm_sysctl.o xfrm_replay.o xfrm_device.o diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index e7a0ce98479f..8a9f02997067 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -153,6 +153,9 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, if (x->encap || x->tfcpad) return -EINVAL; + if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND)) + return -EINVAL; + dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { @@ -190,7 +193,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, xso->dev = dev; xso->num_exthdrs = 1; - xso->flags = xuo->flags; + /* Don't forward bit that is not implemented */ + xso->flags = xuo->flags & ~XFRM_OFFLOAD_IPV6; err = dev->xfrmdev_ops->xdo_dev_state_add(x); if (err) { diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 0ee13d12782f..fcba8a139f61 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -420,7 +420,7 @@ resume: /* only the first xfrm gets the encap type */ encap_type = 0; - if (async && x->repl->recheck(x, skb, seq)) { + if (x->repl->recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface_core.c index 6cc9f6e2dd2b..10fa26103bdf 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface_core.c @@ -219,8 +219,8 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err) skb->dev = dev; if (err) { - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_dropped); return 0; } @@ -260,7 +260,6 @@ static int xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); unsigned int length = skb->len; struct net_device *tdev; @@ -286,7 +285,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) tdev = dst->dev; if (tdev == dev) { - stats->collisions++; + DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", dev->name); goto tx_err_dst_release; @@ -300,16 +299,22 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + if (skb->len > 1280) + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + else + goto xmit; } else { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, - htonl(mtu)); + if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto xmit; + icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); } dst_release(dst); return -EMSGSIZE; } +xmit: xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = tdev; @@ -323,13 +328,13 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); } else { - stats->tx_errors++; - stats->tx_aborted_errors++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_aborted_errors); } return 0; tx_err_link_failure: - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); @@ -339,7 +344,6 @@ tx_err_dst_release: static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; @@ -348,23 +352,23 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->protocol) { case htons(ETH_P_IPV6): - xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + xfrm_decode_session(skb, &fl, AF_INET6); if (!dst) { fl.u.ip6.flowi6_oif = dev->ifindex; fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); if (dst->error) { dst_release(dst); - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, dst); } break; case htons(ETH_P_IP): - xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + xfrm_decode_session(skb, &fl, AF_INET); if (!dst) { struct rtable *rt; @@ -372,7 +376,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); if (IS_ERR(rt)) { - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, &rt->dst); @@ -391,8 +395,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_err: - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } @@ -659,11 +663,16 @@ static int xfrmi_newlink(struct net *src_net, struct net_device *dev, struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); - struct xfrm_if_parms p; + struct xfrm_if_parms p = {}; struct xfrm_if *xi; int err; xfrmi_netlink_parms(data, &p); + if (!p.if_id) { + NL_SET_ERR_MSG(extack, "if_id must be non zero"); + return -EINVAL; + } + xi = xfrmi_locate(net, &p); if (xi) return -EEXIST; @@ -688,9 +697,14 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], { struct xfrm_if *xi = netdev_priv(dev); struct net *net = xi->net; - struct xfrm_if_parms p; + struct xfrm_if_parms p = {}; xfrmi_netlink_parms(data, &p); + if (!p.if_id) { + NL_SET_ERR_MSG(extack, "if_id must be non zero"); + return -EINVAL; + } + xi = xfrmi_locate(net, &p); if (!xi) { xi = netdev_priv(dev); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index a00ec715aa46..32aed1d0f6ee 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -216,6 +216,7 @@ static void ipcomp_free_scratches(void) vfree(*per_cpu_ptr(scratches, i)); free_percpu(scratches); + ipcomp_scratches = NULL; } static void * __percpu *ipcomp_alloc_scratches(void) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 939f3adf075a..c8a7a5739425 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -654,8 +654,6 @@ EXPORT_SYMBOL(xfrm_policy_hash_rebuild); * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { - static u32 idx_generator; - for (;;) { struct hlist_head *list; struct xfrm_policy *p; @@ -663,8 +661,8 @@ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) int found; if (!index) { - idx = (idx_generator | dir); - idx_generator += 8; + idx = (net->xfrm.idx_generator | dir); + net->xfrm.idx_generator += 8; } else { idx = index; index = 0; @@ -727,14 +725,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_unlock_bh(&pq->hold_queue.lock); } -static bool xfrm_policy_mark_match(struct xfrm_policy *policy, - struct xfrm_policy *pol) +static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, + struct xfrm_policy *pol) { - if (policy->mark.v == pol->mark.v && - policy->priority == pol->priority) - return true; - - return false; + return mark->v == pol->mark.v && mark->m == pol->mark.m; } int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) @@ -753,7 +747,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) { @@ -803,11 +797,10 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) } EXPORT_SYMBOL(xfrm_policy_insert); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, - struct xfrm_sec_ctx *ctx, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, struct xfrm_selector *sel, + struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -819,7 +812,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v && + xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) { xfrm_pol_hold(pol); @@ -844,9 +837,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, u32 id, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -861,8 +854,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && - pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v) { + pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( @@ -1703,8 +1695,10 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, *num_xfrms = 0; return 0; } - if (IS_ERR(pols[0])) + if (IS_ERR(pols[0])) { + *num_pols = 0; return PTR_ERR(pols[0]); + } *num_xfrms = pols[0]->xfrm_nr; @@ -1719,6 +1713,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); + *num_pols = 0; return PTR_ERR(pols[1]); } (*num_pols)++; @@ -2101,8 +2096,8 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net, xflo.flags = flags; /* To accelerate a bit... */ - if ((dst_orig->flags & DST_NOXFRM) || - !net->xfrm.policy_count[XFRM_POLICY_OUT]) + if (!if_id && ((dst_orig->flags & DST_NOXFRM) || + !net->xfrm.policy_count[XFRM_POLICY_OUT])) goto nopol; xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); @@ -2243,7 +2238,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, - unsigned short family) + unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); @@ -2254,7 +2249,8 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && - xfrm_state_addr_cmp(tmpl, x, family)); + xfrm_state_addr_cmp(tmpl, x, family)) && + (if_id == 0 || if_id == x->if_id); } /* @@ -2266,7 +2262,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, - unsigned short family) + unsigned short family, u32 if_id) { int idx = start; @@ -2276,7 +2272,7 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star } else start = -1; for (; idx < sp->len; idx++) { - if (xfrm_state_ok(tmpl, sp->xvec[idx], family)) + if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (start == -1) @@ -2406,6 +2402,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); + xfrm_pol_put(pols[0]); return 0; } pols[1]->curlft.use_time = ktime_get_real_seconds(); @@ -2452,7 +2449,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, * are implied between each two transformations. */ for (i = xfrm_nr-1, k = 0; i >= 0; i--) { - k = xfrm_policy_ok(tpp[i], sp, k, family); + k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ @@ -3050,7 +3047,7 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, } static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, - u8 dir, u8 type, struct net *net) + u8 dir, u8 type, struct net *net, u32 if_id) { struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; @@ -3059,7 +3056,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, chain, bydst) { - if (xfrm_migrate_selector_match(sel, &pol->selector) && + if ((if_id == 0 || pol->if_id == if_id) && + xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; priority = ret->priority; @@ -3071,7 +3069,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * if ((pol->priority >= priority) && ret) break; - if (xfrm_migrate_selector_match(sel, &pol->selector) && + if ((if_id == 0 || pol->if_id == if_id) && + xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; break; @@ -3187,7 +3186,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k, struct net *net, - struct xfrm_encap_tmpl *encap) + struct xfrm_encap_tmpl *encap, u32 if_id) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -3206,14 +3205,14 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* Stage 1 - find policy */ - if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) { + if ((pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id)) == NULL) { err = -ENOENT; goto out; } /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { - if ((x = xfrm_migrate_state_find(mp, net))) { + if ((x = xfrm_migrate_state_find(mp, net, if_id))) { x_cur[nx_cur] = x; nx_cur++; xc = xfrm_state_migrate(x, mp, encap); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a649d7c2f48c..cf147e1837a9 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -41,7 +41,6 @@ static void xfrm_state_gc_task(struct work_struct *work); */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; -static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation); static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); @@ -137,7 +136,7 @@ static void xfrm_hash_resize(struct work_struct *work) } spin_lock_bh(&net->xfrm.xfrm_state_lock); - write_seqcount_begin(&xfrm_state_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); @@ -153,7 +152,7 @@ static void xfrm_hash_resize(struct work_struct *work) rcu_assign_pointer(net->xfrm.state_byspi, nspi); net->xfrm.state_hmask = nhashmask; - write_seqcount_end(&xfrm_state_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); @@ -965,7 +964,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, to_put = NULL; - sequence = read_seqcount_begin(&xfrm_state_hash_generation); + sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); @@ -1076,7 +1075,7 @@ out: if (to_put) xfrm_state_put(to_put); - if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) { + if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) { *err = -EAGAIN; if (x) { xfrm_state_put(x); @@ -1443,9 +1442,6 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, memcpy(&x->mark, &orig->mark, sizeof(x->mark)); memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); - if (xfrm_init_state(x) < 0) - goto error; - x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; @@ -1467,7 +1463,8 @@ out: return NULL; } -struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net) +struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, + u32 if_id) { unsigned int h; struct xfrm_state *x = NULL; @@ -1483,6 +1480,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n continue; if (m->reqid && x->props.reqid != m->reqid) continue; + if (if_id != 0 && x->if_id != if_id) + continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, @@ -1498,6 +1497,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n if (x->props.mode != m->mode || x->id.proto != m->proto) continue; + if (if_id != 0 && x->if_id != if_id) + continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, @@ -1524,6 +1525,11 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, if (!xc) return NULL; + xc->props.family = m->new_family; + + if (xfrm_init_state(xc) < 0) + goto error; + memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr)); memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr)); @@ -1825,6 +1831,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) int err = -ENOENT; __be32 minspi = htonl(low); __be32 maxspi = htonl(high); + __be32 newspi = 0; u32 mark = x->mark.v & x->mark.m; spin_lock_bh(&x->lock); @@ -1843,21 +1850,22 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) xfrm_state_put(x0); goto unlock; } - x->id.spi = minspi; + newspi = minspi; } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { spi = low + prandom_u32()%(high-low+1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { - x->id.spi = htonl(spi); + newspi = htonl(spi); break; } xfrm_state_put(x0); } } - if (x->id.spi) { + if (newspi) { spin_lock_bh(&net->xfrm.xfrm_state_lock); + x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); spin_unlock_bh(&net->xfrm.xfrm_state_lock); @@ -2404,6 +2412,7 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); + seqcount_init(&net->xfrm.xfrm_state_hash_generation); return 0; out_byspi: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 0b80c7907715..699e544b4bfd 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -521,7 +521,7 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, struct nlattr *et = attrs[XFRMA_ETIMER_THRESH]; struct nlattr *rt = attrs[XFRMA_REPLAY_THRESH]; - if (re) { + if (re && x->replay_esn && x->preplay_esn) { struct xfrm_replay_state_esn *replay_esn; replay_esn = nla_data(re); memcpy(x->replay_esn, replay_esn, @@ -579,6 +579,20 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, copy_from_user_state(x, p); + if (attrs[XFRMA_ENCAP]) { + x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), + sizeof(*x->encap), GFP_KERNEL); + if (x->encap == NULL) + goto error; + } + + if (attrs[XFRMA_COADDR]) { + x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), + sizeof(*x->coaddr), GFP_KERNEL); + if (x->coaddr == NULL) + goto error; + } + if (attrs[XFRMA_SA_EXTRA_FLAGS]) x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); @@ -599,23 +613,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, attrs[XFRMA_ALG_COMP]))) goto error; - if (attrs[XFRMA_ENCAP]) { - x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), - sizeof(*x->encap), GFP_KERNEL); - if (x->encap == NULL) - goto error; - } - if (attrs[XFRMA_TFCPAD]) x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]); - if (attrs[XFRMA_COADDR]) { - x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), - sizeof(*x->coaddr), GFP_KERNEL); - if (x->coaddr == NULL) - goto error; - } - xfrm_mark_get(attrs, &x->mark); xfrm_smark_init(attrs, &x->props.smark); @@ -1036,6 +1036,15 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) sizeof(*filter), GFP_KERNEL); if (filter == NULL) return -ENOMEM; + + /* see addr_match(), (prefix length >> 5) << 2 + * will be used to compare xfrm_address_t + */ + if (filter->splen > (sizeof(xfrm_address_t) << 3) || + filter->dplen > (sizeof(xfrm_address_t) << 3)) { + kfree(filter); + return -EINVAL; + } } if (attrs[XFRMA_PROTO]) @@ -1862,7 +1871,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; int delete; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; p = nlmsg_data(nlh); @@ -1879,8 +1887,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, + p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1897,8 +1908,8 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, - ctx, delete, &err); + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, + &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) @@ -2165,7 +2176,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type = XFRM_POLICY_TYPE_MAIN; int err = -ENOENT; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); @@ -2179,8 +2189,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, + 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2197,7 +2210,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } @@ -2369,6 +2382,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, int n = 0; struct net *net = sock_net(skb->sk); struct xfrm_encap_tmpl *encap = NULL; + u32 if_id = 0; if (attrs[XFRMA_MIGRATE] == NULL) return -EINVAL; @@ -2393,7 +2407,10 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; } - err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap); + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + + err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap, if_id); kfree(encap); @@ -2565,7 +2582,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_ALG_COMP] = { .len = sizeof(struct xfrm_algo) }, [XFRMA_ENCAP] = { .len = sizeof(struct xfrm_encap_tmpl) }, [XFRMA_TMPL] = { .len = sizeof(struct xfrm_user_tmpl) }, - [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_sec_ctx) }, + [XFRMA_SEC_CTX] = { .len = sizeof(struct xfrm_user_sec_ctx) }, [XFRMA_LTIME_VAL] = { .len = sizeof(struct xfrm_lifetime_cur) }, [XFRMA_REPLAY_VAL] = { .len = sizeof(struct xfrm_replay_state) }, [XFRMA_REPLAY_THRESH] = { .type = NLA_U32 }, @@ -2813,7 +2830,7 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) if (x->props.extra_flags) l += nla_total_size(sizeof(x->props.extra_flags)); if (x->xso.dev) - l += nla_total_size(sizeof(x->xso)); + l += nla_total_size(sizeof(struct xfrm_user_offload)); if (x->props.smark.v | x->props.smark.m) { l += nla_total_size(sizeof(x->props.smark.v)); l += nla_total_size(sizeof(x->props.smark.m)); |