diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 7f5fce9..830fefb 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -3540,7 +3540,13 @@ static int btusb_setup_qca_load_rampatch(struct hci_dev *hdev, "firmware rome 0x%x build 0x%x", rver_rom, rver_patch, ver_rom, ver_patch); - if (rver_rom != ver_rom || rver_patch <= ver_patch) { + /* Allow rampatch when the patch version equals the firmware version. + * A firmware download may be aborted by a transient USB error (e.g. + * disconnect) after the controller updates version info but before + * completion. + * Allowing equal versions enables re-flashing during recovery. + */ + if (rver_rom != ver_rom || rver_patch < ver_patch) { bt_dev_err(hdev, "rampatch file version did not match with firmware"); err = -EINVAL; goto done; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index ed28039..3450013 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1680,8 +1680,8 @@ static void qca_hw_error(struct hci_dev *hdev, u8 code) mod_timer(&qca->tx_idle_timer, jiffies + msecs_to_jiffies(qca->tx_idle_delay)); - /* Controller reset completion time is 50ms */ - msleep(50); + /* Wait for the controller to load the rampatch and NVM. */ + msleep(100); clear_bit(QCA_SSR_TRIGGERED, &qca->flags); clear_bit(QCA_IBS_DISABLED, &qca->flags); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9afc786..c9b1df1 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1727,6 +1727,9 @@ static void mana_fence_rqs(struct mana_port_context *apc) struct mana_rxq *rxq; int err; + if (!apc->rxqs) + return; + for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) { rxq = apc->rxqs[rxq_idx]; err = mana_fence_rq(apc, rxq); @@ -2858,13 +2861,16 @@ static void mana_destroy_vport(struct mana_port_context *apc) struct mana_rxq *rxq; u32 rxq_idx; - for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) { - rxq = apc->rxqs[rxq_idx]; - if (!rxq) - continue; + if (apc->rxqs) { + + for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) { + rxq = apc->rxqs[rxq_idx]; + if (!rxq) + continue; - mana_destroy_rxq(apc, rxq, true); - apc->rxqs[rxq_idx] = NULL; + mana_destroy_rxq(apc, rxq, true); + apc->rxqs[rxq_idx] = NULL; + } } mana_destroy_txq(apc); @@ -3269,7 +3275,8 @@ static int mana_dealloc_queues(struct net_device *ndev) if (apc->port_is_up) return -EINVAL; - mana_chn_setxdp(apc, NULL); + if (apc->rxqs) + mana_chn_setxdp(apc, NULL); if (gd->gdma_context->is_pf && !apc->ac->bm_hostmode) mana_pf_deregister_filter(apc); @@ -3287,33 +3294,38 @@ static int mana_dealloc_queues(struct net_device *ndev) * number of queues. */ - for (i = 0; i < apc->num_queues; i++) { - txq = &apc->tx_qp[i].txq; - tsleep = 1000; - while (atomic_read(&txq->pending_sends) > 0 && - time_before(jiffies, timeout)) { - usleep_range(tsleep, tsleep + 1000); - tsleep <<= 1; - } - if (atomic_read(&txq->pending_sends)) { - err = pcie_flr(to_pci_dev(gd->gdma_context->dev)); - if (err) { - netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n", - err, atomic_read(&txq->pending_sends), - txq->gdma_txq_id); + if (apc->tx_qp) { + for (i = 0; i < apc->num_queues; i++) { + txq = &apc->tx_qp[i].txq; + tsleep = 1000; + while (atomic_read(&txq->pending_sends) > 0 && + time_before(jiffies, timeout)) { + usleep_range(tsleep, tsleep + 1000); + tsleep <<= 1; + } + if (atomic_read(&txq->pending_sends)) { + err = + pcie_flr(to_pci_dev(gd->gdma_context->dev)); + if (err) { + netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n", + err, + atomic_read(&txq->pending_sends), + txq->gdma_txq_id); + } + break; } - break; } - } - for (i = 0; i < apc->num_queues; i++) { - txq = &apc->tx_qp[i].txq; - while ((skb = skb_dequeue(&txq->pending_skbs))) { - mana_unmap_skb(skb, apc); - dev_kfree_skb_any(skb); + for (i = 0; i < apc->num_queues; i++) { + txq = &apc->tx_qp[i].txq; + while ((skb = skb_dequeue(&txq->pending_skbs))) { + mana_unmap_skb(skb, apc); + dev_kfree_skb_any(skb); + } + atomic_set(&txq->pending_sends, 0); } - atomic_set(&txq->pending_sends, 0); } + /* We're 100% sure the queues can no longer be woken up, because * we're sure now mana_poll_tx_cq() can't be running. */ @@ -3338,6 +3350,12 @@ int mana_detach(struct net_device *ndev, bool from_close) ASSERT_RTNL(); + /* If already detached (indicates detach succeeded but attach failed + * previously). Now skip mana detach and just retry mana_attach. + */ + if (!from_close && !netif_device_present(ndev)) + return 0; + apc->port_st_save = apc->port_is_up; apc->port_is_up = false; diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c index c12f808..a753bd8 100644 --- a/drivers/net/pcs/pcs-mtk-lynxi.c +++ b/drivers/net/pcs/pcs-mtk-lynxi.c @@ -129,6 +129,9 @@ static int mtk_pcs_config_polarity(struct mtk_pcs_lynxi *mpcs, unsigned int val = 0; int ret; + if (!fwnode) + return 0; + if (fwnode_property_read_bool(fwnode, "mediatek,pnswap")) default_pol = PHY_POL_INVERT; diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 26e09c3..67d0147 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -177,16 +177,6 @@ static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) trailer_len = padding_len + noise_encrypted_len(0); plaintext_len = skb->len + padding_len; - /* Expand data section to have room for padding and auth tag. */ - num_frags = skb_cow_data(skb, trailer_len, &trailer); - if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) - return false; - - /* Set the padding to zeros, and make sure it and the auth tag are part - * of the skb. - */ - memset(skb_tail_pointer(trailer), 0, padding_len); - /* Expand head section to have room for our header and the network * stack's headers. */ @@ -198,6 +188,16 @@ static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) skb_checksum_help(skb))) return false; + /* Expand data section to have room for padding and auth tag. */ + num_frags = skb_cow_data(skb, trailer_len, &trailer); + if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) + return false; + + /* Set the padding to zeros, and make sure it and the auth tag are part + * of the skb. + */ + memset(skb_tail_pointer(trailer), 0, padding_len); + /* Only after checksumming can we safely add on the padding at the end * and the header. */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 10d3edd..8744091 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -715,6 +715,7 @@ struct xfrm_mgr { const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, + struct net *net, const struct xfrm_encap_tmpl *encap); bool (*is_alive)(const struct km_event *c); }; @@ -1891,7 +1892,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k, + const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap); struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 2f03b78..960a19b 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -486,6 +486,8 @@ static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) int ret; local_skb = skb_clone(skb, GFP_ATOMIC); + if (!local_skb) + continue; BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 17b46ad..54eabaa 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -870,8 +870,10 @@ static int hci_le_big_terminate(struct hci_dev *hdev, struct hci_conn *conn) d->big_sync_term = true; } - if (!d->pa_sync_term && !d->big_sync_term) + if (!d->pa_sync_term && !d->big_sync_term) { + kfree(d); return 0; + } ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index c46c123..28d7929 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -539,46 +539,9 @@ static int hci_dev_do_reset(struct hci_dev *hdev) hci_req_sync_lock(hdev); - /* Drop queues */ - skb_queue_purge(&hdev->rx_q); - skb_queue_purge(&hdev->cmd_q); - - /* Cancel these to avoid queueing non-chained pending work */ - hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); - /* Wait for - * - * if (!hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) - * queue_delayed_work(&hdev->{cmd,ncmd}_timer) - * - * inside RCU section to see the flag or complete scheduling. - */ - synchronize_rcu(); - /* Explicitly cancel works in case scheduled after setting the flag. */ - cancel_delayed_work(&hdev->cmd_timer); - cancel_delayed_work(&hdev->ncmd_timer); - - /* Avoid potential lockdep warnings from the *_flush() calls by - * ensuring the workqueue is empty up front. - */ - drain_workqueue(hdev->workqueue); - - hci_dev_lock(hdev); - hci_inquiry_cache_flush(hdev); - hci_conn_hash_flush(hdev); - hci_dev_unlock(hdev); - - if (hdev->flush) - hdev->flush(hdev); - - hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); - - atomic_set(&hdev->cmd_cnt, 1); - hdev->acl_cnt = 0; - hdev->sco_cnt = 0; - hdev->le_cnt = 0; - hdev->iso_cnt = 0; - - ret = hci_reset_sync(hdev); + ret = hci_dev_close_sync(hdev); + if (!ret) + ret = hci_dev_open_sync(hdev); hci_req_sync_unlock(hdev); return ret; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index aff8562..aeccd80 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -5301,6 +5301,12 @@ int hci_dev_close_sync(struct hci_dev *hdev) bt_dev_dbg(hdev, ""); + /* Set HCI_DRAIN_WORKQUEUE flag to prevent queuing work during + * reset/close. See hci_cmd_work() and handle_cmd_cnt_and_timer(). + */ + hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); + synchronize_rcu(); + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { disable_delayed_work(&hdev->power_off); disable_delayed_work(&hdev->ncmd_timer); @@ -5324,6 +5330,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) if (!test_and_clear_bit(HCI_UP, &hdev->flags)) { cancel_delayed_work_sync(&hdev->cmd_timer); + hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); return err; } @@ -5386,6 +5393,10 @@ int hci_dev_close_sync(struct hci_dev *hdev) /* Reset device */ skb_queue_purge(&hdev->cmd_q); atomic_set(&hdev->cmd_cnt, 1); + hdev->acl_cnt = 0; + hdev->sco_cnt = 0; + hdev->le_cnt = 0; + hdev->iso_cnt = 0; if (hci_test_quirk(hdev, HCI_QUIRK_RESET_ON_CLOSE) && !auto_off && !hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { set_bit(HCI_INIT, &hdev->flags); @@ -5423,6 +5434,7 @@ int hci_dev_close_sync(struct hci_dev *hdev) /* Clear flags */ hdev->flags &= BIT(HCI_RAW); hci_dev_clear_volatile_flags(hdev); + hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); memset(hdev->eir, 0, sizeof(hdev->eir)); memset(hdev->dev_class, 0, sizeof(hdev->dev_class)); @@ -6699,6 +6711,7 @@ int hci_le_create_cis_sync(struct hci_dev *hdev) DEFINE_FLEX(struct hci_cp_le_create_cis, cmd, cis, num_cis, 0x1f); size_t aux_num_cis = 0; struct hci_conn *conn; + u16 timeout = 0; u8 cig = BT_ISO_QOS_CIG_UNSET; /* The spec allows only one pending LE Create CIS command at a time. If @@ -6769,6 +6782,7 @@ int hci_le_create_cis_sync(struct hci_dev *hdev) set_bit(HCI_CONN_CREATE_CIS, &conn->flags); cis->acl_handle = cpu_to_le16(conn->parent->handle); cis->cis_handle = cpu_to_le16(conn->handle); + timeout = conn->conn_timeout; aux_num_cis++; if (aux_num_cis >= cmd->num_cis) @@ -6788,7 +6802,7 @@ done: return __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_CREATE_CIS, struct_size(cmd, cis, cmd->num_cis), cmd, HCI_EVT_LE_CIS_ESTABLISHED, - conn->conn_timeout, NULL); + timeout, NULL); } int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle) diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 976f91e..70344bd 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -179,12 +179,21 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb) { struct input_dev *dev = session->input; unsigned char *keys = session->keys; - unsigned char *udata = skb->data + 1; - signed char *sdata = skb->data + 1; - int i, size = skb->len - 1; + unsigned char *udata; + signed char *sdata; + u8 *hdr; + int i; + + hdr = skb_pull_data(skb, 1); + if (!hdr) + return; - switch (skb->data[0]) { + switch (*hdr) { case 0x01: /* Keyboard report */ + udata = skb_pull_data(skb, 8); + if (!udata) + break; + for (i = 0; i < 8; i++) input_report_key(dev, hidp_keycode[i + 224], (udata[0] >> i) & 1); @@ -213,6 +222,10 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb) break; case 0x02: /* Mouse report */ + sdata = skb_pull_data(skb, 3); + if (!sdata) + break; + input_report_key(dev, BTN_LEFT, sdata[0] & 0x01); input_report_key(dev, BTN_RIGHT, sdata[0] & 0x02); input_report_key(dev, BTN_MIDDLE, sdata[0] & 0x04); @@ -222,7 +235,7 @@ static void hidp_input_report(struct hidp_session *session, struct sk_buff *skb) input_report_rel(dev, REL_X, sdata[1]); input_report_rel(dev, REL_Y, sdata[2]); - if (size > 3) + if (skb->len > 0) input_report_rel(dev, REL_WHEEL, sdata[3]); break; } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index d7af617..8766495 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -564,7 +564,7 @@ static void iso_recv_frame(struct iso_conn *conn, struct sk_buff *skb) struct sock *sk; iso_conn_lock(conn); - sk = conn->sk; + sk = iso_sock_hold(conn); iso_conn_unlock(conn); if (!sk) @@ -573,11 +573,15 @@ static void iso_recv_frame(struct iso_conn *conn, struct sk_buff *skb) BT_DBG("sk %p len %d", sk, skb->len); if (sk->sk_state != BT_CONNECTED) - goto drop; + goto drop_put; - if (!sock_queue_rcv_skb(sk, skb)) + if (!sock_queue_rcv_skb(sk, skb)) { + sock_put(sk); return; + } +drop_put: + sock_put(sk); drop: kfree_skb(skb); } @@ -860,8 +864,8 @@ static void __iso_sock_close(struct sock *sk) /* Must be called on unlocked socket. */ static void iso_sock_close(struct sock *sk) { - iso_sock_clear_timer(sk); lock_sock(sk); + iso_sock_clear_timer(sk); __iso_sock_close(sk); release_sock(sk); iso_sock_kill(sk); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index fdccd62..45b1753 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -411,8 +411,10 @@ static void l2cap_chan_timeout(struct work_struct *work) BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); - if (!conn) + if (!conn) { + l2cap_chan_put(chan); return; + } mutex_lock(&conn->lock); /* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling @@ -5260,6 +5262,7 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, cmd_len -= sizeof(*rsp); list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { + struct l2cap_chan *orig; u16 dcid; if (chan->ident != cmd->ident || @@ -5281,8 +5284,10 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, BT_DBG("dcid[%d] 0x%4.4x", i, dcid); + orig = __l2cap_get_chan_by_dcid(conn, dcid); + /* Check if dcid is already in use */ - if (dcid && __l2cap_get_chan_by_dcid(conn, dcid)) { + if (dcid && orig) { /* If a device receives a * L2CAP_CREDIT_BASED_CONNECTION_RSP packet with an * already-assigned Destination CID, then both the @@ -5291,10 +5296,24 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, */ l2cap_chan_del(chan, ECONNREFUSED); l2cap_chan_unlock(chan); - chan = __l2cap_get_chan_by_dcid(conn, dcid); - l2cap_chan_lock(chan); - l2cap_chan_del(chan, ECONNRESET); - l2cap_chan_unlock(chan); + + /* Check that the dcid channel mode is + * L2CAP_MODE_EXT_FLOWCTL since this procedure is only + * valid for that mode and shouldn't disconnect a dcid + * in other modes. + */ + if (orig->mode == L2CAP_MODE_EXT_FLOWCTL) { + l2cap_chan_lock(orig); + /* Disconnect the original channel as it may be + * considered connected since dcid has already + * been assigned; don't call l2cap_chan_close + * directly since that could lead to + * l2cap_chan_del and then removing the channel + * from the list while we're iterating over it. + */ + __set_chan_timer(orig, 0); + l2cap_chan_unlock(orig); + } continue; } @@ -5458,14 +5477,20 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn, BT_DBG("result 0x%4.4x", result); - if (!result) + if (!result) { + list_for_each_entry(chan, &conn->chan_l, list) { + if (chan->ident == cmd->ident) + chan->ident = 0; + } return 0; + } list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { if (chan->ident != cmd->ident) continue; - l2cap_chan_hold(chan); + if (!l2cap_chan_hold_unless_zero(chan)) + continue; l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNRESET); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index b34e7da..c138aa4 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1499,6 +1499,10 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) * pin it (hold_unless_zero() additionally skips a chan already past * its last reference). We then drop the sk lock before taking * chan->lock, so sk and chan locks are never held together. + * + * Since we cannot call l2cap_chan_close() without conn->lock, + * schedule l2cap_chan_timeout to close the channel; it already + * acquires conn->lock -> chan->lock in the correct order. */ while ((sk = bt_accept_dequeue(parent, NULL))) { struct l2cap_chan *chan; @@ -1516,14 +1520,12 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) state_to_string(chan->state)); l2cap_chan_lock(chan); - __clear_chan_timer(chan); - l2cap_chan_close(chan, ECONNRESET); - /* l2cap_conn_del() may already have killed this socket - * (it sets SOCK_DEAD); skip the duplicate to avoid a - * double sock_put()/l2cap_chan_put(). + /* Since we cannot call l2cap_chan_close() without + * conn->lock, schedule its timer to trigger the close + * and cleanup of this channel. */ - if (!sock_flag(sk, SOCK_DEAD)) - l2cap_sock_kill(sk); + if (chan->conn) + __set_chan_timer(chan, 0); l2cap_chan_unlock(chan); l2cap_chan_put(chan); diff --git a/net/core/filter.c b/net/core/filter.c index 9590877..8043976 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2869,7 +2869,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, psge->length = start - offset; rsge.length -= psge->length; - rsge.offset += start; + rsge.offset += start - offset; sk_msg_iter_var_next(i); sg_unmark_end(psge); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0d3cc11..c02f0a5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6823,6 +6823,11 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, skb_copy_from_linear_data_offset(skb, off, data, new_hlen); skb->len -= off; + /* Remove SKBFL_MANAGED_FRAG_REFS instead of trying to honour it + * while refcounting frags below. + */ + skb_zcopy_downgrade_managed(skb); + memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, @@ -6936,6 +6941,11 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, return -ENOMEM; size = SKB_WITH_OVERHEAD(size); + /* Remove SKBFL_MANAGED_FRAG_REFS instead of trying to honour it + * while refcounting frags below. + */ + skb_zcopy_downgrade_managed(skb); + memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 4366cba..6fd642d 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -143,7 +143,7 @@ static void ah_output_done(void *data, int err) } kfree(AH_SKB_CB(skb)->tmp); - xfrm_output_resume(skb->sk, skb, err); + xfrm_output_resume(skb_to_full_sk(skb), skb, err); } static int ah_output(struct xfrm_state *x, struct sk_buff *skb) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 6a5febb..513c821 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -419,8 +419,8 @@ 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) + if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) > + PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5476b65..bb84a78 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1013,7 +1013,7 @@ ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) list_for_each(p, &idev->addr_list) { struct inet6_ifaddr *ifa = list_entry(p, struct inet6_ifaddr, if_list); - if (ifp_scope > ipv6_addr_src_scope(&ifa->addr)) + if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr)) break; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index de1e681..76f7a2d 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -337,7 +337,7 @@ static void ah6_output_done(void *data, int err) ah6_restore_hdrs(top_iph, iph_ext, extlen); kfree(AH_SKB_CB(skb)->tmp); - xfrm_output_resume(skb->sk, skb, err); + xfrm_output_resume(skb_to_full_sk(skb), skb, err); } static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 9c06c5a..57481e4 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -448,8 +448,8 @@ int esp6_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) + if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) > + PAGE_SIZE) goto cow; if (!skb_cloned(skb)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b106e5f..636f012 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -481,6 +481,9 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; + if (!READ_ONCE(first->fib6_nsiblings)) + break; + nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); if (hash > nh_upper_bound) continue; @@ -5902,6 +5905,8 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } + if (!READ_ONCE(rt->fib6_nsiblings)) + break; } rcu_read_unlock(); diff --git a/net/key/af_key.c b/net/key/af_key.c index a166a88..9cffeef 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3564,7 +3564,7 @@ static int set_ipsecrequest(struct sk_buff *skb, #ifdef CONFIG_NET_KEY_MIGRATE static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k, + const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { int i; @@ -3669,7 +3669,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* broadcast migrate message to sockets */ - pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net); + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, net); return 0; @@ -3680,7 +3680,7 @@ err: #else static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, - const struct xfrm_kmaddress *k, + const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1d2568b..66e12fb 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9403,6 +9403,8 @@ static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p) release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); + if (sk != asoc->base.sk) + goto do_error; *timeo_p = current_timeo; } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index b143290..b106669 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -205,6 +205,7 @@ static u16 virtio_transport_get_type(struct sock *sk) static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *info, size_t payload_len, bool zcopy, + struct ubuf_info *uarg, u32 src_cid, u32 src_port, u32 dst_cid, @@ -245,6 +246,12 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info * if (info->msg && payload_len > 0) { int err; + /* Bind the zerocopy lifetime before filling frags so error + * rollback frees managed fixed-buffer pages through + * the uarg-aware path. + */ + skb_zcopy_set(skb, uarg, NULL); + err = virtio_transport_fill_skb(skb, info, payload_len, zcopy); if (err) goto out; @@ -364,6 +371,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, skb_len = min(max_skb_len, rest_len); skb = virtio_transport_alloc_skb(info, skb_len, can_zcopy, + uarg, src_cid, src_port, dst_cid, dst_port); if (!skb) { @@ -371,8 +379,6 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, break; } - skb_zcopy_set(skb, uarg, NULL); - virtio_transport_inc_tx_pkt(vvs, skb); ret = t_ops->send_pkt(skb, info->net); @@ -1183,7 +1189,7 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t, if (!t) return -ENOTCONN; - reply = virtio_transport_alloc_skb(&info, 0, false, + reply = virtio_transport_alloc_skb(&info, 0, false, NULL, le64_to_cpu(hdr->dst_cid), le32_to_cpu(hdr->dst_port), le64_to_cpu(hdr->src_cid), diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index f65291e..e4c2cd2 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -797,9 +797,12 @@ static void xfrm_trans_reinject(struct work_struct *work) spin_unlock_bh(&trans->queue_lock); local_bh_disable(); - while ((skb = __skb_dequeue(&queue))) - XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net, - NULL, skb); + while ((skb = __skb_dequeue(&queue))) { + struct net *net = XFRM_TRANS_SKB_CB(skb)->net; + + XFRM_TRANS_SKB_CB(skb)->finish(net, NULL, skb); + put_net(net); + } local_bh_enable(); } @@ -808,6 +811,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, struct sk_buff *)) { struct xfrm_trans_tasklet *trans; + struct net *hold_net; trans = this_cpu_ptr(&xfrm_trans_tasklet); @@ -816,8 +820,12 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); + hold_net = maybe_get_net(net); + if (!hold_net) + return -ENODEV; + XFRM_TRANS_SKB_CB(skb)->finish = finish; - XFRM_TRANS_SKB_CB(skb)->net = net; + XFRM_TRANS_SKB_CB(skb)->net = hold_net; spin_lock_bh(&trans->queue_lock); __skb_queue_tail(&trans->queue, skb); spin_unlock_bh(&trans->queue_lock); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 5f38dff..671d48f 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -51,11 +51,15 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen) struct scatterlist *dsg; int len, dlen; - if (unlikely(err)) - goto out_free_req; + if (unlikely(!req)) + return err; extra = acomp_request_extra(req); dsg = extra->sg; + + if (unlikely(err)) + goto out_free_req; + dlen = req->dlen; pskb_trim_unique(skb, 0); @@ -84,10 +88,10 @@ static int ipcomp_post_acomp(struct sk_buff *skb, int err, int hlen) skb_shinfo(skb)->nr_frags++; } while ((dlen -= len)); - for (; dsg; dsg = sg_next(dsg)) +out_free_req: + for (; dsg && sg_page(dsg); dsg = sg_next(dsg)) __free_page(sg_page(dsg)); -out_free_req: acomp_request_free(req); return err; } diff --git a/net/xfrm/xfrm_iptfs.c b/net/xfrm/xfrm_iptfs.c index 97bc979..6c6bbc0 100644 --- a/net/xfrm/xfrm_iptfs.c +++ b/net/xfrm/xfrm_iptfs.c @@ -2650,7 +2650,8 @@ static void __iptfs_init_state(struct xfrm_state *x, x->props.enc_hdr_len = sizeof(struct ip_iptfs_hdr); /* Always keep a module reference when x->mode_data is set */ - __module_get(x->mode_cbs->owner); + if (x->mode_data != xtfs) + __module_get(x->mode_cbs->owner); x->mode_data = xtfs; xtfs->x = x; @@ -2658,22 +2659,39 @@ static void __iptfs_init_state(struct xfrm_state *x, static int iptfs_clone_state(struct xfrm_state *x, struct xfrm_state *orig) { + struct skb_wseq *w_saved = NULL; struct xfrm_iptfs_data *xtfs; xtfs = kmemdup(orig->mode_data, sizeof(*xtfs), GFP_KERNEL); if (!xtfs) return -ENOMEM; - xtfs->ra_newskb = NULL; if (xtfs->cfg.reorder_win_size) { - xtfs->w_saved = kzalloc_objs(*xtfs->w_saved, - xtfs->cfg.reorder_win_size); - if (!xtfs->w_saved) { + w_saved = kzalloc_objs(*w_saved, xtfs->cfg.reorder_win_size); + if (!w_saved) { kfree_sensitive(xtfs); return -ENOMEM; } } + xtfs->w_saved = w_saved; + + __skb_queue_head_init(&xtfs->queue); + xtfs->queue_size = 0; + hrtimer_setup(&xtfs->iptfs_timer, iptfs_delay_timer, CLOCK_MONOTONIC, + IPTFS_HRTIMER_MODE); + + spin_lock_init(&xtfs->drop_lock); + hrtimer_setup(&xtfs->drop_timer, iptfs_drop_timer, CLOCK_MONOTONIC, + IPTFS_HRTIMER_MODE); + xtfs->w_seq_set = false; + xtfs->w_wantseq = 0; + xtfs->w_savedlen = 0; + xtfs->ra_newskb = NULL; + xtfs->ra_wantseq = 0; + xtfs->ra_runtlen = 0; + + __module_get(x->mode_cbs->owner); x->mode_data = xtfs; xtfs->x = x; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index c944327..dd09d20 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4276,21 +4276,21 @@ out_byidx: return -ENOMEM; } -static void xfrm_policy_fini(struct net *net) +static void __net_exit xfrm_net_pre_exit(struct net *net) { - struct xfrm_pol_inexact_bin *b, *t; - unsigned int sz; - int dir; - disable_work_sync(&net->xfrm.policy_hthresh.work); - flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); #endif xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false); +} - synchronize_rcu(); +static void xfrm_policy_fini(struct net *net) +{ + struct xfrm_pol_inexact_bin *b, *t; + unsigned int sz; + int dir; WARN_ON(!list_empty(&net->xfrm.policy_all)); @@ -4368,6 +4368,7 @@ static void __net_exit xfrm_net_exit(struct net *net) static struct pernet_operations __net_initdata xfrm_net_ops = { .init = xfrm_net_init, + .pre_exit = xfrm_net_pre_exit, .exit = xfrm_net_exit, }; @@ -4703,7 +4704,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* Stage 5 - announce */ - km_migrate(sel, dir, type, m, num_migrate, k, encap); + km_migrate(sel, dir, type, m, num_migrate, k, net, encap); xfrm_pol_put(pol); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 686014d..589c3b6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2837,7 +2837,7 @@ EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k, + const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { int err = -EINVAL; @@ -2848,7 +2848,7 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { ret = km->migrate(sel, dir, type, m, num_migrate, k, - encap); + net, encap); if (!ret) err = ret; } @@ -3114,10 +3114,14 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; u32 blksize, net_adj = 0; + u32 overhead, payload_mtu; if (x->km.state != XFRM_STATE_VALID || - !type || type->proto != IPPROTO_ESP) + !type || type->proto != IPPROTO_ESP) { + if (mtu <= x->props.header_len) + return 1; return mtu - x->props.header_len; + } aead = x->data; blksize = ALIGN(crypto_aead_blocksize(aead), 4); @@ -3140,8 +3144,17 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) break; } - return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - - net_adj) & ~(blksize - 1)) + net_adj - 2; + overhead = x->props.header_len + crypto_aead_authsize(aead) + net_adj; + if (mtu <= overhead) + return 1; + + payload_mtu = mtu - overhead; + payload_mtu &= ~(blksize - 1); + if (payload_mtu <= 2) + return 1; + + return payload_mtu + net_adj - 2; + } EXPORT_SYMBOL_GPL(xfrm_state_mtu); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 38a90e5..71a4b72 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -3271,10 +3271,9 @@ out_cancel: static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k, + const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { - struct net *net = &init_net; struct sk_buff *skb; int err; @@ -3292,7 +3291,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, #else static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, - const struct xfrm_kmaddress *k, + const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { return -ENOPROTOOPT; diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index b2b9988..845c26d 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -273,8 +273,8 @@ setup() ip -netns $ioam_node_beta link set ioam-veth-betaR name veth1 &>/dev/null ip -netns $ioam_node_gamma link set ioam-veth-gamma name veth0 &>/dev/null - ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null ip -netns $ioam_node_alpha addr add 2001:db8:1::50/64 dev veth0 &>/dev/null + ip -netns $ioam_node_alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null ip -netns $ioam_node_alpha link set veth0 up &>/dev/null ip -netns $ioam_node_alpha link set lo up &>/dev/null ip -netns $ioam_node_alpha route add 2001:db8:2::/64 \