diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-07-09 08:26:51 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-07-09 08:26:51 -0700 |
| commit | 2c7c88a412aa6d09cd04b414211b4ef8553b5309 (patch) | |
| tree | 79b8874287ea0f25641f509a0dec4591555a5711 | |
| parent | 6bad2e38fe7f2da7dc982b2b80814e632832e568 (diff) | |
| parent | f5089008f90c0a7c5520dff3934e0af00adf322d (diff) | |
Merge tag 'net-7.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from netfilter, Bluetooth and batman-adv.
Current release - regressions:
- bluetooth: fix using chan->conn as indication to no remote netdev
Current release - new code bugs:
- netfilter: cap to maximum number of expectation per master on
updates
Previous releases - regressions:
- bluetooth:
- fix UAF of hci_conn_params in add_device_complete
- fix null ptr deref in hci_abort_conn()
- igmp: remove multicast group from hash table on device destruction
- batman-adv: prevent TVLV OOB check overflow
- eth: mlx5/mlx5e:
- fix off-by-one in single-FDB error rollback
- skip peer flow cleanup when LAG seq is unavailable
- fix crashes in dynamic per-channel stats and HV VHCA agent
- eth: mana: Sync page pool RX frags for CPU
Previous releases - always broken:
- netfilter:
- mark malformed IPv6 extension headers for hotdrop
- terminate table name before find_table_lock()
- ipvs: use parsed transport offset in TCP state lookup
- sched: act_pedit: fix TOCTOU heap OOB write in tc offload
- ethtool: rss: fix hfunc and input_xfrm parsing on big endian
- ipv4/ipv6: fix UAF and memory leak in IGMP/MLD
- tls: consume empty data records in tls_sw_read_sock()
- eth:
- octeontx2-af: fix VF bringup affecting PF promiscuous state
- gue: validate REMCSUM private option length"
* tag 'net-7.2-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (94 commits)
macsec: don't read an unset MAC header in macsec_encrypt()
dibs: loopback: validate offset and size in move_data()
octeontx2-af: fix VF bringup affecting PF promiscuous state
ethtool: rss: Fix hfunc and input_xfrm parsing on big endian
net/mlx5: Fix L3 tunnel entropy refcount leak
net: macb: drop in-flight Tx SKBs on close
net: mana: Sync page pool RX frags for CPU
net: mana: Validate the packet length reported by the NIC
selftests/net: fix EVP_MD_CTX leak in tcp_mmap
ipvs: ensure inner headers in ICMP errors are in headroom
ipvs: use parsed transport offset in SCTP state lookup
ipvs: use parsed transport offset in TCP state lookup
ipvs: pass parsed transport offset to state handlers
netfilter: handle unreadable frags
netfilter: flowtable: support IPIP tunnel with direct xmit
netfilter: flowtable: IPIP tunnel hardware offload is not yet support
netfilter: flowtable: use dst in this direction when pushing IPIP header
netfilter: ipset: allocate the proper memory for the generic hash structure
netfilter: ipset: cleanup the add/del backlog when resize failed
netfilter: ipset: exclude gc when resize is in progress
...
112 files changed, 1402 insertions, 740 deletions
diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c index 2ae38a321c4b..e63d1af250ec 100644 --- a/drivers/bluetooth/bpa10x.c +++ b/drivers/bluetooth/bpa10x.c @@ -255,9 +255,13 @@ static int bpa10x_setup(struct hci_dev *hdev) if (IS_ERR(skb)) return PTR_ERR(skb); - bt_dev_info(hdev, "%s", (char *)(skb->data + 1)); + /* Bounded print: the device controls skb->len. */ + if (skb->len > 1) { + int len = skb->len - 1; - hci_set_fw_info(hdev, "%s", skb->data + 1); + bt_dev_info(hdev, "%.*s", len, (char *)(skb->data + 1)); + hci_set_fw_info(hdev, "%.*s", len, skb->data + 1); + } kfree_skb(skb); return 0; diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 9e39327dc1fe..2b7231be5973 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -2127,6 +2127,9 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev, if (test_bit(BTINTEL_PCIE_CORE_HALTED, &data->flags)) return -ENODEV; + if (test_bit(BTINTEL_PCIE_RECOVERY_IN_PROGRESS, &data->flags)) + return -ENODEV; + /* Due to the fw limitation, the type header of the packet should be * 4 bytes unlike 1 byte for UART. In UART, the firmware can read * the first byte to get the packet type and redirect the rest of data @@ -2485,7 +2488,6 @@ static void btintel_pcie_inc_recovery_count(struct pci_dev *pdev, } } -static int btintel_pcie_setup_hdev(struct btintel_pcie_data *data); static void btintel_pcie_reset(struct hci_dev *hdev); static int btintel_pcie_acpi_reset_method(struct btintel_pcie_data *data) @@ -2596,12 +2598,45 @@ static void btintel_pcie_perform_pldr(struct btintel_pcie_data *data) } } +/* + * Issue a Function Level Reset and hand teardown/re-init off to the PCI + * core via device_reprobe(), mirroring the PLDR path's contract. + * + * Caller must hold pci_lock_rescan_remove() and must have already + * disabled interrupts and drained both rx_work and coredump_work. + */ +static int btintel_pcie_perform_flr(struct btintel_pcie_data *data) +{ + struct pci_dev *pdev = data->pdev; + int err; + + /* pci_try_reset_function() avoids the device_lock ABBA against + * btintel_pcie_remove(): .remove() runs with device_lock held and + * then waits for this work via disable_work_sync(); the blocking + * pci_reset_function() would deadlock by trying to re-acquire + * device_lock here. + */ + err = pci_try_reset_function(pdev); + if (err) { + BT_ERR("Failed resetting the pcie device (%d)", err); + return err; + } + + /* device_reprobe() always detaches the driver first (running + * .remove(), which frees 'data'); any re-probe failure leaves the + * device unbound but 'data' is already gone, so just log it. + */ + if (device_reprobe(&pdev->dev)) + BT_ERR("BT reprobe failed for BDF:%s", pci_name(pdev)); + + return 0; +} + static void btintel_pcie_reset_work(struct work_struct *wk) { struct btintel_pcie_data *data = container_of(wk, struct btintel_pcie_data, reset_work); struct pci_dev *pdev = data->pdev; - int err; pci_lock_rescan_remove(); @@ -2621,60 +2656,27 @@ static void btintel_pcie_reset_work(struct work_struct *wk) disable_work_sync(&data->coredump_work); bt_dev_dbg(data->hdev, "Release bluetooth interface"); + + /* Both reset paths follow the same contract: on success they + * destroy 'data' via device_reprobe() (a fresh probe re-INIT_WORKs + * the coredump_work with disable count 0), so enable_work() must + * NOT be called on the success path. Only the FLR path can fail + * with 'data' still alive, in which case we balance the + * disable_work_sync() above so a later successful reset is not + * permanently blocked. + * + * pci_lock_rescan_remove() (held above) serializes against PCI + * device addition/removal (hotplug), so no device can be added to + * or removed from the bus list while this code runs. + */ if (data->reset_type == BTINTEL_PCIE_IOSF_PRR_PLDR) { - /* This function holds pci_lock_rescan_remove(), which acquires - * pci_rescan_remove_lock. This mutex serializes against PCI device - * addition/removal (hotplug), so no device can be added to or - * removed from the bus list while this code runs. - * - * device_reprobe() inside btintel_pcie_perform_pldr() destroys - * 'data' via .remove(); a fresh probe re-INIT_WORKs the - * coredump_work with disable count 0, so we must not call - * enable_work() on this path. - */ btintel_pcie_perform_pldr(data); goto out; } - btintel_pcie_release_hdev(data); - - /* Use pci_try_reset_function() rather than pci_reset_function() to - * avoid an ABBA deadlock against btintel_pcie_remove(): the PCI core - * calls .remove() with device_lock held, and remove() then waits for - * this work via cancel_work_sync(); pci_reset_function() would in - * turn try to acquire the same device_lock, deadlocking both paths. - */ - err = pci_try_reset_function(pdev); - if (err) { - BT_ERR("Failed resetting the pcie device (%d)", err); - goto out_enable; - } - btintel_pcie_enable_interrupts(data); - btintel_pcie_config_msix(data); - - err = btintel_pcie_enable_bt(data); - if (err) { - BT_ERR("Failed to enable bluetooth hardware after reset (%d)", - err); - goto out_enable; - } - - btintel_pcie_reset_ia(data); - btintel_pcie_start_rx(data); - data->flags = 0; + if (btintel_pcie_perform_flr(data)) + enable_work(&data->coredump_work); - err = btintel_pcie_setup_hdev(data); - if (err) { - BT_ERR("Failed registering hdev (%d)", err); - goto out_enable; - } - -out_enable: - /* Balance disable_work_sync() above on every exit. Leaving the - * counter incremented on a failed reset would permanently disable - * coredump_work even after a later successful reset. - */ - enable_work(&data->coredump_work); out: pci_dev_put(pdev); pci_unlock_rescan_remove(); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index e7036a48ce48..6a1cffe08d5f 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1267,6 +1267,12 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb) } nxpdev->fw_dnld_v3_offset = offset - nxpdev->fw_v3_offset_correction; + if (nxpdev->fw_dnld_v3_offset >= nxpdev->fw->size || + len > nxpdev->fw->size - nxpdev->fw_dnld_v3_offset) { + bt_dev_err(hdev, "FW download out of bounds, ignoring request"); + len = 0; + goto free_skb; + } serdev_device_write_buf(nxpdev->serdev, nxpdev->fw->data + nxpdev->fw_dnld_v3_offset, len); diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 47f4902b40b4..2ad42c3bbaac 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -239,6 +239,8 @@ static int hci_uart_flush(struct hci_dev *hdev) BT_DBG("hdev %p tty %p", hdev, tty); + disable_work_sync(&hu->write_work); + if (hu->tx_skb) { kfree_skb(hu->tx_skb); hu->tx_skb = NULL; } @@ -254,6 +256,14 @@ static int hci_uart_flush(struct hci_dev *hdev) percpu_up_read(&hu->proto_lock); + /* Resume TX. Also reschedule in case work was queued concurrently; + * this may schedule write_work although there's nothing to do. + */ + enable_work(&hu->write_work); + clear_bit(HCI_UART_SENDING, &hu->tx_state); + if (test_bit(HCI_UART_TX_WAKEUP, &hu->tx_state)) + hci_uart_tx_wakeup(hu); + return 0; } @@ -271,12 +281,8 @@ static int hci_uart_open(struct hci_dev *hdev) /* Close device */ static int hci_uart_close(struct hci_dev *hdev) { - struct hci_uart *hu = hci_get_drvdata(hdev); - BT_DBG("hdev %p", hdev); - cancel_work_sync(&hu->write_work); - hci_uart_flush(hdev); hdev->flush = NULL; return 0; diff --git a/drivers/dibs/dibs_loopback.c b/drivers/dibs/dibs_loopback.c index ec3b48cb0e87..0f2e09311152 100644 --- a/drivers/dibs/dibs_loopback.c +++ b/drivers/dibs/dibs_loopback.c @@ -254,6 +254,11 @@ static int dibs_lo_move_data(struct dibs_dev *dibs, u64 dmb_tok, read_unlock_bh(&ldev->dmb_ht_lock); return -EINVAL; } + if ((u64)offset + size > rmb_node->len) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + memcpy((char *)rmb_node->cpu_addr + offset, data, size); sba_idx = rmb_node->sba_idx; read_unlock_bh(&ldev->dmb_ht_lock); diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 724a8163a514..951dd10e192b 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3301,9 +3301,9 @@ static size_t amt_get_size(const struct net_device *dev) nla_total_size(sizeof(__u16)) + /* IFLA_AMT_GATEWAY_PORT */ nla_total_size(sizeof(__u32)) + /* IFLA_AMT_LINK */ nla_total_size(sizeof(__u32)) + /* IFLA_MAX_TUNNELS */ - nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_DISCOVERY_IP */ - nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_REMOTE_IP */ - nla_total_size(sizeof(struct iphdr)); /* IFLA_AMT_LOCAL_IP */ + nla_total_size(sizeof(__be32)) + /* IFLA_AMT_DISCOVERY_IP */ + nla_total_size(sizeof(__be32)) + /* IFLA_AMT_REMOTE_IP */ + nla_total_size(sizeof(__be32)); /* IFLA_AMT_LOCAL_IP */ } static int amt_fill_info(struct sk_buff *skb, const struct net_device *dev) diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index fd282a1700fb..d394f1f43b68 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2668,8 +2668,25 @@ static void macb_free_consistent(struct macb *bp) dma_free_coherent(dev, size, bp->queues[0].rx_ring, bp->queues[0].rx_ring_dma); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - kfree(queue->tx_skb); - queue->tx_skb = NULL; + if (queue->tx_skb) { + unsigned int dropped = 0, tail; + + for (tail = queue->tx_tail; tail != queue->tx_head; + tail++) { + if (macb_tx_skb(queue, tail)->skb) + dropped++; + macb_tx_unmap(bp, macb_tx_skb(queue, tail), 0); + } + + queue->stats.tx_dropped += dropped; + bp->dev->stats.tx_dropped += dropped; + + kfree(queue->tx_skb); + queue->tx_skb = NULL; + } + + queue->tx_head = 0; + queue->tx_tail = 0; queue->tx_ring = NULL; queue->rx_ring = NULL; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 0db08ac3d098..e303956b4bf1 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3779,9 +3779,7 @@ setup_nic_dev_done: static int octeon_enable_sriov(struct octeon_device *oct) { unsigned int num_vfs_alloced = oct->sriov_info.num_vfs_alloced; - struct pci_dev *vfdev; int err; - u32 u; if (OCTEON_CN23XX_PF(oct) && num_vfs_alloced) { err = pci_enable_sriov(oct->pci_dev, @@ -3794,23 +3792,6 @@ static int octeon_enable_sriov(struct octeon_device *oct) return err; } oct->sriov_info.sriov_enabled = 1; - - /* init lookup table that maps DPI ring number to VF pci_dev - * struct pointer - */ - u = 0; - vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, - OCTEON_CN23XX_VF_VID, NULL); - while (vfdev) { - if (vfdev->is_virtfn && - (vfdev->physfn == oct->pci_dev)) { - oct->sriov_info.dpiring_to_vfpcidev_lut[u] = - vfdev; - u += oct->sriov_info.rings_per_vf; - } - vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, - OCTEON_CN23XX_VF_VID, vfdev); - } } return num_vfs_alloced; @@ -3818,8 +3799,6 @@ static int octeon_enable_sriov(struct octeon_device *oct) static int lio_pci_sriov_disable(struct octeon_device *oct) { - int u; - if (pci_vfs_assigned(oct->pci_dev)) { dev_err(&oct->pci_dev->dev, "VFs are still assigned to VMs.\n"); return -EPERM; @@ -3827,12 +3806,6 @@ static int lio_pci_sriov_disable(struct octeon_device *oct) pci_disable_sriov(oct->pci_dev); - u = 0; - while (u < MAX_POSSIBLE_VFS) { - oct->sriov_info.dpiring_to_vfpcidev_lut[u] = NULL; - u += oct->sriov_info.rings_per_vf; - } - oct->sriov_info.num_vfs_alloced = 0; dev_info(&oct->pci_dev->dev, "oct->pf_num:%d disabled VFs\n", oct->pf_num); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index 19344b21f8fb..858a0fff2cc0 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -390,9 +390,6 @@ struct octeon_sriov_info { struct lio_trusted_vf trusted_vf; - /*lookup table that maps DPI ring number to VF pci_dev struct pointer*/ - struct pci_dev *dpiring_to_vfpcidev_lut[MAX_POSSIBLE_VFS]; - u64 vf_macaddr[MAX_POSSIBLE_VFS]; u16 vf_vlantci[MAX_POSSIBLE_VFS]; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c index ad685f5d0a13..697fcdc41e3c 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c @@ -26,6 +26,31 @@ #include "octeon_mailbox.h" #include "cn23xx_pf_device.h" +static struct pci_dev *lio_vf_pci_dev_by_qno(struct octeon_device *oct, u32 q_no) +{ + struct pci_dev *vfdev = NULL; + int vfidx; + + if (!oct->sriov_info.rings_per_vf) + return NULL; + + if (q_no % oct->sriov_info.rings_per_vf) + return NULL; + + vfidx = q_no / oct->sriov_info.rings_per_vf; + if (vfidx >= oct->sriov_info.num_vfs_alloced) + return NULL; + + while ((vfdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, + OCTEON_CN23XX_VF_VID, vfdev))) { + if (pci_physfn(vfdev) && pci_physfn(vfdev) == oct->pci_dev && + pci_iov_vf_id(vfdev) == vfidx) + return vfdev; + } + + return NULL; +} + /** * octeon_mbox_read: * @mbox: Pointer mailbox @@ -237,6 +262,7 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, struct octeon_mbox_cmd *mbox_cmd) { struct octeon_device *oct = mbox->oct_dev; + struct pci_dev *vfdev; switch (mbox_cmd->msg.s.cmd) { case OCTEON_VF_ACTIVE: @@ -260,7 +286,12 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, dev_info(&oct->pci_dev->dev, "got a request for FLR from VF that owns DPI ring %u\n", mbox->q_no); - pcie_flr(oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no]); + vfdev = lio_vf_pci_dev_by_qno(oct, mbox->q_no); + if (!vfdev) + break; + + pcie_flr(vfdev); + pci_dev_put(vfdev); break; case OCTEON_PF_CHANGED_VF_MACADDR: diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0297c7ab0614..6a0ce2665031 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4580,7 +4580,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, rvu_npc_install_allmulti_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base); } else { - if (!nix_rx_multicast) + if (!nix_rx_multicast && !is_vf(pcifunc)) rvu_npc_enable_allmulti_entry(rvu, pcifunc, nixlf, false); } @@ -4590,7 +4590,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, pfvf->rx_chan_base, pfvf->rx_chan_cnt); else - if (!nix_rx_multicast) + if (!nix_rx_multicast && !is_vf(pcifunc)) rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false); return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index b63df5737ff2..2e33b33ec993 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1568,15 +1568,15 @@ static void otx2_free_sq_res(struct otx2_nic *pf) otx2_sq_free_sqbs(pf); for (qidx = 0; qidx < otx2_get_total_tx_queues(pf); qidx++) { sq = &qset->sq[qidx]; - /* Skip freeing Qos queues if they are not initialized */ - if (!sq->sqe) - continue; - qmem_free(pf->dev, sq->sqe); - qmem_free(pf->dev, sq->sqe_ring); - qmem_free(pf->dev, sq->cpt_resp); - qmem_free(pf->dev, sq->tso_hdrs); - qmem_free(pf->dev, sq->timestamps); - kfree(sq->sg); + /* sq->sqe is not initialized for unused QoS queues */ + if (sq->sqe) { + qmem_free(pf->dev, sq->sqe); + qmem_free(pf->dev, sq->sqe_ring); + qmem_free(pf->dev, sq->cpt_resp); + qmem_free(pf->dev, sq->tso_hdrs); + qmem_free(pf->dev, sq->timestamps); + kfree(sq->sg); + } kfree(sq->sqb_ptrs); } } @@ -1711,13 +1711,12 @@ int otx2_init_hw_resources(struct otx2_nic *pf) return err; err_free_nix_queues: - otx2_free_sq_res(pf); otx2_free_cq_res(pf); otx2_ctx_disable(mbox, NIX_AQ_CTYPE_RQ, false); err_free_txsch: otx2_txschq_stop(pf); err_free_sq_ptrs: - otx2_sq_free_sqbs(pf); + otx2_free_sq_res(pf); err_free_rq_ptrs: otx2_free_aura_ptr(pf, AURA_NIX_RQ); otx2_ctx_disable(mbox, NPA_AQ_CTYPE_POOL, true); @@ -2517,10 +2516,42 @@ EXPORT_SYMBOL(otx2_config_hwtstamp_set); static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac) { + struct npc_get_field_status_req *freq; + struct npc_get_field_status_rsp *frsp; struct npc_install_flow_req *req; int err; mutex_lock(&pf->mbox.lock); + + /* Skip installing the DMAC filter if the hardware parser profile + * does not support DMAC extraction. + */ + freq = otx2_mbox_alloc_msg_npc_get_field_status(&pf->mbox); + if (!freq) { + err = -ENOMEM; + goto out; + } + + freq->field = NPC_DMAC; + err = otx2_sync_mbox_msg(&pf->mbox); + if (err) + goto out; + + frsp = (struct npc_get_field_status_rsp *)otx2_mbox_get_rsp + (&pf->mbox.mbox, 0, &freq->hdr); + if (IS_ERR(frsp)) { + err = PTR_ERR(frsp); + goto out; + } + + if (!frsp->enable) { + netdev_warn(pf->netdev, + "VF %d MAC filter not installed: DMAC extraction not supported by parser profile\n", + vf); + err = -EOPNOTSUPP; + goto out; + } + req = otx2_mbox_alloc_msg_npc_install_flow(&pf->mbox); if (!req) { err = -ENOMEM; @@ -2559,13 +2590,12 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (!is_valid_ether_addr(mac)) return -EINVAL; - config = &pf->vf_configs[vf]; - ether_addr_copy(config->mac, mac); - ret = otx2_do_set_vf_mac(pf, vf, mac); - if (ret == 0) - dev_info(&pdev->dev, - "Load/Reload VF driver\n"); + if (ret == 0) { + config = &pf->vf_configs[vf]; + ether_addr_copy(config->mac, mac); + dev_info(&pdev->dev, "Load/Reload VF driver\n"); + } return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2270e2e550dd..d507289096c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -987,6 +987,18 @@ struct mlx5e_priv { struct ethtool_fec_hist_range *fec_ranges; }; +static inline u16 mlx5e_stats_nch_read(const struct mlx5e_priv *priv) +{ + /* Pairs with smp_store_release in mlx5e_stats_nch_write(). */ + return smp_load_acquire(&priv->stats_nch); +} + +static inline void mlx5e_stats_nch_write(struct mlx5e_priv *priv, u16 n) +{ + /* Pairs with smp_load_acquire in mlx5e_stats_nch_read(). */ + smp_store_release(&priv->stats_nch, n); +} + struct mlx5e_dev { struct net_device *netdev; struct devlink_port dl_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c index 195863b2c013..631f802105d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c @@ -33,9 +33,10 @@ mlx5e_hv_vhca_fill_ring_stats(struct mlx5e_priv *priv, int ch, static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data, int buf_len) { + u16 nch = mlx5e_stats_nch_read(priv); int ch, i = 0; - for (ch = 0; ch < priv->stats_nch; ch++) { + for (ch = 0; ch < nch; ch++) { void *buf = data + i; if (WARN_ON_ONCE(buf + @@ -50,8 +51,15 @@ static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data, static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv) { + u16 nch = mlx5e_stats_nch_read(priv); + + return sizeof(struct mlx5e_hv_vhca_per_ring_stats) * nch; +} + +static int mlx5e_hv_vhca_stats_buf_max_size(struct mlx5e_priv *priv) +{ return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) * - priv->stats_nch); + max(priv->max_nch, priv->stats_nch)); } static void mlx5e_hv_vhca_stats_work(struct work_struct *work) @@ -67,7 +75,7 @@ static void mlx5e_hv_vhca_stats_work(struct work_struct *work) sagent = container_of(dwork, struct mlx5e_hv_vhca_stats_agent, work); priv = container_of(sagent, struct mlx5e_priv, stats_agent); buf_len = mlx5e_hv_vhca_stats_buf_size(priv); - agent = sagent->agent; + agent = READ_ONCE(sagent->agent); buf = sagent->buf; memset(buf, 0, buf_len); @@ -100,7 +108,7 @@ static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent, sagent = &priv->stats_agent; block->version = MLX5_HV_VHCA_STATS_VERSION; - block->rings = priv->stats_nch; + block->rings = mlx5e_stats_nch_read(priv); if (!block->command) { cancel_delayed_work_sync(&priv->stats_agent.work); @@ -122,18 +130,21 @@ static void mlx5e_hv_vhca_stats_cleanup(struct mlx5_hv_vhca_agent *agent) void mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv) { - int buf_len = mlx5e_hv_vhca_stats_buf_size(priv); + int buf_len = mlx5e_hv_vhca_stats_buf_max_size(priv); struct mlx5_hv_vhca_agent *agent; priv->stats_agent.buf = kvzalloc(buf_len, GFP_KERNEL); if (!priv->stats_agent.buf) return; + INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work); + agent = mlx5_hv_vhca_agent_create(priv->mdev->hv_vhca, MLX5_HV_VHCA_AGENT_STATS, mlx5e_hv_vhca_stats_control, NULL, mlx5e_hv_vhca_stats_cleanup, - priv); + priv, + &priv->stats_agent.agent); if (IS_ERR_OR_NULL(agent)) { if (IS_ERR(agent)) @@ -142,18 +153,20 @@ void mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv) agent); kvfree(priv->stats_agent.buf); - return; + priv->stats_agent.buf = NULL; } - - priv->stats_agent.agent = agent; - INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work); } void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv) { - if (IS_ERR_OR_NULL(priv->stats_agent.agent)) + struct mlx5_hv_vhca_agent *agent; + + agent = READ_ONCE(priv->stats_agent.agent); + if (IS_ERR_OR_NULL(agent)) return; - mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent); + mlx5_hv_vhca_agent_destroy(agent); + WRITE_ONCE(priv->stats_agent.agent, NULL); kvfree(priv->stats_agent.buf); + priv->stats_agent.buf = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 775f0c6e55c9..aa8610cedaa8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2773,7 +2773,7 @@ static int mlx5e_channel_stats_alloc(struct mlx5e_priv *priv, int ix, int cpu) GFP_KERNEL, cpu_to_node(cpu)); if (!priv->channel_stats[ix]) return -ENOMEM; - priv->stats_nch++; + mlx5e_stats_nch_write(priv, priv->stats_nch + 1); return 0; } @@ -4040,9 +4040,10 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) { + u16 nch = mlx5e_stats_nch_read(priv); int i; - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i]; struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; @@ -5488,7 +5489,7 @@ static void mlx5e_get_queue_stats_rx(struct net_device *dev, int i, struct mlx5e_rq_stats *xskrq_stats; struct mlx5e_rq_stats *rq_stats; - if (mlx5e_is_uplink_rep(priv) || !priv->stats_nch) + if (mlx5e_is_uplink_rep(priv) || !mlx5e_stats_nch_read(priv)) return; channel_stats = priv->channel_stats[i]; @@ -5512,7 +5513,7 @@ static void mlx5e_get_queue_stats_tx(struct net_device *dev, int i, struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_sq_stats *sq_stats; - if (!priv->stats_nch) + if (!mlx5e_stats_nch_read(priv)) return; /* no special case needed for ptp htb etc since txq2sq_stats is kept up @@ -5538,6 +5539,7 @@ static void mlx5e_get_base_stats(struct net_device *dev, struct netdev_queue_stats_tx *tx) { struct mlx5e_priv *priv = netdev_priv(dev); + u16 nch = mlx5e_stats_nch_read(priv); struct mlx5e_ptp *ptp_channel; int i, tc; @@ -5549,7 +5551,7 @@ static void mlx5e_get_base_stats(struct net_device *dev, rx->hw_gro_wire_packets = 0; rx->hw_gro_wire_bytes = 0; - for (i = priv->channels.params.num_channels; i < priv->stats_nch; i++) { + for (i = priv->channels.params.num_channels; i < nch; i++) { struct netdev_queue_stats_rx rx_i = {0}; mlx5e_get_queue_stats_rx(dev, i, &rx_i); @@ -5585,7 +5587,7 @@ static void mlx5e_get_base_stats(struct net_device *dev, tx->stop = 0; tx->wake = 0; - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i]; /* handle two cases: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 7f33261ba655..de38b60806c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -515,6 +515,7 @@ static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c) static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw) { struct mlx5e_sw_stats *s = &priv->stats.sw; + u16 nch = mlx5e_stats_nch_read(priv); int i; memset(s, 0, sizeof(*s)); @@ -522,7 +523,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw) for (i = 0; i < priv->channels.num; i++) /* for active channels only */ mlx5e_stats_update_stats_rq_page_pool(priv->channels.c[i]); - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats = priv->channel_stats[i]; @@ -2614,7 +2615,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(ptp) { return; } static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels) { - int max_nch = priv->stats_nch; + int max_nch = mlx5e_stats_nch_read(priv); return (NUM_RQ_STATS * max_nch) + (NUM_CH_STATS * max_nch) + @@ -2627,8 +2628,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(channels) static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels) { + int max_nch = mlx5e_stats_nch_read(priv); bool is_xsk = priv->xsk.ever_used; - int max_nch = priv->stats_nch; int i, j, tc; for (i = 0; i < max_nch; i++) @@ -2660,8 +2661,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(channels) static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(channels) { + int max_nch = mlx5e_stats_nch_read(priv); bool is_xsk = priv->xsk.ever_used; - int max_nch = priv->stats_nch; int i, j, tc; for (i = 0; i < max_nch; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 910492eb51f2..1bc7b9019124 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -5547,6 +5547,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw) mlx5_devcom_for_each_peer_entry(devcom, peer_esw, pos) { i = mlx5_lag_get_dev_seq(peer_esw->dev); + if (i < 0) + continue; + list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows[i], peer[i]) mlx5e_tc_del_fdb_peers_flow(flow); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 0a6003fe60e9..674bed721e63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -135,10 +135,11 @@ void mlx5i_cleanup(struct mlx5e_priv *priv) static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv) { + u16 nch = mlx5e_stats_nch_read(priv); struct rtnl_link_stats64 s = {}; int i, j; - for (i = 0; i < priv->stats_nch; i++) { + for (i = 0; i < nch; i++) { struct mlx5e_channel_stats *channel_stats; struct mlx5e_rq_stats *rq_stats; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index 50bfb450c71e..abf72026c751 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -194,8 +194,10 @@ static void mlx5_mpesw_work(struct work_struct *work) struct mlx5_lag *ldev = mpesww->lag; devcom = mlx5_lag_get_devcom_comp(ldev); - if (!devcom) - return; + if (!devcom) { + mpesww->result = -ENODEV; + goto complete; + } mlx5_devcom_comp_lock(devcom); mlx5_mpesw_sd_devcoms_lock(ldev); @@ -213,6 +215,7 @@ unlock: mutex_unlock(&ldev->lock); mlx5_mpesw_sd_devcoms_unlock(ldev); mlx5_devcom_comp_unlock(devcom); +complete: complete(&mpesww->comp); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c index 113866494d16..6b4ad3c53f2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/shared_fdb.c @@ -78,7 +78,7 @@ static int mlx5_lag_create_single_fdb_filter(struct mlx5_lag *ldev, u32 filter) } return 0; err: - mlx5_lag_for_each_reverse(j, i, 0, ldev, filter) { + mlx5_lag_for_each_reverse(j, i - 1, 0, ldev, filter) { struct mlx5_eswitch *slave_esw; if (j == master_idx) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c index d6dc7bce855e..305752dab7bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c @@ -190,7 +190,7 @@ mlx5_hv_vhca_control_agent_create(struct mlx5_hv_vhca *hv_vhca) return mlx5_hv_vhca_agent_create(hv_vhca, MLX5_HV_VHCA_AGENT_CONTROL, NULL, mlx5_hv_vhca_control_agent_invalidate, - NULL, NULL); + NULL, NULL, NULL); } static void mlx5_hv_vhca_control_agent_destroy(struct mlx5_hv_vhca_agent *agent) @@ -256,7 +256,8 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, void (*invalidate)(struct mlx5_hv_vhca_agent*, u64 block_mask), void (*cleaup)(struct mlx5_hv_vhca_agent *agent), - void *priv) + void *priv, + struct mlx5_hv_vhca_agent **ctx_update) { struct mlx5_hv_vhca_agent *agent; @@ -284,6 +285,9 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, agent->invalidate = invalidate; agent->cleanup = cleaup; + if (ctx_update) + WRITE_ONCE(*ctx_update, agent); + mutex_lock(&hv_vhca->agents_lock); hv_vhca->agents[type] = agent; mutex_unlock(&hv_vhca->agents_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h index f240ffe5116c..8b3974cf0ee4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h @@ -43,7 +43,8 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, void (*invalidate)(struct mlx5_hv_vhca_agent*, u64 block_mask), void (*cleanup)(struct mlx5_hv_vhca_agent *agent), - void *context); + void *context, + struct mlx5_hv_vhca_agent **ctx_update); void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent); int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent, @@ -84,7 +85,8 @@ mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, void (*invalidate)(struct mlx5_hv_vhca_agent*, u64 block_mask), void (*cleanup)(struct mlx5_hv_vhca_agent *agent), - void *context) + void *context, + struct mlx5_hv_vhca_agent **ctx_update) { return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c index 4571c56ec3c9..97f6097d4c70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c @@ -176,7 +176,8 @@ void mlx5_tun_entropy_refcount_dec(struct mlx5_tun_entropy *tun_entropy, int reformat_type) { mutex_lock(&tun_entropy->lock); - if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN) + if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN || + reformat_type == MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL) tun_entropy->num_enabling_entries--; else if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE && --tun_entropy->num_disabling_entries == 0) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index 72e3b189bac5..eb28df80b281 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -601,7 +601,6 @@ static void lan966x_vcap_admin_free(struct vcap_admin *admin) kfree(admin->cache.keystream); kfree(admin->cache.maskstream); kfree(admin->cache.actionstream); - mutex_destroy(&admin->lock); kfree(admin); } @@ -615,7 +614,7 @@ lan966x_vcap_admin_alloc(struct lan966x *lan966x, struct vcap_control *ctrl, if (!admin) return ERR_PTR(-ENOMEM); - mutex_init(&admin->lock); + admin->vctrl = ctrl; INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); @@ -721,6 +720,7 @@ int lan966x_vcap_init(struct lan966x *lan966x) ctrl->ops = &lan966x_vcap_ops; INIT_LIST_HEAD(&ctrl->list); + mutex_init(&ctrl->lock); for (int i = 0; i < ARRAY_SIZE(lan966x_vcap_inst_cfg); ++i) { cfg = &lan966x_vcap_inst_cfg[i]; @@ -780,5 +780,6 @@ void lan966x_vcap_deinit(struct lan966x *lan966x) lan966x_vcap_admin_free(admin); } + mutex_destroy(&ctrl->lock); kfree(ctrl); } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c index 95b93e46a41d..cf332de6bf73 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -1930,7 +1930,6 @@ static void sparx5_vcap_admin_free(struct vcap_admin *admin) { if (!admin) return; - mutex_destroy(&admin->lock); kfree(admin->cache.keystream); kfree(admin->cache.maskstream); kfree(admin->cache.actionstream); @@ -1950,7 +1949,7 @@ sparx5_vcap_admin_alloc(struct sparx5 *sparx5, struct vcap_control *ctrl, INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); - mutex_init(&admin->lock); + admin->vctrl = ctrl; admin->vtype = cfg->vtype; admin->vinst = cfg->vinst; admin->ingress = cfg->ingress; @@ -2059,6 +2058,7 @@ int sparx5_vcap_init(struct sparx5 *sparx5) ctrl->ops = &sparx5_vcap_ops; INIT_LIST_HEAD(&ctrl->list); + mutex_init(&ctrl->lock); for (idx = 0; idx < ARRAY_SIZE(sparx5_vcap_inst_cfg); ++idx) { cfg = &consts->vcaps_cfg[idx]; admin = sparx5_vcap_admin_alloc(sparx5, ctrl, cfg); @@ -2097,5 +2097,6 @@ void sparx5_vcap_deinit(struct sparx5 *sparx5) list_del(&admin->list); sparx5_vcap_admin_free(admin); } + mutex_destroy(&ctrl->lock); kfree(ctrl); } diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c index 0fdb5e363bad..ff86cde11a32 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -934,6 +934,16 @@ static bool vcap_rule_exists(struct vcap_control *vctrl, u32 id) return false; } +void vcap_lock(struct vcap_admin *admin) +{ + mutex_lock(&admin->vctrl->lock); +} + +void vcap_unlock(struct vcap_admin *admin) +{ + mutex_unlock(&admin->vctrl->lock); +} + /* Find a rule with a provided rule id return a locked vcap */ static struct vcap_rule_internal * vcap_get_locked_rule(struct vcap_control *vctrl, u32 id) @@ -943,11 +953,11 @@ vcap_get_locked_rule(struct vcap_control *vctrl, u32 id) /* Look for the rule id in all vcaps */ list_for_each_entry(admin, &vctrl->list, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) if (ri->data.id == id) return ri; - mutex_unlock(&admin->lock); + vcap_unlock(admin); } return NULL; } @@ -961,14 +971,14 @@ int vcap_lookup_rule_by_cookie(struct vcap_control *vctrl, u64 cookie) /* Look for the rule id in all vcaps */ list_for_each_entry(admin, &vctrl->list, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { if (ri->data.cookie == cookie) { id = ri->data.id; break; } } - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (id) return id; } @@ -985,11 +995,11 @@ int vcap_admin_rule_count(struct vcap_admin *admin, int cid) int count = 0; list_for_each_entry(elem, &admin->rules, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); if (elem->data.vcap_chain_id >= min_cid && elem->data.vcap_chain_id < max_cid) ++count; - mutex_unlock(&admin->lock); + vcap_unlock(admin); } return count; } @@ -2266,7 +2276,7 @@ int vcap_add_rule(struct vcap_rule *rule) if (ret) return ret; /* Insert the new rule in the list of vcap rules */ - mutex_lock(&ri->admin->lock); + vcap_lock(ri->admin); vcap_rule_set_state(ri); ret = vcap_insert_rule(ri, &move); @@ -2302,7 +2312,7 @@ int vcap_add_rule(struct vcap_rule *rule) goto out; } out: - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return ret; } EXPORT_SYMBOL_GPL(vcap_add_rule); @@ -2330,7 +2340,7 @@ struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, if (vctrl->vcaps[admin->vtype].rows == 0) return ERR_PTR(-EINVAL); - mutex_lock(&admin->lock); + vcap_lock(admin); /* Check if a rule with this id already exists */ if (vcap_rule_exists(vctrl, id)) { err = -EINVAL; @@ -2369,13 +2379,13 @@ struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, goto out_free; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); return (struct vcap_rule *)ri; out_free: kfree(ri); out_unlock: - mutex_unlock(&admin->lock); + vcap_unlock(admin); return ERR_PTR(err); } @@ -2446,7 +2456,7 @@ struct vcap_rule *vcap_get_rule(struct vcap_control *vctrl, u32 id) return ERR_PTR(-ENOENT); rule = vcap_decode_rule(elem); - mutex_unlock(&elem->admin->lock); + vcap_unlock(elem->admin); return rule; } EXPORT_SYMBOL_GPL(vcap_get_rule); @@ -2483,7 +2493,7 @@ int vcap_mod_rule(struct vcap_rule *rule) err = vcap_write_counter(ri, &ctr); out: - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return err; } EXPORT_SYMBOL_GPL(vcap_mod_rule); @@ -2570,7 +2580,7 @@ int vcap_del_rule(struct vcap_control *vctrl, struct net_device *ndev, u32 id) admin->last_used_addr = elem->addr; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); return err; } EXPORT_SYMBOL_GPL(vcap_del_rule); @@ -2585,7 +2595,7 @@ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) if (ret) return ret; - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry_safe(ri, next_ri, &admin->rules, list) { vctrl->ops->init(ri->ndev, admin, ri->addr, ri->size); list_del(&ri->list); @@ -2598,7 +2608,7 @@ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) list_del(&eport->list); kfree(eport); } - mutex_unlock(&admin->lock); + vcap_unlock(admin); return 0; } @@ -3016,7 +3026,7 @@ static int vcap_enable_rules(struct vcap_control *vctrl, continue; /* Found the admin, now find the offloadable rules */ - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { /* Is the rule in the lookup defined by the chain */ if (!(ri->data.vcap_chain_id >= chain && @@ -3034,7 +3044,7 @@ static int vcap_enable_rules(struct vcap_control *vctrl, if (err) break; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (err) break; } @@ -3074,7 +3084,7 @@ static int vcap_disable_rules(struct vcap_control *vctrl, continue; /* Found the admin, now find the rules on the chain */ - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { if (ri->data.vcap_chain_id != chain) continue; @@ -3089,7 +3099,7 @@ static int vcap_disable_rules(struct vcap_control *vctrl, if (err) break; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (err) break; } @@ -3133,9 +3143,9 @@ static int vcap_enable(struct vcap_control *vctrl, struct net_device *ndev, eport->cookie = cookie; eport->src_cid = src_cid; eport->dst_cid = dst_cid; - mutex_lock(&admin->lock); + vcap_lock(admin); list_add_tail(&eport->list, &admin->enabled); - mutex_unlock(&admin->lock); + vcap_unlock(admin); if (vcap_path_exist(vctrl, ndev, src_cid)) { /* Enable chained lookups */ @@ -3185,9 +3195,9 @@ static int vcap_disable(struct vcap_control *vctrl, struct net_device *ndev, dst_cid = vcap_get_next_chain(vctrl, ndev, dst_cid); } - mutex_lock(&found->lock); + vcap_lock(found); list_del(&eport->list); - mutex_unlock(&found->lock); + vcap_unlock(found); kfree(eport); return 0; } @@ -3270,9 +3280,9 @@ int vcap_rule_set_counter(struct vcap_rule *rule, struct vcap_counter *ctr) return -EINVAL; } - mutex_lock(&ri->admin->lock); + vcap_lock(ri->admin); err = vcap_write_counter(ri, ctr); - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return err; } @@ -3291,9 +3301,9 @@ int vcap_rule_get_counter(struct vcap_rule *rule, struct vcap_counter *ctr) return -EINVAL; } - mutex_lock(&ri->admin->lock); + vcap_lock(ri->admin); err = vcap_read_counter(ri, ctr); - mutex_unlock(&ri->admin->lock); + vcap_unlock(ri->admin); return err; } @@ -3395,7 +3405,7 @@ int vcap_get_rule_count_by_cookie(struct vcap_control *vctrl, /* Iterate all rules in each VCAP instance */ list_for_each_entry(admin, &vctrl->list, list) { - mutex_lock(&admin->lock); + vcap_lock(admin); list_for_each_entry(ri, &admin->rules, list) { if (ri->data.cookie != cookie) continue; @@ -3412,12 +3422,12 @@ int vcap_get_rule_count_by_cookie(struct vcap_control *vctrl, if (err) goto unlock; } - mutex_unlock(&admin->lock); + vcap_unlock(admin); } return err; unlock: - mutex_unlock(&admin->lock); + vcap_unlock(admin); return err; } EXPORT_SYMBOL_GPL(vcap_get_rule_count_by_cookie); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h index 6069ad95c27e..05b4b02e59ef 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h @@ -164,7 +164,7 @@ struct vcap_admin { struct list_head list; /* for insertion in vcap_control */ struct list_head rules; /* list of rules */ struct list_head enabled; /* list of enabled ports */ - struct mutex lock; /* control access to rules */ + struct vcap_control *vctrl; /* the control instance owning this vcap */ enum vcap_type vtype; /* type of vcap */ int vinst; /* instance number within the same type */ int first_cid; /* first chain id in this vcap */ @@ -275,6 +275,7 @@ struct vcap_control { const struct vcap_info *vcaps; /* client supplied vcap models */ const struct vcap_statistics *stats; /* client supplied vcap stats */ struct list_head list; /* list of vcap instances */ + struct mutex lock; /* serialize access to all vcap instances */ }; #endif /* __VCAP_API__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c index 59bfbda29bb3..e0c65c7ab23e 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs.c @@ -410,9 +410,9 @@ static int vcap_debugfs_show(struct seq_file *m, void *unused) }; int ret; - mutex_lock(&info->admin->lock); + vcap_lock(info->admin); ret = vcap_show_admin(info->vctrl, info->admin, &out); - mutex_unlock(&info->admin->lock); + vcap_unlock(info->admin); return ret; } DEFINE_SHOW_ATTRIBUTE(vcap_debugfs); @@ -427,9 +427,9 @@ static int vcap_raw_debugfs_show(struct seq_file *m, void *unused) }; int ret; - mutex_lock(&info->admin->lock); + vcap_lock(info->admin); ret = vcap_show_admin_raw(info->vctrl, info->admin, &out); - mutex_unlock(&info->admin->lock); + vcap_unlock(info->admin); return ret; } DEFINE_SHOW_ATTRIBUTE(vcap_raw_debugfs); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c index 9c9d38042125..ac2a3b8c4f32 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_debugfs_kunit.c @@ -243,10 +243,11 @@ static void vcap_test_api_init(struct vcap_admin *admin) { /* Initialize the shared objects */ INIT_LIST_HEAD(&test_vctrl.list); + mutex_init(&test_vctrl.lock); INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); - mutex_init(&admin->lock); + admin->vctrl = &test_vctrl; list_add_tail(&admin->list, &test_vctrl.list); memset(test_updateaddr, 0, sizeof(test_updateaddr)); test_updateaddridx = 0; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index ce26ccbdccdf..83de384d3e3b 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -233,10 +233,11 @@ static void vcap_test_api_init(struct vcap_admin *admin) { /* Initialize the shared objects */ INIT_LIST_HEAD(&test_vctrl.list); + mutex_init(&test_vctrl.lock); INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); INIT_LIST_HEAD(&admin->enabled); - mutex_init(&admin->lock); + admin->vctrl = &test_vctrl; list_add_tail(&admin->list, &test_vctrl.list); memset(test_updateaddr, 0, sizeof(test_updateaddr)); test_updateaddridx = 0; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h index 844bdf6b5f45..b4057fbe3d18 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_private.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_private.h @@ -50,6 +50,9 @@ struct vcap_stream_iter { /* Check that the control has a valid set of callbacks */ int vcap_api_check(struct vcap_control *ctrl); +/* Serialize access to the vcap instances of a control */ +void vcap_lock(struct vcap_admin *admin); +void vcap_unlock(struct vcap_admin *admin); /* Erase the VCAP cache area used or encoding and decoding */ void vcap_erase_cache(struct vcap_rule_internal *ri); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 7438ea6b3f26..9d9bfd116dab 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2120,12 +2120,16 @@ drop: } static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, - dma_addr_t *da, bool *from_pool) + dma_addr_t *da, bool *from_pool, + struct page **pp_page, u32 *dma_sync_offset) { struct page *page; u32 offset; void *va; + *from_pool = false; + *pp_page = NULL; + *dma_sync_offset = 0; /* Don't use fragments for jumbo frames or XDP where it's 1 fragment * per page. @@ -2163,31 +2167,47 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, va = page_to_virt(page) + offset; *da = page_pool_get_dma_addr(page) + offset + rxq->headroom; *from_pool = true; + *pp_page = page; + *dma_sync_offset = offset + rxq->headroom; return va; } /* Allocate frag for rx buffer, and save the old buf */ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, - struct mana_recv_buf_oob *rxoob, void **old_buf, - bool *old_fp) + struct mana_recv_buf_oob *rxoob, u32 pktlen, + void **old_buf, bool *old_fp) { + struct page *pp_page; + u32 dma_sync_offset; bool from_pool; dma_addr_t da; void *va; - va = mana_get_rxfrag(rxq, dev, &da, &from_pool); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset); if (!va) return; - if (!rxoob->from_pool || rxq->frag_count == 1) + if (!rxoob->from_pool || rxq->frag_count == 1) { dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize, DMA_FROM_DEVICE); + } else { + /* The page pool maps the whole page and only syncs for device + * automatically (PP_FLAG_DMA_SYNC_DEV). Sync the received bytes + * for the CPU before they are read: this is required if DMA + * is incoherent or bounce buffers are used. + */ + page_pool_dma_sync_for_cpu(rxq->page_pool, rxoob->pp_page, + rxoob->dma_sync_offset, pktlen); + } *old_buf = rxoob->buf_va; *old_fp = rxoob->from_pool; rxoob->buf_va = va; rxoob->sgl[0].address = da; rxoob->from_pool = from_pool; + rxoob->pp_page = pp_page; + rxoob->dma_sync_offset = dma_sync_offset; } static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, @@ -2246,12 +2266,26 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, rxbuf_oob = &rxq->rx_oobs[curr]; WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1); - mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp); + if (unlikely(pktlen > rxq->datasize)) { + /* Increase it even if mana_rx_skb() isn't called. */ + rxq->rx_cq.work_done++; - /* Unsuccessful refill will have old_buf == NULL. - * In this case, mana_rx_skb() will drop the packet. - */ - mana_rx_skb(old_buf, old_fp, oob, rxq, i); + ++ndev->stats.rx_dropped; + netdev_warn_once(ndev, + "Dropped oversized RX packet: len=%u, datasize=%u\n", + pktlen, rxq->datasize); + + /* Reuse the RX buffer since rxbuf_oob is unchanged. */ + } else { + + mana_refill_rx_oob(dev, rxq, rxbuf_oob, pktlen, + &old_buf, &old_fp); + + /* Unsuccessful refill will have old_buf == NULL. + * In this case, mana_rx_skb() will drop the packet. + */ + mana_rx_skb(old_buf, old_fp, oob, rxq, i); + } mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu); @@ -2655,6 +2689,8 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, struct mana_rxq *rxq, struct device *dev) { struct mana_port_context *mpc = netdev_priv(rxq->ndev); + struct page *pp_page = NULL; + u32 dma_sync_offset = 0; bool from_pool = false; dma_addr_t da; void *va; @@ -2662,13 +2698,16 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, if (mpc->rxbufs_pre) va = mana_get_rxbuf_pre(rxq, &da); else - va = mana_get_rxfrag(rxq, dev, &da, &from_pool); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset); if (!va) return -ENOMEM; rx_oob->buf_va = va; rx_oob->from_pool = from_pool; + rx_oob->pp_page = pp_page; + rx_oob->dma_sync_offset = dma_sync_offset; rx_oob->sgl[0].address = da; rx_oob->sgl[0].size = rxq->datasize; diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c index de5e29230b3c..c46408698263 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c @@ -166,18 +166,23 @@ static void mucse_mbx_inc_pf_ack(struct mucse_hw *hw) * * Return: 0 on success, negative errno on failure **/ -static int mucse_read_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) +static int mucse_read_mbx_pf(struct mucse_hw *hw, __le32 *msg, u16 size) { - const int size_in_words = size / sizeof(u32); + const int size_in_words = size / sizeof(__le32); struct mucse_mbx_info *mbx = &hw->mbx; + int off = MUCSE_MBX_FWPF_SHM; int err; err = mucse_obtain_mbx_lock_pf(hw); if (err) return err; + /* memcpy_fromio() is unsuitable: the mailbox uses 32-bit MMIO + * registers, not byte-addressable RAM. readl() guarantees + * the required 32-bit access width. + */ for (int i = 0; i < size_in_words; i++) - msg[i] = mbx_data_rd32(mbx, MUCSE_MBX_FWPF_SHM + 4 * i); + msg[i] = cpu_to_le32(mbx_data_rd32(mbx, off + 4 * i)); /* Hw needs write data_reg at last */ mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM, 0); /* flush reqs as we have read this request data */ @@ -236,7 +241,7 @@ static int mucse_poll_for_msg(struct mucse_hw *hw) * Return: 0 if it successfully received a message notification and * copied it into the receive buffer, negative errno on failure **/ -int mucse_poll_and_read_mbx(struct mucse_hw *hw, u32 *msg, u16 size) +int mucse_poll_and_read_mbx(struct mucse_hw *hw, __le32 *msg, u16 size) { int err; @@ -290,9 +295,9 @@ static void mucse_mbx_inc_pf_req(struct mucse_hw *hw) * Return: 0 if it successfully copied message into the buffer, * negative errno on failure **/ -static int mucse_write_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) +static int mucse_write_mbx_pf(struct mucse_hw *hw, const __le32 *msg, u16 size) { - const int size_in_words = size / sizeof(u32); + const int size_in_words = size / sizeof(__le32); struct mucse_mbx_info *mbx = &hw->mbx; int err; @@ -300,8 +305,12 @@ static int mucse_write_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) if (err) return err; + /* memcpy_toio() would decompose into arbitrary-width accesses; + * the mailbox requires 32-bit MMIO writes via writel(). + */ for (int i = 0; i < size_in_words; i++) - mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM + i * 4, msg[i]); + mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM + i * 4, + le32_to_cpu(msg[i])); /* flush acks as we are overwriting the message buffer */ hw->mbx.fw_ack = mucse_mbx_get_fwack(mbx); @@ -360,7 +369,8 @@ static int mucse_poll_for_ack(struct mucse_hw *hw) * Return: 0 if it successfully copied message into the buffer and * received an ack to that message within delay * timeout_cnt period **/ -int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, u32 *msg, u16 size) +int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, const __le32 *msg, + u16 size) { int err; diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h index e6fcc8d1d3ca..75b88b18b04d 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h @@ -14,7 +14,8 @@ #define MUCSE_MBX_REQ BIT(0) /* Request a req to mailbox */ #define MUCSE_MBX_PFU BIT(3) /* PF owns the mailbox buffer */ -int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, u32 *msg, u16 size); +int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, + const __le32 *msg, u16 size); void mucse_init_mbx_params_pf(struct mucse_hw *hw); -int mucse_poll_and_read_mbx(struct mucse_hw *hw, u32 *msg, u16 size); +int mucse_poll_and_read_mbx(struct mucse_hw *hw, __le32 *msg, u16 size); #endif /* _RNPGBE_MBX_H */ diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c index 8c8bd5e8e1db..5ba74997beac 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c @@ -20,32 +20,32 @@ * Return: 0 on success, negative errno on failure **/ static int mucse_fw_send_cmd_wait_resp(struct mucse_hw *hw, - struct mbx_fw_cmd_req *req, - struct mbx_fw_cmd_reply *reply) + union mbx_fw_cmd_req_u *req, + union mbx_fw_cmd_reply_u *reply) { - int len = le16_to_cpu(req->datalen); + int len = le16_to_cpu(req->r.datalen); int retry_cnt = 3; int err; mutex_lock(&hw->mbx.lock); - err = mucse_write_and_wait_ack_mbx(hw, (u32 *)req, len); + err = mucse_write_and_wait_ack_mbx(hw, req->dwords, len); if (err) goto out; do { - err = mucse_poll_and_read_mbx(hw, (u32 *)reply, - sizeof(*reply)); + err = mucse_poll_and_read_mbx(hw, reply->dwords, + sizeof(reply->r)); if (err) goto out; /* mucse_write_and_wait_ack_mbx return 0 means fw has * received request, wait for the expect opcode * reply with 'retry_cnt' times. */ - } while (--retry_cnt >= 0 && reply->opcode != req->opcode); + } while (--retry_cnt >= 0 && reply->r.opcode != req->r.opcode); out: mutex_unlock(&hw->mbx.lock); if (!err && retry_cnt < 0) return -ETIMEDOUT; - if (!err && reply->error_code) + if (!err && reply->r.error_code) return -EIO; return err; @@ -61,17 +61,19 @@ out: **/ static int mucse_mbx_get_info(struct mucse_hw *hw) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(GET_HW_INFO), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(GET_HW_INFO), + }, }; - struct mbx_fw_cmd_reply reply = {}; + union mbx_fw_cmd_reply_u reply = {}; int err; err = mucse_fw_send_cmd_wait_resp(hw, &req, &reply); if (!err) hw->pfvfnum = FIELD_GET(GENMASK_U16(7, 0), - le16_to_cpu(reply.hw_info.pfnum)); + le16_to_cpu(reply.r.hw_info.pfnum)); return err; } @@ -111,21 +113,23 @@ int mucse_mbx_sync_fw(struct mucse_hw *hw) **/ int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(sizeof(req.powerup) + - MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(POWER_UP), - .powerup = { - /* fw needs this to reply correct cmd */ - .version = cpu_to_le32(GENMASK_U32(31, 0)), - .status = cpu_to_le32(is_powerup ? 1 : 0), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(sizeof(req.r.powerup) + + MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(POWER_UP), + .powerup = { + /* fw needs this to reply correct cmd */ + .version = cpu_to_le32(GENMASK_U32(31, 0)), + .status = cpu_to_le32(is_powerup ? 1 : 0), + }, }, }; int len, err; - len = le16_to_cpu(req.datalen); + len = le16_to_cpu(req.r.datalen); mutex_lock(&hw->mbx.lock); - err = mucse_write_and_wait_ack_mbx(hw, (u32 *)&req, len); + err = mucse_write_and_wait_ack_mbx(hw, req.dwords, len); mutex_unlock(&hw->mbx.lock); return err; @@ -142,11 +146,13 @@ int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup) **/ int mucse_mbx_reset_hw(struct mucse_hw *hw) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(RESET_HW), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(RESET_HW), + }, }; - struct mbx_fw_cmd_reply reply = {}; + union mbx_fw_cmd_reply_u reply = {}; return mucse_fw_send_cmd_wait_resp(hw, &req, &reply); } @@ -166,24 +172,26 @@ int mucse_mbx_get_macaddr(struct mucse_hw *hw, int pfvfnum, u8 *mac_addr, int port) { - struct mbx_fw_cmd_req req = { - .datalen = cpu_to_le16(sizeof(req.get_mac_addr) + - MUCSE_MBX_REQ_HDR_LEN), - .opcode = cpu_to_le16(GET_MAC_ADDRESS), - .get_mac_addr = { - .port_mask = cpu_to_le32(BIT(port)), - .pfvf_num = cpu_to_le32(pfvfnum), + union mbx_fw_cmd_req_u req = { + .r = { + .datalen = cpu_to_le16(sizeof(req.r.get_mac_addr) + + MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(GET_MAC_ADDRESS), + .get_mac_addr = { + .port_mask = cpu_to_le32(BIT(port)), + .pfvf_num = cpu_to_le32(pfvfnum), + }, }, }; - struct mbx_fw_cmd_reply reply = {}; + union mbx_fw_cmd_reply_u reply = {}; int err; err = mucse_fw_send_cmd_wait_resp(hw, &req, &reply); if (err) return err; - if (le32_to_cpu(reply.mac_addr.ports) & BIT(port)) - memcpy(mac_addr, reply.mac_addr.addrs[port].mac, ETH_ALEN); + if (le32_to_cpu(reply.r.mac_addr.ports) & BIT(port)) + memcpy(mac_addr, reply.r.mac_addr.addrs[port].mac, ETH_ALEN); else return -ENODATA; diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h index fb24fc12b613..fe996aeffc4d 100644 --- a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h @@ -80,6 +80,20 @@ struct mbx_fw_cmd_reply { }; } __packed; +/* Union wrappers to expose struct as __le32 dword array for mailbox + * transport, eliminating the need for pointer casts. The __packed + * structs have no padding, so dwords[] overlays the fields exactly. + */ +union mbx_fw_cmd_req_u { + struct mbx_fw_cmd_req r; + __le32 dwords[sizeof(struct mbx_fw_cmd_req) / sizeof(__le32)]; +}; + +union mbx_fw_cmd_reply_u { + struct mbx_fw_cmd_reply r; + __le32 dwords[sizeof(struct mbx_fw_cmd_reply) / sizeof(__le32)]; +}; + int mucse_mbx_sync_fw(struct mucse_hw *hw); int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup); int mucse_mbx_reset_hw(struct mucse_hw *hw); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 33e18bb69774..c11e0d8f98aa 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -765,6 +765,9 @@ qede_tpa_rx_build_skb(struct qede_dev *edev, struct sk_buff *skb; skb = qede_build_skb(rxq, bd, len, pad); + if (unlikely(!skb)) + return NULL; + bd->page_offset += rxq->rx_buf_seg_size; if (bd->page_offset == PAGE_SIZE) { @@ -812,6 +815,8 @@ qede_rx_build_skb(struct qede_dev *edev, } skb = qede_build_skb(rxq, bd, len, pad); + if (unlikely(!skb)) + return NULL; if (unlikely(qede_realloc_rx_buffer(rxq, bd))) { /* Incr page ref count to reuse on allocation failure so diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 9f3479500f85..d055a2628d8c 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -126,7 +126,10 @@ rmnet_map_ingress_handler(struct sk_buff *skb, consume_skb(skb); } else { - __rmnet_map_ingress_handler(skb, port); + if (rmnet_map_validate_packet_len(skb, port)) + __rmnet_map_ingress_handler(skb, port); + else + kfree_skb(skb); } } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h index b70284095568..60ca8b780c88 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h @@ -59,5 +59,6 @@ void rmnet_map_tx_aggregate_init(struct rmnet_port *port); void rmnet_map_tx_aggregate_exit(struct rmnet_port *port); void rmnet_map_update_ul_agg_config(struct rmnet_port *port, u32 size, u32 count, u32 time); +u32 rmnet_map_validate_packet_len(struct sk_buff *skb, struct rmnet_port *port); #endif /* _RMNET_MAP_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index 8b4640c5d61e..305ae15ae8f3 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -333,54 +333,62 @@ done: return map_header; } -/* Deaggregates a single packet - * A whole new buffer is allocated for each portion of an aggregated frame. - * Caller should keep calling deaggregate() on the source skb until 0 is - * returned, indicating that there are no more packets to deaggregate. Caller - * is responsible for freeing the original skb. - */ -struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, - struct rmnet_port *port) +u32 rmnet_map_validate_packet_len(struct sk_buff *skb, struct rmnet_port *port) { struct rmnet_map_v5_csum_header *next_hdr = NULL; struct rmnet_map_header *maph; void *data = skb->data; - struct sk_buff *skbn; - u8 nexthdr_type; u32 packet_len; - if (skb->len == 0) - return NULL; + if (skb->len < sizeof(*maph)) + return 0; maph = (struct rmnet_map_header *)skb->data; + + /* Some hardware can send us empty frames. Catch them */ + if (!maph->pkt_len) + return 0; + packet_len = ntohs(maph->pkt_len) + sizeof(*maph); if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { packet_len += sizeof(struct rmnet_map_dl_csum_trailer); - } else if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) { - if (!(maph->flags & MAP_CMD_FLAG)) { - packet_len += sizeof(*next_hdr); - if (maph->flags & MAP_NEXT_HEADER_FLAG) - next_hdr = data + sizeof(*maph); - else - /* Mapv5 data pkt without csum hdr is invalid */ - return NULL; - } + } else if ((port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) && + !(maph->flags & MAP_CMD_FLAG)) { + /* Mapv5 data pkt without csum hdr is invalid */ + if (!(maph->flags & MAP_NEXT_HEADER_FLAG)) + return 0; + + packet_len += sizeof(*next_hdr); + next_hdr = data + sizeof(*maph); } - if (((int)skb->len - (int)packet_len) < 0) - return NULL; + if (skb->len < packet_len) + return 0; - /* Some hardware can send us empty frames. Catch them */ - if (!maph->pkt_len) - return NULL; + if (next_hdr && + u8_get_bits(next_hdr->header_info, MAPV5_HDRINFO_HDR_TYPE_FMASK) != + RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) + return 0; - if (next_hdr) { - nexthdr_type = u8_get_bits(next_hdr->header_info, - MAPV5_HDRINFO_HDR_TYPE_FMASK); - if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) - return NULL; - } + return packet_len; +} + +/* Deaggregates a single packet + * A whole new buffer is allocated for each portion of an aggregated frame. + * Caller should keep calling deaggregate() on the source skb until 0 is + * returned, indicating that there are no more packets to deaggregate. Caller + * is responsible for freeing the original skb. + */ +struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, + struct rmnet_port *port) +{ + struct sk_buff *skbn; + u32 packet_len; + + packet_len = rmnet_map_validate_packet_len(skb, port); + if (!packet_len) + return NULL; skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC); if (!skbn) diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index fb009120a924..dd89282f0179 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -646,7 +646,7 @@ static struct sk_buff *macsec_encrypt(struct sk_buff *skb, } unprotected_len = skb->len; - eth = eth_hdr(skb); + eth = skb_eth_hdr(skb); sci_present = macsec_send_sci(secy); hh = skb_push(skb, macsec_extra_len(sci_present)); memmove(hh, eth, 2 * ETH_ALEN); diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index c591eec8e97a..e57121019153 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -122,7 +122,8 @@ config MDIO_MVUSB config MDIO_MSCC_MIIM tristate "Microsemi MIIM interface support" - depends on HAS_IOMEM && REGMAP_MMIO + depends on HAS_IOMEM + select REGMAP_MMIO help This driver supports the MIIM (MDIO) interface found in the network switches of the Microsemi SoCs; it is recommended to switch on diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index c4cebacabcb5..cb782d81d84f 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1499,6 +1499,17 @@ multicast_write_done: return; } +static void lan78xx_update_vlan_filter(struct lan78xx_priv *pdata, + struct net_device *netdev, + netdev_features_t features) +{ + if ((features & NETIF_F_HW_VLAN_CTAG_FILTER) && + !(netdev->flags & IFF_PROMISC)) + pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_; + else + pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_; +} + static void lan78xx_set_multicast(struct net_device *netdev) { struct lan78xx_net *dev = netdev_priv(netdev); @@ -1533,6 +1544,8 @@ static void lan78xx_set_multicast(struct net_device *netdev) } } + lan78xx_update_vlan_filter(pdata, dev->net, dev->net->features); + if (netdev_mc_count(dev->net)) { struct netdev_hw_addr *ha; int i; @@ -3074,10 +3087,7 @@ static int lan78xx_set_features(struct net_device *netdev, else pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_; - if (features & NETIF_F_HW_VLAN_CTAG_FILTER) - pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_; - else - pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_; + lan78xx_update_vlan_filter(pdata, netdev, features); spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags); diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c index 5d4a1fd2b524..19f6e1222d93 100644 --- a/drivers/net/usb/net1080.c +++ b/drivers/net/usb/net1080.c @@ -381,7 +381,7 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb) skb_trim(skb, skb->len - sizeof *trailer); if ((packet_len & 0x01) == 0) { - if (skb->data [packet_len] != PAD_BYTE) { + if (packet_len >= skb->len || skb->data[packet_len] != PAD_BYTE) { dev->net->stats.rx_frame_errors++; netdev_dbg(dev->net, "bad pad\n"); return 0; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index dccbeb25f701..6032eea2539a 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -293,6 +293,11 @@ static inline void in_dev_put(struct in_device *idev) #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) +static inline bool in_dev_hold_safe(struct in_device *idev) +{ + return refcount_inc_not_zero(&idev->refcnt); +} + #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 539bbbe54b14..8ced27a8229b 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -446,6 +446,11 @@ static inline void in6_dev_hold(struct inet6_dev *idev) refcount_inc(&idev->refcnt); } +static inline bool in6_dev_hold_safe(struct inet6_dev *idev) +{ + return refcount_inc_not_zero(&idev->refcnt); +} + /* called with rcu_read_lock held */ static inline bool ip6_ignore_linkdown(const struct net_device *dev) { diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 38186a245f14..50f0eef71fb1 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -3413,8 +3413,9 @@ static inline struct hci_iso_hdr *hci_iso_hdr(const struct sk_buff *skb) #define hci_iso_flags_pack(pb, ts) ((pb & 0x03) | ((ts & 0x01) << 2)) /* ISO data length and flags pack/unpack */ -#define hci_iso_data_len_pack(h, f) ((__u16) ((h) | ((f) << 14))) -#define hci_iso_data_len(h) ((h) & 0x3fff) +#define hci_iso_data_len_pack(h, f) ((__u16) (((h) & 0x0fff) | \ + (((f) & 0x3) << 14))) +#define hci_iso_data_len(h) ((h) & 0x0fff) #define hci_iso_data_flags(h) ((h) >> 14) /* codec transport types */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7e15da47fe3a..4ca09298e11a 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -985,6 +985,7 @@ enum { HCI_CONN_AUTH_FAILURE, HCI_CONN_PER_ADV, HCI_CONN_BIG_CREATED, + HCI_CONN_CREATE, HCI_CONN_CREATE_CIS, HCI_CONN_CREATE_BIG_SYNC, HCI_CONN_BIG_SYNC, diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 1640cc9bf83a..ef6ce1c20a4f 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -617,7 +617,8 @@ struct l2cap_chan { struct l2cap_ops { char *name; - struct l2cap_chan *(*new_connection) (struct l2cap_chan *chan); + int (*new_connection)(struct l2cap_chan *chan, + struct l2cap_chan *new_chan); int (*recv) (struct l2cap_chan * chan, struct sk_buff *skb); void (*teardown) (struct l2cap_chan *chan, int err); @@ -882,9 +883,10 @@ static inline __u16 __next_seq(struct l2cap_chan *chan, __u16 seq) return (seq + 1) % (chan->tx_win_max + 1); } -static inline struct l2cap_chan *l2cap_chan_no_new_connection(struct l2cap_chan *chan) +static inline int l2cap_chan_no_new_connection(struct l2cap_chan *chan, + struct l2cap_chan *new_chan) { - return NULL; + return -EOPNOTSUPP; } static inline int l2cap_chan_no_recv(struct l2cap_chan *chan, struct sk_buff *skb) @@ -961,7 +963,7 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len, void l2cap_chan_busy(struct l2cap_chan *chan, int busy); void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail); int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator); -void l2cap_chan_set_defaults(struct l2cap_chan *chan); +void l2cap_chan_set_defaults(struct l2cap_chan *chan, struct l2cap_chan *pchan); int l2cap_ertm_init(struct l2cap_chan *chan); void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan); diff --git a/include/net/gue.h b/include/net/gue.h index dfca298bec9c..caefd6da8693 100644 --- a/include/net/gue.h +++ b/include/net/gue.h @@ -80,7 +80,7 @@ static inline size_t guehdr_flags_len(__be16 flags) static inline size_t guehdr_priv_flags_len(__be32 flags) { - return 0; + return (flags & GUE_PFLAG_REMCSUM) ? GUE_PLEN_REMCSUM : 0; } /* Validate standard and private flags. Returns non-zero (meaning invalid) diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 49297fec448a..417ff51f62fc 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -752,7 +752,8 @@ struct ip_vs_protocol { void (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd); + struct ip_vs_proto_data *pd, + unsigned int iph_len); int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 13c87baf018e..04acb6791dbd 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -305,6 +305,14 @@ struct mana_recv_buf_oob { void *buf_va; bool from_pool; /* allocated from a page pool */ + /* head page of the page_pool fragment; valid only when + * from_pool && frag_count > 1. + */ + struct page *pp_page; + /* Fragment offset plus rxq->headroom, passed to + * page_pool_dma_sync_for_cpu(). + */ + u32 dma_sync_offset; /* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 7b23b245a5a8..ce414118962f 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -155,11 +155,12 @@ struct flow_offload_tuple { tun_num:2, in_vlan_ingress:2; u16 mtu; + u32 dst_cookie; + struct dst_entry *dst_cache; + union { struct { - struct dst_entry *dst_cache; u32 ifidx; - u32 dst_cookie; }; struct { u32 ifidx; @@ -357,6 +358,8 @@ static inline int nf_flow_register_bpf(void) void nf_flow_offload_add(struct nf_flowtable *flowtable, struct flow_offload *flow); +void nf_flow_offload_refresh(struct nf_flowtable *flowtable, + struct flow_offload *flow); void nf_flow_offload_del(struct nf_flowtable *flowtable, struct flow_offload *flow); void nf_flow_offload_stats(struct nf_flowtable *flowtable, diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index cb7b82f2cbc7..97754ea0a827 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -37,17 +37,15 @@ static inline bool is_tcf_pedit(const struct tc_action *a) return false; } -static inline int tcf_pedit_nkeys(const struct tc_action *a) +/* Must be called with act->tcfa_lock held to ensure consistency of parallel + * reads of the same action's pedit keys (e.g. flow_offload count vs fill). + * Note, this is only used for pedit offload. + */ +static inline int tcf_pedit_nkeys_locked(const struct tc_action *a) { - struct tcf_pedit_parms *parms; - int nkeys; - - rcu_read_lock(); - parms = to_pedit_parms(a); - nkeys = parms->tcfp_nkeys; - rcu_read_unlock(); - - return nkeys; + lockdep_assert_held(&a->tcfa_lock); + return rcu_dereference_protected(to_pedit(a)->parms, + lockdep_is_held(&a->tcfa_lock))->tcfp_nkeys; } static inline u32 tcf_pedit_htype(const struct tc_action *a, int index) diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index c40c9e02391b..a6fe4820f65b 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -546,7 +546,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, * the one with the lowest address */ if (tmp_max == max && max_orig_node && - batadv_compare_eth(candidate->orig, max_orig_node->orig)) + memcmp(candidate->orig, max_orig_node->orig, ETH_ALEN) >= 0) goto out; ret = true; diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 8a006a0473a8..2e20a2cb64cb 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -518,8 +518,10 @@ int batadv_frag_send_packet(struct sk_buff *skb, mtu = min_t(unsigned int, mtu, BATADV_FRAG_MAX_FRAG_SIZE); max_fragment_size = mtu - header_size; - if (skb->len == 0 || max_fragment_size == 0) - return -EINVAL; + if (skb->len == 0 || max_fragment_size == 0) { + ret = -EINVAL; + goto free_skb; + } num_fragments = (skb->len - 1) / max_fragment_size + 1; max_fragment_size = (skb->len - 1) / num_fragments + 1; @@ -545,7 +547,7 @@ int batadv_frag_send_packet(struct sk_buff *skb, */ if (skb_has_frag_list(skb) && __skb_linearize(skb)) { ret = -ENOMEM; - goto free_skb; + goto put_primary_if; } /* Create one header to be copied to all fragments */ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4d3807a645b7..67bed3ee77e7 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -259,6 +259,7 @@ err_orig: void batadv_mesh_free(struct net_device *mesh_iface) { struct batadv_priv *bat_priv = netdev_priv(mesh_iface); + struct batadv_meshif_vlan *vlan; WRITE_ONCE(bat_priv->mesh_state, BATADV_MESH_DEACTIVATING); @@ -273,6 +274,13 @@ void batadv_mesh_free(struct net_device *mesh_iface) batadv_mcast_free(bat_priv); + /* destroy the "untagged" VLAN */ + vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (vlan) { + batadv_meshif_destroy_vlan(bat_priv, vlan); + batadv_meshif_vlan_put(vlan); + } + /* Free the TT and the originator tables only after having terminated * all the other depending components which may use these structures for * their purposes. @@ -368,7 +376,7 @@ void batadv_skb_set_priority(struct sk_buff *skb, int offset) switch (ethhdr->h_proto) { case htons(ETH_P_8021Q): - vhdr = skb_header_pointer(skb, offset + sizeof(*vhdr), + vhdr = skb_header_pointer(skb, offset, sizeof(*vhdr), &vhdr_tmp); if (!vhdr) return; diff --git a/net/batman-adv/mesh-interface.c b/net/batman-adv/mesh-interface.c index 511f70e0706a..fbfd99268de4 100644 --- a/net/batman-adv/mesh-interface.c +++ b/net/batman-adv/mesh-interface.c @@ -195,6 +195,9 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, if (READ_ONCE(bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; + if (!pskb_may_pull(skb, ETH_HLEN)) + goto dropped; + /* reset control block to avoid left overs from previous users */ memset(skb->cb, 0, sizeof(struct batadv_skb_cb)); @@ -592,8 +595,8 @@ int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid) * @bat_priv: the bat priv with all the mesh interface information * @vlan: the object to remove */ -static void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv, - struct batadv_meshif_vlan *vlan) +void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv, + struct batadv_meshif_vlan *vlan) { /* explicitly remove the associated TT local entry because it is marked * with the NOPURGE flag @@ -1088,22 +1091,13 @@ static int batadv_meshif_newlink(struct net_device *dev, static void batadv_meshif_destroy_netlink(struct net_device *mesh_iface, struct list_head *head) { - struct batadv_priv *bat_priv = netdev_priv(mesh_iface); struct batadv_hard_iface *hard_iface; - struct batadv_meshif_vlan *vlan; while (!list_empty(&mesh_iface->adj_list.lower)) { hard_iface = netdev_adjacent_get_private(mesh_iface->adj_list.lower.next); batadv_hardif_disable_interface(hard_iface); } - /* destroy the "untagged" VLAN */ - vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS); - if (vlan) { - batadv_meshif_destroy_vlan(bat_priv, vlan); - batadv_meshif_vlan_put(vlan); - } - unregister_netdevice_queue(mesh_iface, head); } diff --git a/net/batman-adv/mesh-interface.h b/net/batman-adv/mesh-interface.h index 53756c5a45e0..5e1e83e04ffb 100644 --- a/net/batman-adv/mesh-interface.h +++ b/net/batman-adv/mesh-interface.h @@ -21,6 +21,8 @@ void batadv_interface_rx(struct net_device *mesh_iface, bool batadv_meshif_is_valid(const struct net_device *net_dev); extern struct rtnl_link_ops batadv_link_ops; int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid); +void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv, + struct batadv_meshif_vlan *vlan); void batadv_meshif_vlan_release(struct kref *ref); struct batadv_meshif_vlan *batadv_meshif_vlan_get(struct batadv_priv *bat_priv, unsigned short vid); diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c index b8668a80b94a..1404a3b7adfb 100644 --- a/net/batman-adv/multicast_forw.c +++ b/net/batman-adv/multicast_forw.c @@ -927,11 +927,11 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv, { struct batadv_tvlv_mcast_tracker *mcast_tracker; struct batadv_neigh_node *neigh_node; - unsigned long offset, num_dests_off; struct sk_buff *nexthop_skb; unsigned char *skb_net_hdr; bool local_recv = false; unsigned int tvlv_len; + unsigned long offset; bool xmitted = false; u8 *dest, *next_dest; u16 num_dests; @@ -940,9 +940,8 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv, /* (at least) TVLV part needs to be linearized */ SKB_LINEAR_ASSERT(skb); - /* check if num_dests is within skb length */ - num_dests_off = offsetof(struct batadv_tvlv_mcast_tracker, num_dests); - if (num_dests_off > skb_network_header_len(skb)) + /* check if batadv_tvlv_mcast_tracker header is within skb length */ + if (sizeof(*mcast_tracker) > skb_network_header_len(skb)) return -EINVAL; skb_net_hdr = skb_network_header(skb); diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 4bfad36a4b70..dae5e1d8c038 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -2971,7 +2971,7 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv, out: batadv_hardif_put(primary_if); - if (ret && tt_req_node) { + if (!ret && tt_req_node) { spin_lock_bh(&bat_priv->tt.req_list_lock); if (!hlist_unhashed(&tt_req_node->list)) { hlist_del_init(&tt_req_node->list); @@ -4033,7 +4033,8 @@ static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv, u16 tvlv_value_len) { struct batadv_tvlv_tt_data *tt_data; - u16 tt_vlan_len, tt_num_entries; + u16 tt_num_entries; + size_t tt_vlan_len; char tt_flag; bool ret; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index cb1e329d66fd..d504a363a30f 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -632,7 +632,7 @@ static struct l2cap_chan *chan_create(void) if (!chan) return NULL; - l2cap_chan_set_defaults(chan); + l2cap_chan_set_defaults(chan, NULL); chan->chan_type = L2CAP_CHAN_CONN_ORIENTED; chan->mode = L2CAP_MODE_LE_FLOWCTL; @@ -745,21 +745,6 @@ static inline void chan_ready_cb(struct l2cap_chan *chan) ifup(dev->netdev); } -static inline struct l2cap_chan *chan_new_conn_cb(struct l2cap_chan *pchan) -{ - struct l2cap_chan *chan; - - chan = chan_create(); - if (!chan) - return NULL; - - chan->ops = pchan->ops; - - BT_DBG("chan %p pchan %p", chan, pchan); - - return chan; -} - static void unregister_dev(struct lowpan_btle_dev *dev) { struct hci_dev *hdev = READ_ONCE(dev->hdev); @@ -797,20 +782,10 @@ static void chan_close_cb(struct l2cap_chan *chan) struct lowpan_btle_dev *dev = NULL; struct lowpan_peer *peer; int err = -ENOENT; - bool last = false, remove = true; + bool last = false; BT_DBG("chan %p conn %p", chan, chan->conn); - if (chan->conn && chan->conn->hcon) { - if (!is_bt_6lowpan(chan->conn->hcon)) - return; - - /* If conn is set, then the netdev is also there and we should - * not remove it. - */ - remove = false; - } - spin_lock(&devices_lock); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { @@ -837,10 +812,8 @@ static void chan_close_cb(struct l2cap_chan *chan) ifdown(dev->netdev); - if (remove) { - INIT_WORK(&entry->delete_netdev, delete_netdev); - schedule_work(&entry->delete_netdev); - } + INIT_WORK(&entry->delete_netdev, delete_netdev); + schedule_work(&entry->delete_netdev); } else { spin_unlock(&devices_lock); } @@ -901,7 +874,6 @@ static long chan_get_sndtimeo_cb(struct l2cap_chan *chan) static const struct l2cap_ops bt_6lowpan_chan_ops = { .name = "L2CAP 6LoWPAN channel", - .new_connection = chan_new_conn_cb, .recv = chan_recv_cb, .close = chan_close_cb, .state_change = chan_state_change_cb, @@ -1029,16 +1001,19 @@ 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, le_addr_type); - hci_dev_unlock(hdev); - hci_dev_put(hdev); - - if (!hcon) + if (!hcon) { + hci_dev_unlock(hdev); + hci_dev_put(hdev); return -ENOENT; + } - *conn = (struct l2cap_conn *)hcon->l2cap_data; + *conn = l2cap_conn_hold_unless_zero(hcon->l2cap_data); BT_DBG("conn %p dst %pMR type %u", *conn, &hcon->dst, hcon->dst_type); + hci_dev_unlock(hdev); + hci_dev_put(hdev); + return 0; } @@ -1093,23 +1068,15 @@ done: } while (nchans); } -struct set_enable { - struct work_struct work; - bool flag; -}; - -static void do_enable_set(struct work_struct *work) +static void do_enable_set(bool flag) { - struct set_enable *set_enable = container_of(work, - struct set_enable, work); - - if (!set_enable->flag || enable_6lowpan != set_enable->flag) + if (!flag || enable_6lowpan != flag) /* Disconnect existing connections if 6lowpan is * disabled */ disconnect_all_peers(); - enable_6lowpan = set_enable->flag; + enable_6lowpan = flag; mutex_lock(&set_lock); if (listen_chan) { @@ -1121,22 +1088,11 @@ static void do_enable_set(struct work_struct *work) listen_chan = bt_6lowpan_listen(); mutex_unlock(&set_lock); - - kfree(set_enable); } static int lowpan_enable_set(void *data, u64 val) { - struct set_enable *set_enable; - - set_enable = kzalloc_obj(*set_enable); - if (!set_enable) - return -ENOMEM; - - set_enable->flag = !!val; - INIT_WORK(&set_enable->work, do_enable_set); - - schedule_work(&set_enable->work); + do_enable_set(!!val); return 0; } @@ -1185,18 +1141,22 @@ static ssize_t lowpan_control_write(struct file *fp, if (conn) { struct lowpan_peer *peer; - if (!is_bt_6lowpan(conn->hcon)) + if (!is_bt_6lowpan(conn->hcon)) { + l2cap_conn_put(conn); return -EINVAL; + } peer = lookup_peer(conn); if (peer) { BT_DBG("6LoWPAN connection already exists"); + l2cap_conn_put(conn); return -EALREADY; } BT_DBG("conn %p dst %pMR type %d user %u", conn, &conn->hcon->dst, conn->hcon->dst_type, addr_type); + l2cap_conn_put(conn); } ret = bt_6lowpan_connect(&addr, addr_type); @@ -1212,6 +1172,8 @@ static ssize_t lowpan_control_write(struct file *fp, return ret; ret = bt_6lowpan_disconnect(conn, addr_type); + if (conn) + l2cap_conn_put(conn); if (ret < 0) return ret; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index bcbc11c9cb15..a2290ffdc2c1 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -305,7 +305,7 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) restart: for (sk = bt_accept_get(parent, NULL); sk; sk = next) { - /* Prevent early freeing of sk due to unlink and sock_kill */ + /* The reference from bt_accept_get() keeps sk alive. */ lock_sock(sk); /* Check sk has not already been unlinked via @@ -321,13 +321,11 @@ restart: next = bt_accept_get(parent, sk); - /* sk is safely in the parent list so reduce reference count */ - sock_put(sk); - /* FIXME: Is this check still needed */ if (sk->sk_state == BT_CLOSED) { bt_accept_unlink(sk); release_sock(sk); + sock_put(sk); continue; } @@ -337,16 +335,6 @@ restart: if (newsock) sock_graft(sk, newsock); - /* Hand the caller a reference taken while sk is - * still locked. bt_accept_unlink() just dropped - * the accept-queue reference; without this hold a - * concurrent teardown (e.g. l2cap_conn_del() -> - * l2cap_sock_kill()) could free sk between - * release_sock() and the caller using it. Every - * caller drops this with sock_put() when done. - */ - sock_hold(sk); - release_sock(sk); if (next) sock_put(next); @@ -354,6 +342,7 @@ restart: } release_sock(sk); + sock_put(sk); } return NULL; diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index add9a8f7535d..f7d88c33e23e 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -559,14 +559,18 @@ static int bnep_session(void *arg) return 0; } -static struct device *bnep_get_device(struct bnep_session *session) +static struct l2cap_conn *bnep_get_conn(struct bnep_session *session) { - struct l2cap_conn *conn = l2cap_pi(session->sock->sk)->chan->conn; + struct l2cap_chan *chan = l2cap_pi(session->sock->sk)->chan; + struct l2cap_conn *conn; - if (!conn || !conn->hcon) - return NULL; + l2cap_chan_lock(chan); + conn = chan->conn; + if (conn) + l2cap_conn_get(conn); + l2cap_chan_unlock(chan); - return &conn->hcon->dev; + return conn; } static const struct device_type bnep_type = { @@ -578,6 +582,7 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) u32 valid_flags = BIT(BNEP_SETUP_RESPONSE); struct net_device *dev; struct bnep_session *s, *ss; + struct l2cap_conn *conn = NULL; u8 dst[ETH_ALEN], src[ETH_ALEN]; int err; @@ -637,10 +642,18 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) bnep_set_default_proto_filter(s); #endif - SET_NETDEV_DEV(dev, bnep_get_device(s)); + conn = bnep_get_conn(s); + if (!conn) { + err = -ENOTCONN; + goto failed; + } + + SET_NETDEV_DEV(dev, &conn->hcon->dev); SET_NETDEV_DEVTYPE(dev, &bnep_type); err = register_netdev(dev); + l2cap_conn_put(conn); + conn = NULL; if (err) goto failed; @@ -662,6 +675,8 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) return 0; failed: + if (conn) + l2cap_conn_put(conn); up_write(&bnep_session_sem); free_netdev(dev); return err; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index c335372e4062..1966cd153d97 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -3178,26 +3178,11 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) conn->abort_reason = reason; - /* If the connection is pending check the command opcode since that - * might be blocking on hci_cmd_sync_work while waiting its respective - * event so we need to hci_cmd_sync_cancel to cancel it. - * - * hci_connect_le serializes the connection attempts so only one - * connection can be in BT_CONNECT at time. + /* Cancel the connect attempt. A return of 0 means the create command + * was still queued and got dequeued, so there is nothing to disconnect. */ - if (conn->state == BT_CONNECT && READ_ONCE(hdev->req_status) == HCI_REQ_PEND) { - switch (hci_skb_event(hdev->sent_cmd)) { - case HCI_EV_CONN_COMPLETE: - case HCI_EV_LE_CONN_COMPLETE: - case HCI_EV_LE_ENHANCED_CONN_COMPLETE: - case HCI_EVT_LE_CIS_ESTABLISHED: - hci_cmd_sync_cancel(hdev, ECANCELED); - break; - } - /* Cancel connect attempt if still queued/pending */ - } else if (!hci_cancel_connect_sync(hdev, conn)) { + if (!hci_cancel_connect_sync(hdev, conn)) return 0; - } /* Run immediately if on cmd_sync_work since this may be called * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 3be8c3581c6c..c896d4edd013 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6633,6 +6633,11 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) bt_dev_dbg(hdev, "conn %p", conn); + /* Hold a reference so conn stays valid for the HCI_CONN_CREATE + * clear_bit() at done. + */ + hci_conn_get(conn); + clear_bit(HCI_CONN_SCANNING, &conn->flags); conn->state = BT_CONNECT; @@ -6645,6 +6650,7 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) hdev->le_scan_type == LE_SCAN_ACTIVE && !hci_dev_test_flag(hdev, HCI_LE_SIMULTANEOUS_ROLES)) { hci_conn_del(conn); + hci_conn_put(conn); return -EBUSY; } @@ -6690,6 +6696,12 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) &own_addr_type); if (err) goto done; + + /* Mark create connection in flight so hci_cancel_connect_sync() can + * cancel it while blocking on the connection complete event. + */ + set_bit(HCI_CONN_CREATE, &conn->flags); + /* Send command LE Extended Create Connection if supported */ if (use_ext_conn(hdev)) { err = hci_le_ext_create_conn_sync(hdev, conn, own_addr_type); @@ -6725,11 +6737,14 @@ static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) conn->conn_timeout, NULL); done: + clear_bit(HCI_CONN_CREATE, &conn->flags); + if (err == -ETIMEDOUT) hci_le_connect_cancel_sync(hdev, conn, 0x00); /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); + hci_conn_put(conn); return err; } @@ -7004,10 +7019,25 @@ static int hci_acl_create_conn_sync(struct hci_dev *hdev, void *data) else cp.role_switch = 0x00; - return __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN, - sizeof(cp), &cp, - HCI_EV_CONN_COMPLETE, - conn->conn_timeout, NULL); + /* Hold a reference so conn stays valid for the HCI_CONN_CREATE + * clear_bit() below. + */ + hci_conn_get(conn); + + /* Mark create connection in flight so hci_cancel_connect_sync() can + * cancel it while blocking on the connection complete event. + */ + set_bit(HCI_CONN_CREATE, &conn->flags); + + err = __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN, + sizeof(cp), &cp, + HCI_EV_CONN_COMPLETE, + conn->conn_timeout, NULL); + + clear_bit(HCI_CONN_CREATE, &conn->flags); + hci_conn_put(conn); + + return err; } int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -7059,22 +7089,97 @@ int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn) return (err == -EEXIST) ? 0 : err; } -int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_acl_cancel_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn) { - if (conn->state != BT_OPEN) - return -EINVAL; + struct hci_cmd_sync_work_entry *entry; + int err = -EBUSY; + + /* cmd_sync_work_lock makes the HCI_CONN_CREATE test and the cancel + * atomic against the worker, which takes this lock to dequeue every + * entry: while it is held no other command can become pending, so + * hci_cmd_sync_cancel() cannot cancel an unrelated command. + */ + mutex_lock(&hdev->cmd_sync_work_lock); + + /* In flight: this connection owns the pending request, cancel it. */ + if (test_bit(HCI_CONN_CREATE, &conn->flags)) { + hci_cmd_sync_cancel(hdev, ECANCELED); + goto unlock; + } + + /* Still queued: a successful dequeue means it never started, so there + * is nothing to disconnect. + */ + entry = _hci_cmd_sync_lookup_entry(hdev, hci_acl_create_conn_sync, conn, + NULL); + if (entry) { + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + err = 0; + } + +unlock: + mutex_unlock(&hdev->cmd_sync_work_lock); + return err; +} + +static int hci_le_cancel_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn) +{ + struct hci_cmd_sync_work_entry *entry; + int err = -EBUSY; + + /* cmd_sync_work_lock keeps the HCI_CONN_CREATE test and the cancel + * atomic against the cmd_sync worker. + */ + mutex_lock(&hdev->cmd_sync_work_lock); + if (test_bit(HCI_CONN_CREATE, &conn->flags)) { + hci_cmd_sync_cancel(hdev, ECANCELED); + goto unlock; + } + + entry = _hci_cmd_sync_lookup_entry(hdev, hci_le_create_conn_sync, conn, + create_le_conn_complete); + if (entry) { + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + err = 0; + } + +unlock: + mutex_unlock(&hdev->cmd_sync_work_lock); + return err; +} + +static int hci_cis_cancel_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn) +{ + /* LE Create CIS is shared by the whole CIG and cannot be dequeued + * per-connection, so only an in-flight command can be cancelled. + * cmd_sync_work_lock keeps the test and the cancel atomic against the + * cmd_sync worker. + */ + mutex_lock(&hdev->cmd_sync_work_lock); + + if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) + hci_cmd_sync_cancel(hdev, ECANCELED); + + mutex_unlock(&hdev->cmd_sync_work_lock); + return -EBUSY; +} + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ switch (conn->type) { case ACL_LINK: - return !hci_cmd_sync_dequeue_once(hdev, - hci_acl_create_conn_sync, - conn, NULL); + return hci_acl_cancel_create_conn_sync(hdev, conn); case LE_LINK: - return !hci_cmd_sync_dequeue_once(hdev, hci_le_create_conn_sync, - conn, create_le_conn_complete); + return hci_le_cancel_create_conn_sync(hdev, conn); + case CIS_LINK: + return hci_cis_cancel_create_conn_sync(hdev, conn); + default: + return -ENOENT; } - - return -ENOENT; } int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn, diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 793a481d7066..2e95a153912c 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1590,6 +1590,7 @@ static void iso_conn_big_sync(struct sock *sk) { int err; struct hci_dev *hdev; + struct iso_conn *conn; bdaddr_t src, dst; u8 src_type; @@ -1612,8 +1613,17 @@ static void iso_conn_big_sync(struct sock *sk) hci_dev_lock(hdev); lock_sock(sk); + /* The socket lock was dropped for hci_get_route(), so the connection + * may have been torn down meanwhile: iso_chan_del() clears conn and + * the broadcast teardown path can clear conn->hcon on its own. Check + * both before dereferencing conn->hcon. + */ + conn = iso_pi(sk)->conn; + if (!conn || !conn->hcon) + goto unlock; + if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { - err = hci_conn_big_create_sync(hdev, iso_pi(sk)->conn->hcon, + err = hci_conn_big_create_sync(hdev, conn->hcon, &iso_pi(sk)->qos, iso_pi(sk)->sync_handle, iso_pi(sk)->bc_num_bis, @@ -1622,6 +1632,7 @@ static void iso_conn_big_sync(struct sock *sk) bt_dev_err(hdev, "hci_big_create_sync: %d", err); } +unlock: release_sock(sk); hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -2529,7 +2540,7 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) switch (pb) { case ISO_START: case ISO_SINGLE: - if (conn->rx_len) { + if (conn->rx_skb || conn->rx_len) { BT_ERR("Unexpected start frame (len %d)", skb->len); kfree_skb(conn->rx_skb); conn->rx_skb = NULL; @@ -2610,12 +2621,14 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) break; case ISO_CONT: - BT_DBG("Cont: frag len %d (expecting %d)", skb->len, + case ISO_END: + BT_DBG("%s: frag len %d (expecting %d)", + (pb == ISO_END) ? "End" : "Cont", skb->len, conn->rx_len); - if (!conn->rx_len) { - BT_ERR("Unexpected continuation frame (len %d)", - skb->len); + if (!conn->rx_skb) { + BT_ERR("Unexpected ISO %s frame (len %d)", + (pb == ISO_END) ? "End" : "Cont", skb->len); goto drop; } @@ -2631,17 +2644,9 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; - break; - - case ISO_END: - if (!conn->rx_len) { - BT_ERR("Unexpected end frame (len %d)", skb->len); - goto drop; - } - skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), - skb->len); - conn->rx_len -= skb->len; + if (pb == ISO_CONT) + break; if (!conn->rx_len) { struct sk_buff *rx_skb = conn->rx_skb; @@ -2652,6 +2657,13 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) */ conn->rx_skb = NULL; iso_recv_frame(conn, rx_skb); + } else { + BT_ERR("ISO fragment incomplete (len %d, expected %d)", + skb->len, conn->rx_len); + kfree_skb(conn->rx_skb); + conn->rx_skb = NULL; + conn->rx_len = 0; + goto drop; } break; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 62133eef9d2f..538ae9aa3479 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -522,7 +522,10 @@ void l2cap_chan_put(struct l2cap_chan *c) } EXPORT_SYMBOL_GPL(l2cap_chan_put); -void l2cap_chan_set_defaults(struct l2cap_chan *chan) +/* Initialise @chan with default values, inheriting from the parent channel + * @pchan when it is given. + */ +void l2cap_chan_set_defaults(struct l2cap_chan *chan, struct l2cap_chan *pchan) { chan->fcs = L2CAP_FCS_CRC16; chan->max_tx = L2CAP_DEFAULT_MAX_TX; @@ -536,6 +539,31 @@ void l2cap_chan_set_defaults(struct l2cap_chan *chan) chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; + if (pchan) { + BT_DBG("chan %p pchan %p", chan, pchan); + + chan->chan_type = pchan->chan_type; + chan->imtu = pchan->imtu; + chan->omtu = pchan->omtu; + chan->mode = pchan->mode; + chan->fcs = pchan->fcs; + chan->max_tx = pchan->max_tx; + chan->tx_win = pchan->tx_win; + chan->tx_win_max = pchan->tx_win_max; + chan->sec_level = pchan->sec_level; + chan->conf_state = pchan->conf_state; + chan->flags = pchan->flags; + chan->tx_credits = pchan->tx_credits; + chan->rx_credits = pchan->rx_credits; + + if (chan->chan_type == L2CAP_CHAN_FIXED) { + chan->scid = pchan->scid; + chan->dcid = pchan->scid; + } + + return; + } + chan->conf_state = 0; set_bit(CONF_NOT_COMPLETE, &chan->conf_state); @@ -1775,19 +1803,13 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) disable_delayed_work_sync(&conn->info_timer); disable_delayed_work_sync(&conn->id_addr_timer); + cancel_work_sync(&conn->pending_rx_work); + mutex_lock(&conn->lock); kfree_skb(conn->rx_skb); skb_queue_purge(&conn->pending_rx); - - /* We can not call flush_work(&conn->pending_rx_work) here since we - * might block if we are running on a worker from the same workqueue - * pending_rx_work is waiting on. - */ - if (work_pending(&conn->pending_rx_work)) - cancel_work_sync(&conn->pending_rx_work); - ida_destroy(&conn->tx_ida); l2cap_unregister_all_users(conn); @@ -3051,13 +3073,24 @@ fail: return NULL; } -static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen, - unsigned long *val) +static inline int l2cap_get_conf_opt(void **ptr, void *end, int *type, + int *olen, unsigned long *val) { struct l2cap_conf_opt *opt = *ptr; int len; + /* opt->len is attacker-controlled. Validate that the full option + * (header + value) actually fits in the buffer before touching + * opt->val, otherwise the switch below reads past the end of the + * caller's buffer. + */ + if (end - *ptr < L2CAP_CONF_OPT_SIZE) + return -EINVAL; + len = L2CAP_CONF_OPT_SIZE + opt->len; + if (end - *ptr < len) + return -EINVAL; + *ptr += len; *type = opt->type; @@ -3429,6 +3462,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data void *ptr = rsp->data; void *endptr = data + data_size; void *req = chan->conf_req; + void *req_end = req + chan->conf_len; int len = chan->conf_len; int type, hint, olen; unsigned long val; @@ -3442,9 +3476,11 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data BT_DBG("chan %p", chan); while (len >= L2CAP_CONF_OPT_SIZE) { - len -= l2cap_get_conf_opt(&req, &type, &olen, &val); - if (len < 0) + int ret = l2cap_get_conf_opt(&req, req_end, &type, &olen, &val); + + if (ret < 0) break; + len -= ret; hint = type & L2CAP_CONF_HINT; type &= L2CAP_CONF_MASK; @@ -3672,6 +3708,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, struct l2cap_conf_req *req = data; void *ptr = req->data; void *endptr = data + size; + void *rsp_end = rsp + len; int type, olen; unsigned long val; struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC }; @@ -3680,9 +3717,11 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, BT_DBG("chan %p, rsp %p, len %d, req %p", chan, rsp, len, data); while (len >= L2CAP_CONF_OPT_SIZE) { - len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); - if (len < 0) + int ret = l2cap_get_conf_opt(&rsp, rsp_end, &type, &olen, &val); + + if (ret < 0) break; + len -= ret; switch (type) { case L2CAP_CONF_MTU: @@ -3933,6 +3972,7 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) { int type, olen; unsigned long val; + void *rsp_end = rsp + len; /* Use sane default values in case a misbehaving remote device * did not send an RFC or extended window size option. */ @@ -3951,9 +3991,11 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) return; while (len >= L2CAP_CONF_OPT_SIZE) { - len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val); - if (len < 0) + int ret = l2cap_get_conf_opt(&rsp, rsp_end, &type, &olen, &val); + + if (ret < 0) break; + len -= ret; switch (type) { case L2CAP_CONF_RFC: @@ -4010,6 +4052,38 @@ static inline int l2cap_command_rej(struct l2cap_conn *conn, return 0; } +/* Allocate and initialise a channel for an incoming connection. + * + * The channel inherits its configuration from @pchan and is linked into @conn + * before ->new_connection() runs, so the conn list reference keeps it alive if + * the callback exposes it (e.g. via the socket accept queue) before this + * returns. The l2cap_chan_create() reference is taken over by the subsystem on + * success and dropped here on failure. + */ +static struct l2cap_chan *l2cap_new_connection(struct l2cap_conn *conn, + struct l2cap_chan *pchan) +{ + struct l2cap_chan *chan; + + chan = l2cap_chan_create(); + if (!chan) + return NULL; + + l2cap_chan_set_defaults(chan, pchan); + chan->ops = pchan->ops; + + __l2cap_chan_add(conn, chan); + + if (pchan->ops->new_connection && + pchan->ops->new_connection(pchan, chan) < 0) { + l2cap_chan_del(chan, 0); + l2cap_chan_put(chan); + return NULL; + } + + return chan; +} + static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data, u8 rsp_code) { @@ -4056,7 +4130,7 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, goto response; } - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (!chan) goto response; @@ -4074,8 +4148,6 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, chan->psm = psm; chan->dcid = scid; - __l2cap_chan_add(conn, chan); - dcid = chan->scid; __set_chan_timer(chan, chan->ops->get_sndtimeo(chan)); @@ -4807,6 +4879,7 @@ static void l2cap_put_ident(struct l2cap_conn *conn, u8 code, u8 id) case L2CAP_ECHO_RSP: case L2CAP_INFO_RSP: case L2CAP_CONN_PARAM_UPDATE_RSP: + case L2CAP_LE_CONN_RSP: case L2CAP_ECRED_CONN_RSP: case L2CAP_ECRED_RECONF_RSP: /* First do a lookup since the remote may send bogus ids that @@ -4958,7 +5031,7 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, goto response_unlock; } - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (!chan) { result = L2CAP_CR_LE_NO_MEM; goto response_unlock; @@ -4973,8 +5046,6 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, chan->omtu = mtu; chan->remote_mps = mps; - __l2cap_chan_add(conn, chan); - l2cap_le_flowctl_init(chan, __le16_to_cpu(req->credits)); dcid = chan->scid; @@ -5182,7 +5253,7 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, continue; } - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (!chan) { result = L2CAP_CR_LE_NO_MEM; continue; @@ -5197,8 +5268,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, chan->omtu = mtu; chan->remote_mps = mps; - __l2cap_chan_add(conn, chan); - l2cap_ecred_init(chan, __le16_to_cpu(req->credits)); /* Init response */ @@ -6704,6 +6773,7 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct l2cap_le_credits pkt; u16 return_credits = l2cap_le_rx_credits(chan); + int ident; if (chan->mode != L2CAP_MODE_LE_FLOWCTL && chan->mode != L2CAP_MODE_EXT_FLOWCTL) @@ -6721,9 +6791,18 @@ static void l2cap_chan_le_send_credits(struct l2cap_chan *chan) pkt.cid = cpu_to_le16(chan->scid); pkt.credits = cpu_to_le16(return_credits); - chan->ident = l2cap_get_ident(conn); + ident = l2cap_get_ident(conn); + + l2cap_send_cmd(conn, ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt); - l2cap_send_cmd(conn, chan->ident, L2CAP_LE_CREDITS, sizeof(pkt), &pkt); + /* L2CAP_LE_CREDITS has no response so the ident is never released by + * l2cap_put_ident() - release it right away, otherwise the tx_ida + * range is exhausted after 254 packets and from then on credits are + * sent with the invalid ident 0, which some remote stacks ignore, + * stalling the channel. + */ + if (ident > 0) + ida_free(&conn->tx_ida, ident); } void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail) @@ -7478,14 +7557,12 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) goto next; l2cap_chan_lock(pchan); - chan = pchan->ops->new_connection(pchan); + chan = l2cap_new_connection(conn, pchan); if (chan) { bacpy(&chan->src, &hcon->src); bacpy(&chan->dst, &hcon->dst); chan->src_type = bdaddr_src_type(hcon); chan->dst_type = dst_type; - - __l2cap_chan_add(conn, chan); } l2cap_chan_unlock(pchan); @@ -7702,6 +7779,7 @@ struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *c) return c; } +EXPORT_SYMBOL(l2cap_conn_hold_unless_zero); int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 4853f1b33449..4058ff50cc27 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -43,7 +43,8 @@ static struct bt_sock_list l2cap_sk_list = { 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); + int proto, gfp_t prio, int kern, + struct l2cap_chan *chan); static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) @@ -1284,6 +1285,23 @@ done: return err; } +/* Release the sock's ref on chan and clear the pointer so that the ref is + * dropped exactly once even if both l2cap_sock_kill() and + * l2cap_sock_destruct() run. Setting chan->data to NULL first stops any other + * task from dereferencing the now-dead sock pointer. + */ +static void l2cap_sock_put_chan(struct sock *sk) +{ + struct l2cap_chan *chan = l2cap_pi(sk)->chan; + + if (!chan) + return; + + chan->data = NULL; + l2cap_pi(sk)->chan = NULL; + l2cap_chan_put(chan); +} + /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket, with l2cap channel lock. */ @@ -1294,13 +1312,9 @@ static void l2cap_sock_kill(struct sock *sk) BT_DBG("sk %p state %s", sk, state_to_string(sk->sk_state)); - /* Sock is dead, so set chan data to NULL, avoid other task use invalid - * sock pointer. - */ - l2cap_pi(sk)->chan->data = NULL; - /* Kill poor orphan */ + l2cap_sock_put_chan(sk); - l2cap_chan_put(l2cap_pi(sk)->chan); + /* Kill poor orphan */ sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } @@ -1492,8 +1506,8 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) /* Close not yet accepted channels. * - * bt_accept_dequeue() now returns sk with an extra reference held - * (taken while sk was still locked) so a concurrent l2cap_conn_del() + * bt_accept_dequeue() returns sk with its temporary queue-walk + * reference held, so a concurrent l2cap_conn_del() * -> l2cap_sock_kill() cannot free sk under us. * * cleanup_listen() runs under the parent sk lock, so unlike @@ -1543,12 +1557,13 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) } } -static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) +static int l2cap_sock_new_connection_cb(struct l2cap_chan *chan, + struct l2cap_chan *new_chan) { struct sock *sk, *parent = chan->data; if (!parent) - return NULL; + return -EINVAL; lock_sock(parent); @@ -1556,25 +1571,28 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) if (sk_acceptq_is_full(parent)) { BT_DBG("backlog full %d", parent->sk_ack_backlog); release_sock(parent); - return NULL; + return -ENOBUFS; } sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, - GFP_ATOMIC, 0); + GFP_ATOMIC, 0, new_chan); if (!sk) { release_sock(parent); - return NULL; - } + return -ENOMEM; + } bt_sock_reclassify_lock(sk, BTPROTO_L2CAP); l2cap_sock_init(sk, parent); + /* The conn list reference taken by l2cap_new_connection() keeps new_chan + * alive once release_sock() lets another task free this socket. + */ bt_accept_enqueue(parent, sk, false); release_sock(parent); - return l2cap_pi(sk)->chan; + return 0; } static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) @@ -1871,10 +1889,7 @@ static void l2cap_sock_destruct(struct sock *sk) BT_DBG("sk %p", sk); - if (l2cap_pi(sk)->chan) { - l2cap_pi(sk)->chan->data = NULL; - l2cap_chan_put(l2cap_pi(sk)->chan); - } + l2cap_sock_put_chan(sk); list_for_each_entry_safe(rx_busy, next, &l2cap_pi(sk)->rx_busy, list) { kfree_skb(rx_busy->skb); @@ -1907,30 +1922,12 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) BT_DBG("sk %p", sk); if (parent) { - struct l2cap_chan *pchan = l2cap_pi(parent)->chan; - sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; - chan->chan_type = pchan->chan_type; - chan->imtu = pchan->imtu; - chan->omtu = pchan->omtu; - chan->conf_state = pchan->conf_state; - chan->mode = pchan->mode; - chan->fcs = pchan->fcs; - chan->max_tx = pchan->max_tx; - chan->tx_win = pchan->tx_win; - chan->tx_win_max = pchan->tx_win_max; - chan->sec_level = pchan->sec_level; - chan->flags = pchan->flags; - chan->tx_credits = pchan->tx_credits; - chan->rx_credits = pchan->rx_credits; - - if (chan->chan_type == L2CAP_CHAN_FIXED) { - chan->scid = pchan->scid; - chan->dcid = pchan->scid; - } - + /* Channel configuration is inherited from the parent by + * l2cap_new_connection(). + */ security_sk_clone(parent, sk); } else { switch (sk->sk_type) { @@ -1956,7 +1953,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->mode = L2CAP_MODE_BASIC; } - l2cap_chan_set_defaults(chan); + l2cap_chan_set_defaults(chan, NULL); } /* Default config options */ @@ -1975,10 +1972,10 @@ static struct proto l2cap_proto = { }; static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, - int proto, gfp_t prio, int kern) + int proto, gfp_t prio, int kern, + struct l2cap_chan *chan) { struct sock *sk; - struct l2cap_chan *chan; sk = bt_sock_alloc(net, sock, &l2cap_proto, proto, prio, kern); if (!sk) @@ -1989,16 +1986,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, INIT_LIST_HEAD(&l2cap_pi(sk)->rx_busy); - chan = l2cap_chan_create(); - if (!chan) { - sk_free(sk); - if (sock) - sock->sk = NULL; - return NULL; - } - - l2cap_chan_hold(chan); - + /* The sock takes ownership of the caller's reference on chan. */ l2cap_pi(sk)->chan = chan; return sk; @@ -2008,6 +1996,7 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; + struct l2cap_chan *chan; BT_DBG("sock %p", sock); @@ -2022,10 +2011,16 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, sock->ops = &l2cap_sock_ops; - sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); - if (!sk) + chan = l2cap_chan_create(); + if (!chan) return -ENOMEM; + sk = l2cap_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern, chan); + if (!sk) { + l2cap_chan_put(chan); + return -ENOMEM; + } + l2cap_sock_init(sk, NULL); bt_sock_link(&l2cap_sk_list, sk); return 0; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d23ca1dd0893..733a4b70e10c 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -5375,6 +5375,8 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, if (monitor->state == ADV_MONITOR_STATE_NOT_REGISTERED) monitor->state = ADV_MONITOR_STATE_REGISTERED; hci_update_passive_scan(hdev); + } else { + hci_free_adv_monitor(hdev, monitor); } mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, @@ -7658,6 +7660,8 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err) if (!err) { struct hci_conn_params *params; + hci_dev_lock(hdev); + params = hci_conn_params_lookup(hdev, &cp->addr.bdaddr, le_addr_type(cp->addr.type)); @@ -7666,6 +7670,7 @@ static void add_device_complete(struct hci_dev *hdev, void *data, int err) device_flags_changed(NULL, hdev, &cp->addr.bdaddr, cp->addr.type, hdev->conn_flags, params ? params->flags : 0); + hci_dev_unlock(hdev); } mgmt_cmd_complete(cmd->sk, hdev->id, MGMT_OP_ADD_DEVICE, diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 2f008167cbaa..d7badce8746c 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -291,7 +291,7 @@ static int msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u16 opcode, monitor->state = ADV_MONITOR_STATE_OFFLOADED; unlock: - if (status) + if (status && msft->resuming) hci_free_adv_monitor(hdev, monitor); hci_dev_unlock(hdev); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index fcc597be5bbd..c05f79b7aa31 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -570,10 +570,23 @@ static void __sco_sock_close(struct sock *sk) /* Must be called on unlocked socket. */ static void sco_sock_close(struct sock *sk) { + struct sco_conn *conn; + + lock_sock(sk); + conn = sco_pi(sk)->conn; + if (conn) + sco_conn_hold(conn); + release_sock(sk); + + if (conn) + disable_delayed_work_sync(&conn->timeout_work); + lock_sock(sk); - sco_sock_clear_timer(sk); __sco_sock_close(sk); release_sock(sk); + + if (conn) + sco_conn_put(conn); } static void sco_sock_init(struct sock *sk, struct sock *parent) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 031d3022cb1e..c4470958b0d5 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -3201,34 +3201,19 @@ static const struct l2cap_ops smp_chan_ops = { .get_sndtimeo = l2cap_chan_no_get_sndtimeo, }; -static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) +static inline int smp_new_conn_cb(struct l2cap_chan *chan, + struct l2cap_chan *new_chan) { - struct l2cap_chan *chan; - - BT_DBG("pchan %p", pchan); - - chan = l2cap_chan_create(); - if (!chan) - return NULL; - - chan->chan_type = pchan->chan_type; - chan->ops = &smp_chan_ops; - chan->scid = pchan->scid; - chan->dcid = chan->scid; - chan->imtu = pchan->imtu; - chan->omtu = pchan->omtu; - chan->mode = pchan->mode; + new_chan->ops = &smp_chan_ops; /* Other L2CAP channels may request SMP routines in order to * change the security level. This means that the SMP channel * lock must be considered in its own category to avoid lockdep * warnings. */ - atomic_set(&chan->nesting, L2CAP_NESTING_SMP); - - BT_DBG("created chan %p", chan); + atomic_set(&new_chan->nesting, L2CAP_NESTING_SMP); - return chan; + return 0; } static const struct l2cap_ops smp_root_chan_ops = { @@ -3288,7 +3273,7 @@ create_chan: l2cap_add_scid(chan, cid); - l2cap_chan_set_defaults(chan); + l2cap_chan_set_defaults(chan, NULL); if (cid == L2CAP_CID_SMP) { u8 bdaddr_type; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index f20c039e44c8..96c9a8f57c87 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -403,6 +403,9 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, left - sizeof(struct ebt_entry_match) < m->match_size) return -EINVAL; + if (strnlen(m->u.name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN) + return -EINVAL; + match = xt_find_match(NFPROTO_BRIDGE, m->u.name, m->u.revision); if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) { if (!IS_ERR(match)) @@ -921,8 +924,7 @@ static int translate_table(struct net *net, const char *name, * if an error occurs */ newinfo->chainstack = - vmalloc_array(nr_cpu_ids, - sizeof(*(newinfo->chainstack))); + vcalloc(nr_cpu_ids, sizeof(*(newinfo->chainstack))); if (!newinfo->chainstack) return -ENOMEM; for_each_possible_cpu(i) { @@ -1434,6 +1436,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; + hlp.name[sizeof(hlp.name) - 1] = '\0'; + if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter)) return -EINVAL; @@ -2273,6 +2277,8 @@ static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl, memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry)); + repl->name[sizeof(repl->name) - 1] = '\0'; + /* starting with hook_entry, 32 vs. 64 bit structures are different */ for (i = 0; i < NF_BR_NUMHOOKS; i++) repl->hook_entry[i] = compat_ptr(tmp.hook_entry[i]); @@ -2395,6 +2401,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; + hlp.name[sizeof(hlp.name) - 1] = '\0'; + /* try real handler in case userland supplied needed padding */ if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter)) return update_counters(net, arg, len); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 4ca2eca2e94b..3e969a070f9f 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -115,6 +115,34 @@ static inline void ethnl_update_u8(u8 *dst, const struct nlattr *attr, } /** + * ethnl_update_u8_u32() - update u8 value from an NLA_U32 attribute + * @dst: value to update + * @attr: netlink attribute with new value or null + * @mod: pointer to bool for modification tracking + * + * Some attributes are NLA_U32 on the wire but are stored in a u8. Read the + * full 32-bit value from NLA_U32 netlink attribute @attr and narrow it into + * the u8 pointed to by @dst; do nothing if @attr is null. + * Bool pointed to by @mod is set to true if this function changed the value + * of *dst, otherwise it is left as is. + */ +static inline void ethnl_update_u8_u32(u8 *dst, const struct nlattr *attr, + bool *mod) +{ + u32 val; + + if (!attr) + return; + val = nla_get_u32(attr); + DEBUG_NET_WARN_ON_ONCE(val > U8_MAX); + if (*dst == val) + return; + + *dst = val; + *mod = true; +} + +/** * ethnl_update_bool32() - update u32 used as bool from NLA_U8 attribute * @dst: value to update * @attr: netlink attribute with new value or null diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index d8adc78e3775..d4a1a4724b67 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -570,7 +570,7 @@ static const struct nla_policy ethnl_rss_flows_policy[] = { const struct nla_policy ethnl_rss_set_policy[ETHTOOL_A_RSS_FLOW_HASH + 1] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32, }, - [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_RANGE(NLA_U32, 1, U8_MAX), [ETHTOOL_A_RSS_INDIR] = { .type = NLA_BINARY, }, [ETHTOOL_A_RSS_HKEY] = NLA_POLICY_MIN(NLA_BINARY, 1), [ETHTOOL_A_RSS_INPUT_XFRM] = @@ -851,7 +851,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) indir_mod = !!tb[ETHTOOL_A_RSS_INDIR]; rxfh.hfunc = data.hfunc; - ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); + ethnl_update_u8_u32(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); if (rxfh.hfunc == data.hfunc) rxfh.hfunc = ETH_RSS_HASH_NO_CHANGE; @@ -860,7 +860,8 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) goto exit_free_indir; rxfh.input_xfrm = data.input_xfrm; - ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); + ethnl_update_u8_u32(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], + &mod); xfrm_sym = rxfh.input_xfrm || data.input_xfrm; if (rxfh.input_xfrm == data.input_xfrm) rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; @@ -934,7 +935,7 @@ const struct ethnl_request_ops ethnl_rss_request_ops = { const struct nla_policy ethnl_rss_create_policy[ETHTOOL_A_RSS_INPUT_XFRM + 1] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = NLA_POLICY_MIN(NLA_U32, 1), - [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_RANGE(NLA_U32, 1, U8_MAX), [ETHTOOL_A_RSS_INDIR] = NLA_POLICY_MIN(NLA_BINARY, 1), [ETHTOOL_A_RSS_HKEY] = NLA_POLICY_MIN(NLA_BINARY, 1), [ETHTOOL_A_RSS_INPUT_XFRM] = @@ -1048,14 +1049,15 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info) goto exit_clean_data; indir_user_size = ret; - ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); + ethnl_update_u8_u32(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); ret = rss_set_prep_hkey(dev, info, &data, &rxfh, &mod); if (ret) goto exit_free_indir; rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; - ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); + ethnl_update_u8_u32(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], + &mod); ctx = ethtool_rxfh_ctx_alloc(ops, data.indir_size, data.hkey_size); if (!ctx) { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b6337a47c141..bb2d4441a492 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -217,13 +217,18 @@ static void ip_sf_list_clear_all(struct ip_sf_list *psf) static void igmp_stop_timer(struct ip_mc_list *im) { + bool put = false; + spin_lock_bh(&im->lock); if (timer_delete(&im->timer)) - refcount_dec(&im->refcnt); + put = true; WRITE_ONCE(im->tm_running, 0); WRITE_ONCE(im->reporter, 0); im->unsolicit_count = 0; spin_unlock_bh(&im->lock); + + if (put) + ip_ma_put(im); } /* It must be called with locked im->lock */ @@ -248,20 +253,26 @@ static void igmp_gq_start_timer(struct in_device *in_dev) return; in_dev->mr_gq_running = 1; - if (!mod_timer(&in_dev->mr_gq_timer, exp)) - in_dev_hold(in_dev); + if (in_dev_hold_safe(in_dev)) { + if (mod_timer(&in_dev->mr_gq_timer, exp)) + in_dev_put(in_dev); + } } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { - int tv = get_random_u32_below(delay); + if (in_dev_hold_safe(in_dev)) { + int tv = get_random_u32_below(delay); - if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) - in_dev_hold(in_dev); + if (mod_timer(&in_dev->mr_ifc_timer, jiffies + tv + 2)) + in_dev_put(in_dev); + } } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { + bool put = false; + spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (timer_delete(&im->timer)) { @@ -271,10 +282,13 @@ static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) spin_unlock_bh(&im->lock); return; } - refcount_dec(&im->refcnt); + put = true; } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); + + if (put) + ip_ma_put(im); } @@ -1922,6 +1936,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { + ip_mc_hash_remove(in_dev, i); in_dev->mc_list = i->next_rcu; WRITE_ONCE(in_dev->mc_count, in_dev->mc_count - 1); ip_mc_clear_src(i); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 04b811b3be97..4d2b9377ba2d 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1083,8 +1083,10 @@ static void mld_gq_start_work(struct inet6_dev *idev) mc_assert_locked(idev); idev->mc_gq_running = 1; - if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) - in6_dev_hold(idev); + if (in6_dev_hold_safe(idev)) { + if (mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) + in6_dev_put(idev); + } } static void mld_gq_stop_work(struct inet6_dev *idev) @@ -1102,8 +1104,10 @@ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) mc_assert_locked(idev); - if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) - in6_dev_hold(idev); + if (in6_dev_hold_safe(idev)) { + if (mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) + in6_dev_put(idev); + } } static void mld_ifc_stop_work(struct inet6_dev *idev) @@ -1121,8 +1125,10 @@ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) mc_assert_locked(idev); - if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) - in6_dev_hold(idev); + if (in6_dev_hold_safe(idev)) { + if (mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) + in6_dev_put(idev); + } } static void mld_dad_stop_work(struct inet6_dev *idev) @@ -1395,18 +1401,23 @@ static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); + bool put = false; if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_query_lock); - if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { + if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS && + in6_dev_hold_safe(idev)) { __skb_queue_tail(&idev->mc_query_queue, skb); - if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) - in6_dev_hold(idev); + if (mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) + put = true; skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); + + if (put) + in6_dev_put(idev); out: kfree_skb(skb); } @@ -1570,18 +1581,23 @@ static void mld_query_work(struct work_struct *work) void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); + bool put = false; if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_report_lock); - if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { + if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS && + in6_dev_hold_safe(idev)) { __skb_queue_tail(&idev->mc_report_queue, skb); - if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) - in6_dev_hold(idev); + if (mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) + put = true; skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); + + if (put) + in6_dev_put(idev); out: kfree_skb(skb); } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 70da2f2ce064..1258783ed876 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -56,6 +56,11 @@ static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par) } hdrlen = ipv6_authlen(ah); + if (skb->len - ptr < hdrlen) { + /* Packet smaller than its length field */ + par->hotdrop = true; + return false; + } pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen); pr_debug("RES %04X ", ah->reserved); diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index 450dd53846a2..6d1a5d2026a6 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -75,6 +75,7 @@ hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par) hdrlen = ipv6_optlen(oh); if (skb->len - ptr < hdrlen) { /* Packet smaller than it's length field */ + par->hotdrop = true; return false; } diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 5561bd9cea81..278b52752f36 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -56,7 +56,8 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par) hdrlen = ipv6_optlen(rh); if (skb->len - ptr < hdrlen) { - /* Pcket smaller than its length field */ + /* Packet smaller than its length field */ + par->hotdrop = true; return false; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 64ab23ff559b..599c49bf0a0a 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -348,7 +348,8 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; memmove(skb->head + sizeof(struct frag_hdr), skb->head, (skb->data - skb->head) - sizeof(struct frag_hdr)); - skb->mac_header += sizeof(struct frag_hdr); + if (skb_mac_header_was_set(skb)) + skb->mac_header += sizeof(struct frag_hdr); skb->network_header += sizeof(struct frag_hdr); skb_reset_transport_header(skb); @@ -418,7 +419,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return -1; } if (skb_copy_bits(skb, start, &hdr, sizeof(hdr))) - BUG(); + return -1; if (nexthdr == NEXTHDR_AUTH) hdrlen = ipv6_authlen(&hdr); else diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 8ed1be1ecccc..b0447c33dbf0 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -312,6 +312,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) /* assign new connection to its SAP */ llc_sap_add_socket(sap, sk); sock_reset_flag(sk, SOCK_ZAPPED); + llc_sap_put(sap); rc = 0; out: dev_put(dev); diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 000be60d9580..b823720630e7 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -703,7 +703,7 @@ void ieee802154_remove_interfaces(struct ieee802154_local *local) mutex_lock(&local->iflist_mtx); list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) { - list_del(&sdata->list); + list_del_rcu(&sdata->list); unregister_netdevice(sdata->dev); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index dedf59b661dd..8231317b0f1f 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -75,15 +75,17 @@ struct hbucket { struct htable_gc { struct delayed_work dwork; struct ip_set *set; /* Set the gc belongs to */ + spinlock_t lock; /* Lock to exclude gc and resize */ u32 region; /* Last gc run position */ }; /* The hash table: the table size stored here in order to make resizing easy */ struct htable { - atomic_t ref; /* References for resizing */ + bool resizing; /* Mark ongoing resize */ atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ u32 maxelem; /* Maxelem per region */ + struct list_head ad; /* Resize add|del backlist */ struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[]; /* hashtable buckets */ }; @@ -301,11 +303,13 @@ struct htype { u8 netmask; /* netmask value for subnets to store */ union nf_inet_addr bitmask; /* stores bitmask */ #endif - struct list_head ad; /* Resize add|del backlist */ - struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif + /* Because 'next' is IPv4/IPv6 dependent, no elements of this + * structure and referred in create() may come after 'next'. + */ + struct mtype_elem next; /* temporary storage for uadd */ }; /* ADD|DEL entries saved during resize */ @@ -451,13 +455,14 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct htable *t = (__force struct htable *)h->table; struct list_head *l, *lt; - mtype_ahash_destroy(set, (__force struct htable *)h->table, true); - list_for_each_safe(l, lt, &h->ad) { + list_for_each_safe(l, lt, &t->ad) { list_del(l); kfree(l); } + mtype_ahash_destroy(set, t, true); kfree(h); set->data = NULL; @@ -569,9 +574,10 @@ mtype_gc(struct work_struct *work) set = gc->set; h = set->data; - spin_lock_bh(&set->lock); - t = ipset_dereference_set(h->table, set); + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); atomic_inc(&t->uref); + rcu_read_unlock_bh(); numof_locks = ahash_numof_locks(t->htable_bits); r = gc->region++; if (r >= numof_locks) { @@ -580,11 +586,13 @@ mtype_gc(struct work_struct *work) next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; if (next_run < HZ/10) next_run = HZ/10; - spin_unlock_bh(&set->lock); - mtype_gc_do(set, h, t, r); + spin_lock_bh(&gc->lock); + if (!t->resizing) + mtype_gc_do(set, h, t, r); + spin_unlock_bh(&gc->lock); - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize by expire: %p\n", t); mtype_ahash_destroy(set, t, false); } @@ -668,15 +676,18 @@ retry: } t->htable_bits = htable_bits; t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + INIT_LIST_HEAD(&t->ad); for (i = 0; i < ahash_numof_locks(htable_bits); i++) spin_lock_init(&t->hregion[i].lock); /* There can't be another parallel resizing, - * but dumping, gc, kernel side add/del are possible + * but dumping and kernel side add/del are possible */ orig = ipset_dereference_bh_nfnl(h->table); - atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); + spin_lock_bh(&h->gc.lock); + orig->resizing = true; + spin_unlock_bh(&h->gc.lock); pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { @@ -768,7 +779,7 @@ retry: * Kernel-side add cannot trigger a resize and userspace actions * are serialized by the mutex. */ - list_for_each_safe(l, lt, &h->ad) { + list_for_each_safe(l, lt, &orig->ad) { x = list_entry(l, struct mtype_resize_ad, list); if (x->ad == IPSET_ADD) { mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); @@ -792,11 +803,24 @@ out: cleanup: rcu_read_unlock_bh(); - atomic_set(&orig->ref, 0); + spin_lock_bh(&h->gc.lock); + orig->resizing = false; + spin_unlock_bh(&h->gc.lock); + /* Make sure parallel readers see that orig->resizing is false + * before we decrement uref */ + synchronize_rcu(); atomic_dec(&orig->uref); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; + + /* Cleanup the backlog of ADD/DEL elements */ + spin_lock_bh(&set->lock); + list_for_each_safe(l, lt, &orig->ad) { + list_del(l); + kfree(l); + } + spin_unlock_bh(&set->lock); goto out; hbwarn: @@ -860,15 +884,13 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, key = HKEY(value, h->initval, t->htable_bits); r = ahash_region(key); atomic_inc(&t->uref); + rcu_read_unlock_bh(); elements = t->hregion[r].elements; maxelem = t->maxelem; if (elements >= maxelem) { u32 e; - if (SET_WITH_TIMEOUT(set)) { - rcu_read_unlock_bh(); + if (SET_WITH_TIMEOUT(set)) mtype_gc_do(set, h, t, r); - rcu_read_lock_bh(); - } maxelem = h->maxelem; elements = 0; for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) @@ -876,7 +898,6 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } - rcu_read_unlock_bh(); spin_lock_bh(&t->hregion[r].lock); n = rcu_dereference_bh(hbucket(t, key)); @@ -1003,7 +1024,7 @@ overwrite_extensions: ret = 0; resize: spin_unlock_bh(&t->hregion[r].lock); - if (atomic_read(&t->ref) && ext->target) { + if (t->resizing && ext && ext->target) { /* Resize is in process and kernel side add, save values */ struct mtype_resize_ad *x; @@ -1017,7 +1038,7 @@ resize: memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); x->flags = flags; spin_lock_bh(&set->lock); - list_add_tail(&x->list, &h->ad); + list_add_tail(&x->list, &t->ad); spin_unlock_bh(&set->lock); } goto out; @@ -1030,7 +1051,7 @@ set_full: unlock: spin_unlock_bh(&t->hregion[r].lock); out: - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize by add: %p\n", t); mtype_ahash_destroy(set, t, false); } @@ -1093,7 +1114,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, #endif ip_set_ext_destroy(set, data); - if (atomic_read(&t->ref) && ext->target) { + if (t->resizing && ext && ext->target) { /* Resize is in process and kernel side del, * save values */ @@ -1141,10 +1162,10 @@ out: spin_unlock_bh(&t->hregion[r].lock); if (x) { spin_lock_bh(&set->lock); - list_add(&x->list, &h->ad); + list_add(&x->list, &t->ad); spin_unlock_bh(&set->lock); } - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize by del: %p\n", t); mtype_ahash_destroy(set, t, false); } @@ -1353,7 +1374,7 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; - if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + if (atomic_dec_and_test(&t->uref) && t->resizing) { pr_debug("Table destroy after resize " " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); @@ -1566,7 +1587,13 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, if (tb[IPSET_ATTR_MAXELEM]) maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); - hsize = sizeof(*h); +#ifdef IP_SET_PROTO_UNDEF + hsize = sizeof(struct htype); +#else + hsize = set->family == NFPROTO_IPV6 ? + sizeof(struct IPSET_TOKEN(HTYPE, 6)) : + sizeof(struct IPSET_TOKEN(HTYPE, 4)); +#endif h = kzalloc(hsize, GFP_KERNEL); if (!h) return -ENOMEM; @@ -1593,6 +1620,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, return -ENOMEM; } h->gc.set = set; + spin_lock_init(&h->gc.lock); for (i = 0; i < ahash_numof_locks(hbits); i++) spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; @@ -1619,9 +1647,8 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, } t->htable_bits = hbits; t->maxelem = h->maxelem / ahash_numof_locks(hbits); + INIT_LIST_HEAD(&t->ad); RCU_INIT_POINTER(h->table, t); - - INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index cb36641f8d1c..6ed2622363f0 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1420,8 +1420,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, cp->app = NULL; cp->app_data = NULL; /* reset struct ip_vs_seq */ - cp->in_seq.delta = 0; - cp->out_seq.delta = 0; + memset(&cp->in_seq, 0, sizeof(cp->in_seq)); + memset(&cp->out_seq, 0, sizeof(cp->out_seq)); if (unlikely(flags & IP_VS_CONN_F_NO_CPORT)) { int af_id = ip_vs_af_index(cp->af); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index d40b404c1bf6..35cbe821c259 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -398,10 +398,10 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) static inline void ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, unsigned int iph_len) { if (likely(pd->pp->state_transition)) - pd->pp->state_transition(cp, direction, skb, pd); + pd->pp->state_transition(cp, direction, skb, pd, iph_len); } static inline int @@ -803,7 +803,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_in_stats(cp, skb); /* set state */ - ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph->len); /* transmit the first SYN packet */ ret = cp->packet_xmit(skb, cp, pd->pp, iph); @@ -1484,7 +1484,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, after_nat: ip_vs_out_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd, iph->len); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); @@ -1767,6 +1767,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, bool tunnel, new_cp = false; union nf_inet_addr *raddr; char *outer_proto = "IPIP"; + unsigned int hlen_ipip; + int ulen = 0; *related = 1; @@ -1803,9 +1805,10 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Now find the contained IP header */ offset += sizeof(_icmph); cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ raddr = (union nf_inet_addr *)&cih->daddr; + hlen_ipip = cih->ihl * 4; /* Special case for errors for IPIP/UDP/GRE tunnel packets */ tunnel = false; @@ -1821,9 +1824,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Only for known tunnel */ if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) return NF_ACCEPT; - offset += cih->ihl * 4; + offset += hlen_ipip; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); - if (cih == NULL) + if (!(cih && cih->version == 4 && cih->ihl >= 5)) return NF_ACCEPT; /* The packet looks wrong, ignore */ tunnel = true; } else if ((cih->protocol == IPPROTO_UDP || /* Can be UDP encap */ @@ -1831,12 +1834,11 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* Error for our tunnel must arrive at LOCAL_IN */ (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { __u8 iproto; - int ulen; /* Non-first fragment has no UDP/GRE header */ if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; - offset2 = offset + cih->ihl * 4; + offset2 = offset + hlen_ipip; if (cih->protocol == IPPROTO_UDP) { ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, &iproto); @@ -1905,6 +1907,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, } if (tunnel) { + unsigned int hlen_orig = cih->ihl * 4; __be32 info = ic->un.gateway; __u8 type = ic->type; __u8 code = ic->code; @@ -1921,6 +1924,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, goto ignore_tunnel; offset2 -= ihl + sizeof(_icmph); skb_reset_network_header(skb); + /* Ensure the IP header is present in headroom */ + if (!pskb_may_pull(skb, hlen_ipip)) + goto ignore_tunnel; IP_VS_DBG(12, "ICMP for %s %pI4->%pI4: mtu=%u\n", outer_proto, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); @@ -1936,8 +1942,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (dest_dst) mtu = dst_mtu(dest_dst->dst_cache); } - if (mtu > 68 + sizeof(struct iphdr)) - mtu -= sizeof(struct iphdr); + if (mtu > 68 + hlen_ipip + ulen) + mtu -= hlen_ipip + ulen; info = htonl(mtu); } /* Strip outer IP, ICMP and IPIP/UDP/GRE, go to IP header of @@ -1946,6 +1952,9 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, if (pskb_pull(skb, offset2) == NULL) goto ignore_tunnel; skb_reset_network_header(skb); + /* Ensure the IP header is present in headroom */ + if (!pskb_may_pull(skb, hlen_orig)) + goto ignore_tunnel; IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, type, code, ntohl(info)); @@ -2233,7 +2242,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); ip_vs_in_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); + ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd, iph.len); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp, &iph); /* do not touch skb anymore */ diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 63c78a1f3918..c67317be17df 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -372,20 +372,15 @@ static const char *sctp_state_name(int state) static inline void set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, - int direction, const struct sk_buff *skb) + int direction, const struct sk_buff *skb, + unsigned int iph_len) { struct sctp_chunkhdr _sctpch, *sch; unsigned char chunk_type; int event, next_state; - int ihl, cofs; + int cofs; -#ifdef CONFIG_IP_VS_IPV6 - ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); -#else - ihl = ip_hdrlen(skb); -#endif - - cofs = ihl + sizeof(struct sctphdr); + cofs = iph_len + sizeof(struct sctphdr); sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch); if (sch == NULL) return; @@ -468,10 +463,11 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, static void sctp_state_transition(struct ip_vs_conn *cp, int direction, - const struct sk_buff *skb, struct ip_vs_proto_data *pd) + const struct sk_buff *skb, struct ip_vs_proto_data *pd, + unsigned int iph_len) { spin_lock_bh(&cp->lock); - set_sctp_state(pd, cp, direction, skb); + set_sctp_state(pd, cp, direction, skb, iph_len); spin_unlock_bh(&cp->lock); } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 8cc0a8ce6241..f86b763efcc4 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -579,17 +579,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, static void tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, + unsigned int iph_len) { struct tcphdr _tcph, *th; -#ifdef CONFIG_IP_VS_IPV6 - int ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr); -#else - int ihl = ip_hdrlen(skb); -#endif - - th = skb_header_pointer(skb, ihl, sizeof(_tcph), &_tcph); + th = skb_header_pointer(skb, iph_len, sizeof(_tcph), &_tcph); if (th == NULL) return; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index f9de632e38cd..58f9e255927e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -444,7 +444,8 @@ static const char * udp_state_name(int state) static void udp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_proto_data *pd) + struct ip_vs_proto_data *pd, + unsigned int iph_len) { if (unlikely(!pd)) { pr_err("UDP no ns data\n"); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 99c5b9d671a0..2a829b5e8240 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -127,12 +127,18 @@ static int flow_offload_fill_route(struct flow_offload *flow, switch (route->tuple[dir].xmit_type) { case FLOW_OFFLOAD_XMIT_DIRECT: + if (flow_tuple->tun_num) { + flow_tuple->dst_cache = dst; + flow_tuple->dst_cookie = + flow_offload_dst_cookie(flow_tuple); + } memcpy(flow_tuple->out.h_dest, route->tuple[dir].out.h_dest, ETH_ALEN); memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; - dst_release(dst); + if (!flow_tuple->tun_num) + dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: @@ -152,9 +158,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, static void nft_flow_dst_release(struct flow_offload *flow, enum flow_offload_tuple_dir dir) { - if (flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_NEIGH || - flow->tuplehash[dir].tuple.xmit_type == FLOW_OFFLOAD_XMIT_XFRM) - dst_release(flow->tuplehash[dir].tuple.dst_cache); + dst_release(flow->tuplehash[dir].tuple.dst_cache); } void flow_offload_route_init(struct flow_offload *flow, @@ -345,10 +349,8 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) nf_ct_refresh(flow->ct, NF_CT_DAY); - if (nf_flowtable_hw_offload(flow_table)) { - __set_bit(NF_FLOW_HW, &flow->flags); + if (nf_flowtable_hw_offload(flow_table)) nf_flow_offload_add(flow_table, flow); - } return 0; } @@ -369,7 +371,8 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, test_bit(NF_FLOW_CLOSING, &flow->flags)) return; - nf_flow_offload_add(flow_table, flow); + if (test_bit(NF_FLOW_HW, &flow->flags)) + nf_flow_offload_refresh(flow_table, flow); } EXPORT_SYMBOL_GPL(flow_offload_refresh); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 29e93ac1e2e4..0b78decce8a9 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -299,8 +299,7 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) static inline bool nf_flow_dst_check(struct flow_offload_tuple *tuple) { - if (tuple->xmit_type != FLOW_OFFLOAD_XMIT_NEIGH && - tuple->xmit_type != FLOW_OFFLOAD_XMIT_XFRM) + if (!tuple->dst_cache) return true; return dst_check(tuple->dst_cache, tuple->dst_cookie); @@ -590,10 +589,10 @@ static int nf_flow_pppoe_push(struct sk_buff *skb, u16 id, static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, - __be32 *ip_daddr) + struct dst_entry *dst, __be32 *ip_daddr) { struct iphdr *iph = (struct iphdr *)skb_network_header(skb); - struct rtable *rt = dst_rtable(tuple->dst_cache); + struct rtable *rt = dst_rtable(dst); u8 tos = iph->tos, ttl = iph->ttl; __be16 frag_off = iph->frag_off; u32 headroom = sizeof(*iph); @@ -636,21 +635,22 @@ static int nf_flow_tunnel_ipip_push(struct net *net, struct sk_buff *skb, static int nf_flow_tunnel_v4_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, - __be32 *ip_daddr) + struct dst_entry *dst, __be32 *ip_daddr) { if (tuple->tun_num) - return nf_flow_tunnel_ipip_push(net, skb, tuple, ip_daddr); + return nf_flow_tunnel_ipip_push(net, skb, tuple, dst, ip_daddr); return 0; } static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, + struct dst_entry *dst, struct in6_addr **ip6_daddr) { struct ipv6hdr *ip6h = (struct ipv6hdr *)skb_network_header(skb); - struct rtable *rt = dst_rtable(tuple->dst_cache); __u8 dsfield = ipv6_get_dsfield(ip6h); + struct rtable *rt = dst_rtable(dst); struct flowi6 fl6 = { .daddr = tuple->tun.src_v6, .saddr = tuple->tun.dst_v6, @@ -696,10 +696,11 @@ static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb, static int nf_flow_tunnel_v6_push(struct net *net, struct sk_buff *skb, struct flow_offload_tuple *tuple, + struct dst_entry *dst, struct in6_addr **ip6_daddr) { if (tuple->tun_num) - return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, ip6_daddr); + return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, dst, ip6_daddr); return 0; } @@ -842,7 +843,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, other_tuple = &flow->tuplehash[!dir].tuple; ip_daddr = other_tuple->src_v4.s_addr; - if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple, &ip_daddr) < 0) + if (nf_flow_tunnel_v4_push(state->net, skb, other_tuple, + tuplehash->tuple.dst_cache, &ip_daddr) < 0) return NF_DROP; switch (tuplehash->tuple.xmit_type) { @@ -1158,6 +1160,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, ip6_daddr = &other_tuple->src_v6; if (nf_flow_tunnel_v6_push(state->net, skb, other_tuple, + tuplehash->tuple.dst_cache, &ip6_daddr) < 0) return NF_DROP; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 002ec15d988b..801a3dd9ceea 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -1101,9 +1101,17 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable, return offload; } +static bool nf_flow_offload_unsupported(struct flow_offload *flow) +{ + if (flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.tun_num || + flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.tun_num) + return true; -void nf_flow_offload_add(struct nf_flowtable *flowtable, - struct flow_offload *flow) + return false; +} + +void nf_flow_offload_refresh(struct nf_flowtable *flowtable, + struct flow_offload *flow) { struct flow_offload_work *offload; @@ -1114,6 +1122,16 @@ void nf_flow_offload_add(struct nf_flowtable *flowtable, flow_offload_queue_work(offload); } +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + if (nf_flow_offload_unsupported(flow)) + return; + + set_bit(NF_FLOW_HW, &flow->flags); + nf_flow_offload_refresh(flowtable, flow); +} + void nf_flow_offload_del(struct nf_flowtable *flowtable, struct flow_offload *flow) { diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 67c04d8143ab..aea02f6aff09 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -289,13 +289,24 @@ next: /* Mangle destination port for Cisco phones, then fix up checksums */ if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) { + int doff = *dptr - (const char *)skb->data; struct udphdr *uh; + if (doff <= 0) { + DEBUG_NET_WARN_ON_ONCE(1); + return NF_DROP; + } + + /* ct_sip_info->forced_dport only expected with UDP */ + if (nf_ct_protonum(ct) != IPPROTO_UDP) + return NF_DROP; + if (skb_ensure_writable(skb, skb->len)) { nf_ct_helper_log(skb, ct, "cannot mangle packet"); return NF_DROP; } + *dptr = skb->data + doff; uh = (void *)skb->data + protoff; uh->dest = ct_sip_info->forced_dport; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4884f7f7aaee..a9eaf9455c77 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -6563,6 +6563,9 @@ static int nft_get_set_elem(struct nft_ctx *ctx, const struct nft_set *set, if (err < 0) return err; + if (!elem.priv) + return 0; + err = -ENOMEM; skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (skb == NULL) diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 2cbcca9110db..f062ac210343 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -316,6 +316,8 @@ nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy, new_policy->max_expected = ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX])); + if (!new_policy->max_expected) + new_policy->max_expected = NF_CT_EXPECT_MAX_CNT; if (new_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index fa3657599861..5fee61b3813c 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -676,7 +676,7 @@ __build_packet_message(struct nfnl_log_net *log, goto nla_put_failure; if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) - BUG(); + goto nla_put_failure; } nlh->nlmsg_len = inst->skb->tail - old_tail; @@ -698,6 +698,21 @@ static const struct nf_loginfo default_loginfo = { }, }; +static unsigned int nfulnl_get_copy_len(const struct nf_loginfo *li, + const struct sk_buff *skb, + unsigned int copy_len) +{ + unsigned int len = skb->len; + + if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && + li->u.ulog.copy_len < copy_len) + copy_len = li->u.ulog.copy_len; + if (!skb_frags_readable(skb)) + len = skb_headlen(skb); + + return min(len, copy_len); +} + /* log handler for internal netfilter logging api */ static void nfulnl_log_packet(struct net *net, @@ -790,14 +805,7 @@ nfulnl_log_packet(struct net *net, break; case NFULNL_COPY_PACKET: - data_len = inst->copy_range; - if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && - (li->u.ulog.copy_len < data_len)) - data_len = li->u.ulog.copy_len; - - if (data_len > skb->len) - data_len = skb->len; - + data_len = nfulnl_get_copy_len(li, skb, inst->copy_range); size += nla_total_size(data_len); break; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 35d4c6c628ff..b8aaf39cb4d8 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -690,6 +690,17 @@ static int nfqnl_put_master_ifindex(struct sk_buff *nlskb, int attr, } #endif +static unsigned int nfqnl_get_data_len(const struct sk_buff *entskb, + unsigned int copy_range) +{ + unsigned int data_len = entskb->len; + + if (!skb_frags_readable(entskb)) + data_len = skb_headlen(entskb); + + return min(data_len, copy_range); +} + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -755,10 +766,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, nf_queue_checksum_help(entskb)) return NULL; - data_len = READ_ONCE(queue->copy_range); - if (data_len > entskb->len) - data_len = entskb->len; - + data_len = nfqnl_get_data_len(entskb, READ_ONCE(queue->copy_range)); hlen = skb_zerocopy_headlen(entskb); hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index ba512e94b402..19887439847d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -103,13 +103,13 @@ void nft_lookup_eval(const struct nft_expr *expr, bool found; ext = nft_set_do_lookup(net, set, ®s->data[priv->sreg]); + if (!ext) + ext = nft_set_catchall_lookup(net, set); + found = !!ext ^ priv->invert; if (!found) { - ext = nft_set_catchall_lookup(net, set); - if (!ext) { - regs->verdict.code = NFT_BREAK; - return; - } + regs->verdict.code = NFT_BREAK; + return; } if (ext) { diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 018bbb6df4ce..6222e9bb57bc 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -184,10 +184,14 @@ nft_rbtree_get(const struct net *net, const struct nft_set *set, if (!interval || nft_set_elem_expired(interval->from)) return ERR_PTR(-ENOENT); - if (flags & NFT_SET_ELEM_INTERVAL_END) + if (flags & NFT_SET_ELEM_INTERVAL_END) { + if (!interval->to) + return NULL; + rbe = container_of(interval->to, struct nft_rbtree_elem, ext); - else + } else { rbe = container_of(interval->from, struct nft_rbtree_elem, ext); + } return &rbe->priv; } diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 4277084de2e7..2cf27f7d59b9 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -112,6 +112,16 @@ static int connmark_tg_check(const struct xt_tgchk_param *par) return ret; } +static int connmark_tg_check_v2(const struct xt_tgchk_param *par) +{ + const struct xt_connmark_tginfo2 *info = par->targinfo; + + if (info->shift_dir > D_SHIFT_RIGHT || info->shift_bits >= 32) + return -EINVAL; + + return connmark_tg_check(par); +} + static void connmark_tg_destroy(const struct xt_tgdtor_param *par) { nf_ct_netns_put(par->net, par->family); @@ -162,7 +172,7 @@ static struct xt_target connmark_tg_reg[] __read_mostly = { .name = "CONNMARK", .revision = 2, .family = NFPROTO_IPV4, - .checkentry = connmark_tg_check, + .checkentry = connmark_tg_check_v2, .target = connmark_tg_v2, .targetsize = sizeof(struct xt_connmark_tginfo2), .destroy = connmark_tg_destroy, @@ -183,7 +193,7 @@ static struct xt_target connmark_tg_reg[] __read_mostly = { .name = "CONNMARK", .revision = 2, .family = NFPROTO_IPV6, - .checkentry = connmark_tg_check, + .checkentry = connmark_tg_check_v2, .target = connmark_tg_v2, .targetsize = sizeof(struct xt_connmark_tginfo2), .destroy = connmark_tg_destroy, diff --git a/net/netfilter/xt_rateest.c b/net/netfilter/xt_rateest.c index b1d736c15fcb..7c05b6342578 100644 --- a/net/netfilter/xt_rateest.c +++ b/net/netfilter/xt_rateest.c @@ -16,7 +16,7 @@ xt_rateest_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rateest_match_info *info = par->matchinfo; struct gnet_stats_rate_est64 sample = {0}; - u_int32_t bps1, bps2, pps1, pps2; + u64 bps1, bps2, pps1, pps2; bool ret = true; gen_estimator_read(&info->est1->rate_est, &sample); diff --git a/net/netfilter/xt_u32.c b/net/netfilter/xt_u32.c index 117d4615d668..dabbaa742874 100644 --- a/net/netfilter/xt_u32.c +++ b/net/netfilter/xt_u32.c @@ -14,8 +14,8 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_u32.h> -static bool u32_match_it(const struct xt_u32 *data, - const struct sk_buff *skb) +static int u32_match_it(const struct xt_u32 *data, + const struct sk_buff *skb) { const struct xt_u32_test *ct; unsigned int testind; @@ -40,7 +40,8 @@ static bool u32_match_it(const struct xt_u32 *data, return false; if (skb_copy_bits(skb, pos, &n, sizeof(n)) < 0) - BUG(); + return -1; + val = ntohl(n); nnums = ct->nnums; @@ -68,7 +69,7 @@ static bool u32_match_it(const struct xt_u32 *data, if (skb_copy_bits(skb, at + pos, &n, sizeof(n)) < 0) - BUG(); + return -1; val = ntohl(n); break; } @@ -90,9 +91,14 @@ static bool u32_match_it(const struct xt_u32 *data, static bool u32_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_u32 *data = par->matchinfo; - bool ret; + int ret; ret = u32_match_it(data, skb); + if (ret < 0) { + par->hotdrop = true; + return false; + } + return ret ^ data->invert; } @@ -100,7 +106,7 @@ 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; + unsigned int i, j; if (data->ntests > ARRAY_SIZE(data->tests)) return -EINVAL; @@ -111,6 +117,16 @@ static int u32_mt_checkentry(const struct xt_mtchk_param *par) if (ct->nnums > ARRAY_SIZE(ct->location) || ct->nvalues > ARRAY_SIZE(ct->value)) return -EINVAL; + + for (j = 1; j < ct->nnums; ++j) { + switch (ct->location[j].nextop) { + case XT_U32_LEFTSH: + case XT_U32_RIGHTSH: + if (ct->location[j].number >= 32) + return -EINVAL; + break; + } + } } return 0; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b68be143a067..f141634df214 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -148,10 +148,15 @@ static void offload_action_hw_count_dec(struct tc_action *act, static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act) { - if (is_tcf_pedit(act)) - return tcf_pedit_nkeys(act); - else - return 1; + unsigned int count; + + if (is_tcf_pedit(act)) { + spin_lock_bh(&act->tcfa_lock); + count = tcf_pedit_nkeys_locked(act); + spin_unlock_bh(&act->tcfa_lock); + return count; + } + return 1; } static bool tc_act_skip_hw(u32 flags) diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 0d652dea4a69..d4d47a9921f4 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -567,9 +567,18 @@ static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data, { if (bind) { struct flow_action_entry *entry = entry_data; + int nkeys = tcf_pedit_nkeys_locked(act); int k; - for (k = 0; k < tcf_pedit_nkeys(act); k++) { + /* If the required keys exceed the remaining capacity return + * -ENOSPC to abort the offload and fallback to software. + */ + if (nkeys > *index_inc) { + NL_SET_ERR_MSG_MOD(extack, "Not enough space to offload all pedit keys"); + return -ENOSPC; + } + + for (k = 0; k < nkeys; k++) { switch (tcf_pedit_cmd(act, k)) { case TCA_PEDIT_KEY_EX_CMD_SET: entry->id = FLOW_ACTION_MANGLE; @@ -606,7 +615,7 @@ static int tcf_pedit_offload_act_setup(struct tc_action *act, void *entry_data, return -EOPNOTSUPP; } - for (k = 1; k < tcf_pedit_nkeys(act); k++) { + for (k = 1; k < tcf_pedit_nkeys_locked(act); k++) { if (cmd != tcf_pedit_cmd(act, k)) { NL_SET_ERR_MSG_MOD(extack, "Unsupported pedit command offload"); return -EOPNOTSUPP; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 3e67600a4a1a..ffeea6db8337 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3886,12 +3886,21 @@ int tc_setup_action(struct flow_action *flow_action, entry = &flow_action->entries[j]; spin_lock_bh(&act->tcfa_lock); + + /* Abort the offload if we have exhausted the allocated capacity */ + if (j >= flow_action->num_entries) { + NL_SET_ERR_MSG_MOD(extack, "Flow action buffer overflow"); + err = -ENOSPC; + goto err_out_locked; + } + err = tcf_act_get_user_cookie(entry, act); if (err) goto err_out_locked; - index = 0; - err = tc_setup_offload_act(act, entry, &index, extack); + index = flow_action->num_entries - j; + err = tc_setup_offload_act(act, entry, &index, + extack); if (err) goto err_out_locked; @@ -3945,10 +3954,13 @@ unsigned int tcf_exts_num_actions(struct tcf_exts *exts) int i; tcf_exts_for_each_action(i, act, exts) { - if (is_tcf_pedit(act)) - num_acts += tcf_pedit_nkeys(act); - else + if (is_tcf_pedit(act)) { + spin_lock_bh(&act->tcfa_lock); + num_acts += tcf_pedit_nkeys_locked(act); + spin_unlock_bh(&act->tcfa_lock); + } else { num_acts++; + } } return num_acts; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index a3c185505afc..f78f8e950776 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1389,10 +1389,7 @@ static u32 cake_calc_overhead(struct cake_sched_data *qd, u32 len, u32 off) if (qd->min_netlen > len) WRITE_ONCE(qd->min_netlen, len); - len += q->rate_overhead; - - if (len < q->rate_mpu) - len = q->rate_mpu; + len = max((s32)len + q->rate_overhead, (s32)q->rate_mpu); if (q->atm_mode == CAKE_ATM_ATM) { len += 47; diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 24ba31f8c828..5c42a29a981c 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -311,14 +311,14 @@ static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev) int subq = skb_get_queue_mapping(skb); struct sk_buff *skb_res = NULL; - rcu_read_lock_bh(); - - start = rcu_dereference_bh(master->slaves); - restart: nores = 0; busy = 0; + rcu_read_lock(); + + start = rcu_dereference(master->slaves); + q = start; if (!q) goto drop; @@ -345,17 +345,17 @@ restart: netdev_start_xmit(skb, slave, slave_txq, false) == NETDEV_TX_OK) { __netif_tx_unlock(slave_txq); - spin_lock_bh(&master->slaves_lock); + spin_lock(&master->slaves_lock); if (rcu_dereference_protected(master->slaves, lockdep_is_held(&master->slaves_lock)) == q) rcu_assign_pointer(master->slaves, rcu_dereference_protected(NEXT_SLAVE(q), lockdep_is_held(&master->slaves_lock))); - spin_unlock_bh(&master->slaves_lock); + spin_unlock(&master->slaves_lock); netif_wake_queue(dev); master->tx_packets++; master->tx_bytes += length; - rcu_read_unlock_bh(); + rcu_read_unlock(); return NETDEV_TX_OK; } __netif_tx_unlock(slave_txq); @@ -364,37 +364,38 @@ restart: busy = 1; break; case 1: - spin_lock_bh(&master->slaves_lock); + spin_lock(&master->slaves_lock); if (rcu_dereference_protected(master->slaves, lockdep_is_held(&master->slaves_lock)) == q) rcu_assign_pointer(master->slaves, rcu_dereference_protected(NEXT_SLAVE(q), lockdep_is_held(&master->slaves_lock))); - spin_unlock_bh(&master->slaves_lock); - rcu_read_unlock_bh(); + spin_unlock(&master->slaves_lock); + rcu_read_unlock(); return NETDEV_TX_OK; default: nores = 1; break; } __skb_pull(skb, skb_network_offset(skb)); - } while ((q = rcu_dereference_bh(NEXT_SLAVE(q))) != start); + } while ((q = rcu_dereference(NEXT_SLAVE(q))) != start); if (nores && skb_res == NULL) { skb_res = skb; + rcu_read_unlock(); goto restart; } if (busy) { netif_stop_queue(dev); - rcu_read_unlock_bh(); + rcu_read_unlock(); return NETDEV_TX_BUSY; } master->tx_errors++; drop: master->tx_dropped++; - rcu_read_unlock_bh(); + rcu_read_unlock(); dev_kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index 619b3bab3824..32d6d03df321 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -470,9 +470,9 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) { struct smc_link *link = (struct smc_link *)wc->qp->qp_context; struct smc_cdc_msg *cdc = buf; + struct smc_sock *smc = NULL; struct smc_connection *conn; struct smc_link_group *lgr; - struct smc_sock *smc; if (wc->byte_len < offsetof(struct smc_cdc_msg, reserved)) return; /* short message */ @@ -483,21 +483,26 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf) lgr = smc_get_lgr(link); read_lock_bh(&lgr->conns_lock); conn = smc_lgr_find_conn(ntohl(cdc->token), lgr); - read_unlock_bh(&lgr->conns_lock); - if (!conn || conn->out_of_sync) + if (!conn || conn->out_of_sync) { + read_unlock_bh(&lgr->conns_lock); return; + } smc = container_of(conn, struct smc_sock, conn); + sock_hold(&smc->sk); + read_unlock_bh(&lgr->conns_lock); if (cdc->prod_flags.failover_validation) { smc_cdc_msg_validate(smc, cdc, link); - return; + goto out; } if (smc_cdc_before(ntohs(cdc->seqno), conn->local_rx_ctrl.seqno)) /* received seqno is old */ - return; + goto out; smc_cdc_msg_recv(smc, cdc); +out: + sock_put(&smc->sk); } static struct smc_wr_rx_handler smc_cdc_rx_handlers[] = { diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9324e4ed20a3..d4afc90fd796 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2115,6 +2115,17 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc, goto read_sock_requeue; } + /* An empty data record (legal in TLS 1.3) gives a zero + * read_actor return, indistinguishable from the consumer + * stalling; the used <= 0 path would requeue it at the + * head of rx_list and block all later records. Consume it + * here instead. + */ + if (rxm->full_len == 0) { + consume_skb(skb); + continue; + } + used = read_actor(desc, skb, rxm->offset, rxm->full_len); if (used <= 0) { if (!copied) diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index b3827b43782b..d46d2cec89e4 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -70,12 +70,33 @@ ksft_exit_status_merge() $ksft_xfail $ksft_pass $ksft_skip $ksft_fail } +timestamp_ms() +{ + local now + local seconds + local nanoseconds + + now=$(date -u +%s:%N) || return + seconds=${now%:*} + nanoseconds=${now#*:} + + if [[ $nanoseconds =~ ^[0-9]+$ ]]; then + nanoseconds=${nanoseconds:0:9} + else + nanoseconds=0 + fi + + echo $((seconds * 1000 + 10#$nanoseconds / 1000000)) +} + loopy_wait() { local sleep_cmd=$1; shift local timeout_ms=$1; shift + local start_time + local current_time - local start_time="$(date -u +%s%3N)" + start_time=$(timestamp_ms) || return while true do local out @@ -84,7 +105,7 @@ loopy_wait() return 0 fi - local current_time="$(date -u +%s%3N)" + current_time=$(timestamp_ms) || return if ((current_time - start_time > timeout_ms)); then echo -n "$out" return 1 diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4fcce5150850..2544ae35d07a 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -313,6 +313,8 @@ end: tcp_info_get_rcv_mss(fd)); } error: + if (ctx) + EVP_MD_CTX_free(ctx); munmap(buffer, buffer_sz); close(fd); if (zflg) @@ -606,6 +608,8 @@ int main(int argc, char *argv[]) EVP_DigestFinal_ex(ctx, digest, &digest_len); send(fd, digest, (size_t)SHA256_DIGEST_LENGTH, 0); } + if (ctx) + EVP_MD_CTX_free(ctx); close(fd); munmap(buffer, buffer_sz); return 0; |