summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2021-06-07 22:01:52 +0200
committerDavid S. Miller <davem@davemloft.net>2021-06-07 22:01:52 +0200
commit126285651b7f95282a0afe3a1b0221419b31d989 (patch)
treee5d547255814a5ed55b6b74be3155464598b39f2
parentsch_htb: fix doc warning in htb_lookup_leaf() (diff)
parentcxgb4: avoid link re-train during TC-MQPRIO configuration (diff)
downloadlinux-126285651b7f95282a0afe3a1b0221419b31d989.tar.xz
linux-126285651b7f95282a0afe3a1b0221419b31d989.zip
Merge ra.kernel.org:/pub/scm/linux/kernel/git/netdev/net
Bug fixes overlapping feature additions and refactoring, mostly. Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--MAINTAINERS10
-rw-r--r--drivers/bluetooth/btusb.c23
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4.h2
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c4
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c14
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c9
-rw-r--r--drivers/net/ethernet/chelsio/cxgb4/sge.c6
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_txrx.c7
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_xsk.c8
-rw-r--r--drivers/net/ethernet/intel/ice/ice.h8
-rw-r--r--drivers/net/ethernet/intel/ice/ice_ethtool.c51
-rw-r--r--drivers/net/ethernet/intel/ice/ice_hw_autogen.h1
-rw-r--r--drivers/net/ethernet/intel/ice/ice_lib.c12
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx.c17
-rw-r--r--drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c19
-rw-r--r--drivers/net/ethernet/intel/ice/ice_xsk.c11
-rw-r--r--drivers/net/ethernet/intel/igb/igb.h2
-rw-r--r--drivers/net/ethernet/intel/igb/igb_main.c55
-rw-r--r--drivers/net/ethernet/intel/igb/igb_ptp.c23
-rw-r--r--drivers/net/ethernet/intel/igc/igc_main.c12
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_main.c16
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c14
-rw-r--r--drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c12
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_main.c77
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c9
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c3
-rw-r--r--drivers/net/ethernet/myricom/myri10ge/myri10ge.c1
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c5
-rw-r--r--drivers/net/ieee802154/mrf24j40.c4
-rw-r--r--drivers/net/virtio_net.c3
-rw-r--r--drivers/net/wireguard/Makefile3
-rw-r--r--drivers/net/wireguard/allowedips.c189
-rw-r--r--drivers/net/wireguard/allowedips.h14
-rw-r--r--drivers/net/wireguard/main.c17
-rw-r--r--drivers/net/wireguard/peer.c27
-rw-r--r--drivers/net/wireguard/peer.h3
-rw-r--r--drivers/net/wireguard/selftest/allowedips.c165
-rw-r--r--drivers/net/wireguard/socket.c2
-rw-r--r--drivers/net/wireless/mediatek/mt76/mac80211.c26
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7615/init.c1
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7615/mac.c5
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c19
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c3
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c4
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt76x0/pci.c81
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7921/init.c4
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7921/mac.c5
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7921/main.c3
-rw-r--r--drivers/net/wireless/mediatek/mt76/mt7921/mcu.c17
-rw-r--r--include/linux/avf/virtchnl.h1
-rw-r--r--include/linux/mlx5/mlx5_ifc.h2
-rw-r--r--include/net/caif/caif_dev.h2
-rw-r--r--include/net/caif/cfcnfg.h2
-rw-r--r--include/net/caif/cfserl.h1
-rw-r--r--include/net/netfilter/nf_tables.h6
-rw-r--r--include/net/tls.h10
-rw-r--r--include/uapi/linux/virtio_ids.h2
-rw-r--r--kernel/bpf/helpers.c7
-rw-r--r--kernel/trace/bpf_trace.c32
-rw-r--r--net/bluetooth/hci_core.c7
-rw-r--r--net/bluetooth/hci_sock.c4
-rw-r--r--net/caif/caif_dev.c13
-rw-r--r--net/caif/caif_usb.c14
-rw-r--r--net/caif/cfcnfg.c16
-rw-r--r--net/caif/cfserl.c5
-rw-r--r--net/compat.c2
-rw-r--r--net/core/devlink.c8
-rw-r--r--net/core/fib_rules.c2
-rw-r--r--net/core/rtnetlink.c4
-rw-r--r--net/core/sock.c16
-rw-r--r--net/dsa/tag_8021q.c2
-rw-r--r--net/ieee802154/nl-mac.c10
-rw-r--r--net/ieee802154/nl-phy.c4
-rw-r--r--net/ieee802154/nl802154.c9
-rw-r--r--net/ipv4/ipconfig.c13
-rw-r--r--net/ipv6/route.c8
-rw-r--r--net/ipv6/sit.c3
-rw-r--r--net/kcm/kcmsock.c5
-rw-r--r--net/mptcp/protocol.c16
-rw-r--r--net/mptcp/subflow.c79
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c2
-rw-r--r--net/netfilter/nf_conntrack_proto.c2
-rw-r--r--net/netfilter/nf_tables_api.c84
-rw-r--r--net/netfilter/nfnetlink_cthelper.c8
-rw-r--r--net/netfilter/nft_ct.c2
-rw-r--r--net/nfc/llcp_sock.c2
-rw-r--r--net/sched/act_ct.c10
-rw-r--r--net/sched/sch_htb.c8
-rw-r--r--net/tls/tls_device.c60
-rw-r--r--net/tls/tls_device_fallback.c7
-rw-r--r--net/tls/tls_main.c1
-rw-r--r--net/x25/af_x25.c2
-rw-r--r--scripts/Makefile.modfinal2
-rwxr-xr-xscripts/link-vmlinux.sh2
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_connect.sh13
-rwxr-xr-xtools/testing/selftests/wireguard/netns.sh1
-rw-r--r--tools/testing/selftests/wireguard/qemu/kernel.config1
102 files changed, 994 insertions, 560 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index d8e882229a48..85a87a93e194 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12910,7 +12910,7 @@ F: net/ipv4/nexthop.c
NFC SUBSYSTEM
M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
-L: linux-nfc@lists.01.org (moderated for non-subscribers)
+L: linux-nfc@lists.01.org (subscribers-only)
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/nfc/
@@ -12923,7 +12923,7 @@ F: net/nfc/
NFC VIRTUAL NCI DEVICE DRIVER
M: Bongsu Jeon <bongsu.jeon@samsung.com>
L: netdev@vger.kernel.org
-L: linux-nfc@lists.01.org (moderated for non-subscribers)
+L: linux-nfc@lists.01.org (subscribers-only)
S: Supported
F: drivers/nfc/virtual_ncidev.c
F: tools/testing/selftests/nci/
@@ -13229,7 +13229,7 @@ F: sound/soc/codecs/tfa9879*
NXP-NCI NFC DRIVER
R: Charles Gorand <charles.gorand@effinnov.com>
-L: linux-nfc@lists.01.org (moderated for non-subscribers)
+L: linux-nfc@lists.01.org (subscribers-only)
S: Supported
F: drivers/nfc/nxp-nci
@@ -16156,7 +16156,7 @@ F: include/media/drv-intf/s3c_camif.h
SAMSUNG S3FWRN5 NFC DRIVER
M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
M: Krzysztof Opasiak <k.opasiak@samsung.com>
-L: linux-nfc@lists.01.org (moderated for non-subscribers)
+L: linux-nfc@lists.01.org (subscribers-only)
S: Maintained
F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml
F: drivers/nfc/s3fwrn5
@@ -18347,7 +18347,7 @@ F: sound/soc/codecs/tas571x*
TI TRF7970A NFC DRIVER
M: Mark Greer <mgreer@animalcreek.com>
L: linux-wireless@vger.kernel.org
-L: linux-nfc@lists.01.org (moderated for non-subscribers)
+L: linux-nfc@lists.01.org (subscribers-only)
S: Supported
F: Documentation/devicetree/bindings/net/nfc/trf7970a.txt
F: drivers/nfc/trf7970a.c
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 5d603ef39bad..b88c63fbf7fb 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2527,10 +2527,17 @@ static int btusb_intel_download_firmware_newgen(struct hci_dev *hdev,
}
btusb_setup_intel_newgen_get_fw_name(ver, fwname, sizeof(fwname), "sfi");
- err = request_firmware(&fw, fwname, &hdev->dev);
+ err = firmware_request_nowarn(&fw, fwname, &hdev->dev);
if (err < 0) {
+ if (!test_bit(BTUSB_BOOTLOADER, &data->flags)) {
+ /* Firmware has already been loaded */
+ set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
+ return 0;
+ }
+
bt_dev_err(hdev, "Failed to load Intel firmware file %s (%d)",
fwname, err);
+
return err;
}
@@ -2680,12 +2687,24 @@ download:
err = btusb_setup_intel_new_get_fw_name(ver, params, fwname,
sizeof(fwname), "sfi");
if (err < 0) {
+ if (!test_bit(BTUSB_BOOTLOADER, &data->flags)) {
+ /* Firmware has already been loaded */
+ set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
+ return 0;
+ }
+
bt_dev_err(hdev, "Unsupported Intel firmware naming");
return -EINVAL;
}
- err = request_firmware(&fw, fwname, &hdev->dev);
+ err = firmware_request_nowarn(&fw, fwname, &hdev->dev);
if (err < 0) {
+ if (!test_bit(BTUSB_BOOTLOADER, &data->flags)) {
+ /* Firmware has already been loaded */
+ set_bit(BTUSB_FIRMWARE_LOADED, &data->flags);
+ return 0;
+ }
+
bt_dev_err(hdev, "Failed to load Intel firmware file %s (%d)",
fwname, err);
return err;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 314f8d806723..9058f09f921e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -2177,8 +2177,6 @@ int cxgb4_update_mac_filt(struct port_info *pi, unsigned int viid,
bool persistent, u8 *smt_idx);
int cxgb4_get_msix_idx_from_bmap(struct adapter *adap);
void cxgb4_free_msix_idx_in_bmap(struct adapter *adap, u32 msix_idx);
-int cxgb_open(struct net_device *dev);
-int cxgb_close(struct net_device *dev);
void cxgb4_enable_rx(struct adapter *adap, struct sge_rspq *q);
void cxgb4_quiesce_rx(struct sge_rspq *q);
int cxgb4_port_mirror_alloc(struct net_device *dev);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index b730aa1cb141..6479ceedc352 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2834,7 +2834,7 @@ static void cxgb_down(struct adapter *adapter)
/*
* net_device operations
*/
-int cxgb_open(struct net_device *dev)
+static int cxgb_open(struct net_device *dev)
{
struct port_info *pi = netdev_priv(dev);
struct adapter *adapter = pi->adapter;
@@ -2882,7 +2882,7 @@ out_unlock:
return err;
}
-int cxgb_close(struct net_device *dev)
+static int cxgb_close(struct net_device *dev)
{
struct port_info *pi = netdev_priv(dev);
struct adapter *adapter = pi->adapter;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 1b88bd1c2dbe..dd9be229819a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -997,20 +997,16 @@ int cxgb4_tc_flower_destroy(struct net_device *dev,
if (!ch_flower)
return -ENOENT;
+ rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
+ adap->flower_ht_params);
+
ret = cxgb4_flow_rule_destroy(dev, ch_flower->fs.tc_prio,
&ch_flower->fs, ch_flower->filter_id);
if (ret)
- goto err;
+ netdev_err(dev, "Flow rule destroy failed for tid: %u, ret: %d",
+ ch_flower->filter_id, ret);
- ret = rhashtable_remove_fast(&adap->flower_tbl, &ch_flower->node,
- adap->flower_ht_params);
- if (ret) {
- netdev_err(dev, "Flow remove from rhashtable failed");
- goto err;
- }
kfree_rcu(ch_flower, rcu);
-
-err:
return ret;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
index 6c259de96f96..338b04f339b3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c
@@ -589,7 +589,8 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
* down before configuring tc params.
*/
if (netif_running(dev)) {
- cxgb_close(dev);
+ netif_tx_stop_all_queues(dev);
+ netif_carrier_off(dev);
needs_bring_up = true;
}
@@ -615,8 +616,10 @@ int cxgb4_setup_tc_mqprio(struct net_device *dev,
}
out:
- if (needs_bring_up)
- cxgb_open(dev);
+ if (needs_bring_up) {
+ netif_tx_start_all_queues(dev);
+ netif_carrier_on(dev);
+ }
mutex_unlock(&adap->tc_mqprio->mqprio_mutex);
return ret;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 1e5f2edb70cf..6a099cb34b12 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2556,6 +2556,12 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc)
if (!eosw_txq)
return -ENOMEM;
+ if (!(adap->flags & CXGB4_FW_OK)) {
+ /* Don't stall caller when access to FW is lost */
+ complete(&eosw_txq->completion);
+ return -EIO;
+ }
+
skb = alloc_skb(len, GFP_KERNEL);
if (!skb)
return -ENOMEM;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index de70c16ef619..b883ab809df3 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2313,15 +2313,20 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
case XDP_TX:
xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+ if (result == I40E_XDP_CONSUMED)
+ goto out_failure;
break;
case XDP_REDIRECT:
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
+ result = I40E_XDP_REDIR;
break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough; /* handle aborts by dropping packet */
case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 46d884417c63..68f177a86403 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -162,9 +162,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
if (likely(act == XDP_REDIRECT)) {
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
rcu_read_unlock();
- return result;
+ return I40E_XDP_REDIR;
}
switch (act) {
@@ -173,11 +174,14 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
case XDP_TX:
xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index];
result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring);
+ if (result == I40E_XDP_CONSUMED)
+ goto out_failure;
break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough; /* handle aborts by dropping packet */
case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 228055e8f33b..ea1ab7ca82c4 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -341,6 +341,7 @@ struct ice_vsi {
struct ice_tc_cfg tc_cfg;
struct bpf_prog *xdp_prog;
struct ice_ring **xdp_rings; /* XDP ring array */
+ unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */
u16 num_xdp_txq; /* Used XDP queues */
u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */
@@ -559,15 +560,16 @@ static inline void ice_set_ring_xdp(struct ice_ring *ring)
*/
static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_ring *ring)
{
+ struct ice_vsi *vsi = ring->vsi;
u16 qid = ring->q_index;
if (ice_ring_is_xdp(ring))
- qid -= ring->vsi->num_xdp_txq;
+ qid -= vsi->num_xdp_txq;
- if (!ice_is_xdp_ena_vsi(ring->vsi))
+ if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
return NULL;
- return xsk_get_pool_from_qid(ring->vsi->netdev, qid);
+ return xsk_get_pool_from_qid(vsi->netdev, qid);
}
/**
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index d9ddd0bcf65f..99301ad95290 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -1773,49 +1773,6 @@ ice_phy_type_to_ethtool(struct net_device *netdev,
ice_ethtool_advertise_link_mode(ICE_AQ_LINK_SPEED_100GB,
100000baseKR4_Full);
}
-
- /* Autoneg PHY types */
- if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX ||
- phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T ||
- phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX ||
- phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T ||
- phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX ||
- phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T ||
- phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR ||
- phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T ||
- phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 ||
- phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T ||
- phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR ||
- phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S ||
- phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 ||
- phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR ||
- phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S ||
- phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 ||
- phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 ||
- phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) {
- ethtool_link_ksettings_add_link_mode(ks, supported,
- Autoneg);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- Autoneg);
- }
- if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
- phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
- phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
- phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
- ethtool_link_ksettings_add_link_mode(ks, supported,
- Autoneg);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- Autoneg);
- }
- if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
- phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
- phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
- phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) {
- ethtool_link_ksettings_add_link_mode(ks, supported,
- Autoneg);
- ethtool_link_ksettings_add_link_mode(ks, advertising,
- Autoneg);
- }
}
#define TEST_SET_BITS_TIMEOUT 50
@@ -1972,9 +1929,7 @@ ice_get_link_ksettings(struct net_device *netdev,
ks->base.port = PORT_TP;
break;
case ICE_MEDIA_BACKPLANE:
- ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
ethtool_link_ksettings_add_link_mode(ks, supported, Backplane);
- ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
ethtool_link_ksettings_add_link_mode(ks, advertising,
Backplane);
ks->base.port = PORT_NONE;
@@ -2049,6 +2004,12 @@ ice_get_link_ksettings(struct net_device *netdev,
if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN)
ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+ /* Set supported and advertised autoneg */
+ if (ice_is_phy_caps_an_enabled(caps)) {
+ ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+ ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+ }
+
done:
kfree(caps);
return err;
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 65b18b3e2bcc..5386285c39e7 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -31,6 +31,7 @@
#define PF_FW_ATQLEN_ATQOVFL_M BIT(29)
#define PF_FW_ATQLEN_ATQCRIT_M BIT(30)
#define VF_MBX_ARQLEN(_VF) (0x0022BC00 + ((_VF) * 4))
+#define VF_MBX_ATQLEN(_VF) (0x0022A800 + ((_VF) * 4))
#define PF_FW_ATQLEN_ATQENABLE_M BIT(31)
#define PF_FW_ATQT 0x00080400
#define PF_MBX_ARQBAH 0x0022E400
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 56e1ae558761..89bb573e5bcd 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -105,8 +105,14 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
if (!vsi->q_vectors)
goto err_vectors;
+ vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL);
+ if (!vsi->af_xdp_zc_qps)
+ goto err_zc_qps;
+
return 0;
+err_zc_qps:
+ devm_kfree(dev, vsi->q_vectors);
err_vectors:
devm_kfree(dev, vsi->rxq_map);
err_rxq_map:
@@ -194,6 +200,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
break;
case ICE_VSI_VF:
vf = &pf->vf[vsi->vf_id];
+ if (vf->num_req_qs)
+ vf->num_vf_qs = vf->num_req_qs;
vsi->alloc_txq = vf->num_vf_qs;
vsi->alloc_rxq = vf->num_vf_qs;
/* pf->num_msix_per_vf includes (VF miscellaneous vector +
@@ -288,6 +296,10 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)
dev = ice_pf_to_dev(pf);
+ if (vsi->af_xdp_zc_qps) {
+ bitmap_free(vsi->af_xdp_zc_qps);
+ vsi->af_xdp_zc_qps = NULL;
+ }
/* free the ring and vector containers */
if (vsi->q_vectors) {
devm_kfree(dev, vsi->q_vectors);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index e2b4b29ea207..04748aa4c7c8 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -523,7 +523,7 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct ice_ring *xdp_ring;
- int err;
+ int err, result;
u32 act;
act = bpf_prog_run_xdp(xdp_prog, xdp);
@@ -532,14 +532,20 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp,
return ICE_XDP_PASS;
case XDP_TX:
xdp_ring = rx_ring->vsi->xdp_rings[smp_processor_id()];
- return ice_xmit_xdp_buff(xdp, xdp_ring);
+ result = ice_xmit_xdp_buff(xdp, xdp_ring);
+ if (result == ICE_XDP_CONSUMED)
+ goto out_failure;
+ return result;
case XDP_REDIRECT:
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- return !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
+ return ICE_XDP_REDIR;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_DROP:
@@ -2143,6 +2149,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
struct ice_tx_offload_params offload = { 0 };
struct ice_vsi *vsi = tx_ring->vsi;
struct ice_tx_buf *first;
+ struct ethhdr *eth;
unsigned int count;
int tso, csum;
@@ -2189,7 +2196,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
goto out_drop;
/* allow CONTROL frames egress from main VSI if FW LLDP disabled */
- if (unlikely(skb->priority == TC_PRIO_CONTROL &&
+ eth = (struct ethhdr *)skb_mac_header(skb);
+ if (unlikely((skb->priority == TC_PRIO_CONTROL ||
+ eth->h_proto == htons(ETH_P_LLDP)) &&
vsi->type == ICE_VSI_PF &&
vsi->port_info->qos_cfg.is_sw_lldp))
offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index a1d22d2aa0bd..97a46c616aca 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -713,13 +713,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr)
*/
clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
- /* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it
- * in the case of VFR. If this is done for PFR, it can mess up VF
- * resets because the VF driver may already have started cleanup
- * by the time we get here.
+ /* VF_MBX_ARQLEN and VF_MBX_ATQLEN are cleared by PFR, so the driver
+ * needs to clear them in the case of VFR/VFLR. If this is done for
+ * PFR, it can mess up VF resets because the VF driver may already
+ * have started cleanup by the time we get here.
*/
- if (!is_pfr)
+ if (!is_pfr) {
wr32(hw, VF_MBX_ARQLEN(vf->vf_id), 0);
+ wr32(hw, VF_MBX_ATQLEN(vf->vf_id), 0);
+ }
/* In the case of a VFLR, the HW has already reset the VF and we
* just need to clean up, so don't hit the VFRTRIG register.
@@ -1698,7 +1700,12 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
ice_vf_ctrl_vsi_release(vf);
ice_vf_pre_vsi_rebuild(vf);
- ice_vf_rebuild_vsi_with_release(vf);
+
+ if (ice_vf_rebuild_vsi_with_release(vf)) {
+ dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id);
+ return false;
+ }
+
ice_vf_post_vsi_rebuild(vf);
/* if the VF has been reset allow it to come up again */
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index faa7b8d96adb..a1f89ea3c2bd 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -270,6 +270,7 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
if (!pool)
return -EINVAL;
+ clear_bit(qid, vsi->af_xdp_zc_qps);
xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR);
return 0;
@@ -300,6 +301,8 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
if (err)
return err;
+ set_bit(qid, vsi->af_xdp_zc_qps);
+
return 0;
}
@@ -473,9 +476,10 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
if (likely(act == XDP_REDIRECT)) {
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- result = !err ? ICE_XDP_REDIR : ICE_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
rcu_read_unlock();
- return result;
+ return ICE_XDP_REDIR;
}
switch (act) {
@@ -484,11 +488,14 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp)
case XDP_TX:
xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->q_index];
result = ice_xmit_xdp_buff(xdp, xdp_ring);
+ if (result == ICE_XDP_CONSUMED)
+ goto out_failure;
break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 7bda8c5edea5..2d3daf022651 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -749,7 +749,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter);
void igb_ptp_tx_hang(struct igb_adapter *adapter);
void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
- struct sk_buff *skb);
+ ktime_t *timestamp);
int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
void igb_set_flag_queue_pairs(struct igb_adapter *, const u32);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f555670e9271..5db303d64d14 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -8281,7 +8281,7 @@ static void igb_add_rx_frag(struct igb_ring *rx_ring,
static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
struct igb_rx_buffer *rx_buffer,
struct xdp_buff *xdp,
- union e1000_adv_rx_desc *rx_desc)
+ ktime_t timestamp)
{
#if (PAGE_SIZE < 8192)
unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
@@ -8301,12 +8301,8 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
if (unlikely(!skb))
return NULL;
- if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
- if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) {
- xdp->data += IGB_TS_HDR_LEN;
- size -= IGB_TS_HDR_LEN;
- }
- }
+ if (timestamp)
+ skb_hwtstamps(skb)->hwtstamp = timestamp;
/* Determine available headroom for copy */
headlen = size;
@@ -8337,7 +8333,7 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring,
static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
struct igb_rx_buffer *rx_buffer,
struct xdp_buff *xdp,
- union e1000_adv_rx_desc *rx_desc)
+ ktime_t timestamp)
{
#if (PAGE_SIZE < 8192)
unsigned int truesize = igb_rx_pg_size(rx_ring) / 2;
@@ -8364,11 +8360,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring,
if (metasize)
skb_metadata_set(skb, metasize);
- /* pull timestamp out of packet data */
- if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
- if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb))
- __skb_pull(skb, IGB_TS_HDR_LEN);
- }
+ if (timestamp)
+ skb_hwtstamps(skb)->hwtstamp = timestamp;
/* update buffer offset */
#if (PAGE_SIZE < 8192)
@@ -8402,18 +8395,20 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
break;
case XDP_TX:
result = igb_xdp_xmit_back(adapter, xdp);
+ if (result == IGB_XDP_CONSUMED)
+ goto out_failure;
break;
case XDP_REDIRECT:
err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
- if (!err)
- result = IGB_XDP_REDIR;
- else
- result = IGB_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
+ result = IGB_XDP_REDIR;
break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough;
case XDP_DROP:
@@ -8683,7 +8678,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
while (likely(total_packets < budget)) {
union e1000_adv_rx_desc *rx_desc;
struct igb_rx_buffer *rx_buffer;
+ ktime_t timestamp = 0;
+ int pkt_offset = 0;
unsigned int size;
+ void *pktbuf;
/* return some buffers to hardware, one at a time is too slow */
if (cleaned_count >= IGB_RX_BUFFER_WRITE) {
@@ -8703,14 +8701,24 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
dma_rmb();
rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt);
+ pktbuf = page_address(rx_buffer->page) + rx_buffer->page_offset;
+
+ /* pull rx packet timestamp if available and valid */
+ if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+ int ts_hdr_len;
+
+ ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector,
+ pktbuf, &timestamp);
+
+ pkt_offset += ts_hdr_len;
+ size -= ts_hdr_len;
+ }
/* retrieve a buffer from the ring */
if (!skb) {
- unsigned int offset = igb_rx_offset(rx_ring);
- unsigned char *hard_start;
+ unsigned char *hard_start = pktbuf - igb_rx_offset(rx_ring);
+ unsigned int offset = pkt_offset + igb_rx_offset(rx_ring);
- hard_start = page_address(rx_buffer->page) +
- rx_buffer->page_offset - offset;
xdp_prepare_buff(&xdp, hard_start, offset, size, true);
#if (PAGE_SIZE > 4096)
/* At larger PAGE_SIZE, frame_sz depend on len size */
@@ -8733,10 +8741,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
} else if (skb)
igb_add_rx_frag(rx_ring, rx_buffer, skb, size);
else if (ring_uses_build_skb(rx_ring))
- skb = igb_build_skb(rx_ring, rx_buffer, &xdp, rx_desc);
+ skb = igb_build_skb(rx_ring, rx_buffer, &xdp,
+ timestamp);
else
skb = igb_construct_skb(rx_ring, rx_buffer,
- &xdp, rx_desc);
+ &xdp, timestamp);
/* exit if we failed to retrieve a buffer */
if (!skb) {
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index de08ae8db4d5..0011b15e678c 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -856,30 +856,28 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter)
dev_kfree_skb_any(skb);
}
-#define IGB_RET_PTP_DISABLED 1
-#define IGB_RET_PTP_INVALID 2
-
/**
* igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp
* @q_vector: Pointer to interrupt specific structure
* @va: Pointer to address containing Rx buffer
- * @skb: Buffer containing timestamp and packet
+ * @timestamp: Pointer where timestamp will be stored
*
* This function is meant to retrieve a timestamp from the first buffer of an
* incoming frame. The value is stored in little endian format starting on
* byte 8
*
- * Returns: 0 if success, nonzero if failure
+ * Returns: The timestamp header length or 0 if not available
**/
int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
- struct sk_buff *skb)
+ ktime_t *timestamp)
{
struct igb_adapter *adapter = q_vector->adapter;
+ struct skb_shared_hwtstamps ts;
__le64 *regval = (__le64 *)va;
int adjust = 0;
if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
- return IGB_RET_PTP_DISABLED;
+ return 0;
/* The timestamp is recorded in little endian format.
* DWORD: 0 1 2 3
@@ -888,10 +886,9 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
/* check reserved dwords are zero, be/le doesn't matter for zero */
if (regval[0])
- return IGB_RET_PTP_INVALID;
+ return 0;
- igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
- le64_to_cpu(regval[1]));
+ igb_ptp_systim_to_hwtstamp(adapter, &ts, le64_to_cpu(regval[1]));
/* adjust timestamp for the RX latency based on link speed */
if (adapter->hw.mac.type == e1000_i210) {
@@ -907,10 +904,10 @@ int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
break;
}
}
- skb_hwtstamps(skb)->hwtstamp =
- ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
- return 0;
+ *timestamp = ktime_sub_ns(ts.hwtstamp, adjust);
+
+ return IGB_TS_HDR_LEN;
}
/**
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 2e71b006b660..3f6b6d4543a8 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2214,15 +2214,19 @@ static int __igc_xdp_run_prog(struct igc_adapter *adapter,
case XDP_PASS:
return IGC_XDP_PASS;
case XDP_TX:
- return igc_xdp_xmit_back(adapter, xdp) < 0 ?
- IGC_XDP_CONSUMED : IGC_XDP_TX;
+ if (igc_xdp_xmit_back(adapter, xdp) < 0)
+ goto out_failure;
+ return IGC_XDP_TX;
case XDP_REDIRECT:
- return xdp_do_redirect(adapter->netdev, xdp, prog) < 0 ?
- IGC_XDP_CONSUMED : IGC_XDP_REDIRECT;
+ if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0)
+ goto out_failure;
+ return IGC_XDP_REDIRECT;
+ break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(adapter->netdev, prog, act);
fallthrough;
case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index c5ec17d19c59..2ac5b82676f3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2213,23 +2213,23 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
break;
case XDP_TX:
xdpf = xdp_convert_buff_to_frame(xdp);
- if (unlikely(!xdpf)) {
- result = IXGBE_XDP_CONSUMED;
- break;
- }
+ if (unlikely(!xdpf))
+ goto out_failure;
result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+ if (result == IXGBE_XDP_CONSUMED)
+ goto out_failure;
break;
case XDP_REDIRECT:
err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
- if (!err)
- result = IXGBE_XDP_REDIR;
- else
- result = IXGBE_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
+ result = IXGBE_XDP_REDIR;
break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough; /* handle aborts by dropping packet */
case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 91ad5b902673..f72d2978263b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -106,9 +106,10 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
if (likely(act == XDP_REDIRECT)) {
err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
- result = !err ? IXGBE_XDP_REDIR : IXGBE_XDP_CONSUMED;
+ if (err)
+ goto out_failure;
rcu_read_unlock();
- return result;
+ return IXGBE_XDP_REDIR;
}
switch (act) {
@@ -116,16 +117,17 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
break;
case XDP_TX:
xdpf = xdp_convert_buff_to_frame(xdp);
- if (unlikely(!xdpf)) {
- result = IXGBE_XDP_CONSUMED;
- break;
- }
+ if (unlikely(!xdpf))
+ goto out_failure;
result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+ if (result == IXGBE_XDP_CONSUMED)
+ goto out_failure;
break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough; /* handle aborts by dropping packet */
case XDP_DROP:
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 588c3aa50d94..dc56931fc1dc 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1067,11 +1067,14 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter,
case XDP_TX:
xdp_ring = adapter->xdp_ring[rx_ring->queue_index];
result = ixgbevf_xmit_xdp_ring(xdp_ring, xdp);
+ if (result == IXGBEVF_XDP_CONSUMED)
+ goto out_failure;
break;
default:
bpf_warn_invalid_xdp_action(act);
fallthrough;
case XDP_ABORTED:
+out_failure:
trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
fallthrough; /* handle aborts by dropping packet */
case XDP_DROP:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 5daf7185b035..bd72572e03d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1624,12 +1624,13 @@ static int mlx5e_set_fecparam(struct net_device *netdev,
{
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = priv->mdev;
+ unsigned long fec_bitmap;
u16 fec_policy = 0;
int mode;
int err;
- if (bitmap_weight((unsigned long *)&fecparam->fec,
- ETHTOOL_FEC_LLRS_BIT + 1) > 1)
+ bitmap_from_arr32(&fec_bitmap, &fecparam->fec, sizeof(fecparam->fec) * BITS_PER_BYTE);
+ if (bitmap_weight(&fec_bitmap, ETHTOOL_FEC_LLRS_BIT + 1) > 1)
return -EOPNOTSUPP;
for (mode = 0; mode < ARRAY_SIZE(pplm_fec_2_ethtool); mode++) {
@@ -1893,6 +1894,13 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val
if (curr_val == new_val)
return 0;
+ if (new_val && !priv->profile->rx_ptp_support &&
+ priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) {
+ netdev_err(priv->netdev,
+ "Profile doesn't support enabling of CQE compression while hardware time-stamping is enabled.\n");
+ return -EINVAL;
+ }
+
new_params = priv->channels.params;
MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val);
if (priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0d59639f8ac0..59ee28156603 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3862,6 +3862,16 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n");
}
+ if (mlx5e_is_uplink_rep(priv)) {
+ features &= ~NETIF_F_HW_TLS_RX;
+ if (netdev->features & NETIF_F_HW_TLS_RX)
+ netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n");
+
+ features &= ~NETIF_F_HW_TLS_TX;
+ if (netdev->features & NETIF_F_HW_TLS_TX)
+ netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n");
+ }
+
mutex_unlock(&priv->state_lock);
return features;
@@ -3978,11 +3988,45 @@ int mlx5e_ptp_rx_manage_fs_ctx(struct mlx5e_priv *priv, void *ctx)
return mlx5e_ptp_rx_manage_fs(priv, set);
}
-int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
+static int mlx5e_hwstamp_config_no_ptp_rx(struct mlx5e_priv *priv, bool rx_filter)
+{
+ bool rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def;
+ int err;
+
+ if (!rx_filter)
+ /* Reset CQE compression to Admin default */
+ return mlx5e_modify_rx_cqe_compression_locked(priv, rx_cqe_compress_def);
+
+ if (!MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS))
+ return 0;
+
+ /* Disable CQE compression */
+ netdev_warn(priv->netdev, "Disabling RX cqe compression\n");
+ err = mlx5e_modify_rx_cqe_compression_locked(priv, false);
+ if (err)
+ netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err);
+
+ return err;
+}
+
+static int mlx5e_hwstamp_config_ptp_rx(struct mlx5e_priv *priv, bool ptp_rx)
{
struct mlx5e_params new_params;
+
+ if (ptp_rx == priv->channels.params.ptp_rx)
+ return 0;
+
+ new_params = priv->channels.params;
+ new_params.ptp_rx = ptp_rx;
+ return mlx5e_safe_switch_params(priv, &new_params, mlx5e_ptp_rx_manage_fs_ctx,
+ &new_params.ptp_rx, true);
+}
+
+int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
+{
struct hwtstamp_config config;
bool rx_cqe_compress_def;
+ bool ptp_rx;
int err;
if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
@@ -4002,13 +4046,12 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
}
mutex_lock(&priv->state_lock);
- new_params = priv->channels.params;
rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def;
/* RX HW timestamp */
switch (config.rx_filter) {
case HWTSTAMP_FILTER_NONE:
- new_params.ptp_rx = false;
+ ptp_rx = false;
break;
case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_SOME:
@@ -4025,24 +4068,25 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
case HWTSTAMP_FILTER_PTP_V2_SYNC:
case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
case HWTSTAMP_FILTER_NTP_ALL:
- new_params.ptp_rx = rx_cqe_compress_def;
config.rx_filter = HWTSTAMP_FILTER_ALL;
+ /* ptp_rx is set if both HW TS is set and CQE
+ * compression is set
+ */
+ ptp_rx = rx_cqe_compress_def;
break;
default:
- mutex_unlock(&priv->state_lock);
- return -ERANGE;
+ err = -ERANGE;
+ goto err_unlock;
}
- if (new_params.ptp_rx == priv->channels.params.ptp_rx)
- goto out;
+ if (!priv->profile->rx_ptp_support)
+ err = mlx5e_hwstamp_config_no_ptp_rx(priv,
+ config.rx_filter != HWTSTAMP_FILTER_NONE);
+ else
+ err = mlx5e_hwstamp_config_ptp_rx(priv, ptp_rx);
+ if (err)
+ goto err_unlock;
- err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_ptp_rx_manage_fs_ctx,
- &new_params.ptp_rx, true);
- if (err) {
- mutex_unlock(&priv->state_lock);
- return err;
- }
-out:
memcpy(&priv->tstamp, &config, sizeof(config));
mutex_unlock(&priv->state_lock);
@@ -4051,6 +4095,9 @@ out:
return copy_to_user(ifr->ifr_data, &config,
sizeof(config)) ? -EFAULT : 0;
+err_unlock:
+ mutex_unlock(&priv->state_lock);
+ return err;
}
int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3fa314ac5729..cf4558e12325 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2043,11 +2043,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
misc_parameters_3);
struct flow_rule *rule = flow_cls_offload_flow_rule(f);
struct flow_dissector *dissector = rule->match.dissector;
+ enum fs_flow_table_type fs_type;
u16 addr_type = 0;
u8 ip_proto = 0;
u8 *match_level;
int err;
+ fs_type = mlx5e_is_eswitch_flow(flow) ? FS_FT_FDB : FS_FT_NIC_RX;
match_level = outer_match_level;
if (dissector->used_keys &
@@ -2173,6 +2175,13 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
if (match.mask->vlan_id ||
match.mask->vlan_priority ||
match.mask->vlan_tpid) {
+ if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ft_field_support.outer_second_vid,
+ fs_type)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Matching on CVLAN is not supported");
+ return -EOPNOTSUPP;
+ }
+
if (match.key->vlan_tpid == htons(ETH_P_8021AD)) {
MLX5_SET(fte_match_set_misc, misc_c,
outer_second_svlan_tag, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index db1e74280e57..d18a28a6e9a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -219,7 +219,8 @@ esw_setup_slow_path_dest(struct mlx5_flow_destination *dest,
struct mlx5_fs_chains *chains,
int i)
{
- flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+ if (mlx5_chains_ignore_flow_level_supported(chains))
+ flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
dest[i].ft = mlx5_chains_get_tc_end_ft(chains);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index d5d57630015f..106b50e42b46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -349,6 +349,9 @@ static void mlx5_sync_reset_abort_event(struct work_struct *work)
reset_abort_work);
struct mlx5_core_dev *dev = fw_reset->dev;
+ if (!test_bit(MLX5_FW_RESET_FLAGS_RESET_REQUESTED, &fw_reset->reset_flags))
+ return;
+
mlx5_sync_reset_clear_reset_requested(dev, true);
mlx5_core_warn(dev, "PCI Sync FW Update Reset Aborted.\n");
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index d0cfe7adb8a0..97e5845b4cfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -91,7 +91,7 @@ bool mlx5_chains_prios_supported(struct mlx5_fs_chains *chains)
return chains->flags & MLX5_CHAINS_AND_PRIOS_SUPPORTED;
}
-static bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
+bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
{
return chains->flags & MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
index e96f345e7dae..d50bdb226cef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h
@@ -28,6 +28,7 @@ struct mlx5_chains_attr {
bool
mlx5_chains_prios_supported(struct mlx5_fs_chains *chains);
+bool mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains);
bool
mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains);
u32
@@ -70,6 +71,10 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,
#else /* CONFIG_MLX5_CLS_ACT */
+static inline bool
+mlx5_chains_ignore_flow_level_supported(struct mlx5_fs_chains *chains)
+{ return false; }
+
static inline struct mlx5_flow_table *
mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
u32 level) { return ERR_PTR(-EOPNOTSUPP); }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
index 1fbcd012bb85..7ccfd40586ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
@@ -112,7 +112,8 @@ int mlx5dr_fw_create_md_tbl(struct mlx5dr_domain *dmn,
int ret;
ft_attr.table_type = MLX5_FLOW_TABLE_TYPE_FDB;
- ft_attr.level = dmn->info.caps.max_ft_level - 2;
+ ft_attr.level = min_t(int, dmn->info.caps.max_ft_level - 2,
+ MLX5_FT_MAX_MULTIPATH_LEVEL);
ft_attr.reformat_en = reformat_req;
ft_attr.decap_en = reformat_req;
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index c84c8bf2bc20..fc99ad8e4a38 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -3815,6 +3815,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
dev_err(&pdev->dev,
"invalid sram_size %dB or board span %ldB\n",
mgp->sram_size, mgp->board_span);
+ status = -EINVAL;
goto abort_with_ioremap;
}
memcpy_fromio(mgp->eeprom_strings,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 6d41dd6f9f7a..0a266fa0af7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1222,7 +1222,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
priv->phylink_config.dev = &priv->dev->dev;
priv->phylink_config.type = PHYLINK_NETDEV;
priv->phylink_config.pcs_poll = true;
- priv->phylink_config.ovr_an_inband = mdio_bus_data->xpcs_an_inband;
+ if (priv->plat->mdio_bus_data)
+ priv->phylink_config.ovr_an_inband =
+ mdio_bus_data->xpcs_an_inband;
if (!fwnode)
fwnode = dev_fwnode(priv->device);
@@ -7035,7 +7037,6 @@ error_mdio_register:
stmmac_napi_del(ndev);
error_hw_init:
destroy_workqueue(priv->wq);
- stmmac_bus_clks_config(priv, false);
bitmap_free(priv->af_xdp_zc_qps);
return ret;
diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c
index b9be530b285f..ff83e00b77af 100644
--- a/drivers/net/ieee802154/mrf24j40.c
+++ b/drivers/net/ieee802154/mrf24j40.c
@@ -8,8 +8,8 @@
#include <linux/spi/spi.h>
#include <linux/interrupt.h>
+#include <linux/mod_devicetable.h>
#include <linux/module.h>
-#include <linux/of.h>
#include <linux/regmap.h>
#include <linux/ieee802154.h>
#include <linux/irq.h>
@@ -1388,7 +1388,7 @@ MODULE_DEVICE_TABLE(spi, mrf24j40_ids);
static struct spi_driver mrf24j40_driver = {
.driver = {
- .of_match_table = of_match_ptr(mrf24j40_of_match),
+ .of_match_table = mrf24j40_of_match,
.name = "mrf24j40",
},
.id_table = mrf24j40_ids,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ed969b65126e..f8f5b8646a43 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -401,6 +401,9 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
/* If whole_page, there is an offset between the beginning of the
* data and the allocated space, otherwise the data and the allocated
* space are aligned.
+ *
+ * Buffers with headroom use PAGE_SIZE as alloc size, see
+ * add_recvbuf_mergeable() + get_mergeable_buf_len()
*/
if (whole_page) {
/* Buffers with whole_page use PAGE_SIZE as alloc size,
diff --git a/drivers/net/wireguard/Makefile b/drivers/net/wireguard/Makefile
index fc52b2cb500b..dbe1f8514efc 100644
--- a/drivers/net/wireguard/Makefile
+++ b/drivers/net/wireguard/Makefile
@@ -1,5 +1,4 @@
-ccflags-y := -O3
-ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
+ccflags-y := -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
ccflags-$(CONFIG_WIREGUARD_DEBUG) += -DDEBUG
wireguard-y := main.o
wireguard-y += noise.o
diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c
index 3725e9cd85f4..b7197e80f226 100644
--- a/drivers/net/wireguard/allowedips.c
+++ b/drivers/net/wireguard/allowedips.c
@@ -6,6 +6,8 @@
#include "allowedips.h"
#include "peer.h"
+static struct kmem_cache *node_cache;
+
static void swap_endian(u8 *dst, const u8 *src, u8 bits)
{
if (bits == 32) {
@@ -28,8 +30,11 @@ static void copy_and_assign_cidr(struct allowedips_node *node, const u8 *src,
node->bitlen = bits;
memcpy(node->bits, src, bits / 8U);
}
-#define CHOOSE_NODE(parent, key) \
- parent->bit[(key[parent->bit_at_a] >> parent->bit_at_b) & 1]
+
+static inline u8 choose(struct allowedips_node *node, const u8 *key)
+{
+ return (key[node->bit_at_a] >> node->bit_at_b) & 1;
+}
static void push_rcu(struct allowedips_node **stack,
struct allowedips_node __rcu *p, unsigned int *len)
@@ -40,6 +45,11 @@ static void push_rcu(struct allowedips_node **stack,
}
}
+static void node_free_rcu(struct rcu_head *rcu)
+{
+ kmem_cache_free(node_cache, container_of(rcu, struct allowedips_node, rcu));
+}
+
static void root_free_rcu(struct rcu_head *rcu)
{
struct allowedips_node *node, *stack[128] = {
@@ -49,7 +59,7 @@ static void root_free_rcu(struct rcu_head *rcu)
while (len > 0 && (node = stack[--len])) {
push_rcu(stack, node->bit[0], &len);
push_rcu(stack, node->bit[1], &len);
- kfree(node);
+ kmem_cache_free(node_cache, node);
}
}
@@ -66,60 +76,6 @@ static void root_remove_peer_lists(struct allowedips_node *root)
}
}
-static void walk_remove_by_peer(struct allowedips_node __rcu **top,
- struct wg_peer *peer, struct mutex *lock)
-{
-#define REF(p) rcu_access_pointer(p)
-#define DEREF(p) rcu_dereference_protected(*(p), lockdep_is_held(lock))
-#define PUSH(p) ({ \
- WARN_ON(IS_ENABLED(DEBUG) && len >= 128); \
- stack[len++] = p; \
- })
-
- struct allowedips_node __rcu **stack[128], **nptr;
- struct allowedips_node *node, *prev;
- unsigned int len;
-
- if (unlikely(!peer || !REF(*top)))
- return;
-
- for (prev = NULL, len = 0, PUSH(top); len > 0; prev = node) {
- nptr = stack[len - 1];
- node = DEREF(nptr);
- if (!node) {
- --len;
- continue;
- }
- if (!prev || REF(prev->bit[0]) == node ||
- REF(prev->bit[1]) == node) {
- if (REF(node->bit[0]))
- PUSH(&node->bit[0]);
- else if (REF(node->bit[1]))
- PUSH(&node->bit[1]);
- } else if (REF(node->bit[0]) == prev) {
- if (REF(node->bit[1]))
- PUSH(&node->bit[1]);
- } else {
- if (rcu_dereference_protected(node->peer,
- lockdep_is_held(lock)) == peer) {
- RCU_INIT_POINTER(node->peer, NULL);
- list_del_init(&node->peer_list);
- if (!node->bit[0] || !node->bit[1]) {
- rcu_assign_pointer(*nptr, DEREF(
- &node->bit[!REF(node->bit[0])]));
- kfree_rcu(node, rcu);
- node = DEREF(nptr);
- }
- }
- --len;
- }
- }
-
-#undef REF
-#undef DEREF
-#undef PUSH
-}
-
static unsigned int fls128(u64 a, u64 b)
{
return a ? fls64(a) + 64U : fls64(b);
@@ -159,7 +115,7 @@ static struct allowedips_node *find_node(struct allowedips_node *trie, u8 bits,
found = node;
if (node->cidr == bits)
break;
- node = rcu_dereference_bh(CHOOSE_NODE(node, key));
+ node = rcu_dereference_bh(node->bit[choose(node, key)]);
}
return found;
}
@@ -191,8 +147,7 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
u8 cidr, u8 bits, struct allowedips_node **rnode,
struct mutex *lock)
{
- struct allowedips_node *node = rcu_dereference_protected(trie,
- lockdep_is_held(lock));
+ struct allowedips_node *node = rcu_dereference_protected(trie, lockdep_is_held(lock));
struct allowedips_node *parent = NULL;
bool exact = false;
@@ -202,13 +157,24 @@ static bool node_placement(struct allowedips_node __rcu *trie, const u8 *key,
exact = true;
break;
}
- node = rcu_dereference_protected(CHOOSE_NODE(parent, key),
- lockdep_is_held(lock));
+ node = rcu_dereference_protected(parent->bit[choose(parent, key)], lockdep_is_held(lock));
}
*rnode = parent;
return exact;
}
+static inline void connect_node(struct allowedips_node **parent, u8 bit, struct allowedips_node *node)
+{
+ node->parent_bit_packed = (unsigned long)parent | bit;
+ rcu_assign_pointer(*parent, node);
+}
+
+static inline void choose_and_connect_node(struct allowedips_node *parent, struct allowedips_node *node)
+{
+ u8 bit = choose(parent, node->bits);
+ connect_node(&parent->bit[bit], bit, node);
+}
+
static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
u8 cidr, struct wg_peer *peer, struct mutex *lock)
{
@@ -218,13 +184,13 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
return -EINVAL;
if (!rcu_access_pointer(*trie)) {
- node = kzalloc(sizeof(*node), GFP_KERNEL);
+ node = kmem_cache_zalloc(node_cache, GFP_KERNEL);
if (unlikely(!node))
return -ENOMEM;
RCU_INIT_POINTER(node->peer, peer);
list_add_tail(&node->peer_list, &peer->allowedips_list);
copy_and_assign_cidr(node, key, cidr, bits);
- rcu_assign_pointer(*trie, node);
+ connect_node(trie, 2, node);
return 0;
}
if (node_placement(*trie, key, cidr, bits, &node, lock)) {
@@ -233,7 +199,7 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
return 0;
}
- newnode = kzalloc(sizeof(*newnode), GFP_KERNEL);
+ newnode = kmem_cache_zalloc(node_cache, GFP_KERNEL);
if (unlikely(!newnode))
return -ENOMEM;
RCU_INIT_POINTER(newnode->peer, peer);
@@ -243,10 +209,10 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
if (!node) {
down = rcu_dereference_protected(*trie, lockdep_is_held(lock));
} else {
- down = rcu_dereference_protected(CHOOSE_NODE(node, key),
- lockdep_is_held(lock));
+ const u8 bit = choose(node, key);
+ down = rcu_dereference_protected(node->bit[bit], lockdep_is_held(lock));
if (!down) {
- rcu_assign_pointer(CHOOSE_NODE(node, key), newnode);
+ connect_node(&node->bit[bit], bit, newnode);
return 0;
}
}
@@ -254,30 +220,29 @@ static int add(struct allowedips_node __rcu **trie, u8 bits, const u8 *key,
parent = node;
if (newnode->cidr == cidr) {
- rcu_assign_pointer(CHOOSE_NODE(newnode, down->bits), down);
+ choose_and_connect_node(newnode, down);
if (!parent)
- rcu_assign_pointer(*trie, newnode);
+ connect_node(trie, 2, newnode);
else
- rcu_assign_pointer(CHOOSE_NODE(parent, newnode->bits),
- newnode);
- } else {
- node = kzalloc(sizeof(*node), GFP_KERNEL);
- if (unlikely(!node)) {
- list_del(&newnode->peer_list);
- kfree(newnode);
- return -ENOMEM;
- }
- INIT_LIST_HEAD(&node->peer_list);
- copy_and_assign_cidr(node, newnode->bits, cidr, bits);
+ choose_and_connect_node(parent, newnode);
+ return 0;
+ }
- rcu_assign_pointer(CHOOSE_NODE(node, down->bits), down);
- rcu_assign_pointer(CHOOSE_NODE(node, newnode->bits), newnode);
- if (!parent)
- rcu_assign_pointer(*trie, node);
- else
- rcu_assign_pointer(CHOOSE_NODE(parent, node->bits),
- node);
+ node = kmem_cache_zalloc(node_cache, GFP_KERNEL);
+ if (unlikely(!node)) {
+ list_del(&newnode->peer_list);
+ kmem_cache_free(node_cache, newnode);
+ return -ENOMEM;
}
+ INIT_LIST_HEAD(&node->peer_list);
+ copy_and_assign_cidr(node, newnode->bits, cidr, bits);
+
+ choose_and_connect_node(node, down);
+ choose_and_connect_node(node, newnode);
+ if (!parent)
+ connect_node(trie, 2, node);
+ else
+ choose_and_connect_node(parent, node);
return 0;
}
@@ -335,9 +300,41 @@ int wg_allowedips_insert_v6(struct allowedips *table, const struct in6_addr *ip,
void wg_allowedips_remove_by_peer(struct allowedips *table,
struct wg_peer *peer, struct mutex *lock)
{
+ struct allowedips_node *node, *child, **parent_bit, *parent, *tmp;
+ bool free_parent;
+
+ if (list_empty(&peer->allowedips_list))
+ return;
++table->seq;
- walk_remove_by_peer(&table->root4, peer, lock);
- walk_remove_by_peer(&table->root6, peer, lock);
+ list_for_each_entry_safe(node, tmp, &peer->allowedips_list, peer_list) {
+ list_del_init(&node->peer_list);
+ RCU_INIT_POINTER(node->peer, NULL);
+ if (node->bit[0] && node->bit[1])
+ continue;
+ child = rcu_dereference_protected(node->bit[!rcu_access_pointer(node->bit[0])],
+ lockdep_is_held(lock));
+ if (child)
+ child->parent_bit_packed = node->parent_bit_packed;
+ parent_bit = (struct allowedips_node **)(node->parent_bit_packed & ~3UL);
+ *parent_bit = child;
+ parent = (void *)parent_bit -
+ offsetof(struct allowedips_node, bit[node->parent_bit_packed & 1]);
+ free_parent = !rcu_access_pointer(node->bit[0]) &&
+ !rcu_access_pointer(node->bit[1]) &&
+ (node->parent_bit_packed & 3) <= 1 &&
+ !rcu_access_pointer(parent->peer);
+ if (free_parent)
+ child = rcu_dereference_protected(
+ parent->bit[!(node->parent_bit_packed & 1)],
+ lockdep_is_held(lock));
+ call_rcu(&node->rcu, node_free_rcu);
+ if (!free_parent)
+ continue;
+ if (child)
+ child->parent_bit_packed = parent->parent_bit_packed;
+ *(struct allowedips_node **)(parent->parent_bit_packed & ~3UL) = child;
+ call_rcu(&parent->rcu, node_free_rcu);
+ }
}
int wg_allowedips_read_node(struct allowedips_node *node, u8 ip[16], u8 *cidr)
@@ -374,4 +371,16 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
return NULL;
}
+int __init wg_allowedips_slab_init(void)
+{
+ node_cache = KMEM_CACHE(allowedips_node, 0);
+ return node_cache ? 0 : -ENOMEM;
+}
+
+void wg_allowedips_slab_uninit(void)
+{
+ rcu_barrier();
+ kmem_cache_destroy(node_cache);
+}
+
#include "selftest/allowedips.c"
diff --git a/drivers/net/wireguard/allowedips.h b/drivers/net/wireguard/allowedips.h
index e5c83cafcef4..2346c797eb4d 100644
--- a/drivers/net/wireguard/allowedips.h
+++ b/drivers/net/wireguard/allowedips.h
@@ -15,14 +15,11 @@ struct wg_peer;
struct allowedips_node {
struct wg_peer __rcu *peer;
struct allowedips_node __rcu *bit[2];
- /* While it may seem scandalous that we waste space for v4,
- * we're alloc'ing to the nearest power of 2 anyway, so this
- * doesn't actually make a difference.
- */
- u8 bits[16] __aligned(__alignof(u64));
u8 cidr, bit_at_a, bit_at_b, bitlen;
+ u8 bits[16] __aligned(__alignof(u64));
- /* Keep rarely used list at bottom to be beyond cache line. */
+ /* Keep rarely used members at bottom to be beyond cache line. */
+ unsigned long parent_bit_packed;
union {
struct list_head peer_list;
struct rcu_head rcu;
@@ -33,7 +30,7 @@ struct allowedips {
struct allowedips_node __rcu *root4;
struct allowedips_node __rcu *root6;
u64 seq;
-};
+} __aligned(4); /* We pack the lower 2 bits of &root, but m68k only gives 16-bit alignment. */
void wg_allowedips_init(struct allowedips *table);
void wg_allowedips_free(struct allowedips *table, struct mutex *mutex);
@@ -56,4 +53,7 @@ struct wg_peer *wg_allowedips_lookup_src(struct allowedips *table,
bool wg_allowedips_selftest(void);
#endif
+int wg_allowedips_slab_init(void);
+void wg_allowedips_slab_uninit(void);
+
#endif /* _WG_ALLOWEDIPS_H */
diff --git a/drivers/net/wireguard/main.c b/drivers/net/wireguard/main.c
index 7a7d5f1a80fc..75dbe77b0b4b 100644
--- a/drivers/net/wireguard/main.c
+++ b/drivers/net/wireguard/main.c
@@ -21,13 +21,22 @@ static int __init mod_init(void)
{
int ret;
+ ret = wg_allowedips_slab_init();
+ if (ret < 0)
+ goto err_allowedips;
+
#ifdef DEBUG
+ ret = -ENOTRECOVERABLE;
if (!wg_allowedips_selftest() || !wg_packet_counter_selftest() ||
!wg_ratelimiter_selftest())
- return -ENOTRECOVERABLE;
+ goto err_peer;
#endif
wg_noise_init();
+ ret = wg_peer_init();
+ if (ret < 0)
+ goto err_peer;
+
ret = wg_device_init();
if (ret < 0)
goto err_device;
@@ -44,6 +53,10 @@ static int __init mod_init(void)
err_netlink:
wg_device_uninit();
err_device:
+ wg_peer_uninit();
+err_peer:
+ wg_allowedips_slab_uninit();
+err_allowedips:
return ret;
}
@@ -51,6 +64,8 @@ static void __exit mod_exit(void)
{
wg_genetlink_uninit();
wg_device_uninit();
+ wg_peer_uninit();
+ wg_allowedips_slab_uninit();
}
module_init(mod_init);
diff --git a/drivers/net/wireguard/peer.c b/drivers/net/wireguard/peer.c
index cd5cb0292cb6..1acd00ab2fbc 100644
--- a/drivers/net/wireguard/peer.c
+++ b/drivers/net/wireguard/peer.c
@@ -15,6 +15,7 @@
#include <linux/rcupdate.h>
#include <linux/list.h>
+static struct kmem_cache *peer_cache;
static atomic64_t peer_counter = ATOMIC64_INIT(0);
struct wg_peer *wg_peer_create(struct wg_device *wg,
@@ -29,10 +30,10 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
if (wg->num_peers >= MAX_PEERS_PER_DEVICE)
return ERR_PTR(ret);
- peer = kzalloc(sizeof(*peer), GFP_KERNEL);
+ peer = kmem_cache_zalloc(peer_cache, GFP_KERNEL);
if (unlikely(!peer))
return ERR_PTR(ret);
- if (dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))
+ if (unlikely(dst_cache_init(&peer->endpoint_cache, GFP_KERNEL)))
goto err;
peer->device = wg;
@@ -64,7 +65,7 @@ struct wg_peer *wg_peer_create(struct wg_device *wg,
return peer;
err:
- kfree(peer);
+ kmem_cache_free(peer_cache, peer);
return ERR_PTR(ret);
}
@@ -88,7 +89,7 @@ static void peer_make_dead(struct wg_peer *peer)
/* Mark as dead, so that we don't allow jumping contexts after. */
WRITE_ONCE(peer->is_dead, true);
- /* The caller must now synchronize_rcu() for this to take effect. */
+ /* The caller must now synchronize_net() for this to take effect. */
}
static void peer_remove_after_dead(struct wg_peer *peer)
@@ -160,7 +161,7 @@ void wg_peer_remove(struct wg_peer *peer)
lockdep_assert_held(&peer->device->device_update_lock);
peer_make_dead(peer);
- synchronize_rcu();
+ synchronize_net();
peer_remove_after_dead(peer);
}
@@ -178,7 +179,7 @@ void wg_peer_remove_all(struct wg_device *wg)
peer_make_dead(peer);
list_add_tail(&peer->peer_list, &dead_peers);
}
- synchronize_rcu();
+ synchronize_net();
list_for_each_entry_safe(peer, temp, &dead_peers, peer_list)
peer_remove_after_dead(peer);
}
@@ -193,7 +194,8 @@ static void rcu_release(struct rcu_head *rcu)
/* The final zeroing takes care of clearing any remaining handshake key
* material and other potentially sensitive information.
*/
- kfree_sensitive(peer);
+ memzero_explicit(peer, sizeof(*peer));
+ kmem_cache_free(peer_cache, peer);
}
static void kref_release(struct kref *refcount)
@@ -225,3 +227,14 @@ void wg_peer_put(struct wg_peer *peer)
return;
kref_put(&peer->refcount, kref_release);
}
+
+int __init wg_peer_init(void)
+{
+ peer_cache = KMEM_CACHE(wg_peer, 0);
+ return peer_cache ? 0 : -ENOMEM;
+}
+
+void wg_peer_uninit(void)
+{
+ kmem_cache_destroy(peer_cache);
+}
diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h
index 8d53b687a1d1..76e4d3128ad4 100644
--- a/drivers/net/wireguard/peer.h
+++ b/drivers/net/wireguard/peer.h
@@ -80,4 +80,7 @@ void wg_peer_put(struct wg_peer *peer);
void wg_peer_remove(struct wg_peer *peer);
void wg_peer_remove_all(struct wg_device *wg);
+int wg_peer_init(void);
+void wg_peer_uninit(void);
+
#endif /* _WG_PEER_H */
diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c
index 846db14cb046..e173204ae7d7 100644
--- a/drivers/net/wireguard/selftest/allowedips.c
+++ b/drivers/net/wireguard/selftest/allowedips.c
@@ -19,32 +19,22 @@
#include <linux/siphash.h>
-static __init void swap_endian_and_apply_cidr(u8 *dst, const u8 *src, u8 bits,
- u8 cidr)
-{
- swap_endian(dst, src, bits);
- memset(dst + (cidr + 7) / 8, 0, bits / 8 - (cidr + 7) / 8);
- if (cidr)
- dst[(cidr + 7) / 8 - 1] &= ~0U << ((8 - (cidr % 8)) % 8);
-}
-
static __init void print_node(struct allowedips_node *node, u8 bits)
{
char *fmt_connection = KERN_DEBUG "\t\"%p/%d\" -> \"%p/%d\";\n";
- char *fmt_declaration = KERN_DEBUG
- "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
+ char *fmt_declaration = KERN_DEBUG "\t\"%p/%d\"[style=%s, color=\"#%06x\"];\n";
+ u8 ip1[16], ip2[16], cidr1, cidr2;
char *style = "dotted";
- u8 ip1[16], ip2[16];
u32 color = 0;
+ if (node == NULL)
+ return;
if (bits == 32) {
fmt_connection = KERN_DEBUG "\t\"%pI4/%d\" -> \"%pI4/%d\";\n";
- fmt_declaration = KERN_DEBUG
- "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
+ fmt_declaration = KERN_DEBUG "\t\"%pI4/%d\"[style=%s, color=\"#%06x\"];\n";
} else if (bits == 128) {
fmt_connection = KERN_DEBUG "\t\"%pI6/%d\" -> \"%pI6/%d\";\n";
- fmt_declaration = KERN_DEBUG
- "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
+ fmt_declaration = KERN_DEBUG "\t\"%pI6/%d\"[style=%s, color=\"#%06x\"];\n";
}
if (node->peer) {
hsiphash_key_t key = { { 0 } };
@@ -55,24 +45,20 @@ static __init void print_node(struct allowedips_node *node, u8 bits)
hsiphash_1u32(0xabad1dea, &key) % 200;
style = "bold";
}
- swap_endian_and_apply_cidr(ip1, node->bits, bits, node->cidr);
- printk(fmt_declaration, ip1, node->cidr, style, color);
+ wg_allowedips_read_node(node, ip1, &cidr1);
+ printk(fmt_declaration, ip1, cidr1, style, color);
if (node->bit[0]) {
- swap_endian_and_apply_cidr(ip2,
- rcu_dereference_raw(node->bit[0])->bits, bits,
- node->cidr);
- printk(fmt_connection, ip1, node->cidr, ip2,
- rcu_dereference_raw(node->bit[0])->cidr);
- print_node(rcu_dereference_raw(node->bit[0]), bits);
+ wg_allowedips_read_node(rcu_dereference_raw(node->bit[0]), ip2, &cidr2);
+ printk(fmt_connection, ip1, cidr1, ip2, cidr2);
}
if (node->bit[1]) {
- swap_endian_and_apply_cidr(ip2,
- rcu_dereference_raw(node->bit[1])->bits,
- bits, node->cidr);
- printk(fmt_connection, ip1, node->cidr, ip2,
- rcu_dereference_raw(node->bit[1])->cidr);
- print_node(rcu_dereference_raw(node->bit[1]), bits);
+ wg_allowedips_read_node(rcu_dereference_raw(node->bit[1]), ip2, &cidr2);
+ printk(fmt_connection, ip1, cidr1, ip2, cidr2);
}
+ if (node->bit[0])
+ print_node(rcu_dereference_raw(node->bit[0]), bits);
+ if (node->bit[1])
+ print_node(rcu_dereference_raw(node->bit[1]), bits);
}
static __init void print_tree(struct allowedips_node __rcu *top, u8 bits)
@@ -121,8 +107,8 @@ static __init inline union nf_inet_addr horrible_cidr_to_mask(u8 cidr)
{
union nf_inet_addr mask;
- memset(&mask, 0x00, 128 / 8);
- memset(&mask, 0xff, cidr / 8);
+ memset(&mask, 0, sizeof(mask));
+ memset(&mask.all, 0xff, cidr / 8);
if (cidr % 32)
mask.all[cidr / 32] = (__force u32)htonl(
(0xFFFFFFFFUL << (32 - (cidr % 32))) & 0xFFFFFFFFUL);
@@ -149,42 +135,36 @@ horrible_mask_self(struct horrible_allowedips_node *node)
}
static __init inline bool
-horrible_match_v4(const struct horrible_allowedips_node *node,
- struct in_addr *ip)
+horrible_match_v4(const struct horrible_allowedips_node *node, struct in_addr *ip)
{
return (ip->s_addr & node->mask.ip) == node->ip.ip;
}
static __init inline bool
-horrible_match_v6(const struct horrible_allowedips_node *node,
- struct in6_addr *ip)
+horrible_match_v6(const struct horrible_allowedips_node *node, struct in6_addr *ip)
{
- return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) ==
- node->ip.ip6[0] &&
- (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) ==
- node->ip.ip6[1] &&
- (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) ==
- node->ip.ip6[2] &&
+ return (ip->in6_u.u6_addr32[0] & node->mask.ip6[0]) == node->ip.ip6[0] &&
+ (ip->in6_u.u6_addr32[1] & node->mask.ip6[1]) == node->ip.ip6[1] &&
+ (ip->in6_u.u6_addr32[2] & node->mask.ip6[2]) == node->ip.ip6[2] &&
(ip->in6_u.u6_addr32[3] & node->mask.ip6[3]) == node->ip.ip6[3];
}
static __init void
-horrible_insert_ordered(struct horrible_allowedips *table,
- struct horrible_allowedips_node *node)
+horrible_insert_ordered(struct horrible_allowedips *table, struct horrible_allowedips_node *node)
{
struct horrible_allowedips_node *other = NULL, *where = NULL;
u8 my_cidr = horrible_mask_to_cidr(node->mask);
hlist_for_each_entry(other, &table->head, table) {
- if (!memcmp(&other->mask, &node->mask,
- sizeof(union nf_inet_addr)) &&
- !memcmp(&other->ip, &node->ip,
- sizeof(union nf_inet_addr)) &&
- other->ip_version == node->ip_version) {
+ if (other->ip_version == node->ip_version &&
+ !memcmp(&other->mask, &node->mask, sizeof(union nf_inet_addr)) &&
+ !memcmp(&other->ip, &node->ip, sizeof(union nf_inet_addr))) {
other->value = node->value;
kfree(node);
return;
}
+ }
+ hlist_for_each_entry(other, &table->head, table) {
where = other;
if (horrible_mask_to_cidr(other->mask) <= my_cidr)
break;
@@ -201,8 +181,7 @@ static __init int
horrible_allowedips_insert_v4(struct horrible_allowedips *table,
struct in_addr *ip, u8 cidr, void *value)
{
- struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
- GFP_KERNEL);
+ struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);
if (unlikely(!node))
return -ENOMEM;
@@ -219,8 +198,7 @@ static __init int
horrible_allowedips_insert_v6(struct horrible_allowedips *table,
struct in6_addr *ip, u8 cidr, void *value)
{
- struct horrible_allowedips_node *node = kzalloc(sizeof(*node),
- GFP_KERNEL);
+ struct horrible_allowedips_node *node = kzalloc(sizeof(*node), GFP_KERNEL);
if (unlikely(!node))
return -ENOMEM;
@@ -234,39 +212,43 @@ horrible_allowedips_insert_v6(struct horrible_allowedips *table,
}
static __init void *
-horrible_allowedips_lookup_v4(struct horrible_allowedips *table,
- struct in_addr *ip)
+horrible_allowedips_lookup_v4(struct horrible_allowedips *table, struct in_addr *ip)
{
struct horrible_allowedips_node *node;
- void *ret = NULL;
hlist_for_each_entry(node, &table->head, table) {
- if (node->ip_version != 4)
- continue;
- if (horrible_match_v4(node, ip)) {
- ret = node->value;
- break;
- }
+ if (node->ip_version == 4 && horrible_match_v4(node, ip))
+ return node->value;
}
- return ret;
+ return NULL;
}
static __init void *
-horrible_allowedips_lookup_v6(struct horrible_allowedips *table,
- struct in6_addr *ip)
+horrible_allowedips_lookup_v6(struct horrible_allowedips *table, struct in6_addr *ip)
{
struct horrible_allowedips_node *node;
- void *ret = NULL;
hlist_for_each_entry(node, &table->head, table) {
- if (node->ip_version != 6)
+ if (node->ip_version == 6 && horrible_match_v6(node, ip))
+ return node->value;
+ }
+ return NULL;
+}
+
+
+static __init void
+horrible_allowedips_remove_by_value(struct horrible_allowedips *table, void *value)
+{
+ struct horrible_allowedips_node *node;
+ struct hlist_node *h;
+
+ hlist_for_each_entry_safe(node, h, &table->head, table) {
+ if (node->value != value)
continue;
- if (horrible_match_v6(node, ip)) {
- ret = node->value;
- break;
- }
+ hlist_del(&node->table);
+ kfree(node);
}
- return ret;
+
}
static __init bool randomized_test(void)
@@ -296,6 +278,7 @@ static __init bool randomized_test(void)
goto free;
}
kref_init(&peers[i]->refcount);
+ INIT_LIST_HEAD(&peers[i]->allowedips_list);
}
mutex_lock(&mutex);
@@ -333,7 +316,7 @@ static __init bool randomized_test(void)
if (wg_allowedips_insert_v4(&t,
(struct in_addr *)mutated,
cidr, peer, &mutex) < 0) {
- pr_err("allowedips random malloc: FAIL\n");
+ pr_err("allowedips random self-test malloc: FAIL\n");
goto free_locked;
}
if (horrible_allowedips_insert_v4(&h,
@@ -396,23 +379,33 @@ static __init bool randomized_test(void)
print_tree(t.root6, 128);
}
- for (i = 0; i < NUM_QUERIES; ++i) {
- prandom_bytes(ip, 4);
- if (lookup(t.root4, 32, ip) !=
- horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
- pr_err("allowedips random self-test: FAIL\n");
- goto free;
+ for (j = 0;; ++j) {
+ for (i = 0; i < NUM_QUERIES; ++i) {
+ prandom_bytes(ip, 4);
+ if (lookup(t.root4, 32, ip) != horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip)) {
+ horrible_allowedips_lookup_v4(&h, (struct in_addr *)ip);
+ pr_err("allowedips random v4 self-test: FAIL\n");
+ goto free;
+ }
+ prandom_bytes(ip, 16);
+ if (lookup(t.root6, 128, ip) != horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
+ pr_err("allowedips random v6 self-test: FAIL\n");
+ goto free;
+ }
}
+ if (j >= NUM_PEERS)
+ break;
+ mutex_lock(&mutex);
+ wg_allowedips_remove_by_peer(&t, peers[j], &mutex);
+ mutex_unlock(&mutex);
+ horrible_allowedips_remove_by_value(&h, peers[j]);
}
- for (i = 0; i < NUM_QUERIES; ++i) {
- prandom_bytes(ip, 16);
- if (lookup(t.root6, 128, ip) !=
- horrible_allowedips_lookup_v6(&h, (struct in6_addr *)ip)) {
- pr_err("allowedips random self-test: FAIL\n");
- goto free;
- }
+ if (t.root4 || t.root6) {
+ pr_err("allowedips random self-test removal: FAIL\n");
+ goto free;
}
+
ret = true;
free:
diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c
index d9ad850daa79..8c496b747108 100644
--- a/drivers/net/wireguard/socket.c
+++ b/drivers/net/wireguard/socket.c
@@ -430,7 +430,7 @@ void wg_socket_reinit(struct wg_device *wg, struct sock *new4,
if (new4)
wg->incoming_port = ntohs(inet_sk(new4)->inet_sport);
mutex_unlock(&wg->socket_update_lock);
- synchronize_rcu();
+ synchronize_net();
sock_free(old4);
sock_free(old6);
}
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 977acab0360a..03fe62837557 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -514,10 +514,36 @@ EXPORT_SYMBOL_GPL(mt76_free_device);
static void mt76_rx_release_amsdu(struct mt76_phy *phy, enum mt76_rxq_id q)
{
struct sk_buff *skb = phy->rx_amsdu[q].head;
+ struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
struct mt76_dev *dev = phy->dev;
phy->rx_amsdu[q].head = NULL;
phy->rx_amsdu[q].tail = NULL;
+
+ /*
+ * Validate if the amsdu has a proper first subframe.
+ * A single MSDU can be parsed as A-MSDU when the unauthenticated A-MSDU
+ * flag of the QoS header gets flipped. In such cases, the first
+ * subframe has a LLC/SNAP header in the location of the destination
+ * address.
+ */
+ if (skb_shinfo(skb)->frag_list) {
+ int offset = 0;
+
+ if (!(status->flag & RX_FLAG_8023)) {
+ offset = ieee80211_get_hdrlen_from_skb(skb);
+
+ if ((status->flag &
+ (RX_FLAG_DECRYPTED | RX_FLAG_IV_STRIPPED)) ==
+ RX_FLAG_DECRYPTED)
+ offset += 8;
+ }
+
+ if (ether_addr_equal(skb->data + offset, rfc1042_header)) {
+ dev_kfree_skb(skb);
+ return;
+ }
+ }
__skb_queue_tail(&dev->rx_skb[q], skb);
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index 86341d1f82f3..d20f05a7717d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -510,7 +510,6 @@ void mt7615_init_device(struct mt7615_dev *dev)
mutex_init(&dev->pm.mutex);
init_waitqueue_head(&dev->pm.wait);
spin_lock_init(&dev->pm.txq_lock);
- set_bit(MT76_STATE_PM, &dev->mphy.state);
INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7615_mac_work);
INIT_DELAYED_WORK(&dev->phy.scan_work, mt7615_scan_work);
INIT_DELAYED_WORK(&dev->coredump.work, mt7615_coredump_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index f81a17d56008..e2dcfee6be81 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -1912,8 +1912,9 @@ void mt7615_pm_wake_work(struct work_struct *work)
napi_schedule(&dev->mt76.napi[i]);
mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_WM], false);
- ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
- MT7615_WATCHDOG_TIME);
+ if (test_bit(MT76_STATE_RUNNING, &mphy->state))
+ ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
+ MT7615_WATCHDOG_TIME);
}
ieee80211_wake_queues(mphy->hw);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
index 17fe4187d1de..d1be78b0711c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c
@@ -51,16 +51,13 @@ mt7663s_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
return ret;
}
-static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
+static int __mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
{
struct sdio_func *func = dev->mt76.sdio.func;
struct mt76_phy *mphy = &dev->mt76.phy;
u32 status;
int ret;
- if (!test_and_clear_bit(MT76_STATE_PM, &mphy->state))
- goto out;
-
sdio_claim_host(func);
sdio_writel(func, WHLPCR_FW_OWN_REQ_CLR, MCR_WHLPCR, NULL);
@@ -76,13 +73,21 @@ static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
}
sdio_release_host(func);
-
-out:
dev->pm.last_activity = jiffies;
return 0;
}
+static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev)
+{
+ struct mt76_phy *mphy = &dev->mt76.phy;
+
+ if (test_and_clear_bit(MT76_STATE_PM, &mphy->state))
+ return __mt7663s_mcu_drv_pmctrl(dev);
+
+ return 0;
+}
+
static int mt7663s_mcu_fw_pmctrl(struct mt7615_dev *dev)
{
struct sdio_func *func = dev->mt76.sdio.func;
@@ -123,7 +128,7 @@ int mt7663s_mcu_init(struct mt7615_dev *dev)
struct mt7615_mcu_ops *mcu_ops;
int ret;
- ret = mt7663s_mcu_drv_pmctrl(dev);
+ ret = __mt7663s_mcu_drv_pmctrl(dev);
if (ret)
return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
index c55698f9c49a..028ff432d811 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_mcu.c
@@ -55,10 +55,7 @@ int mt7663u_mcu_init(struct mt7615_dev *dev)
dev->mt76.mcu_ops = &mt7663u_mcu_ops,
- /* usb does not support runtime-pm */
- clear_bit(MT76_STATE_PM, &dev->mphy.state);
mt76_set(dev, MT_UDMA_TX_QSEL, MT_FW_DL_EN);
-
if (test_and_clear_bit(MT76_STATE_POWER_OFF, &dev->mphy.state)) {
mt7615_mcu_restart(&dev->mt76);
if (!mt76_poll_msec(dev, MT_CONN_ON_MISC,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index fe0ab5e5ff81..619561606f96 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -721,6 +721,10 @@ void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb,
phy->phy_type = mt76_connac_get_phy_mode_v2(mphy, vif, band, sta);
phy->basic_rate = cpu_to_le16((u16)vif->bss_conf.basic_rates);
phy->rcpi = rcpi;
+ phy->ampdu = FIELD_PREP(IEEE80211_HT_AMPDU_PARM_FACTOR,
+ sta->ht_cap.ampdu_factor) |
+ FIELD_PREP(IEEE80211_HT_AMPDU_PARM_DENSITY,
+ sta->ht_cap.ampdu_density);
tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra_info));
ra_info = (struct sta_rec_ra_info *)tlv;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 5847f943e8da..b795e7245c07 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -87,7 +87,7 @@ static const struct ieee80211_ops mt76x0e_ops = {
.reconfig_complete = mt76x02_reconfig_complete,
};
-static int mt76x0e_register_device(struct mt76x02_dev *dev)
+static int mt76x0e_init_hardware(struct mt76x02_dev *dev, bool resume)
{
int err;
@@ -100,9 +100,11 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev)
if (err < 0)
return err;
- err = mt76x02_dma_init(dev);
- if (err < 0)
- return err;
+ if (!resume) {
+ err = mt76x02_dma_init(dev);
+ if (err < 0)
+ return err;
+ }
err = mt76x0_init_hardware(dev);
if (err < 0)
@@ -123,6 +125,17 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev)
mt76_clear(dev, 0x110, BIT(9));
mt76_set(dev, MT_MAX_LEN_CFG, BIT(13));
+ return 0;
+}
+
+static int mt76x0e_register_device(struct mt76x02_dev *dev)
+{
+ int err;
+
+ err = mt76x0e_init_hardware(dev, false);
+ if (err < 0)
+ return err;
+
err = mt76x0_register_device(dev);
if (err < 0)
return err;
@@ -167,6 +180,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
if (ret)
return ret;
+ mt76_pci_disable_aspm(pdev);
+
mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt76x0e_ops,
&drv_ops);
if (!mdev)
@@ -220,6 +235,60 @@ mt76x0e_remove(struct pci_dev *pdev)
mt76_free_device(mdev);
}
+#ifdef CONFIG_PM
+static int mt76x0e_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct mt76_dev *mdev = pci_get_drvdata(pdev);
+ struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+ int i;
+
+ mt76_worker_disable(&mdev->tx_worker);
+ for (i = 0; i < ARRAY_SIZE(mdev->phy.q_tx); i++)
+ mt76_queue_tx_cleanup(dev, mdev->phy.q_tx[i], true);
+ for (i = 0; i < ARRAY_SIZE(mdev->q_mcu); i++)
+ mt76_queue_tx_cleanup(dev, mdev->q_mcu[i], true);
+ napi_disable(&mdev->tx_napi);
+
+ mt76_for_each_q_rx(mdev, i)
+ napi_disable(&mdev->napi[i]);
+
+ mt76x02_dma_disable(dev);
+ mt76x02_mcu_cleanup(dev);
+ mt76x0_chip_onoff(dev, false, false);
+
+ pci_enable_wake(pdev, pci_choose_state(pdev, state), true);
+ pci_save_state(pdev);
+
+ return pci_set_power_state(pdev, pci_choose_state(pdev, state));
+}
+
+static int mt76x0e_resume(struct pci_dev *pdev)
+{
+ struct mt76_dev *mdev = pci_get_drvdata(pdev);
+ struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76);
+ int err, i;
+
+ err = pci_set_power_state(pdev, PCI_D0);
+ if (err)
+ return err;
+
+ pci_restore_state(pdev);
+
+ mt76_worker_enable(&mdev->tx_worker);
+
+ mt76_for_each_q_rx(mdev, i) {
+ mt76_queue_rx_reset(dev, i);
+ napi_enable(&mdev->napi[i]);
+ napi_schedule(&mdev->napi[i]);
+ }
+
+ napi_enable(&mdev->tx_napi);
+ napi_schedule(&mdev->tx_napi);
+
+ return mt76x0e_init_hardware(dev, true);
+}
+#endif /* CONFIG_PM */
+
static const struct pci_device_id mt76x0e_device_table[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7610) },
{ PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7630) },
@@ -237,6 +306,10 @@ static struct pci_driver mt76x0e_driver = {
.id_table = mt76x0e_device_table,
.probe = mt76x0e_probe,
.remove = mt76x0e_remove,
+#ifdef CONFIG_PM
+ .suspend = mt76x0e_suspend,
+ .resume = mt76x0e_resume,
+#endif /* CONFIG_PM */
};
module_pci_driver(mt76x0e_driver);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index fe28bf4050c4..1763ea0614ce 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -76,8 +76,8 @@ mt7921_init_wiphy(struct ieee80211_hw *hw)
struct wiphy *wiphy = hw->wiphy;
hw->queues = 4;
- hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
- hw->max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+ hw->max_rx_aggregation_subframes = 64;
+ hw->max_tx_aggregation_subframes = 128;
hw->radiotap_timestamp.units_pos =
IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 214bd1859792..decf2d5f0ce3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -1404,8 +1404,9 @@ void mt7921_pm_wake_work(struct work_struct *work)
napi_schedule(&dev->mt76.napi[i]);
mt76_connac_pm_dequeue_skbs(mphy, &dev->pm);
mt7921_tx_cleanup(dev);
- ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
- MT7921_WATCHDOG_TIME);
+ if (test_bit(MT76_STATE_RUNNING, &mphy->state))
+ ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
+ MT7921_WATCHDOG_TIME);
}
ieee80211_wake_queues(mphy->hw);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index f4c27aa41048..97a0ef331ac3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -74,8 +74,7 @@ mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band,
IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G;
else if (band == NL80211_BAND_5GHZ)
he_cap_elem->phy_cap_info[0] =
- IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
- IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G;
+ IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G;
he_cap_elem->phy_cap_info[1] =
IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 5f3d56d570a5..67dc4b4cc094 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -402,20 +402,22 @@ static void
mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb,
u16 wlan_idx)
{
- struct mt7921_mcu_wlan_info_event *wtbl_info =
- (struct mt7921_mcu_wlan_info_event *)(skb->data);
- struct rate_info rate = {};
- u8 curr_idx = wtbl_info->rate_info.rate_idx;
- u16 curr = le16_to_cpu(wtbl_info->rate_info.rate[curr_idx]);
- struct mt7921_mcu_peer_cap peer = wtbl_info->peer_cap;
+ struct mt7921_mcu_wlan_info_event *wtbl_info;
struct mt76_phy *mphy = &dev->mphy;
struct mt7921_sta_stats *stats;
+ struct rate_info rate = {};
struct mt7921_sta *msta;
struct mt76_wcid *wcid;
+ u8 idx;
if (wlan_idx >= MT76_N_WCIDS)
return;
+ wtbl_info = (struct mt7921_mcu_wlan_info_event *)skb->data;
+ idx = wtbl_info->rate_info.rate_idx;
+ if (idx >= ARRAY_SIZE(wtbl_info->rate_info.rate))
+ return;
+
rcu_read_lock();
wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
@@ -426,7 +428,8 @@ mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb,
stats = &msta->stats;
/* current rate */
- mt7921_mcu_tx_rate_parse(mphy, &peer, &rate, curr);
+ mt7921_mcu_tx_rate_parse(mphy, &wtbl_info->peer_cap, &rate,
+ le16_to_cpu(wtbl_info->rate_info.rate[idx]));
stats->tx_rate = rate;
out:
rcu_read_unlock();
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 565deea6ffe8..8612f8fc86c1 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -830,6 +830,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_proto_hdr);
struct virtchnl_proto_hdrs {
u8 tunnel_level;
+ u8 pad[3];
/**
* specify where protocol header start from.
* 0 - from the outer layer
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6d16eed6850e..eb86e80e4643 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1289,6 +1289,8 @@ enum mlx5_fc_bulk_alloc_bitmask {
#define MLX5_FC_BULK_NUM_FCS(fc_enum) (MLX5_FC_BULK_SIZE_FACTOR * (fc_enum))
+#define MLX5_FT_MAX_MULTIPATH_LEVEL 63
+
enum {
MLX5_STEERING_FORMAT_CONNECTX_5 = 0,
MLX5_STEERING_FORMAT_CONNECTX_6DX = 1,
diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h
index 48ecca8530ff..b655d8666f55 100644
--- a/include/net/caif/caif_dev.h
+++ b/include/net/caif/caif_dev.h
@@ -119,7 +119,7 @@ void caif_free_client(struct cflayer *adap_layer);
* The link_support layer is used to add any Link Layer specific
* framing.
*/
-void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
struct cflayer *link_support, int head_room,
struct cflayer **layer, int (**rcv_func)(
struct sk_buff *, struct net_device *,
diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h
index 2aa5e91d8457..8819ff4db35a 100644
--- a/include/net/caif/cfcnfg.h
+++ b/include/net/caif/cfcnfg.h
@@ -62,7 +62,7 @@ void cfcnfg_remove(struct cfcnfg *cfg);
* @fcs: Specify if checksum is used in CAIF Framing Layer.
* @head_room: Head space needed by link specific protocol.
*/
-void
+int
cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
struct net_device *dev, struct cflayer *phy_layer,
enum cfcnfg_phy_preference pref,
diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h
index 14a55e03bb3c..67cce8757175 100644
--- a/include/net/caif/cfserl.h
+++ b/include/net/caif/cfserl.h
@@ -9,4 +9,5 @@
#include <net/caif/caif_layer.h>
struct cflayer *cfserl_create(int instance, bool use_stx);
+void cfserl_release(struct cflayer *layer);
#endif
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 6783164428f1..148f5d8ee5ab 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1516,16 +1516,10 @@ struct nft_trans_chain {
struct nft_trans_table {
bool update;
- u8 state;
- u32 flags;
};
#define nft_trans_table_update(trans) \
(((struct nft_trans_table *)trans->data)->update)
-#define nft_trans_table_state(trans) \
- (((struct nft_trans_table *)trans->data)->state)
-#define nft_trans_table_flags(trans) \
- (((struct nft_trans_table *)trans->data)->flags)
struct nft_trans_elem {
struct nft_set *set;
diff --git a/include/net/tls.h b/include/net/tls.h
index 3eccb525e8f7..8341a8d1e807 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -193,7 +193,11 @@ struct tls_offload_context_tx {
(sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX)
enum tls_context_flags {
- TLS_RX_SYNC_RUNNING = 0,
+ /* tls_device_down was called after the netdev went down, device state
+ * was released, and kTLS works in software, even though rx_conf is
+ * still TLS_HW (needed for transition).
+ */
+ TLS_RX_DEV_DEGRADED = 0,
/* Unlike RX where resync is driven entirely by the core in TX only
* the driver knows when things went out of sync, so we need the flag
* to be atomic.
@@ -266,6 +270,7 @@ struct tls_context {
/* cache cold stuff */
struct proto *sk_proto;
+ struct sock *sk;
void (*sk_destruct)(struct sock *sk);
@@ -448,6 +453,9 @@ static inline u16 tls_user_config(struct tls_context *ctx, bool tx)
struct sk_buff *
tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
struct sk_buff *skb);
+struct sk_buff *
+tls_validate_xmit_skb_sw(struct sock *sk, struct net_device *dev,
+ struct sk_buff *skb);
static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
{
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index f0c35ce8628c..4fe842c3a3a9 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -54,7 +54,7 @@
#define VIRTIO_ID_SOUND 25 /* virtio sound */
#define VIRTIO_ID_FS 26 /* virtio filesystem */
#define VIRTIO_ID_PMEM 27 /* virtio pmem */
-#define VIRTIO_ID_BT 28 /* virtio bluetooth */
#define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_BT 40 /* virtio bluetooth */
#endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 73443498d88f..a2f1f15ce432 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -14,6 +14,7 @@
#include <linux/jiffies.h>
#include <linux/pid_namespace.h>
#include <linux/proc_ns.h>
+#include <linux/security.h>
#include "../../lib/kstrtox.h"
@@ -1069,11 +1070,13 @@ bpf_base_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_probe_read_user:
return &bpf_probe_read_user_proto;
case BPF_FUNC_probe_read_kernel:
- return &bpf_probe_read_kernel_proto;
+ return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+ NULL : &bpf_probe_read_kernel_proto;
case BPF_FUNC_probe_read_user_str:
return &bpf_probe_read_user_str_proto;
case BPF_FUNC_probe_read_kernel_str:
- return &bpf_probe_read_kernel_str_proto;
+ return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+ NULL : &bpf_probe_read_kernel_str_proto;
case BPF_FUNC_snprintf_btf:
return &bpf_snprintf_btf_proto;
case BPF_FUNC_snprintf:
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d2d7cf6cfe83..7a52bc172841 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -215,16 +215,11 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = {
static __always_inline int
bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
{
- int ret = security_locked_down(LOCKDOWN_BPF_READ);
+ int ret;
- if (unlikely(ret < 0))
- goto fail;
ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
- goto fail;
- return ret;
-fail:
- memset(dst, 0, size);
+ memset(dst, 0, size);
return ret;
}
@@ -246,10 +241,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_proto = {
static __always_inline int
bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
{
- int ret = security_locked_down(LOCKDOWN_BPF_READ);
-
- if (unlikely(ret < 0))
- goto fail;
+ int ret;
/*
* The strncpy_from_kernel_nofault() call will likely not fill the
@@ -262,11 +254,7 @@ bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr)
*/
ret = strncpy_from_kernel_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
- goto fail;
-
- return ret;
-fail:
- memset(dst, 0, size);
+ memset(dst, 0, size);
return ret;
}
@@ -1011,16 +999,20 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_probe_read_user:
return &bpf_probe_read_user_proto;
case BPF_FUNC_probe_read_kernel:
- return &bpf_probe_read_kernel_proto;
+ return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+ NULL : &bpf_probe_read_kernel_proto;
case BPF_FUNC_probe_read_user_str:
return &bpf_probe_read_user_str_proto;
case BPF_FUNC_probe_read_kernel_str:
- return &bpf_probe_read_kernel_str_proto;
+ return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+ NULL : &bpf_probe_read_kernel_str_proto;
#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
case BPF_FUNC_probe_read:
- return &bpf_probe_read_compat_proto;
+ return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+ NULL : &bpf_probe_read_compat_proto;
case BPF_FUNC_probe_read_str:
- return &bpf_probe_read_compat_str_proto;
+ return security_locked_down(LOCKDOWN_BPF_READ) < 0 ?
+ NULL : &bpf_probe_read_compat_str_proto;
#endif
#ifdef CONFIG_CGROUPS
case BPF_FUNC_get_current_cgroup_id:
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index aa214834c374..25484bb0773d 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1610,8 +1610,13 @@ setup_failed:
} else {
/* Init failed, cleanup */
flush_work(&hdev->tx_work);
- flush_work(&hdev->cmd_work);
+
+ /* Since hci_rx_work() is possible to awake new cmd_work
+ * it should be flushed first to avoid unexpected call of
+ * hci_cmd_work()
+ */
flush_work(&hdev->rx_work);
+ flush_work(&hdev->cmd_work);
skb_queue_purge(&hdev->cmd_q);
skb_queue_purge(&hdev->rx_q);
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 6ef98a887571..e8d53af7c6a6 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -762,7 +762,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event)
/* Detach sockets from device */
read_lock(&hci_sk_list.lock);
sk_for_each(sk, &hci_sk_list.head) {
- bh_lock_sock_nested(sk);
+ lock_sock(sk);
if (hci_pi(sk)->hdev == hdev) {
hci_pi(sk)->hdev = NULL;
sk->sk_err = EPIPE;
@@ -771,7 +771,7 @@ void hci_sock_dev_event(struct hci_dev *hdev, int event)
hci_dev_put(hdev);
}
- bh_unlock_sock(sk);
+ release_sock(sk);
}
read_unlock(&hci_sk_list.lock);
}
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index c10e5a55758d..440139706130 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -308,7 +308,7 @@ static void dev_flowctrl(struct net_device *dev, int on)
caifd_put(caifd);
}
-void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
struct cflayer *link_support, int head_room,
struct cflayer **layer,
int (**rcv_func)(struct sk_buff *, struct net_device *,
@@ -319,11 +319,12 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
enum cfcnfg_phy_preference pref;
struct cfcnfg *cfg = get_cfcnfg(dev_net(dev));
struct caif_device_entry_list *caifdevs;
+ int res;
caifdevs = caif_device_list(dev_net(dev));
caifd = caif_device_alloc(dev);
if (!caifd)
- return;
+ return -ENOMEM;
*layer = &caifd->layer;
spin_lock_init(&caifd->flow_lock);
@@ -344,7 +345,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
strlcpy(caifd->layer.name, dev->name,
sizeof(caifd->layer.name));
caifd->layer.transmit = transmit;
- cfcnfg_add_phy_layer(cfg,
+ res = cfcnfg_add_phy_layer(cfg,
dev,
&caifd->layer,
pref,
@@ -354,6 +355,7 @@ void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
mutex_unlock(&caifdevs->lock);
if (rcv_func)
*rcv_func = receive;
+ return res;
}
EXPORT_SYMBOL(caif_enroll_dev);
@@ -368,6 +370,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
struct cflayer *layer, *link_support;
int head_room = 0;
struct caif_device_entry_list *caifdevs;
+ int res;
cfg = get_cfcnfg(dev_net(dev));
caifdevs = caif_device_list(dev_net(dev));
@@ -393,8 +396,10 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
break;
}
}
- caif_enroll_dev(dev, caifdev, link_support, head_room,
+ res = caif_enroll_dev(dev, caifdev, link_support, head_room,
&layer, NULL);
+ if (res)
+ cfserl_release(link_support);
caifdev->flowctrl = dev_flowctrl;
break;
diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
index a0116b9503d9..b02e1292f7f1 100644
--- a/net/caif/caif_usb.c
+++ b/net/caif/caif_usb.c
@@ -115,6 +115,11 @@ static struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN],
return (struct cflayer *) this;
}
+static void cfusbl_release(struct cflayer *layer)
+{
+ kfree(layer);
+}
+
static struct packet_type caif_usb_type __read_mostly = {
.type = cpu_to_be16(ETH_P_802_EX1),
};
@@ -127,6 +132,7 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what,
struct cflayer *layer, *link_support;
struct usbnet *usbnet;
struct usb_device *usbdev;
+ int res;
/* Check whether we have a NCM device, and find its VID/PID. */
if (!(dev->dev.parent && dev->dev.parent->driver &&
@@ -169,8 +175,11 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what,
if (dev->num_tx_queues > 1)
pr_warn("USB device uses more than one tx queue\n");
- caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN,
+ res = caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN,
&layer, &caif_usb_type.func);
+ if (res)
+ goto err;
+
if (!pack_added)
dev_add_pack(&caif_usb_type);
pack_added = true;
@@ -178,6 +187,9 @@ static int cfusbl_device_notify(struct notifier_block *me, unsigned long what,
strlcpy(layer->name, dev->name, sizeof(layer->name));
return 0;
+err:
+ cfusbl_release(link_support);
+ return res;
}
static struct notifier_block caif_device_notifier = {
diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c
index 399239a14420..cac30e676ac9 100644
--- a/net/caif/cfcnfg.c
+++ b/net/caif/cfcnfg.c
@@ -450,7 +450,7 @@ unlock:
rcu_read_unlock();
}
-void
+int
cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
struct net_device *dev, struct cflayer *phy_layer,
enum cfcnfg_phy_preference pref,
@@ -459,7 +459,7 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
{
struct cflayer *frml;
struct cfcnfg_phyinfo *phyinfo = NULL;
- int i;
+ int i, res = 0;
u8 phyid;
mutex_lock(&cnfg->lock);
@@ -473,12 +473,15 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
goto got_phyid;
}
pr_warn("Too many CAIF Link Layers (max 6)\n");
+ res = -EEXIST;
goto out;
got_phyid:
phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC);
- if (!phyinfo)
+ if (!phyinfo) {
+ res = -ENOMEM;
goto out_err;
+ }
phy_layer->id = phyid;
phyinfo->pref = pref;
@@ -492,8 +495,10 @@ got_phyid:
frml = cffrml_create(phyid, fcs);
- if (!frml)
+ if (!frml) {
+ res = -ENOMEM;
goto out_err;
+ }
phyinfo->frm_layer = frml;
layer_set_up(frml, cnfg->mux);
@@ -511,11 +516,12 @@ got_phyid:
list_add_rcu(&phyinfo->node, &cnfg->phys);
out:
mutex_unlock(&cnfg->lock);
- return;
+ return res;
out_err:
kfree(phyinfo);
mutex_unlock(&cnfg->lock);
+ return res;
}
EXPORT_SYMBOL(cfcnfg_add_phy_layer);
diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c
index e11725a4bb0e..40cd57ad0a0f 100644
--- a/net/caif/cfserl.c
+++ b/net/caif/cfserl.c
@@ -31,6 +31,11 @@ static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt);
static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
int phyid);
+void cfserl_release(struct cflayer *layer)
+{
+ kfree(layer);
+}
+
struct cflayer *cfserl_create(int instance, bool use_stx)
{
struct cfserl *this = kzalloc(sizeof(struct cfserl), GFP_ATOMIC);
diff --git a/net/compat.c b/net/compat.c
index ddd15af3a283..210fc3b4d0d8 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -177,7 +177,7 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk,
if (kcmlen > stackbuf_size)
kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL);
if (kcmsg == NULL)
- return -ENOBUFS;
+ return -ENOMEM;
/* Now copy them over neatly. */
memset(kcmsg, 0, kcmlen);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 464f56408247..5260bdfb2403 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -799,7 +799,6 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
case DEVLINK_PORT_FLAVOUR_PHYSICAL:
case DEVLINK_PORT_FLAVOUR_CPU:
case DEVLINK_PORT_FLAVOUR_DSA:
- case DEVLINK_PORT_FLAVOUR_VIRTUAL:
if (nla_put_u32(msg, DEVLINK_ATTR_PORT_NUMBER,
attrs->phys.port_number))
return -EMSGSIZE;
@@ -9294,6 +9293,13 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
if (n < len && attrs->split)
n += snprintf(name + n, len - n, "s%u",
attrs->phys.split_subport_number);
+ if (!attrs->split)
+ n = snprintf(name, len, "p%u", attrs->phys.port_number);
+ else
+ n = snprintf(name, len, "p%us%u",
+ attrs->phys.port_number,
+ attrs->phys.split_subport_number);
+
break;
case DEVLINK_PORT_FLAVOUR_CPU:
case DEVLINK_PORT_FLAVOUR_DSA:
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index cd80ffed6d26..a9f937975080 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -1168,7 +1168,7 @@ static void notify_rule_change(int event, struct fib_rule *rule,
{
struct net *net;
struct sk_buff *skb;
- int err = -ENOBUFS;
+ int err = -ENOMEM;
net = ops->fro_net;
skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dbf59b2d5700..cd87c7661c72 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4830,8 +4830,10 @@ static int rtnl_bridge_notify(struct net_device *dev)
if (err < 0)
goto errout;
- if (!skb->len)
+ if (!skb->len) {
+ err = -EINVAL;
goto errout;
+ }
rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
return 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index bd887cb075ce..ddfa88082a2b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -867,10 +867,18 @@ void sock_set_rcvbuf(struct sock *sk, int val)
}
EXPORT_SYMBOL(sock_set_rcvbuf);
+static void __sock_set_mark(struct sock *sk, u32 val)
+{
+ if (val != sk->sk_mark) {
+ sk->sk_mark = val;
+ sk_dst_reset(sk);
+ }
+}
+
void sock_set_mark(struct sock *sk, u32 val)
{
lock_sock(sk);
- sk->sk_mark = val;
+ __sock_set_mark(sk, val);
release_sock(sk);
}
EXPORT_SYMBOL(sock_set_mark);
@@ -1139,10 +1147,10 @@ set_sndbuf:
case SO_MARK:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
ret = -EPERM;
- } else if (val != sk->sk_mark) {
- sk->sk_mark = val;
- sk_dst_reset(sk);
+ break;
}
+
+ __sock_set_mark(sk, val);
break;
case SO_RXQ_OVFL:
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 008c1ec6e20c..122ad5833fb1 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -64,7 +64,7 @@
#define DSA_8021Q_SUBVLAN_HI_SHIFT 9
#define DSA_8021Q_SUBVLAN_HI_MASK GENMASK(9, 9)
#define DSA_8021Q_SUBVLAN_LO_SHIFT 4
-#define DSA_8021Q_SUBVLAN_LO_MASK GENMASK(4, 3)
+#define DSA_8021Q_SUBVLAN_LO_MASK GENMASK(5, 4)
#define DSA_8021Q_SUBVLAN_HI(x) (((x) & GENMASK(2, 2)) >> 2)
#define DSA_8021Q_SUBVLAN_LO(x) ((x) & GENMASK(1, 0))
#define DSA_8021Q_SUBVLAN(x) \
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 0c1b0770c59e..29bf97640166 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -680,8 +680,10 @@ int ieee802154_llsec_getparams(struct sk_buff *skb, struct genl_info *info)
nla_put_u8(msg, IEEE802154_ATTR_LLSEC_SECLEVEL, params.out_level) ||
nla_put_u32(msg, IEEE802154_ATTR_LLSEC_FRAME_COUNTER,
be32_to_cpu(params.frame_counter)) ||
- ieee802154_llsec_fill_key_id(msg, &params.out_key))
+ ieee802154_llsec_fill_key_id(msg, &params.out_key)) {
+ rc = -ENOBUFS;
goto out_free;
+ }
dev_put(dev);
@@ -1184,7 +1186,7 @@ static int llsec_iter_devkeys(struct llsec_dump_data *data)
{
struct ieee802154_llsec_device *dpos;
struct ieee802154_llsec_device_key *kpos;
- int rc = 0, idx = 0, idx2;
+ int idx = 0, idx2;
list_for_each_entry(dpos, &data->table->devices, list) {
if (idx++ < data->s_idx)
@@ -1200,7 +1202,7 @@ static int llsec_iter_devkeys(struct llsec_dump_data *data)
data->nlmsg_seq,
dpos->hwaddr, kpos,
data->dev)) {
- return rc = -EMSGSIZE;
+ return -EMSGSIZE;
}
data->s_idx2++;
@@ -1209,7 +1211,7 @@ static int llsec_iter_devkeys(struct llsec_dump_data *data)
data->s_idx++;
}
- return rc;
+ return 0;
}
int ieee802154_llsec_dump_devkeys(struct sk_buff *skb,
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 2cdc7e63fe17..88215b5c93aa 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -241,8 +241,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
}
if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
- nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name))
+ nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name)) {
+ rc = -EMSGSIZE;
goto nla_put_failure;
+ }
dev_put(dev);
wpan_phy_put(phy);
diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c
index 05f6bd89a7dd..0cf2374c143b 100644
--- a/net/ieee802154/nl802154.c
+++ b/net/ieee802154/nl802154.c
@@ -1298,19 +1298,20 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla,
if (!nla || nla_parse_nested_deprecated(attrs, NL802154_DEV_ADDR_ATTR_MAX, nla, nl802154_dev_addr_policy, NULL))
return -EINVAL;
- if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] ||
- !attrs[NL802154_DEV_ADDR_ATTR_MODE] ||
- !(attrs[NL802154_DEV_ADDR_ATTR_SHORT] ||
- attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]))
+ if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || !attrs[NL802154_DEV_ADDR_ATTR_MODE])
return -EINVAL;
addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]);
addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]);
switch (addr->mode) {
case NL802154_DEV_ADDR_SHORT:
+ if (!attrs[NL802154_DEV_ADDR_ATTR_SHORT])
+ return -EINVAL;
addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]);
break;
case NL802154_DEV_ADDR_EXTENDED:
+ if (!attrs[NL802154_DEV_ADDR_ATTR_EXTENDED])
+ return -EINVAL;
addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]);
break;
default:
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index bc2f6ca97152..816d8aad5a68 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -886,7 +886,7 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d
/*
- * Copy BOOTP-supplied string if not already set.
+ * Copy BOOTP-supplied string
*/
static int __init ic_bootp_string(char *dest, char *src, int len, int max)
{
@@ -935,12 +935,15 @@ static void __init ic_do_bootp_ext(u8 *ext)
}
break;
case 12: /* Host name */
- ic_bootp_string(utsname()->nodename, ext+1, *ext,
- __NEW_UTS_LEN);
- ic_host_name_set = 1;
+ if (!ic_host_name_set) {
+ ic_bootp_string(utsname()->nodename, ext+1, *ext,
+ __NEW_UTS_LEN);
+ ic_host_name_set = 1;
+ }
break;
case 15: /* Domain name (DNS) */
- ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain));
+ if (!ic_domain[0])
+ ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain));
break;
case 17: /* Root path */
if (!root_server_path[0])
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c46889381ae4..7b756a7dc036 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3800,11 +3800,11 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
if (nh) {
if (rt->fib6_src.plen) {
NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
- goto out;
+ goto out_free;
}
if (!nexthop_get(nh)) {
NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
- goto out;
+ goto out_free;
}
rt->nh = nh;
fib6_nh = nexthop_fib6_nh(rt->nh);
@@ -3841,6 +3841,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
out:
fib6_info_release(rt);
return ERR_PTR(err);
+out_free:
+ ip_fib_metrics_put(rt->fib6_metrics);
+ kfree(rt);
+ return ERR_PTR(err);
}
int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 71b57bdb1519..e0a39b0bb4c1 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -271,6 +271,9 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
if (ipip6_tunnel_create(dev) < 0)
goto failed_free;
+ if (!parms->name[0])
+ strcpy(parms->name, dev->name);
+
return nt;
failed_free:
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 6201965bd822..1c572c8daced 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1066,6 +1066,11 @@ out_error:
goto partial_message;
}
+ if (skb_has_frag_list(head)) {
+ kfree_skb_list(skb_shinfo(head)->frag_list);
+ skb_shinfo(head)->frag_list = NULL;
+ }
+
if (head != kcm->seq_skb)
kfree_skb(head);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 3897d35fd9df..993095089990 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -956,6 +956,10 @@ static void __mptcp_update_wmem(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
+#ifdef CONFIG_LOCKDEP
+ WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
+#endif
+
if (!msk->wmem_reserved)
return;
@@ -1094,10 +1098,20 @@ out:
static void __mptcp_clean_una_wakeup(struct sock *sk)
{
+#ifdef CONFIG_LOCKDEP
+ WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock));
+#endif
__mptcp_clean_una(sk);
mptcp_write_space(sk);
}
+static void mptcp_clean_una_wakeup(struct sock *sk)
+{
+ mptcp_data_lock(sk);
+ __mptcp_clean_una_wakeup(sk);
+ mptcp_data_unlock(sk);
+}
+
static void mptcp_enter_memory_pressure(struct sock *sk)
{
struct mptcp_subflow_context *subflow;
@@ -2321,7 +2335,7 @@ static void __mptcp_retrans(struct sock *sk)
struct sock *ssk;
int ret;
- __mptcp_clean_una_wakeup(sk);
+ mptcp_clean_una_wakeup(sk);
dfrag = mptcp_rtx_head(sk);
if (!dfrag) {
if (mptcp_data_fin_enabled(msk)) {
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 2a58503e55bd..33956337c46b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -630,21 +630,20 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
/* if the sk is MP_CAPABLE, we try to fetch the client key */
if (subflow_req->mp_capable) {
- if (TCP_SKB_CB(skb)->seq != subflow_req->ssn_offset + 1) {
- /* here we can receive and accept an in-window,
- * out-of-order pkt, which will not carry the MP_CAPABLE
- * opt even on mptcp enabled paths
- */
- goto create_msk;
- }
-
+ /* we can receive and accept an in-window, out-of-order pkt,
+ * which may not carry the MP_CAPABLE opt even on mptcp enabled
+ * paths: always try to extract the peer key, and fallback
+ * for packets missing it.
+ * Even OoO DSS packets coming legitly after dropped or
+ * reordered MPC will cause fallback, but we don't have other
+ * options.
+ */
mptcp_get_options(skb, &mp_opt);
if (!mp_opt.mp_capable) {
fallback = true;
goto create_child;
}
-create_msk:
new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
if (!new_msk)
fallback = true;
@@ -1012,21 +1011,11 @@ static bool subflow_check_data_avail(struct sock *ssk)
status = get_mapping_status(ssk, msk);
trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
- if (status == MAPPING_INVALID) {
- ssk->sk_err = EBADMSG;
- goto fatal;
- }
- if (status == MAPPING_DUMMY) {
- __mptcp_do_fallback(msk);
- skb = skb_peek(&ssk->sk_receive_queue);
- subflow->map_valid = 1;
- subflow->map_seq = READ_ONCE(msk->ack_seq);
- subflow->map_data_len = skb->len;
- subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq -
- subflow->ssn_offset;
- subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
- return true;
- }
+ if (unlikely(status == MAPPING_INVALID))
+ goto fallback;
+
+ if (unlikely(status == MAPPING_DUMMY))
+ goto fallback;
if (status != MAPPING_OK)
goto no_data;
@@ -1039,10 +1028,8 @@ static bool subflow_check_data_avail(struct sock *ssk)
* MP_CAPABLE-based mapping
*/
if (unlikely(!READ_ONCE(msk->can_ack))) {
- if (!subflow->mpc_map) {
- ssk->sk_err = EBADMSG;
- goto fatal;
- }
+ if (!subflow->mpc_map)
+ goto fallback;
WRITE_ONCE(msk->remote_key, subflow->remote_key);
WRITE_ONCE(msk->ack_seq, subflow->map_seq);
WRITE_ONCE(msk->can_ack, true);
@@ -1070,17 +1057,31 @@ static bool subflow_check_data_avail(struct sock *ssk)
no_data:
subflow_sched_work_if_closed(msk, ssk);
return false;
-fatal:
- /* fatal protocol error, close the socket */
- /* This barrier is coupled with smp_rmb() in tcp_poll() */
- smp_wmb();
- ssk->sk_error_report(ssk);
- tcp_set_state(ssk, TCP_CLOSE);
- subflow->reset_transient = 0;
- subflow->reset_reason = MPTCP_RST_EMPTCP;
- tcp_send_active_reset(ssk, GFP_ATOMIC);
- subflow->data_avail = 0;
- return false;
+
+fallback:
+ /* RFC 8684 section 3.7. */
+ if (subflow->mp_join || subflow->fully_established) {
+ /* fatal protocol error, close the socket.
+ * subflow_error_report() will introduce the appropriate barriers
+ */
+ ssk->sk_err = EBADMSG;
+ ssk->sk_error_report(ssk);
+ tcp_set_state(ssk, TCP_CLOSE);
+ subflow->reset_transient = 0;
+ subflow->reset_reason = MPTCP_RST_EMPTCP;
+ tcp_send_active_reset(ssk, GFP_ATOMIC);
+ subflow->data_avail = 0;
+ return false;
+ }
+
+ __mptcp_do_fallback(msk);
+ skb = skb_peek(&ssk->sk_receive_queue);
+ subflow->map_valid = 1;
+ subflow->map_seq = READ_ONCE(msk->ack_seq);
+ subflow->map_data_len = skb->len;
+ subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
+ subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
+ return true;
}
bool mptcp_subflow_data_available(struct sock *sk)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index d45dbcba8b49..c25097092a06 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1367,7 +1367,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
ip_vs_addr_copy(svc->af, &svc->addr, &u->addr);
svc->port = u->port;
svc->fwmark = u->fwmark;
- svc->flags = u->flags;
+ svc->flags = u->flags & ~IP_VS_SVC_F_HASHED;
svc->timeout = u->timeout * HZ;
svc->netmask = u->netmask;
svc->ipvs = ipvs;
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 89e5bac384d7..dc9ca12b0489 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -664,7 +664,7 @@ int nf_conntrack_proto_init(void)
#if IS_ENABLED(CONFIG_IPV6)
cleanup_sockopt:
- nf_unregister_sockopt(&so_getorigdst6);
+ nf_unregister_sockopt(&so_getorigdst);
#endif
return ret;
}
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d63d2d8f769c..72bc759179ef 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -736,7 +736,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
goto nla_put_failure;
if (nla_put_string(skb, NFTA_TABLE_NAME, table->name) ||
- nla_put_be32(skb, NFTA_TABLE_FLAGS, htonl(table->flags)) ||
+ nla_put_be32(skb, NFTA_TABLE_FLAGS,
+ htonl(table->flags & NFT_TABLE_F_MASK)) ||
nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)) ||
nla_put_be64(skb, NFTA_TABLE_HANDLE, cpu_to_be64(table->handle),
NFTA_TABLE_PAD))
@@ -947,20 +948,22 @@ err_register_hooks:
static void nf_tables_table_disable(struct net *net, struct nft_table *table)
{
+ table->flags &= ~NFT_TABLE_F_DORMANT;
nft_table_disable(net, table, 0);
+ table->flags |= NFT_TABLE_F_DORMANT;
}
-enum {
- NFT_TABLE_STATE_UNCHANGED = 0,
- NFT_TABLE_STATE_DORMANT,
- NFT_TABLE_STATE_WAKEUP
-};
+#define __NFT_TABLE_F_INTERNAL (NFT_TABLE_F_MASK + 1)
+#define __NFT_TABLE_F_WAS_DORMANT (__NFT_TABLE_F_INTERNAL << 0)
+#define __NFT_TABLE_F_WAS_AWAKEN (__NFT_TABLE_F_INTERNAL << 1)
+#define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \
+ __NFT_TABLE_F_WAS_AWAKEN)
static int nf_tables_updtable(struct nft_ctx *ctx)
{
struct nft_trans *trans;
u32 flags;
- int ret = 0;
+ int ret;
if (!ctx->nla[NFTA_TABLE_FLAGS])
return 0;
@@ -985,21 +988,27 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
if ((flags & NFT_TABLE_F_DORMANT) &&
!(ctx->table->flags & NFT_TABLE_F_DORMANT)) {
- nft_trans_table_state(trans) = NFT_TABLE_STATE_DORMANT;
+ ctx->table->flags |= NFT_TABLE_F_DORMANT;
+ if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE))
+ ctx->table->flags |= __NFT_TABLE_F_WAS_AWAKEN;
} else if (!(flags & NFT_TABLE_F_DORMANT) &&
ctx->table->flags & NFT_TABLE_F_DORMANT) {
- ret = nf_tables_table_enable(ctx->net, ctx->table);
- if (ret >= 0)
- nft_trans_table_state(trans) = NFT_TABLE_STATE_WAKEUP;
+ ctx->table->flags &= ~NFT_TABLE_F_DORMANT;
+ if (!(ctx->table->flags & __NFT_TABLE_F_UPDATE)) {
+ ret = nf_tables_table_enable(ctx->net, ctx->table);
+ if (ret < 0)
+ goto err_register_hooks;
+
+ ctx->table->flags |= __NFT_TABLE_F_WAS_DORMANT;
+ }
}
- if (ret < 0)
- goto err;
- nft_trans_table_flags(trans) = flags;
nft_trans_table_update(trans) = true;
nft_trans_commit_list_add_tail(ctx->net, trans);
+
return 0;
-err:
+
+err_register_hooks:
nft_trans_destroy(trans);
return ret;
}
@@ -1905,7 +1914,7 @@ static int nft_chain_parse_netdev(struct net *net,
static int nft_chain_parse_hook(struct net *net,
const struct nlattr * const nla[],
struct nft_chain_hook *hook, u8 family,
- bool autoload)
+ struct netlink_ext_ack *extack, bool autoload)
{
struct nftables_pernet *nft_net = nft_pernet(net);
struct nlattr *ha[NFTA_HOOK_MAX + 1];
@@ -1935,8 +1944,10 @@ static int nft_chain_parse_hook(struct net *net,
if (nla[NFTA_CHAIN_TYPE]) {
type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE],
family, autoload);
- if (IS_ERR(type))
+ if (IS_ERR(type)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]);
return PTR_ERR(type);
+ }
}
if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
return -EOPNOTSUPP;
@@ -1945,8 +1956,11 @@ static int nft_chain_parse_hook(struct net *net,
hook->priority <= NF_IP_PRI_CONNTRACK)
return -EOPNOTSUPP;
- if (!try_module_get(type->owner))
+ if (!try_module_get(type->owner)) {
+ if (nla[NFTA_CHAIN_TYPE])
+ NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TYPE]);
return -ENOENT;
+ }
hook->type = type;
@@ -2057,7 +2071,8 @@ static int nft_chain_add(struct nft_table *table, struct nft_chain *chain)
static u64 chain_id;
static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
- u8 policy, u32 flags)
+ u8 policy, u32 flags,
+ struct netlink_ext_ack *extack)
{
const struct nlattr * const *nla = ctx->nla;
struct nft_table *table = ctx->table;
@@ -2079,7 +2094,8 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
if (flags & NFT_CHAIN_BINDING)
return -EOPNOTSUPP;
- err = nft_chain_parse_hook(net, nla, &hook, family, true);
+ err = nft_chain_parse_hook(net, nla, &hook, family, extack,
+ true);
if (err < 0)
return err;
@@ -2234,7 +2250,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
return -EEXIST;
}
err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family,
- false);
+ extack, false);
if (err < 0)
return err;
@@ -2447,7 +2463,7 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info,
extack);
}
- return nf_tables_addchain(&ctx, family, genmask, policy, flags);
+ return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack);
}
static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info,
@@ -3328,8 +3344,10 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info,
if (n == NFT_RULE_MAXEXPRS)
goto err1;
err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]);
- if (err < 0)
+ if (err < 0) {
+ NL_SET_BAD_ATTR(extack, tmp);
goto err1;
+ }
size += expr_info[n].ops->size;
n++;
}
@@ -8547,10 +8565,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
switch (trans->msg_type) {
case NFT_MSG_NEWTABLE:
if (nft_trans_table_update(trans)) {
- if (nft_trans_table_state(trans) == NFT_TABLE_STATE_DORMANT)
+ if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) {
+ nft_trans_destroy(trans);
+ break;
+ }
+ if (trans->ctx.table->flags & NFT_TABLE_F_DORMANT)
nf_tables_table_disable(net, trans->ctx.table);
- trans->ctx.table->flags = nft_trans_table_flags(trans);
+ trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE;
} else {
nft_clear(net, trans->ctx.table);
}
@@ -8768,9 +8790,17 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
switch (trans->msg_type) {
case NFT_MSG_NEWTABLE:
if (nft_trans_table_update(trans)) {
- if (nft_trans_table_state(trans) == NFT_TABLE_STATE_WAKEUP)
+ if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) {
+ nft_trans_destroy(trans);
+ break;
+ }
+ if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_DORMANT) {
nf_tables_table_disable(net, trans->ctx.table);
-
+ trans->ctx.table->flags |= NFT_TABLE_F_DORMANT;
+ } else if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_AWAKEN) {
+ trans->ctx.table->flags &= ~NFT_TABLE_F_DORMANT;
+ }
+ trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE;
nft_trans_destroy(trans);
} else {
list_del_rcu(&trans->ctx.table->list);
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index df58cd534ff5..5c622f55c9d6 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -380,10 +380,14 @@ static int
nfnl_cthelper_update(const struct nlattr * const tb[],
struct nf_conntrack_helper *helper)
{
+ u32 size;
int ret;
- if (tb[NFCTH_PRIV_DATA_LEN])
- return -EBUSY;
+ if (tb[NFCTH_PRIV_DATA_LEN]) {
+ size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
+ if (size != helper->data_len)
+ return -EBUSY;
+ }
if (tb[NFCTH_POLICY]) {
ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]);
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 0592a9456084..337e22d8b40b 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -1217,7 +1217,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj,
struct nf_conn *ct;
ct = nf_ct_get(pkt->skb, &ctinfo);
- if (!ct || ctinfo == IP_CT_UNTRACKED) {
+ if (!ct || nf_ct_is_confirmed(ct) || nf_ct_is_template(ct)) {
regs->verdict.code = NFT_BREAK;
return;
}
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 53dbe733f998..6cfd30fc0798 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -110,6 +110,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
if (!llcp_sock->service_name) {
nfc_llcp_local_put(llcp_sock->local);
llcp_sock->local = NULL;
+ llcp_sock->dev = NULL;
ret = -ENOMEM;
goto put_dev;
}
@@ -119,6 +120,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
llcp_sock->local = NULL;
kfree(llcp_sock->service_name);
llcp_sock->service_name = NULL;
+ llcp_sock->dev = NULL;
ret = -EADDRINUSE;
goto put_dev;
}
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index ec7a1c438df9..18edd9ad1410 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -984,7 +984,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
*/
cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force);
if (!cached) {
- if (!commit && tcf_ct_flow_table_lookup(p, skb, family)) {
+ if (tcf_ct_flow_table_lookup(p, skb, family)) {
skip_add = true;
goto do_nat;
}
@@ -1022,10 +1022,11 @@ do_nat:
* even if the connection is already confirmed.
*/
nf_conntrack_confirm(skb);
- } else if (!skip_add) {
- tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo);
}
+ if (!skip_add)
+ tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo);
+
out_push:
skb_push_rcsum(skb, nh_ofs);
@@ -1202,9 +1203,6 @@ static int tcf_ct_fill_params(struct net *net,
sizeof(p->zone));
}
- if (p->zone == NF_CT_DEFAULT_ZONE_ID)
- return 0;
-
nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0);
tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL);
if (!tmpl) {
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 7a69e4e608c3..5f7ac27a5264 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1523,7 +1523,8 @@ static void htb_parent_to_leaf_offload(struct Qdisc *sch,
struct Qdisc *old_q;
/* One ref for cl->leaf.q, the other for dev_queue->qdisc. */
- qdisc_refcount_inc(new_q);
+ if (new_q)
+ qdisc_refcount_inc(new_q);
old_q = htb_graft_helper(dev_queue, new_q);
WARN_ON(!(old_q->flags & TCQ_F_BUILTIN));
}
@@ -1710,10 +1711,9 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
cl->parent->common.classid,
NULL);
if (q->offload) {
- if (new_q) {
+ if (new_q)
htb_set_lockdep_class_child(new_q);
- htb_parent_to_leaf_offload(sch, dev_queue, new_q);
- }
+ htb_parent_to_leaf_offload(sch, dev_queue, new_q);
}
}
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 76a6f8c2eec4..bd9f1567aa39 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -50,6 +50,7 @@ static void tls_device_gc_task(struct work_struct *work);
static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task);
static LIST_HEAD(tls_device_gc_list);
static LIST_HEAD(tls_device_list);
+static LIST_HEAD(tls_device_down_list);
static DEFINE_SPINLOCK(tls_device_lock);
static void tls_device_free_ctx(struct tls_context *ctx)
@@ -680,15 +681,13 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx,
struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
struct net_device *netdev;
- if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags)))
- return;
-
trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type);
+ rcu_read_lock();
netdev = READ_ONCE(tls_ctx->netdev);
if (netdev)
netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn,
TLS_OFFLOAD_CTX_DIR_RX);
- clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags);
+ rcu_read_unlock();
TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC);
}
@@ -761,6 +760,8 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq)
if (tls_ctx->rx_conf != TLS_HW)
return;
+ if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags)))
+ return;
prot = &tls_ctx->prot_info;
rx_ctx = tls_offload_ctx_rx(tls_ctx);
@@ -963,6 +964,17 @@ int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,
ctx->sw.decrypted |= is_decrypted;
+ if (unlikely(test_bit(TLS_RX_DEV_DEGRADED, &tls_ctx->flags))) {
+ if (likely(is_encrypted || is_decrypted))
+ return 0;
+
+ /* After tls_device_down disables the offload, the next SKB will
+ * likely have initial fragments decrypted, and final ones not
+ * decrypted. We need to reencrypt that single SKB.
+ */
+ return tls_device_reencrypt(sk, skb);
+ }
+
/* Return immediately if the record is either entirely plaintext or
* entirely ciphertext. Otherwise handle reencrypt partially decrypted
* record.
@@ -1292,6 +1304,26 @@ static int tls_device_down(struct net_device *netdev)
spin_unlock_irqrestore(&tls_device_lock, flags);
list_for_each_entry_safe(ctx, tmp, &list, list) {
+ /* Stop offloaded TX and switch to the fallback.
+ * tls_is_sk_tx_device_offloaded will return false.
+ */
+ WRITE_ONCE(ctx->sk->sk_validate_xmit_skb, tls_validate_xmit_skb_sw);
+
+ /* Stop the RX and TX resync.
+ * tls_dev_resync must not be called after tls_dev_del.
+ */
+ WRITE_ONCE(ctx->netdev, NULL);
+
+ /* Start skipping the RX resync logic completely. */
+ set_bit(TLS_RX_DEV_DEGRADED, &ctx->flags);
+
+ /* Sync with inflight packets. After this point:
+ * TX: no non-encrypted packets will be passed to the driver.
+ * RX: resync requests from the driver will be ignored.
+ */
+ synchronize_net();
+
+ /* Release the offload context on the driver side. */
if (ctx->tx_conf == TLS_HW)
netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
TLS_OFFLOAD_CTX_DIR_TX);
@@ -1299,15 +1331,21 @@ static int tls_device_down(struct net_device *netdev)
!test_bit(TLS_RX_DEV_CLOSED, &ctx->flags))
netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
TLS_OFFLOAD_CTX_DIR_RX);
- WRITE_ONCE(ctx->netdev, NULL);
- smp_mb__before_atomic(); /* pairs with test_and_set_bit() */
- while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags))
- usleep_range(10, 200);
+
dev_put(netdev);
- list_del_init(&ctx->list);
- if (refcount_dec_and_test(&ctx->refcount))
- tls_device_free_ctx(ctx);
+ /* Move the context to a separate list for two reasons:
+ * 1. When the context is deallocated, list_del is called.
+ * 2. It's no longer an offloaded context, so we don't want to
+ * run offload-specific code on this context.
+ */
+ spin_lock_irqsave(&tls_device_lock, flags);
+ list_move_tail(&ctx->list, &tls_device_down_list);
+ spin_unlock_irqrestore(&tls_device_lock, flags);
+
+ /* Device contexts for RX and TX will be freed in on sk_destruct
+ * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW.
+ */
}
up_write(&device_offload_lock);
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index cacf040872c7..e40bedd112b6 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -431,6 +431,13 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
}
EXPORT_SYMBOL_GPL(tls_validate_xmit_skb);
+struct sk_buff *tls_validate_xmit_skb_sw(struct sock *sk,
+ struct net_device *dev,
+ struct sk_buff *skb)
+{
+ return tls_sw_fallback(sk, skb);
+}
+
struct sk_buff *tls_encrypt_skb(struct sk_buff *skb)
{
return tls_sw_fallback(skb->sk, skb);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 47b7c5334c34..fde56ff49163 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -636,6 +636,7 @@ struct tls_context *tls_ctx_create(struct sock *sk)
mutex_init(&ctx->tx_lock);
rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
ctx->sk_proto = READ_ONCE(sk->sk_prot);
+ ctx->sk = sk;
return ctx;
}
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 44d6566dd23e..1816899499ce 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -536,7 +536,7 @@ static int x25_create(struct net *net, struct socket *sock, int protocol,
if (protocol)
goto out;
- rc = -ENOBUFS;
+ rc = -ENOMEM;
if ((sk = x25_alloc_socket(net, kern)) == NULL)
goto out;
diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
index dd87cea9fba7..a7883e455290 100644
--- a/scripts/Makefile.modfinal
+++ b/scripts/Makefile.modfinal
@@ -59,7 +59,7 @@ quiet_cmd_ld_ko_o = LD [M] $@
quiet_cmd_btf_ko = BTF [M] $@
cmd_btf_ko = \
if [ -f vmlinux ]; then \
- LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@; \
+ LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J --btf_base vmlinux $@; \
else \
printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \
fi;
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index f4de4c97015b..0e0f6466b18d 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -240,7 +240,7 @@ gen_btf()
fi
info "BTF" ${2}
- LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${extra_paholeopt} ${1}
+ LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${extra_paholeopt} ${1}
# Create ${2} which contains just .BTF section but no symbols. Add
# SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all
diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 3c4cb72ed8a4..9ca5f1ba461e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -501,6 +501,7 @@ do_transfer()
local stat_ackrx_now_l=$(get_mib_counter "${listener_ns}" "MPTcpExtMPCapableACKRX")
local stat_cookietx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesSent")
local stat_cookierx_now=$(get_mib_counter "${listener_ns}" "TcpExtSyncookiesRecv")
+ local stat_ooo_now=$(get_mib_counter "${listener_ns}" "TcpExtTCPOFOQueue")
expect_synrx=$((stat_synrx_last_l))
expect_ackrx=$((stat_ackrx_last_l))
@@ -518,10 +519,14 @@ do_transfer()
"${stat_synrx_now_l}" "${expect_synrx}" 1>&2
retc=1
fi
- if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then
- printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \
- "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2
- rets=1
+ if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then
+ if [ ${stat_ooo_now} -eq 0 ]; then
+ printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \
+ "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2
+ rets=1
+ else
+ printf "[ Note ] fallback due to TCP OoO"
+ fi
fi
if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 7ed7cd95e58f..ebc4ee0fe179 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -363,6 +363,7 @@ ip1 -6 rule add table main suppress_prefixlength 0
ip1 -4 route add default dev wg0 table 51820
ip1 -4 rule add not fwmark 51820 table 51820
ip1 -4 rule add table main suppress_prefixlength 0
+n1 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/vethc/rp_filter'
# Flood the pings instead of sending just one, to trigger routing table reference counting bugs.
n1 ping -W 1 -c 100 -f 192.168.99.7
n1 ping -W 1 -c 100 -f abab::1111
diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config
index 4eecb432a66c..74db83a0aedd 100644
--- a/tools/testing/selftests/wireguard/qemu/kernel.config
+++ b/tools/testing/selftests/wireguard/qemu/kernel.config
@@ -19,7 +19,6 @@ CONFIG_NETFILTER_XTABLES=y
CONFIG_NETFILTER_XT_NAT=y
CONFIG_NETFILTER_XT_MATCH_LENGTH=y
CONFIG_NETFILTER_XT_MARK=y
-CONFIG_NF_CONNTRACK_IPV4=y
CONFIG_NF_NAT_IPV4=y
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_FILTER=y