aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-07-28 11:54:59 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-07-28 11:54:59 -0700
commit33ea1340bafe1f394e5bf96fceef73e9771d066b (patch)
tree3b1d816103a2d02692e4845e5c4570ed6f4afecd
parente64ab2dbd882933b65cd82ff6235d705ad65dbb6 (diff)
parent4d3d3a1b244fd54629a6b7047f39a7bbc8d11910 (diff)
downloadlinux-gpio-intel-33ea1340bafe1f394e5bf96fceef73e9771d066b.tar.gz
Merge tag 'net-5.19-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski: "Including fixes from bluetooth and netfilter, no known blockers for the release. Current release - regressions: - wifi: mac80211: do not abuse fq.lock in ieee80211_do_stop(), fix taking the lock before its initialized - Bluetooth: mgmt: fix double free on error path Current release - new code bugs: - eth: ice: fix tunnel checksum offload with fragmented traffic Previous releases - regressions: - tcp: md5: fix IPv4-mapped support after refactoring, don't take the pure v6 path - Revert "tcp: change pingpong threshold to 3", improving detection of interactive sessions - mld: fix netdev refcount leak in mld_{query | report}_work() due to a race - Bluetooth: - always set event mask on suspend, avoid early wake ups - L2CAP: fix use-after-free caused by l2cap_chan_put - bridge: do not send empty IFLA_AF_SPEC attribute Previous releases - always broken: - ping6: fix memleak in ipv6_renew_options() - sctp: prevent null-deref caused by over-eager error paths - virtio-net: fix the race between refill work and close, resulting in NAPI scheduled after close and a BUG() - macsec: - fix three netlink parsing bugs - avoid breaking the device state on invalid change requests - fix a memleak in another error path Misc: - dt-bindings: net: ethernet-controller: rework 'fixed-link' schema - two more batches of sysctl data race adornment" * tag 'net-5.19-final' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits) stmmac: dwmac-mediatek: fix resource leak in probe ipv6/addrconf: fix a null-ptr-deref bug for ip6_ptr net: ping6: Fix memleak in ipv6_renew_options(). net/funeth: Fix fun_xdp_tx() and XDP packet reclaim sctp: leave the err path free in sctp_stream_init to sctp_stream_free sfc: disable softirqs for ptp TX ptp: ocp: Select CRC16 in the Kconfig. tcp: md5: fix IPv4-mapped support virtio-net: fix the race between refill work and close mptcp: Do not return EINPROGRESS when subflow creation succeeds Bluetooth: L2CAP: Fix use-after-free caused by l2cap_chan_put Bluetooth: Always set event mask on suspend Bluetooth: mgmt: Fix double free on error path wifi: mac80211: do not abuse fq.lock in ieee80211_do_stop() ice: do not setup vlan for loopback VSI ice: check (DD | EOF) bits on Rx descriptor rather than (EOP | RS) ice: Fix VSIs unable to share unicast MAC ice: Fix tunnel checksum offload with fragmented traffic ice: Fix max VLANs available for VF netfilter: nft_queue: only allow supported familes and hooks ...
-rw-r--r--Documentation/devicetree/bindings/net/ethernet-controller.yaml123
-rw-r--r--Documentation/devicetree/bindings/net/fsl,fec.yaml3
-rw-r--r--Documentation/networking/ip-sysctl.rst9
-rw-r--r--drivers/net/ethernet/fungible/funeth/funeth_rx.c5
-rw-r--r--drivers/net/ethernet/fungible/funeth/funeth_tx.c20
-rw-r--r--drivers/net/ethernet/fungible/funeth/funeth_txrx.h6
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_main.c4
-rw-r--r--drivers/net/ethernet/intel/ice/ice_ethtool.c3
-rw-r--r--drivers/net/ethernet/intel/ice/ice_main.c10
-rw-r--r--drivers/net/ethernet/intel/ice/ice_sriov.c40
-rw-r--r--drivers/net/ethernet/intel/ice/ice_txrx.c8
-rw-r--r--drivers/net/ethernet/intel/ice/ice_virtchnl.c3
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c106
-rw-r--r--drivers/net/ethernet/netronome/nfp/bpf/jit.c2
-rw-r--r--drivers/net/ethernet/sfc/ptp.c22
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c9
-rw-r--r--drivers/net/ipa/ipa_qmi_msg.h2
-rw-r--r--drivers/net/macsec.c33
-rw-r--r--drivers/net/pcs/pcs-xpcs.c2
-rw-r--r--drivers/net/sungem_phy.c1
-rw-r--r--drivers/net/virtio_net.c37
-rw-r--r--drivers/ptp/Kconfig1
-rw-r--r--drivers/s390/net/qeth_core_main.c2
-rw-r--r--include/net/addrconf.h3
-rw-r--r--include/net/bluetooth/l2cap.h1
-rw-r--r--include/net/inet_connection_sock.h10
-rw-r--r--include/net/sock.h8
-rw-r--r--include/net/tcp.h2
-rw-r--r--net/bluetooth/hci_sync.c6
-rw-r--r--net/bluetooth/l2cap_core.c61
-rw-r--r--net/bluetooth/mgmt.c1
-rw-r--r--net/bridge/br_netlink.c8
-rw-r--r--net/caif/caif_socket.c20
-rw-r--r--net/decnet/af_decnet.c4
-rw-r--r--net/dsa/switch.c1
-rw-r--r--net/ipv4/fib_trie.c7
-rw-r--r--net/ipv4/tcp.c23
-rw-r--r--net/ipv4/tcp_input.c41
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/tcp_metrics.c10
-rw-r--r--net/ipv4/tcp_output.c27
-rw-r--r--net/ipv6/mcast.c14
-rw-r--r--net/ipv6/ping.c6
-rw-r--r--net/ipv6/tcp_ipv6.c4
-rw-r--r--net/mac80211/iface.c3
-rw-r--r--net/mptcp/options.c2
-rw-r--r--net/mptcp/protocol.c8
-rw-r--r--net/mptcp/subflow.c2
-rw-r--r--net/netfilter/nf_tables_api.c6
-rw-r--r--net/netfilter/nfnetlink_queue.c7
-rw-r--r--net/netfilter/nft_queue.c27
-rw-r--r--net/sctp/associola.c5
-rw-r--r--net/sctp/stream.c19
-rw-r--r--net/sctp/stream_sched.c2
-rw-r--r--net/tipc/socket.c2
-rw-r--r--net/tls/tls_device.c7
56 files changed, 481 insertions, 321 deletions
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 4f15463611f8bb..170cd201adc2e0 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -167,70 +167,65 @@ properties:
- in-band-status
fixed-link:
- allOf:
- - if:
- type: array
- then:
- deprecated: true
- items:
- - minimum: 0
- maximum: 31
- description:
- Emulated PHY ID, choose any but unique to the all
- specified fixed-links
-
- - enum: [0, 1]
- description:
- Duplex configuration. 0 for half duplex or 1 for
- full duplex
-
- - enum: [10, 100, 1000, 2500, 10000]
- description:
- Link speed in Mbits/sec.
-
- - enum: [0, 1]
- description:
- Pause configuration. 0 for no pause, 1 for pause
-
- - enum: [0, 1]
- description:
- Asymmetric pause configuration. 0 for no asymmetric
- pause, 1 for asymmetric pause
-
-
- - if:
- type: object
- then:
- properties:
- speed:
- description:
- Link speed.
- $ref: /schemas/types.yaml#/definitions/uint32
- enum: [10, 100, 1000, 2500, 10000]
-
- full-duplex:
- $ref: /schemas/types.yaml#/definitions/flag
- description:
- Indicates that full-duplex is used. When absent, half
- duplex is assumed.
-
- pause:
- $ref: /schemas/types.yaml#definitions/flag
- description:
- Indicates that pause should be enabled.
-
- asym-pause:
- $ref: /schemas/types.yaml#/definitions/flag
- description:
- Indicates that asym_pause should be enabled.
-
- link-gpios:
- maxItems: 1
- description:
- GPIO to determine if the link is up
-
- required:
- - speed
+ oneOf:
+ - $ref: /schemas/types.yaml#/definitions/uint32-array
+ deprecated: true
+ items:
+ - minimum: 0
+ maximum: 31
+ description:
+ Emulated PHY ID, choose any but unique to the all
+ specified fixed-links
+
+ - enum: [0, 1]
+ description:
+ Duplex configuration. 0 for half duplex or 1 for
+ full duplex
+
+ - enum: [10, 100, 1000, 2500, 10000]
+ description:
+ Link speed in Mbits/sec.
+
+ - enum: [0, 1]
+ description:
+ Pause configuration. 0 for no pause, 1 for pause
+
+ - enum: [0, 1]
+ description:
+ Asymmetric pause configuration. 0 for no asymmetric
+ pause, 1 for asymmetric pause
+ - type: object
+ additionalProperties: false
+ properties:
+ speed:
+ description:
+ Link speed.
+ $ref: /schemas/types.yaml#/definitions/uint32
+ enum: [10, 100, 1000, 2500, 10000]
+
+ full-duplex:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Indicates that full-duplex is used. When absent, half
+ duplex is assumed.
+
+ pause:
+ $ref: /schemas/types.yaml#definitions/flag
+ description:
+ Indicates that pause should be enabled.
+
+ asym-pause:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Indicates that asym_pause should be enabled.
+
+ link-gpios:
+ maxItems: 1
+ description:
+ GPIO to determine if the link is up
+
+ required:
+ - speed
additionalProperties: true
diff --git a/Documentation/devicetree/bindings/net/fsl,fec.yaml b/Documentation/devicetree/bindings/net/fsl,fec.yaml
index daa2f79a294f53..1b1853062cd3f0 100644
--- a/Documentation/devicetree/bindings/net/fsl,fec.yaml
+++ b/Documentation/devicetree/bindings/net/fsl,fec.yaml
@@ -183,6 +183,7 @@ properties:
Should specify the gpio for phy reset.
phy-reset-duration:
+ $ref: /schemas/types.yaml#/definitions/uint32
deprecated: true
description:
Reset duration in milliseconds. Should present only if property
@@ -191,12 +192,14 @@ properties:
and 1 millisecond will be used instead.
phy-reset-active-high:
+ type: boolean
deprecated: true
description:
If present then the reset sequence using the GPIO specified in the
"phy-reset-gpios" property is reversed (H=reset state, L=operation state).
phy-reset-post-delay:
+ $ref: /schemas/types.yaml#/definitions/uint32
deprecated: true
description:
Post reset delay in milliseconds. If present then a delay of phy-reset-post-delay
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 66c72230eaade9..d7a1bf1a55b5eb 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2866,7 +2866,14 @@ sctp_rmem - vector of 3 INTEGERs: min, default, max
Default: 4K
sctp_wmem - vector of 3 INTEGERs: min, default, max
- Currently this tunable has no effect.
+ Only the first value ("min") is used, "default" and "max" are
+ ignored.
+
+ min: Minimum size of send buffer that can be used by SCTP sockets.
+ It is guaranteed to each SCTP socket (but not association) even
+ under moderate memory pressure.
+
+ Default: 4K
addr_scope_policy - INTEGER
Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_rx.c b/drivers/net/ethernet/fungible/funeth/funeth_rx.c
index 0f6a549b9f6797..29a6c2ede43a69 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_rx.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_rx.c
@@ -142,6 +142,7 @@ static void *fun_run_xdp(struct funeth_rxq *q, skb_frag_t *frags, void *buf_va,
int ref_ok, struct funeth_txq *xdp_q)
{
struct bpf_prog *xdp_prog;
+ struct xdp_frame *xdpf;
struct xdp_buff xdp;
u32 act;
@@ -163,7 +164,9 @@ static void *fun_run_xdp(struct funeth_rxq *q, skb_frag_t *frags, void *buf_va,
case XDP_TX:
if (unlikely(!ref_ok))
goto pass;
- if (!fun_xdp_tx(xdp_q, xdp.data, xdp.data_end - xdp.data))
+
+ xdpf = xdp_convert_buff_to_frame(&xdp);
+ if (!xdpf || !fun_xdp_tx(xdp_q, xdpf))
goto xdp_error;
FUN_QSTAT_INC(q, xdp_tx);
q->xdp_flush |= FUN_XDP_FLUSH_TX;
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_tx.c b/drivers/net/ethernet/fungible/funeth/funeth_tx.c
index ff6e292372535e..2f6698b98b0344 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_tx.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_tx.c
@@ -466,7 +466,7 @@ static unsigned int fun_xdpq_clean(struct funeth_txq *q, unsigned int budget)
do {
fun_xdp_unmap(q, reclaim_idx);
- page_frag_free(q->info[reclaim_idx].vaddr);
+ xdp_return_frame(q->info[reclaim_idx].xdpf);
trace_funeth_tx_free(q, reclaim_idx, 1, head);
@@ -479,11 +479,11 @@ static unsigned int fun_xdpq_clean(struct funeth_txq *q, unsigned int budget)
return npkts;
}
-bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len)
+bool fun_xdp_tx(struct funeth_txq *q, struct xdp_frame *xdpf)
{
struct fun_eth_tx_req *req;
struct fun_dataop_gl *gle;
- unsigned int idx;
+ unsigned int idx, len;
dma_addr_t dma;
if (fun_txq_avail(q) < FUN_XDP_CLEAN_THRES)
@@ -494,7 +494,8 @@ bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len)
return false;
}
- dma = dma_map_single(q->dma_dev, data, len, DMA_TO_DEVICE);
+ len = xdpf->len;
+ dma = dma_map_single(q->dma_dev, xdpf->data, len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(q->dma_dev, dma))) {
FUN_QSTAT_INC(q, tx_map_err);
return false;
@@ -514,7 +515,7 @@ bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len)
gle = (struct fun_dataop_gl *)req->dataop.imm;
fun_dataop_gl_init(gle, 0, 0, len, dma);
- q->info[idx].vaddr = data;
+ q->info[idx].xdpf = xdpf;
u64_stats_update_begin(&q->syncp);
q->stats.tx_bytes += len;
@@ -545,12 +546,9 @@ int fun_xdp_xmit_frames(struct net_device *dev, int n,
if (unlikely(q_idx >= fp->num_xdpqs))
return -ENXIO;
- for (q = xdpqs[q_idx], i = 0; i < n; i++) {
- const struct xdp_frame *xdpf = frames[i];
-
- if (!fun_xdp_tx(q, xdpf->data, xdpf->len))
+ for (q = xdpqs[q_idx], i = 0; i < n; i++)
+ if (!fun_xdp_tx(q, frames[i]))
break;
- }
if (unlikely(flags & XDP_XMIT_FLUSH))
fun_txq_wr_db(q);
@@ -577,7 +575,7 @@ static void fun_xdpq_purge(struct funeth_txq *q)
unsigned int idx = q->cons_cnt & q->mask;
fun_xdp_unmap(q, idx);
- page_frag_free(q->info[idx].vaddr);
+ xdp_return_frame(q->info[idx].xdpf);
q->cons_cnt++;
}
}
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
index 04c9f91b7489bf..8708e2895946dd 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
+++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
@@ -95,8 +95,8 @@ struct funeth_txq_stats { /* per Tx queue SW counters */
struct funeth_tx_info { /* per Tx descriptor state */
union {
- struct sk_buff *skb; /* associated packet */
- void *vaddr; /* start address for XDP */
+ struct sk_buff *skb; /* associated packet (sk_buff path) */
+ struct xdp_frame *xdpf; /* associated XDP frame (XDP path) */
};
};
@@ -245,7 +245,7 @@ static inline int fun_irq_node(const struct fun_irq *p)
int fun_rxq_napi_poll(struct napi_struct *napi, int budget);
int fun_txq_napi_poll(struct napi_struct *napi, int budget);
netdev_tx_t fun_start_xmit(struct sk_buff *skb, struct net_device *netdev);
-bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len);
+bool fun_xdp_tx(struct funeth_txq *q, struct xdp_frame *xdpf);
int fun_xdp_xmit_frames(struct net_device *dev, int n,
struct xdp_frame **frames, u32 flags);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7f1a0d90dc51ea..685556e968f206 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1925,11 +1925,15 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
* non-zero req_queue_pairs says that user requested a new
* queue count via ethtool's set_channels, so use this
* value for queues distribution across traffic classes
+ * We need at least one queue pair for the interface
+ * to be usable as we see in else statement.
*/
if (vsi->req_queue_pairs > 0)
vsi->num_queue_pairs = vsi->req_queue_pairs;
else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
vsi->num_queue_pairs = pf->num_lan_msix;
+ else
+ vsi->num_queue_pairs = 1;
}
/* Number of queues per enabled TC */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 70335f6e85243b..4efa5e5846e013 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -658,7 +658,8 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring)
rx_desc = ICE_RX_DESC(rx_ring, i);
if (!(rx_desc->wb.status_error0 &
- cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)))
+ (cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S)) |
+ cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)))))
continue;
rx_buf = &rx_ring->rx_buf[i];
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index ff2eac2f8c6442..9f02b60459f10d 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4656,6 +4656,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
ice_set_safe_mode_caps(hw);
}
+ hw->ucast_shared = true;
+
err = ice_init_pf(pf);
if (err) {
dev_err(dev, "ice_init_pf failed: %d\n", err);
@@ -6011,10 +6013,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi)
if (vsi->netdev) {
ice_set_rx_mode(vsi->netdev);
- err = ice_vsi_vlan_setup(vsi);
+ if (vsi->type != ICE_VSI_LB) {
+ err = ice_vsi_vlan_setup(vsi);
- if (err)
- return err;
+ if (err)
+ return err;
+ }
}
ice_vsi_cfg_dcb_rings(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index bb1721f1321db8..f4907a3c2d193c 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -1310,39 +1310,6 @@ out_put_vf:
}
/**
- * ice_unicast_mac_exists - check if the unicast MAC exists on the PF's switch
- * @pf: PF used to reference the switch's rules
- * @umac: unicast MAC to compare against existing switch rules
- *
- * Return true on the first/any match, else return false
- */
-static bool ice_unicast_mac_exists(struct ice_pf *pf, u8 *umac)
-{
- struct ice_sw_recipe *mac_recipe_list =
- &pf->hw.switch_info->recp_list[ICE_SW_LKUP_MAC];
- struct ice_fltr_mgmt_list_entry *list_itr;
- struct list_head *rule_head;
- struct mutex *rule_lock; /* protect MAC filter list access */
-
- rule_head = &mac_recipe_list->filt_rules;
- rule_lock = &mac_recipe_list->filt_rule_lock;
-
- mutex_lock(rule_lock);
- list_for_each_entry(list_itr, rule_head, list_entry) {
- u8 *existing_mac = &list_itr->fltr_info.l_data.mac.mac_addr[0];
-
- if (ether_addr_equal(existing_mac, umac)) {
- mutex_unlock(rule_lock);
- return true;
- }
- }
-
- mutex_unlock(rule_lock);
-
- return false;
-}
-
-/**
* ice_set_vf_mac
* @netdev: network interface device structure
* @vf_id: VF identifier
@@ -1376,13 +1343,6 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
if (ret)
goto out_put_vf;
- if (ice_unicast_mac_exists(pf, mac)) {
- netdev_err(netdev, "Unicast MAC %pM already exists on this PF. Preventing setting VF %u unicast MAC address to %pM\n",
- mac, vf_id, mac);
- ret = -EINVAL;
- goto out_put_vf;
- }
-
mutex_lock(&vf->cfg_lock);
/* VF is notified of its new MAC via the PF's response to the
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 3f8b7274ed2f10..836dce8407124f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1751,11 +1751,13 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
protocol = vlan_get_protocol(skb);
- if (eth_p_mpls(protocol))
+ if (eth_p_mpls(protocol)) {
ip.hdr = skb_inner_network_header(skb);
- else
+ l4.hdr = skb_checksum_start(skb);
+ } else {
ip.hdr = skb_network_header(skb);
- l4.hdr = skb_checksum_start(skb);
+ l4.hdr = skb_transport_header(skb);
+ }
/* compute outer L2 header size */
l2_len = ip.hdr - skb->data;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 4547bc1f7cee7e..24188ec594d5aa 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -2948,7 +2948,8 @@ ice_vc_validate_add_vlan_filter_list(struct ice_vsi *vsi,
struct virtchnl_vlan_filtering_caps *vfc,
struct virtchnl_vlan_filter_list_v2 *vfl)
{
- u16 num_requested_filters = vsi->num_vlan + vfl->num_elements;
+ u16 num_requested_filters = ice_vsi_num_non_zero_vlans(vsi) +
+ vfl->num_elements;
if (num_requested_filters > vfc->max_filters)
return false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 28b19945d716cf..e64318c110fdd4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -28,6 +28,9 @@
#define MAX_RATE_EXPONENT 0x0FULL
#define MAX_RATE_MANTISSA 0xFFULL
+#define CN10K_MAX_BURST_MANTISSA 0x7FFFULL
+#define CN10K_MAX_BURST_SIZE 8453888ULL
+
/* Bitfields in NIX_TLX_PIR register */
#define TLX_RATE_MANTISSA GENMASK_ULL(8, 1)
#define TLX_RATE_EXPONENT GENMASK_ULL(12, 9)
@@ -35,6 +38,9 @@
#define TLX_BURST_MANTISSA GENMASK_ULL(36, 29)
#define TLX_BURST_EXPONENT GENMASK_ULL(40, 37)
+#define CN10K_TLX_BURST_MANTISSA GENMASK_ULL(43, 29)
+#define CN10K_TLX_BURST_EXPONENT GENMASK_ULL(47, 44)
+
struct otx2_tc_flow_stats {
u64 bytes;
u64 pkts;
@@ -77,33 +83,42 @@ int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic)
}
EXPORT_SYMBOL(otx2_tc_alloc_ent_bitmap);
-static void otx2_get_egress_burst_cfg(u32 burst, u32 *burst_exp,
- u32 *burst_mantissa)
+static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
+ u32 *burst_exp, u32 *burst_mantissa)
{
+ int max_burst, max_mantissa;
unsigned int tmp;
+ if (is_dev_otx2(nic->pdev)) {
+ max_burst = MAX_BURST_SIZE;
+ max_mantissa = MAX_BURST_MANTISSA;
+ } else {
+ max_burst = CN10K_MAX_BURST_SIZE;
+ max_mantissa = CN10K_MAX_BURST_MANTISSA;
+ }
+
/* Burst is calculated as
* ((256 + BURST_MANTISSA) << (1 + BURST_EXPONENT)) / 256
* Max supported burst size is 130,816 bytes.
*/
- burst = min_t(u32, burst, MAX_BURST_SIZE);
+ burst = min_t(u32, burst, max_burst);
if (burst) {
*burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0;
tmp = burst - rounddown_pow_of_two(burst);
- if (burst < MAX_BURST_MANTISSA)
+ if (burst < max_mantissa)
*burst_mantissa = tmp * 2;
else
*burst_mantissa = tmp / (1ULL << (*burst_exp - 7));
} else {
*burst_exp = MAX_BURST_EXPONENT;
- *burst_mantissa = MAX_BURST_MANTISSA;
+ *burst_mantissa = max_mantissa;
}
}
-static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp,
+static void otx2_get_egress_rate_cfg(u64 maxrate, u32 *exp,
u32 *mantissa, u32 *div_exp)
{
- unsigned int tmp;
+ u64 tmp;
/* Rate calculation by hardware
*
@@ -132,21 +147,44 @@ static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp,
}
}
-static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 maxrate)
+static u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic,
+ u64 maxrate, u32 burst)
{
- struct otx2_hw *hw = &nic->hw;
- struct nix_txschq_config *req;
u32 burst_exp, burst_mantissa;
u32 exp, mantissa, div_exp;
+ u64 regval = 0;
+
+ /* Get exponent and mantissa values from the desired rate */
+ otx2_get_egress_burst_cfg(nic, burst, &burst_exp, &burst_mantissa);
+ otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp);
+
+ if (is_dev_otx2(nic->pdev)) {
+ regval = FIELD_PREP(TLX_BURST_EXPONENT, (u64)burst_exp) |
+ FIELD_PREP(TLX_BURST_MANTISSA, (u64)burst_mantissa) |
+ FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
+ FIELD_PREP(TLX_RATE_EXPONENT, exp) |
+ FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+ } else {
+ regval = FIELD_PREP(CN10K_TLX_BURST_EXPONENT, (u64)burst_exp) |
+ FIELD_PREP(CN10K_TLX_BURST_MANTISSA, (u64)burst_mantissa) |
+ FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
+ FIELD_PREP(TLX_RATE_EXPONENT, exp) |
+ FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+ }
+
+ return regval;
+}
+
+static int otx2_set_matchall_egress_rate(struct otx2_nic *nic,
+ u32 burst, u64 maxrate)
+{
+ struct otx2_hw *hw = &nic->hw;
+ struct nix_txschq_config *req;
int txschq, err;
/* All SQs share the same TL4, so pick the first scheduler */
txschq = hw->txschq_list[NIX_TXSCH_LVL_TL4][0];
- /* Get exponent and mantissa values from the desired rate */
- otx2_get_egress_burst_cfg(burst, &burst_exp, &burst_mantissa);
- otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp);
-
mutex_lock(&nic->mbox.lock);
req = otx2_mbox_alloc_msg_nix_txschq_cfg(&nic->mbox);
if (!req) {
@@ -157,11 +195,7 @@ static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 ma
req->lvl = NIX_TXSCH_LVL_TL4;
req->num_regs = 1;
req->reg[0] = NIX_AF_TL4X_PIR(txschq);
- req->regval[0] = FIELD_PREP(TLX_BURST_EXPONENT, burst_exp) |
- FIELD_PREP(TLX_BURST_MANTISSA, burst_mantissa) |
- FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
- FIELD_PREP(TLX_RATE_EXPONENT, exp) |
- FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+ req->regval[0] = otx2_get_txschq_rate_regval(nic, maxrate, burst);
err = otx2_sync_mbox_msg(&nic->mbox);
mutex_unlock(&nic->mbox.lock);
@@ -230,7 +264,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic,
struct netlink_ext_ack *extack = cls->common.extack;
struct flow_action *actions = &cls->rule->action;
struct flow_action_entry *entry;
- u32 rate;
+ u64 rate;
int err;
err = otx2_tc_validate_flow(nic, actions, extack);
@@ -256,7 +290,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic,
}
/* Convert bytes per second to Mbps */
rate = entry->police.rate_bytes_ps * 8;
- rate = max_t(u32, rate / 1000000, 1);
+ rate = max_t(u64, rate / 1000000, 1);
err = otx2_set_matchall_egress_rate(nic, entry->police.burst, rate);
if (err)
return err;
@@ -614,21 +648,27 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
flow_spec->dport = match.key->dst;
flow_mask->dport = match.mask->dst;
- if (ip_proto == IPPROTO_UDP)
- req->features |= BIT_ULL(NPC_DPORT_UDP);
- else if (ip_proto == IPPROTO_TCP)
- req->features |= BIT_ULL(NPC_DPORT_TCP);
- else if (ip_proto == IPPROTO_SCTP)
- req->features |= BIT_ULL(NPC_DPORT_SCTP);
+
+ if (flow_mask->dport) {
+ if (ip_proto == IPPROTO_UDP)
+ req->features |= BIT_ULL(NPC_DPORT_UDP);
+ else if (ip_proto == IPPROTO_TCP)
+ req->features |= BIT_ULL(NPC_DPORT_TCP);
+ else if (ip_proto == IPPROTO_SCTP)
+ req->features |= BIT_ULL(NPC_DPORT_SCTP);
+ }
flow_spec->sport = match.key->src;
flow_mask->sport = match.mask->src;
- if (ip_proto == IPPROTO_UDP)
- req->features |= BIT_ULL(NPC_SPORT_UDP);
- else if (ip_proto == IPPROTO_TCP)
- req->features |= BIT_ULL(NPC_SPORT_TCP);
- else if (ip_proto == IPPROTO_SCTP)
- req->features |= BIT_ULL(NPC_SPORT_SCTP);
+
+ if (flow_mask->sport) {
+ if (ip_proto == IPPROTO_UDP)
+ req->features |= BIT_ULL(NPC_SPORT_UDP);
+ else if (ip_proto == IPPROTO_TCP)
+ req->features |= BIT_ULL(NPC_SPORT_TCP);
+ else if (ip_proto == IPPROTO_SCTP)
+ req->features |= BIT_ULL(NPC_SPORT_SCTP);
+ }
}
return otx2_tc_parse_actions(nic, &rule->action, req, f, node);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index e31f8fbbc696d7..df2ab5cbd49bd1 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -4233,7 +4233,7 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
}
/* If the chain is ended by an load/store pair then this
- * could serve as the new head of the the next chain.
+ * could serve as the new head of the next chain.
*/
if (curr_pair_is_memcpy(meta1, meta2)) {
head_ld_meta = meta1;
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 4625f85acab2ea..10ad0b93d283b0 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1100,7 +1100,29 @@ static void efx_ptp_xmit_skb_queue(struct efx_nic *efx, struct sk_buff *skb)
tx_queue = efx_channel_get_tx_queue(ptp_data->channel, type);
if (tx_queue && tx_queue->timestamping) {
+ /* This code invokes normal driver TX code which is always
+ * protected from softirqs when called from generic TX code,
+ * which in turn disables preemption. Look at __dev_queue_xmit
+ * which uses rcu_read_lock_bh disabling preemption for RCU
+ * plus disabling softirqs. We do not need RCU reader
+ * protection here.
+ *
+ * Although it is theoretically safe for current PTP TX/RX code
+ * running without disabling softirqs, there are three good
+ * reasond for doing so:
+ *
+ * 1) The code invoked is mainly implemented for non-PTP
+ * packets and it is always executed with softirqs
+ * disabled.
+ * 2) This being a single PTP packet, better to not
+ * interrupt its processing by softirqs which can lead
+ * to high latencies.
+ * 3) netdev_xmit_more checks preemption is disabled and
+ * triggers a BUG_ON if not.
+ */
+ local_bh_disable();
efx_enqueue_skb(tx_queue, skb);
+ local_bh_enable();
} else {
WARN_ONCE(1, "PTP channel has no timestamped tx queue\n");
dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index ca8ab290013ce3..d42e1afb652134 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -688,18 +688,19 @@ static int mediatek_dwmac_probe(struct platform_device *pdev)
ret = mediatek_dwmac_clks_config(priv_plat, true);
if (ret)
- return ret;
+ goto err_remove_config_dt;
ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
- if (ret) {
- stmmac_remove_config_dt(pdev, plat_dat);
+ if (ret)
goto err_drv_probe;
- }
return 0;
err_drv_probe:
mediatek_dwmac_clks_config(priv_plat, false);
+err_remove_config_dt:
+ stmmac_remove_config_dt(pdev, plat_dat);
+
return ret;
}
diff --git a/drivers/net/ipa/ipa_qmi_msg.h b/drivers/net/ipa/ipa_qmi_msg.h
index 3233d145fd87c3..495e85abe50bdb 100644
--- a/drivers/net/ipa/ipa_qmi_msg.h
+++ b/drivers/net/ipa/ipa_qmi_msg.h
@@ -214,7 +214,7 @@ struct ipa_init_modem_driver_req {
/* The response to a IPA_QMI_INIT_DRIVER request begins with a standard
* QMI response, but contains other information as well. Currently we
- * simply wait for the the INIT_DRIVER transaction to complete and
+ * simply wait for the INIT_DRIVER transaction to complete and
* ignore any other data that might be returned.
*/
struct ipa_init_modem_driver_rsp {
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 817577e713d709..f354fad05714ad 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -243,6 +243,7 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb)
#define DEFAULT_SEND_SCI true
#define DEFAULT_ENCRYPT false
#define DEFAULT_ENCODING_SA 0
+#define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1))
static bool send_sci(const struct macsec_secy *secy)
{
@@ -1697,7 +1698,7 @@ static bool validate_add_rxsa(struct nlattr **attrs)
return false;
if (attrs[MACSEC_SA_ATTR_PN] &&
- *(u64 *)nla_data(attrs[MACSEC_SA_ATTR_PN]) == 0)
+ nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
return false;
if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -1753,7 +1754,8 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
}
pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN;
- if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
+ if (tb_sa[MACSEC_SA_ATTR_PN] &&
+ nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n",
nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len);
rtnl_unlock();
@@ -1769,7 +1771,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
pr_notice("macsec: nl: add_rxsa: bad salt length: %d != %d\n",
nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
- MACSEC_SA_ATTR_SALT);
+ MACSEC_SALT_LEN);
rtnl_unlock();
return -EINVAL;
}
@@ -1842,7 +1844,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
return 0;
cleanup:
- kfree(rx_sa);
+ macsec_rxsa_put(rx_sa);
rtnl_unlock();
return err;
}
@@ -1939,7 +1941,7 @@ static bool validate_add_txsa(struct nlattr **attrs)
if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
return false;
- if (nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+ if (nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
return false;
if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -2011,7 +2013,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
pr_notice("macsec: nl: add_txsa: bad salt length: %d != %d\n",
nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
- MACSEC_SA_ATTR_SALT);
+ MACSEC_SALT_LEN);
rtnl_unlock();
return -EINVAL;
}
@@ -2085,7 +2087,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
cleanup:
secy->operational = was_operational;
- kfree(tx_sa);
+ macsec_txsa_put(tx_sa);
rtnl_unlock();
return err;
}
@@ -2293,7 +2295,7 @@ static bool validate_upd_sa(struct nlattr **attrs)
if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
return false;
- if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+ if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
return false;
if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -3745,9 +3747,6 @@ static int macsec_changelink_common(struct net_device *dev,
secy->operational = tx_sa && tx_sa->active;
}
- if (data[IFLA_MACSEC_WINDOW])
- secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
-
if (data[IFLA_MACSEC_ENCRYPT])
tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]);
@@ -3793,6 +3792,16 @@ static int macsec_changelink_common(struct net_device *dev,
}
}
+ if (data[IFLA_MACSEC_WINDOW]) {
+ secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
+
+ /* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window
+ * for XPN cipher suites */
+ if (secy->xpn &&
+ secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW)
+ return -EINVAL;
+ }
+
return 0;
}
@@ -3822,7 +3831,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
ret = macsec_changelink_common(dev, data);
if (ret)
- return ret;
+ goto cleanup;
/* If h/w offloading is available, propagate to the device */
if (macsec_is_offloaded(macsec)) {
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 4cfd05c15aeedf..d25fbb9caebab4 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -896,7 +896,7 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs,
*/
ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS);
if (ret < 0)
- return false;
+ return ret;
if (ret & DW_VR_MII_C37_ANSGM_SP_LNKSTS) {
int speed_value;
diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c
index ff22b6b1c6861b..36803d932dff47 100644
--- a/drivers/net/sungem_phy.c
+++ b/drivers/net/sungem_phy.c
@@ -450,6 +450,7 @@ static int bcm5421_init(struct mii_phy* phy)
int can_low_power = 1;
if (np == NULL || of_get_property(np, "no-autolowpower", NULL))
can_low_power = 0;
+ of_node_put(np);
if (can_low_power) {
/* Enable automatic low-power */
sungem_phy_write(phy, 0x1c, 0x9002);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 356cf8dd4164b9..ec8e1b3108c3a8 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -242,9 +242,15 @@ struct virtnet_info {
/* Packet virtio header size */
u8 hdr_len;
- /* Work struct for refilling if we run low on memory. */
+ /* Work struct for delayed refilling if we run low on memory. */
struct delayed_work refill;
+ /* Is delayed refill enabled? */
+ bool refill_enabled;
+
+ /* The lock to synchronize the access to refill_enabled */
+ spinlock_t refill_lock;
+
/* Work struct for config space updates */
struct work_struct config_work;
@@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
return p;
}
+static void enable_delayed_refill(struct virtnet_info *vi)
+{
+ spin_lock_bh(&vi->refill_lock);
+ vi->refill_enabled = true;
+ spin_unlock_bh(&vi->refill_lock);
+}
+
+static void disable_delayed_refill(struct virtnet_info *vi)
+{
+ spin_lock_bh(&vi->refill_lock);
+ vi->refill_enabled = false;
+ spin_unlock_bh(&vi->refill_lock);
+}
+
static void virtqueue_napi_schedule(struct napi_struct *napi,
struct virtqueue *vq)
{
@@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
}
if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
- if (!try_fill_recv(vi, rq, GFP_ATOMIC))
- schedule_delayed_work(&vi->refill, 0);
+ if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
+ spin_lock(&vi->refill_lock);
+ if (vi->refill_enabled)
+ schedule_delayed_work(&vi->refill, 0);
+ spin_unlock(&vi->refill_lock);
+ }
}
u64_stats_update_begin(&rq->stats.syncp);
@@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
struct virtnet_info *vi = netdev_priv(dev);
int i, err;
+ enable_delayed_refill(vi);
+
for (i = 0; i < vi->max_queue_pairs; i++) {
if (i < vi->curr_queue_pairs)
/* Make sure we have some buffers: if oom use wq. */
@@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
struct virtnet_info *vi = netdev_priv(dev);
int i;
+ /* Make sure NAPI doesn't schedule refill work */
+ disable_delayed_refill(vi);
/* Make sure refill_work doesn't re-enable napi! */
cancel_delayed_work_sync(&vi->refill);
@@ -2792,6 +2820,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
virtio_device_ready(vdev);
+ enable_delayed_refill(vi);
+
if (netif_running(vi->dev)) {
err = virtnet_open(vi->dev);
if (err)
@@ -3535,6 +3565,7 @@ static int virtnet_probe(struct virtio_device *vdev)
vdev->priv = vi;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
+ spin_lock_init(&vi->refill_lock);
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 458218f88c5eb9..fe4971b65c6481 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -176,6 +176,7 @@ config PTP_1588_CLOCK_OCP
depends on !S390
depends on COMMON_CLK
select NET_DEVLINK
+ select CRC16
help
This driver adds support for an OpenCompute time card.
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 9e54fe76a9b2e8..35d4b398c197e8 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3565,7 +3565,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
if (!atomic_read(&queue->set_pci_flags_count)) {
/*
* there's no outstanding PCI any more, so we
- * have to request a PCI to be sure the the PCI
+ * have to request a PCI to be sure the PCI
* will wake at some time in the future then we
* can flush packed buffers that might still be
* hanging around, which can happen if no
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f7506f08e505a9..c04f359655b86f 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -405,6 +405,9 @@ static inline bool ip6_ignore_linkdown(const struct net_device *dev)
{
const struct inet6_dev *idev = __in6_dev_get(dev);
+ if (unlikely(!idev))
+ return true;
+
return !!idev->cnf.ignore_routes_with_linkdown;
}
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 3c4f550e5a8b75..2f766e3437ce2e 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -847,6 +847,7 @@ enum {
};
void l2cap_chan_hold(struct l2cap_chan *c);
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c);
void l2cap_chan_put(struct l2cap_chan *c);
static inline void l2cap_chan_lock(struct l2cap_chan *chan)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 85cd695e7fd1d3..ee88f0f1350f4e 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -321,7 +321,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
-#define TCP_PINGPONG_THRESH 3
+#define TCP_PINGPONG_THRESH 1
static inline void inet_csk_enter_pingpong_mode(struct sock *sk)
{
@@ -338,14 +338,6 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
}
-static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_ack.pingpong < U8_MAX)
- icsk->icsk_ack.pingpong++;
-}
-
static inline bool inet_csk_has_ulp(struct sock *sk)
{
return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;
diff --git a/include/net/sock.h b/include/net/sock.h
index 9fa54762e07752..7a48991cdb198a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2843,18 +2843,18 @@ static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
{
/* Does this proto have per netns sysctl_wmem ? */
if (proto->sysctl_wmem_offset)
- return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+ return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset));
- return *proto->sysctl_wmem;
+ return READ_ONCE(*proto->sysctl_wmem);
}
static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
{
/* Does this proto have per netns sysctl_rmem ? */
if (proto->sysctl_rmem_offset)
- return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+ return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset));
- return *proto->sysctl_rmem;
+ return READ_ONCE(*proto->sysctl_rmem);
}
/* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 071735e10872c1..78a64e1b33a7e7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1419,7 +1419,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
static inline int tcp_win_from_space(const struct sock *sk, int space)
{
- int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
+ int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);
return tcp_adv_win_scale <= 0 ?
(space>>(-tcp_adv_win_scale)) :
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 1739e8cb3291ef..c17021642234ba 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4973,6 +4973,9 @@ int hci_suspend_sync(struct hci_dev *hdev)
return err;
}
+ /* Update event mask so only the allowed event can wakeup the host */
+ hci_set_event_mask_sync(hdev);
+
/* Only configure accept list if disconnect succeeded and wake
* isn't being prevented.
*/
@@ -4984,9 +4987,6 @@ int hci_suspend_sync(struct hci_dev *hdev)
/* Unpause to take care of updating scanning params */
hdev->scanning_paused = false;
- /* Update event mask so only the allowed event can wakeup the host */
- hci_set_event_mask_sync(hdev);
-
/* Enable event filter for paired devices */
hci_update_event_filter_sync(hdev);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ae78490ecd3d4b..52668662ae8de1 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -111,7 +111,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn,
}
/* Find channel with given SCID.
- * Returns locked channel. */
+ * Returns a reference locked channel.
+ */
static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
u16 cid)
{
@@ -119,15 +120,19 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_scid(conn, cid);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
}
/* Find channel with given DCID.
- * Returns locked channel.
+ * Returns a reference locked channel.
*/
static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
u16 cid)
@@ -136,8 +141,12 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_dcid(conn, cid);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
@@ -162,8 +171,12 @@ static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_ident(conn, ident);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
@@ -497,6 +510,16 @@ void l2cap_chan_hold(struct l2cap_chan *c)
kref_get(&c->kref);
}
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c)
+{
+ BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
+
+ if (!kref_get_unless_zero(&c->kref))
+ return NULL;
+
+ return c;
+}
+
void l2cap_chan_put(struct l2cap_chan *c)
{
BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
@@ -1968,7 +1991,10 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
src_match = !bacmp(&c->src, src);
dst_match = !bacmp(&c->dst, dst);
if (src_match && dst_match) {
- l2cap_chan_hold(c);
+ c = l2cap_chan_hold_unless_zero(c);
+ if (!c)
+ continue;
+
read_unlock(&chan_list_lock);
return c;
}
@@ -1983,7 +2009,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
}
if (c1)
- l2cap_chan_hold(c1);
+ c1 = l2cap_chan_hold_unless_zero(c1);
read_unlock(&chan_list_lock);
@@ -4463,6 +4489,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
unlock:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -4577,6 +4604,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -5304,6 +5332,7 @@ send_move_response:
l2cap_send_move_chan_rsp(chan, result);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5396,6 +5425,7 @@ static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result)
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
@@ -5425,6 +5455,7 @@ static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static int l2cap_move_channel_rsp(struct l2cap_conn *conn,
@@ -5488,6 +5519,7 @@ static int l2cap_move_channel_confirm(struct l2cap_conn *conn,
l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5523,6 +5555,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn,
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5895,12 +5928,11 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
if (credits > max_credits) {
BT_ERR("LE credits overflow");
l2cap_send_disconn_req(chan, ECONNRESET);
- l2cap_chan_unlock(chan);
/* Return 0 so that we don't trigger an unnecessary
* command reject packet.
*/
- return 0;
+ goto unlock;
}
chan->tx_credits += credits;
@@ -5911,7 +5943,9 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
if (chan->tx_credits)
chan->ops->resume(chan);
+unlock:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -7597,6 +7631,7 @@ drop:
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
@@ -8085,7 +8120,7 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
if (src_type != c->src_type)
continue;
- l2cap_chan_hold(c);
+ c = l2cap_chan_hold_unless_zero(c);
read_unlock(&chan_list_lock);
return c;
}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ae758ab1b558d3..2f91a8c2b67809 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4723,7 +4723,6 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev,
else
status = MGMT_STATUS_FAILED;
- mgmt_pending_remove(cmd);
goto unlock;
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index bb01776d2d88c4..c96509c442a57c 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -589,9 +589,13 @@ static int br_fill_ifinfo(struct sk_buff *skb,
}
done:
+ if (af) {
+ if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0))
+ nla_nest_end(skb, af);
+ else
+ nla_nest_cancel(skb, af);
+ }
- if (af)
- nla_nest_end(skb, af);
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 251e666ba9a28d..748be72532485a 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -47,7 +47,7 @@ enum caif_states {
struct caifsock {
struct sock sk; /* must be first member */
struct cflayer layer;
- u32 flow_state;
+ unsigned long flow_state;
struct caif_connect_request conn_req;
struct mutex readlock;
struct dentry *debugfs_socket_dir;
@@ -56,38 +56,32 @@ struct caifsock {
static int rx_flow_is_on(struct caifsock *cf_sk)
{
- return test_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ return test_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static int tx_flow_is_on(struct caifsock *cf_sk)
{
- return test_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ return test_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_rx_flow_off(struct caifsock *cf_sk)
{
- clear_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ clear_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_rx_flow_on(struct caifsock *cf_sk)
{
- set_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ set_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_tx_flow_off(struct caifsock *cf_sk)
{
- clear_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ clear_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_tx_flow_on(struct caifsock *cf_sk)
{
- set_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ set_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void caif_read_lock(struct sock *sk)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index dc92a67baea394..7d542eb4617295 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -480,8 +480,8 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
sk->sk_family = PF_DECnet;
sk->sk_protocol = 0;
sk->sk_allocation = gfp;
- sk->sk_sndbuf = sysctl_decnet_wmem[1];
- sk->sk_rcvbuf = sysctl_decnet_rmem[1];
+ sk->sk_sndbuf = READ_ONCE(sysctl_decnet_wmem[1]);
+ sk->sk_rcvbuf = READ_ONCE(sysctl_decnet_rmem[1]);
/* Initialization of DECnet Session Control Port */
scp = DN_SK(sk);
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 2b56218fc57c76..4dfd68cf61c5a3 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -344,6 +344,7 @@ static int dsa_switch_do_lag_fdb_add(struct dsa_switch *ds, struct dsa_lag *lag,
ether_addr_copy(a->addr, addr);
a->vid = vid;
+ a->db = db;
refcount_set(&a->refcount, 1);
list_add_tail(&a->list, &lag->fdbs);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 46e8a5125853ae..452ff177e4da95 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1042,6 +1042,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
{
+ u8 fib_notify_on_flag_change;
struct fib_alias *fa_match;
struct sk_buff *skb;
int err;
@@ -1063,14 +1064,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
WRITE_ONCE(fa_match->offload, fri->offload);
WRITE_ONCE(fa_match->trap, fri->trap);
+ fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change);
+
/* 2 means send notifications only if offload_failed was changed. */
- if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
+ if (fib_notify_on_flag_change == 2 &&
READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
goto out;
WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
- if (!net->ipv4.sysctl_fib_notify_on_flag_change)
+ if (!fib_notify_on_flag_change)
goto out;
skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2faaaaf540ac1d..766881775abb79 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -452,8 +452,8 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
- WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+ WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+ WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
sk_sockets_allocated_inc(sk);
}
@@ -686,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
int size_goal)
{
return skb->len < size_goal &&
- sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
!tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize &&
tcp_skb_can_collapse_to(skb);
@@ -1724,7 +1724,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
cap = sk->sk_rcvbuf >> 1;
else
- cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+ cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
val = min(val, cap);
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
@@ -4459,9 +4459,18 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
}
- /* check the signature */
- genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected,
- NULL, skb);
+ /* Check the signature.
+ * To support dual stack listeners, we need to handle
+ * IPv4-mapped case.
+ */
+ if (family == AF_INET)
+ genhash = tcp_v4_md5_hash_skb(newhash,
+ hash_expected,
+ NULL, skb);
+ else
+ genhash = tp->af_specific->calc_md5_hash(newhash,
+ hash_expected,
+ NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 07dbcbae778288..b1637990d57084 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -426,7 +426,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
if (sk->sk_sndbuf < sndmem)
WRITE_ONCE(sk->sk_sndbuf,
- min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
+ min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -461,7 +461,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
- int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+ int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
@@ -534,7 +534,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
*/
static void tcp_init_buffer_space(struct sock *sk)
{
- int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+ int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
@@ -574,16 +574,17 @@ static void tcp_clamp_window(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
+ int rmem2;
icsk->icsk_ack.quick = 0;
+ rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
- if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+ if (sk->sk_rcvbuf < rmem2 &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
WRITE_ONCE(sk->sk_rcvbuf,
- min(atomic_read(&sk->sk_rmem_alloc),
- net->ipv4.sysctl_tcp_rmem[2]));
+ min(atomic_read(&sk->sk_rmem_alloc), rmem2));
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -724,7 +725,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -745,7 +746,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
do_div(rcvwin, tp->advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
@@ -910,9 +911,9 @@ static void tcp_update_pacing_rate(struct sock *sk)
* end of slow start and should slow down.
*/
if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2)
- rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
+ rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio);
else
- rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
+ rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio);
rate *= max(tcp_snd_cwnd(tp), tp->packets_out);
@@ -2175,7 +2176,7 @@ void tcp_enter_loss(struct sock *sk)
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
*/
- tp->frto = net->ipv4.sysctl_tcp_frto &&
+ tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
(new_recovery || icsk->icsk_retransmits) &&
!inet_csk(sk)->icsk_mtup.probe_size;
}
@@ -3058,7 +3059,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
{
- u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+ u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
struct tcp_sock *tp = tcp_sk(sk);
if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -3581,7 +3582,8 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
if (*last_oow_ack_time) {
s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
- if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+ if (0 <= elapsed &&
+ elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
NET_INC_STATS(net, mib_idx);
return true; /* rate-limited: don't send yet! */
}
@@ -3629,7 +3631,7 @@ static void tcp_send_challenge_ack(struct sock *sk)
/* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
if (now != challenge_timestamp) {
- u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+ u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
u32 half = (ack_limit + 1) >> 1;
challenge_timestamp = now;
@@ -4426,7 +4428,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4473,7 +4475,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
tcp_rcv_spurious_retrans(sk, skb);
@@ -5519,7 +5521,7 @@ send_now:
}
if (!tcp_is_sack(tp) ||
- tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+ tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
goto send_now;
if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
@@ -5540,11 +5542,12 @@ send_now:
if (tp->srtt_us && tp->srtt_us < rtt)
rtt = tp->srtt_us;
- delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+ delay = min_t(unsigned long,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
rtt * (NSEC_PER_USEC >> 3)/20);
sock_hold(sk);
hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
- sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns),
HRTIMER_MODE_REL_PINNED_SOFT);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d16e6e40f47ba4..586c102ce152d0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1006,7 +1006,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
- tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(inet_sk(sk)->tos & INET_ECN_MASK) :
inet_sk(sk)->tos;
@@ -1526,7 +1526,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
if (!dst) {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index a501150deaa3b3..d58e672be31c76 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
int m;
sk_dst_confirm(sk);
- if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
+ if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst)
return;
rcu_read_lock();
@@ -385,7 +385,7 @@ void tcp_update_metrics(struct sock *sk)
if (tcp_in_initial_slowstart(tp)) {
/* Slow start still did not finish. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && (tcp_snd_cwnd(tp) >> 1) > val)
@@ -401,7 +401,7 @@ void tcp_update_metrics(struct sock *sk)
} else if (!tcp_in_slow_start(tp) &&
icsk->icsk_ca_state == TCP_CA_Open) {
/* Cong. avoidance phase, cwnd is reliable. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
max(tcp_snd_cwnd(tp) >> 1, tp->snd_ssthresh));
@@ -418,7 +418,7 @@ void tcp_update_metrics(struct sock *sk)
tcp_metric_set(tm, TCP_METRIC_CWND,
(val + tp->snd_ssthresh) >> 1);
}
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && tp->snd_ssthresh > val)
@@ -463,7 +463,7 @@ void tcp_init_metrics(struct sock *sk)
if (tcp_metric_locked(tm, TCP_METRIC_CWND))
tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
- val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+ val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val) {
tp->snd_ssthresh = val;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c38e07b50639c7..4c376b6d87649c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
if (tcp_packets_in_flight(tp) == 0)
tcp_ca_event(sk, CA_EVENT_TX_START);
- /* If this is the first data packet sent in response to the
- * previous received data,
- * and it is a reply for ato after last received packet,
- * increase pingpong count.
- */
- if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
- (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
- inet_csk_inc_pingpong_cnt(sk);
-
tp->lsndtime = now;
+
+ /* If it is a reply for ato after last received
+ * packet, enter pingpong mode.
+ */
+ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+ inet_csk_enter_pingpong_mode(sk);
}
/* Account for an ACK we sent. */
@@ -230,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
* which we interpret as a sign the remote TCP is not
* misinterpreting the window field as a signed quantity.
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
else
(*rcv_wnd) = min_t(u32, space, U16_MAX);
@@ -241,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
*rcv_wscale = 0;
if (wscale_ok) {
/* Set window scaling on max possible window */
- space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
space = max_t(u32, space, sysctl_rmem_max);
space = min_t(u32, space, *window_clamp);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
@@ -285,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk)
* scaled window.
*/
if (!tp->rx_opt.rcv_wscale &&
- sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -1976,7 +1973,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift);
- r = tcp_min_rtt(tcp_sk(sk)) >> sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log;
+ r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log);
if (r < BITS_PER_TYPE(sk->sk_gso_max_size))
bytes += sk->sk_gso_max_size >> r;
@@ -1995,7 +1992,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
min_tso = ca_ops->min_tso_segs ?
ca_ops->min_tso_segs(sk) :
- sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2507,7 +2504,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
if (sk->sk_pacing_status == SK_PACING_NONE)
limit = min_t(unsigned long, limit,
- sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
limit <<= factor;
if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7f695c39d9a8c4..87c699d57b3669 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1522,7 +1522,6 @@ static void mld_query_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_query_work, 0);
break;
}
}
@@ -1533,8 +1532,10 @@ static void mld_query_work(struct work_struct *work)
__mld_query_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
/* called with rcu_read_lock() */
@@ -1624,7 +1625,6 @@ static void mld_report_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_report_work, 0);
break;
}
}
@@ -1635,8 +1635,10 @@ static void mld_report_work(struct work_struct *work)
__mld_report_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type,
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index ecf3a553a0dc46..8c6c2d82c1cd6d 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -22,6 +22,11 @@
#include <linux/proc_fs.h>
#include <net/ping.h>
+static void ping_v6_destroy(struct sock *sk)
+{
+ inet6_destroy_sock(sk);
+}
+
/* Compatibility glue so we can support IPv6 when it's compiled as a module */
static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len)
@@ -181,6 +186,7 @@ struct proto pingv6_prot = {
.owner = THIS_MODULE,
.init = ping_init_sock,
.close = ping_close,
+ .destroy = ping_v6_destroy,
.connect = ip6_datagram_connect_v6_only,
.disconnect = __udp_disconnect,
.setsockopt = ipv6_setsockopt,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9d3ede2932582e..be09941fe6d9a8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -546,7 +546,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
- tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(np->tclass & INET_ECN_MASK) :
np->tclass;
@@ -1314,7 +1314,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
/* Clone native IPv6 options from listening socket (if any)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 15a73b7fdd75a1..1a9ada41187932 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -377,9 +377,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
bool cancel_scan;
struct cfg80211_nan_func *func;
- spin_lock_bh(&local->fq.lock);
clear_bit(SDATA_STATE_RUNNING, &sdata->state);
- spin_unlock_bh(&local->fq.lock);
+ synchronize_rcu(); /* flush _ieee80211_wake_txqs() */
cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata;
if (cancel_scan)
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index bd8f0f425be4ca..30d289044e71b1 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1271,7 +1271,7 @@ raise_win:
if (unlikely(th->syn))
new_win = min(new_win, 65535U) << tp->rx_opt.rcv_wscale;
if (!tp->rx_opt.rcv_wscale &&
- sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ READ_ONCE(sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows))
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 21a3ed64226e56..7e1518bb6115d5 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1908,7 +1908,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (msk->rcvq_space.copied <= msk->rcvq_space.space)
goto new_measure;
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -1926,7 +1926,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
do_div(rcvwin, advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
u32 window_clamp;
@@ -2669,8 +2669,8 @@ static int mptcp_init_sock(struct sock *sk)
mptcp_ca_reset(sk);
sk_sockets_allocated_inc(sk);
- sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
- sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+ sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+ sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
return 0;
}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 63e8892ec807d3..af28f3b6038994 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1533,7 +1533,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
mptcp_sock_graft(ssk, sk->sk_socket);
iput(SOCK_INODE(sf));
WRITE_ONCE(msk->allow_infinite_fallback, false);
- return err;
+ return 0;
failed_unlink:
list_del(&subflow->node);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 646d5fd53604bd..9f976b11d89671 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3340,6 +3340,8 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
if (err < 0)
return err;
}
+
+ cond_resched();
}
return 0;
@@ -9367,9 +9369,13 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
break;
}
}
+
+ cond_resched();
}
list_for_each_entry(set, &ctx->table->sets, list) {
+ cond_resched();
+
if (!nft_is_active_next(ctx->net, set))
continue;
if (!(set->flags & NFT_SET_MAP) ||
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index a364f8e5e698f8..87a9009d5234dd 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -843,11 +843,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
}
static int
-nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff)
+nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff)
{
struct sk_buff *nskb;
if (diff < 0) {
+ unsigned int min_len = skb_transport_offset(e->skb);
+
+ if (data_len < min_len)
+ return -EINVAL;
+
if (pskb_trim(e->skb, data_len))
return -ENOMEM;
} else if (diff > 0) {
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index 15e4b7640dc000..da29e92c03e276 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -68,6 +68,31 @@ static void nft_queue_sreg_eval(const struct nft_expr *expr,
regs->verdict.code = ret;
}
+static int nft_queue_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ static const unsigned int supported_hooks = ((1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_POST_ROUTING));
+
+ switch (ctx->family) {
+ case NFPROTO_IPV4:
+ case NFPROTO_IPV6:
+ case NFPROTO_INET:
+ case NFPROTO_BRIDGE:
+ break;
+ case NFPROTO_NETDEV: /* lacks okfn */
+ fallthrough;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return nft_chain_validate_hooks(ctx->chain, supported_hooks);
+}
+
static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = {
[NFTA_QUEUE_NUM] = { .type = NLA_U16 },
[NFTA_QUEUE_TOTAL] = { .type = NLA_U16 },
@@ -164,6 +189,7 @@ static const struct nft_expr_ops nft_queue_ops = {
.eval = nft_queue_eval,
.init = nft_queue_init,
.dump = nft_queue_dump,
+ .validate = nft_queue_validate,
.reduce = NFT_REDUCE_READONLY,
};
@@ -173,6 +199,7 @@ static const struct nft_expr_ops nft_queue_sreg_ops = {
.eval = nft_queue_sreg_eval,
.init = nft_queue_sreg_init,
.dump = nft_queue_sreg_dump,
+ .validate = nft_queue_validate,
.reduce = NFT_REDUCE_READONLY,
};
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index be29da09cc7ab0..3460abceba443b 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -229,9 +229,8 @@ static struct sctp_association *sctp_association_init(
if (!sctp_ulpq_init(&asoc->ulpq, asoc))
goto fail_init;
- if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams,
- 0, gfp))
- goto fail_init;
+ if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp))
+ goto stream_free;
/* Initialize default path MTU. */
asoc->pathmtu = sp->pathmtu;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6dc95dcc0ff4f0..ef9fceadef8d5a 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -137,7 +137,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
ret = sctp_stream_alloc_out(stream, outcnt, gfp);
if (ret)
- goto out_err;
+ return ret;
for (i = 0; i < stream->outcnt; i++)
SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
@@ -145,22 +145,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
handle_in:
sctp_stream_interleave_init(stream);
if (!incnt)
- goto out;
-
- ret = sctp_stream_alloc_in(stream, incnt, gfp);
- if (ret)
- goto in_err;
-
- goto out;
+ return 0;
-in_err:
- sched->free(stream);
- genradix_free(&stream->in);
-out_err:
- genradix_free(&stream->out);
- stream->outcnt = 0;
-out:
- return ret;
+ return sctp_stream_alloc_in(stream, incnt, gfp);
}
int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index 518b1b9bf89d68..1ad565ed56273c 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -160,7 +160,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc,
if (!SCTP_SO(&asoc->stream, i)->ext)
continue;
- ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
+ ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC);
if (ret)
goto err;
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43509c7e90fc28..f1c3b8eb4b3d33 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -517,7 +517,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
sk->sk_shutdown = 0;
sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
- sk->sk_rcvbuf = sysctl_tipc_rmem[1];
+ sk->sk_rcvbuf = READ_ONCE(sysctl_tipc_rmem[1]);
sk->sk_data_ready = tipc_data_ready;
sk->sk_write_space = tipc_write_space;
sk->sk_destruct = tipc_sock_destruct;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 879b9024678edf..9975df34d9c243 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -1376,8 +1376,13 @@ static int tls_device_down(struct net_device *netdev)
* by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW.
* Now release the ref taken above.
*/
- if (refcount_dec_and_test(&ctx->refcount))
+ if (refcount_dec_and_test(&ctx->refcount)) {
+ /* sk_destruct ran after tls_device_down took a ref, and
+ * it returned early. Complete the destruction here.
+ */
+ list_del(&ctx->list);
tls_device_free_ctx(ctx);
+ }
}
up_write(&device_offload_lock);