Merge tag 'net-6.10-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from bluetooth and netfilter.
Slim pickings this time, probably a combination of summer, DevConf.cz,
and the end of first half of the year at corporations.
Current release - regressions:
- Revert "igc: fix a log entry using uninitialized netdev", it traded
lack of netdev name in a printk() for a crash
Previous releases - regressions:
- Bluetooth: L2CAP: fix rejecting L2CAP_CONN_PARAM_UPDATE_REQ
- geneve: fix incorrectly setting lengths of inner headers in the
skb, confusing the drivers and causing mangled packets
- sched: initialize noop_qdisc owner to avoid false-positive
recursion detection (recursing on CPU 0), which bubbles up to user
space as a sendmsg() error, while noop_qdisc should silently drop
- netdevsim: fix backwards compatibility in nsim_get_iflink()
Previous releases - always broken:
- netfilter: ipset: fix race between namespace cleanup and gc in the
list:set type"
* tag 'net-6.10-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (35 commits)
bnxt_en: Adjust logging of firmware messages in case of released token in __hwrm_send()
af_unix: Read with MSG_PEEK loops if the first unread byte is OOB
bnxt_en: Cap the size of HWRM_PORT_PHY_QCFG forwarded response
gve: Clear napi->skb before dev_kfree_skb_any()
ionic: fix use after netif_napi_del()
Revert "igc: fix a log entry using uninitialized netdev"
net: bridge: mst: fix suspicious rcu usage in br_mst_set_state
net: bridge: mst: pass vlan group directly to br_mst_vlan_set_state
net/ipv6: Fix the RT cache flush via sysctl using a previous delay
net: stmmac: replace priv->speed with the portTransmitRate from the tc-cbs parameters
gve: ignore nonrelevant GSO type bits when processing TSO headers
net: pse-pd: Use EOPNOTSUPP error code instead of ENOTSUPP
netfilter: Use flowlabel flow key when re-routing mangled packets
netfilter: ipset: Fix race between namespace cleanup and gc in the list:set type
netfilter: nft_inner: validate mandatory meta and payload
tcp: use signed arithmetic in tcp_rtx_probe0_timed_out()
mailmap: map Geliang's new email address
mptcp: pm: update add_addr counters after connect
mptcp: pm: inc RmAddr MIB counter once per RM_ADDR ID
mptcp: ensure snd_una is properly initialized on connect
...
diff --git a/.mailmap b/.mailmap
index b6e9fe0..3f67060 100644
--- a/.mailmap
+++ b/.mailmap
@@ -219,6 +219,7 @@
Geliang Tang <geliang@kernel.org> <geliangtang@xiaomi.com>
Geliang Tang <geliang@kernel.org> <geliangtang@gmail.com>
Geliang Tang <geliang@kernel.org> <geliangtang@163.com>
+Geliang Tang <geliang@kernel.org> <tanggeliang@kylinos.cn>
Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c
index 811ebee..43ac680 100644
--- a/drivers/net/dsa/qca/qca8k-leds.c
+++ b/drivers/net/dsa/qca/qca8k-leds.c
@@ -431,8 +431,11 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p
init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d",
priv->internal_mdio_bus->id,
port_num);
- if (!init_data.devicename)
+ if (!init_data.devicename) {
+ fwnode_handle_put(led);
+ fwnode_handle_put(leds);
return -ENOMEM;
+ }
ret = devm_led_classdev_register_ext(priv->dev, &port_led->cdev, &init_data);
if (ret)
@@ -441,6 +444,7 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p
kfree(init_data.devicename);
}
+ fwnode_handle_put(leds);
return 0;
}
@@ -471,9 +475,13 @@ qca8k_setup_led_ctrl(struct qca8k_priv *priv)
* the correct port for LED setup.
*/
ret = qca8k_parse_port_leds(priv, port, qca8k_port_to_phy(port_num));
- if (ret)
+ if (ret) {
+ fwnode_handle_put(port);
+ fwnode_handle_put(ports);
return ret;
+ }
}
+ fwnode_handle_put(ports);
return 0;
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 656ab81c..bbc7edc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1434,6 +1434,57 @@ struct bnxt_l2_filter {
atomic_t refcnt;
};
+/* Compat version of hwrm_port_phy_qcfg_output capped at 96 bytes. The
+ * first 95 bytes are identical to hwrm_port_phy_qcfg_output in bnxt_hsi.h.
+ * The last valid byte in the compat version is different.
+ */
+struct hwrm_port_phy_qcfg_output_compat {
+ __le16 error_code;
+ __le16 req_type;
+ __le16 seq_id;
+ __le16 resp_len;
+ u8 link;
+ u8 active_fec_signal_mode;
+ __le16 link_speed;
+ u8 duplex_cfg;
+ u8 pause;
+ __le16 support_speeds;
+ __le16 force_link_speed;
+ u8 auto_mode;
+ u8 auto_pause;
+ __le16 auto_link_speed;
+ __le16 auto_link_speed_mask;
+ u8 wirespeed;
+ u8 lpbk;
+ u8 force_pause;
+ u8 module_status;
+ __le32 preemphasis;
+ u8 phy_maj;
+ u8 phy_min;
+ u8 phy_bld;
+ u8 phy_type;
+ u8 media_type;
+ u8 xcvr_pkg_type;
+ u8 eee_config_phy_addr;
+ u8 parallel_detect;
+ __le16 link_partner_adv_speeds;
+ u8 link_partner_adv_auto_mode;
+ u8 link_partner_adv_pause;
+ __le16 adv_eee_link_speed_mask;
+ __le16 link_partner_adv_eee_link_speed_mask;
+ __le32 xcvr_identifier_type_tx_lpi_timer;
+ __le16 fec_cfg;
+ u8 duplex_state;
+ u8 option_flags;
+ char phy_vendor_name[16];
+ char phy_vendor_partnumber[16];
+ __le16 support_pam4_speeds;
+ __le16 force_pam4_link_speed;
+ __le16 auto_pam4_link_speed_mask;
+ u8 link_partner_pam4_adv_speeds;
+ u8 valid;
+};
+
struct bnxt_link_info {
u8 phy_type;
u8 media_type;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
index 1df3d56..d2fd2d0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
@@ -680,7 +680,7 @@ static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx)
req_type);
else if (rc && rc != HWRM_ERR_CODE_PF_UNAVAILABLE)
hwrm_err(bp, ctx, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n",
- req_type, token->seq_id, rc);
+ req_type, le16_to_cpu(ctx->req->seq_id), rc);
rc = __hwrm_to_stderr(rc);
exit:
if (token)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 175192e..22898d3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -950,8 +950,11 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf,
struct hwrm_fwd_resp_input *req;
int rc;
- if (BNXT_FWD_RESP_SIZE_ERR(msg_size))
+ if (BNXT_FWD_RESP_SIZE_ERR(msg_size)) {
+ netdev_warn_once(bp->dev, "HWRM fwd response too big (%d bytes)\n",
+ msg_size);
return -EINVAL;
+ }
rc = hwrm_req_init(bp, req, HWRM_FWD_RESP);
if (!rc) {
@@ -1085,7 +1088,7 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf)
rc = bnxt_hwrm_exec_fwd_resp(
bp, vf, sizeof(struct hwrm_port_phy_qcfg_input));
} else {
- struct hwrm_port_phy_qcfg_output phy_qcfg_resp = {0};
+ struct hwrm_port_phy_qcfg_output_compat phy_qcfg_resp = {};
struct hwrm_port_phy_qcfg_input *phy_qcfg_req;
phy_qcfg_req =
@@ -1096,6 +1099,11 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf)
mutex_unlock(&bp->link_lock);
phy_qcfg_resp.resp_len = cpu_to_le16(sizeof(phy_qcfg_resp));
phy_qcfg_resp.seq_id = phy_qcfg_req->seq_id;
+ /* New SPEEDS2 fields are beyond the legacy structure, so
+ * clear the SPEEDS2_SUPPORTED flag.
+ */
+ phy_qcfg_resp.option_flags &=
+ ~PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED;
phy_qcfg_resp.valid = 1;
if (vf->flags & BNXT_VF_LINK_UP) {
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
index 96c6ea1..989b4dd 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
@@ -272,13 +272,12 @@ lio_vf_rep_copy_packet(struct octeon_device *oct,
pg_info->page_offset;
memcpy(skb->data, va, MIN_SKB_SIZE);
skb_put(skb, MIN_SKB_SIZE);
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+ pg_info->page,
+ pg_info->page_offset + MIN_SKB_SIZE,
+ len - MIN_SKB_SIZE,
+ LIO_RXBUFFER_SZ);
}
-
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
- pg_info->page,
- pg_info->page_offset + MIN_SKB_SIZE,
- len - MIN_SKB_SIZE,
- LIO_RXBUFFER_SZ);
} else {
struct octeon_skb_page_info *pg_info =
((struct octeon_skb_page_info *)(skb->cb));
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index c1c912d..1154c1d 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -647,11 +647,13 @@ static void gve_rx_skb_hash(struct sk_buff *skb,
skb_set_hash(skb, le32_to_cpu(compl_desc->hash), hash_type);
}
-static void gve_rx_free_skb(struct gve_rx_ring *rx)
+static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx)
{
if (!rx->ctx.skb_head)
return;
+ if (rx->ctx.skb_head == napi->skb)
+ napi->skb = NULL;
dev_kfree_skb_any(rx->ctx.skb_head);
rx->ctx.skb_head = NULL;
rx->ctx.skb_tail = NULL;
@@ -950,7 +952,7 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget)
err = gve_rx_dqo(napi, rx, compl_desc, complq->head, rx->q_num);
if (err < 0) {
- gve_rx_free_skb(rx);
+ gve_rx_free_skb(napi, rx);
u64_stats_update_begin(&rx->statss);
if (err == -ENOMEM)
rx->rx_skb_alloc_fail++;
@@ -993,7 +995,7 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget)
/* gve_rx_complete_skb() will consume skb if successful */
if (gve_rx_complete_skb(rx, napi, compl_desc, feat) != 0) {
- gve_rx_free_skb(rx);
+ gve_rx_free_skb(napi, rx);
u64_stats_update_begin(&rx->statss);
rx->rx_desc_err_dropped_pkt++;
u64_stats_update_end(&rx->statss);
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index fe1b26a..0b3cca3 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -555,28 +555,18 @@ static int gve_prep_tso(struct sk_buff *skb)
if (unlikely(skb_shinfo(skb)->gso_size < GVE_TX_MIN_TSO_MSS_DQO))
return -1;
+ if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+ return -EINVAL;
+
/* Needed because we will modify header. */
err = skb_cow_head(skb, 0);
if (err < 0)
return err;
tcp = tcp_hdr(skb);
-
- /* Remove payload length from checksum. */
paylen = skb->len - skb_transport_offset(skb);
-
- switch (skb_shinfo(skb)->gso_type) {
- case SKB_GSO_TCPV4:
- case SKB_GSO_TCPV6:
- csum_replace_by_diff(&tcp->check,
- (__force __wsum)htonl(paylen));
-
- /* Compute length of segmentation header. */
- header_len = skb_tcp_all_headers(skb);
- break;
- default:
- return -EINVAL;
- }
+ csum_replace_by_diff(&tcp->check, (__force __wsum)htonl(paylen));
+ header_len = skb_tcp_all_headers(skb);
if (unlikely(header_len > GVE_TX_MAX_HDR_SIZE_DQO))
return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index ff71fb1..a5fc020 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3535,6 +3535,9 @@ static int hns3_alloc_ring_buffers(struct hns3_enet_ring *ring)
ret = hns3_alloc_and_attach_buffer(ring, i);
if (ret)
goto out_buffer_fail;
+
+ if (!(i % HNS3_RESCHED_BD_NUM))
+ cond_resched();
}
return 0;
@@ -5107,6 +5110,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv)
}
u64_stats_init(&priv->ring[i].syncp);
+ cond_resched();
}
return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index acd756b..d36c4ed 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -214,6 +214,8 @@ enum hns3_nic_state {
#define HNS3_CQ_MODE_EQE 1U
#define HNS3_CQ_MODE_CQE 0U
+#define HNS3_RESCHED_BD_NUM 1024
+
enum hns3_pkt_l2t_type {
HNS3_L2_TYPE_UNICAST,
HNS3_L2_TYPE_MULTICAST,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 43cc6ee..82574ce 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3086,9 +3086,7 @@ static void hclge_push_link_status(struct hclge_dev *hdev)
static void hclge_update_link_status(struct hclge_dev *hdev)
{
- struct hnae3_handle *rhandle = &hdev->vport[0].roce;
struct hnae3_handle *handle = &hdev->vport[0].nic;
- struct hnae3_client *rclient = hdev->roce_client;
struct hnae3_client *client = hdev->nic_client;
int state;
int ret;
@@ -3112,8 +3110,15 @@ static void hclge_update_link_status(struct hclge_dev *hdev)
client->ops->link_status_change(handle, state);
hclge_config_mac_tnl_int(hdev, state);
- if (rclient && rclient->ops->link_status_change)
- rclient->ops->link_status_change(rhandle, state);
+
+ if (test_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state)) {
+ struct hnae3_handle *rhandle = &hdev->vport[0].roce;
+ struct hnae3_client *rclient = hdev->roce_client;
+
+ if (rclient && rclient->ops->link_status_change)
+ rclient->ops->link_status_change(rhandle,
+ state);
+ }
hclge_push_link_status(hdev);
}
@@ -11319,6 +11324,12 @@ static int hclge_init_client_instance(struct hnae3_client *client,
return ret;
}
+static bool hclge_uninit_need_wait(struct hclge_dev *hdev)
+{
+ return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+ test_bit(HCLGE_STATE_LINK_UPDATING, &hdev->state);
+}
+
static void hclge_uninit_client_instance(struct hnae3_client *client,
struct hnae3_ae_dev *ae_dev)
{
@@ -11327,7 +11338,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
if (hdev->roce_client) {
clear_bit(HCLGE_STATE_ROCE_REGISTERED, &hdev->state);
- while (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+ while (hclge_uninit_need_wait(hdev))
msleep(HCLGE_WAIT_RESET_DONE);
hdev->roce_client->ops->uninit_instance(&vport->roce, 0);
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 305e052..87b655b8 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -7032,6 +7032,8 @@ static int igc_probe(struct pci_dev *pdev,
device_set_wakeup_enable(&adapter->pdev->dev,
adapter->flags & IGC_FLAG_WOL_SUPPORTED);
+ igc_ptp_init(adapter);
+
igc_tsn_clear_schedule(adapter);
/* reset the hardware with the new settings */
@@ -7053,9 +7055,6 @@ static int igc_probe(struct pci_dev *pdev,
/* Check if Media Autosense is enabled */
adapter->ei = *ei;
- /* do hw tstamp init after resetting */
- igc_ptp_init(adapter);
-
/* print pcie link status and MAC address */
pcie_print_link_status(pdev);
netdev_info(netdev, "MAC: %pM\n", netdev->dev_addr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c53c99d..a605eae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4875,7 +4875,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
/* Verify if UDP port is being offloaded by HW */
if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port))
- return features;
+ return vxlan_features_check(skb, features);
#if IS_ENABLED(CONFIG_GENEVE)
/* Support Geneve offload for default UDP port */
@@ -4901,7 +4901,6 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
struct mlx5e_priv *priv = netdev_priv(netdev);
features = vlan_features_check(skb, features);
- features = vxlan_features_check(skb, features);
/* Validate if the tunneled packet is being offloaded by HW */
if (skb->encapsulation &&
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 24870da..1934e9d 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -304,10 +304,8 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq)
if (ret)
return ret;
- if (qcq->napi.poll)
- napi_enable(&qcq->napi);
-
if (qcq->flags & IONIC_QCQ_F_INTR) {
+ napi_enable(&qcq->napi);
irq_set_affinity_hint(qcq->intr.vector,
&qcq->intr.affinity_mask);
ionic_intr_mask(idev->intr_ctrl, qcq->intr.index,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index e254b21..65d7370 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -93,6 +93,7 @@ struct ethqos_emac_driver_data {
bool has_emac_ge_3;
const char *link_clk_name;
bool has_integrated_pcs;
+ u32 dma_addr_width;
struct dwmac4_addrs dwmac4_addrs;
};
@@ -276,6 +277,7 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = {
.has_emac_ge_3 = true,
.link_clk_name = "phyaux",
.has_integrated_pcs = true,
+ .dma_addr_width = 36,
.dwmac4_addrs = {
.dma_chan = 0x00008100,
.dma_chan_offset = 0x1000,
@@ -845,6 +847,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
plat_dat->flags |= STMMAC_FLAG_RX_CLK_RUNS_IN_LPI;
if (data->has_integrated_pcs)
plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS;
+ if (data->dma_addr_width)
+ plat_dat->host_dma_width = data->dma_addr_width;
if (ethqos->serdes_phy) {
plat_dat->serdes_powerup = qcom_ethqos_serdes_powerup;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 222540b..1562fbd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -343,10 +343,11 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
struct tc_cbs_qopt_offload *qopt)
{
u32 tx_queues_count = priv->plat->tx_queues_to_use;
+ s64 port_transmit_rate_kbps;
u32 queue = qopt->queue;
- u32 ptr, speed_div;
u32 mode_to_use;
u64 value;
+ u32 ptr;
int ret;
/* Queue 0 is not AVB capable */
@@ -355,30 +356,26 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
if (!priv->dma_cap.av)
return -EOPNOTSUPP;
+ port_transmit_rate_kbps = qopt->idleslope - qopt->sendslope;
+
/* Port Transmit Rate and Speed Divider */
- switch (priv->speed) {
+ switch (div_s64(port_transmit_rate_kbps, 1000)) {
case SPEED_10000:
- ptr = 32;
- speed_div = 10000000;
- break;
case SPEED_5000:
ptr = 32;
- speed_div = 5000000;
break;
case SPEED_2500:
- ptr = 8;
- speed_div = 2500000;
- break;
case SPEED_1000:
ptr = 8;
- speed_div = 1000000;
break;
case SPEED_100:
ptr = 4;
- speed_div = 100000;
break;
default:
- return -EOPNOTSUPP;
+ netdev_err(priv->dev,
+ "Invalid portTransmitRate %lld (idleSlope - sendSlope)\n",
+ port_transmit_rate_kbps);
+ return -EINVAL;
}
mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
@@ -398,10 +395,10 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
}
/* Final adjustments for HW */
- value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div);
+ value = div_s64(qopt->idleslope * 1024ll * ptr, port_transmit_rate_kbps);
priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0);
- value = div_s64(-qopt->sendslope * 1024ll * ptr, speed_div);
+ value = div_s64(-qopt->sendslope * 1024ll * ptr, port_transmit_rate_kbps);
priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0);
value = qopt->hicredit * 1024ll * 8;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 51495cb..838e85d 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -815,6 +815,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct geneve_dev *geneve,
const struct ip_tunnel_info *info)
{
+ bool inner_proto_inherit = geneve->cfg.inner_proto_inherit;
bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
const struct ip_tunnel_key *key = &info->key;
@@ -826,7 +827,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
__be16 sport;
int err;
- if (!skb_vlan_inet_prepare(skb))
+ if (!skb_vlan_inet_prepare(skb, inner_proto_inherit))
return -EINVAL;
if (!gs4)
@@ -908,7 +909,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
}
err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr),
- geneve->cfg.inner_proto_inherit);
+ inner_proto_inherit);
if (unlikely(err))
return err;
@@ -925,6 +926,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct geneve_dev *geneve,
const struct ip_tunnel_info *info)
{
+ bool inner_proto_inherit = geneve->cfg.inner_proto_inherit;
bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);
const struct ip_tunnel_key *key = &info->key;
@@ -935,7 +937,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
__be16 sport;
int err;
- if (!skb_vlan_inet_prepare(skb))
+ if (!skb_vlan_inet_prepare(skb, inner_proto_inherit))
return -EINVAL;
if (!gs6)
@@ -997,7 +999,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
ttl = ttl ? : ip6_dst_hoplimit(dst);
}
err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr),
- geneve->cfg.inner_proto_inherit);
+ inner_proto_inherit);
if (unlikely(err))
return err;
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index c22897b..017a610 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -324,7 +324,8 @@ static int nsim_get_iflink(const struct net_device *dev)
rcu_read_lock();
peer = rcu_dereference(nsim->peer);
- iflink = peer ? READ_ONCE(peer->netdev->ifindex) : 0;
+ iflink = peer ? READ_ONCE(peer->netdev->ifindex) :
+ READ_ONCE(dev->ifindex);
rcu_read_unlock();
return iflink;
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 3f9cbd7..a5684ef 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -2429,8 +2429,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event)
/* Handle remove event globally, it resets this state machine */
if (event == SFP_E_REMOVE) {
- if (sfp->sm_mod_state > SFP_MOD_PROBE)
- sfp_sm_mod_remove(sfp);
+ sfp_sm_mod_remove(sfp);
sfp_sm_mod_next(sfp, SFP_MOD_EMPTY, 0);
return;
}
diff --git a/include/dt-bindings/net/ti-dp83867.h b/include/dt-bindings/net/ti-dp83867.h
index 6fc4b44..b8a4f3f 100644
--- a/include/dt-bindings/net/ti-dp83867.h
+++ b/include/dt-bindings/net/ti-dp83867.h
@@ -1,10 +1,10 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
/*
* Device Tree constants for the Texas Instruments DP83867 PHY
*
* Author: Dan Murphy <dmurphy@ti.com>
*
- * Copyright: (C) 2015 Texas Instruments, Inc.
+ * Copyright (C) 2015-2024 Texas Instruments Incorporated - https://www.ti.com/
*/
#ifndef _DT_BINDINGS_TI_DP83867_H
diff --git a/include/dt-bindings/net/ti-dp83869.h b/include/dt-bindings/net/ti-dp83869.h
index 218b1a6..917114a 100644
--- a/include/dt-bindings/net/ti-dp83869.h
+++ b/include/dt-bindings/net/ti-dp83869.h
@@ -1,10 +1,10 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
/*
* Device Tree constants for the Texas Instruments DP83869 PHY
*
* Author: Dan Murphy <dmurphy@ti.com>
*
- * Copyright: (C) 2019 Texas Instruments, Inc.
+ * Copyright (C) 2015-2024 Texas Instruments Incorporated - https://www.ti.com/
*/
#ifndef _DT_BINDINGS_TI_DP83869_H
diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h
index 6d07c95..6eec24f 100644
--- a/include/linux/pse-pd/pse.h
+++ b/include/linux/pse-pd/pse.h
@@ -167,14 +167,14 @@ static inline int pse_ethtool_get_status(struct pse_control *psec,
struct netlink_ext_ack *extack,
struct pse_control_status *status)
{
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
static inline int pse_ethtool_set_config(struct pse_control *psec,
struct netlink_ext_ack *extack,
const struct pse_control_config *config)
{
- return -ENOTSUPP;
+ return -EOPNOTSUPP;
}
static inline bool pse_has_podl(struct pse_control *psec)
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 9231396..c43716e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -2113,18 +2113,46 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency,
{
u16 max_latency;
- if (min > max || min < 6 || max > 3200)
+ if (min > max) {
+ BT_WARN("min %d > max %d", min, max);
return -EINVAL;
+ }
- if (to_multiplier < 10 || to_multiplier > 3200)
+ if (min < 6) {
+ BT_WARN("min %d < 6", min);
return -EINVAL;
+ }
- if (max >= to_multiplier * 8)
+ if (max > 3200) {
+ BT_WARN("max %d > 3200", max);
return -EINVAL;
+ }
+
+ if (to_multiplier < 10) {
+ BT_WARN("to_multiplier %d < 10", to_multiplier);
+ return -EINVAL;
+ }
+
+ if (to_multiplier > 3200) {
+ BT_WARN("to_multiplier %d > 3200", to_multiplier);
+ return -EINVAL;
+ }
+
+ if (max >= to_multiplier * 8) {
+ BT_WARN("max %d >= to_multiplier %d * 8", max, to_multiplier);
+ return -EINVAL;
+ }
max_latency = (to_multiplier * 4 / max) - 1;
- if (latency > 499 || latency > max_latency)
+ if (latency > 499) {
+ BT_WARN("latency %d > 499", latency);
return -EINVAL;
+ }
+
+ if (latency > max_latency) {
+ BT_WARN("latency %d > max_latency %d", latency, max_latency);
+ return -EINVAL;
+ }
return 0;
}
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 9a6a08e..1db2417 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -461,9 +461,10 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb)
/* Variant of pskb_inet_may_pull().
*/
-static inline bool skb_vlan_inet_prepare(struct sk_buff *skb)
+static inline bool skb_vlan_inet_prepare(struct sk_buff *skb,
+ bool inner_proto_inherit)
{
- int nhlen = 0, maclen = ETH_HLEN;
+ int nhlen = 0, maclen = inner_proto_inherit ? 0 : ETH_HLEN;
__be16 type = skb->protocol;
/* Essentially this is skb_protocol(skb, true)
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 16daa79..a8a7d2b 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1194,7 +1194,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
cp.own_addr_type = own_addr_type;
cp.channel_map = hdev->le_adv_channel_map;
- cp.handle = instance;
+ cp.handle = adv ? adv->handle : instance;
if (flags & MGMT_ADV_FLAG_SEC_2M) {
cp.primary_phy = HCI_ADV_PHY_1M;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 5b509b7..aed0257 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4011,8 +4011,8 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd,
status = L2CAP_CS_AUTHOR_PEND;
chan->ops->defer(chan);
} else {
- l2cap_state_change(chan, BT_CONNECT2);
- result = L2CAP_CR_PEND;
+ l2cap_state_change(chan, BT_CONFIG);
+ result = L2CAP_CR_SUCCESS;
status = L2CAP_CS_NO_INFO;
}
} else {
@@ -4647,13 +4647,7 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn,
memset(&rsp, 0, sizeof(rsp));
- if (max > hcon->le_conn_max_interval) {
- BT_DBG("requested connection interval exceeds current bounds.");
- err = -EINVAL;
- } else {
- err = hci_check_conn_params(min, max, latency, to_multiplier);
- }
-
+ err = hci_check_conn_params(min, max, latency, to_multiplier);
if (err)
rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED);
else
diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c
index 3c66141..1820f09 100644
--- a/net/bridge/br_mst.c
+++ b/net/bridge/br_mst.c
@@ -73,11 +73,10 @@ int br_mst_get_state(const struct net_device *dev, u16 msti, u8 *state)
}
EXPORT_SYMBOL_GPL(br_mst_get_state);
-static void br_mst_vlan_set_state(struct net_bridge_port *p, struct net_bridge_vlan *v,
+static void br_mst_vlan_set_state(struct net_bridge_vlan_group *vg,
+ struct net_bridge_vlan *v,
u8 state)
{
- struct net_bridge_vlan_group *vg = nbp_vlan_group(p);
-
if (br_vlan_get_state(v) == state)
return;
@@ -103,7 +102,7 @@ int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state,
int err = 0;
rcu_read_lock();
- vg = nbp_vlan_group(p);
+ vg = nbp_vlan_group_rcu(p);
if (!vg)
goto out;
@@ -121,7 +120,7 @@ int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state,
if (v->brvlan->msti != msti)
continue;
- br_mst_vlan_set_state(p, v, state);
+ br_mst_vlan_set_state(vg, v, state);
}
out:
@@ -140,13 +139,13 @@ static void br_mst_vlan_sync_state(struct net_bridge_vlan *pv, u16 msti)
* it.
*/
if (v != pv && v->brvlan->msti == msti) {
- br_mst_vlan_set_state(pv->port, pv, v->state);
+ br_mst_vlan_set_state(vg, pv, v->state);
return;
}
}
/* Otherwise, start out in a new MSTI with all ports disabled. */
- return br_mst_vlan_set_state(pv->port, pv, BR_STATE_DISABLED);
+ return br_mst_vlan_set_state(vg, pv, BR_STATE_DISABLED);
}
int br_mst_vlan_set_msti(struct net_bridge_vlan *mv, u16 msti)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 83fe7f6..5bfd76a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -485,8 +485,12 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
{
const struct tcp_sock *tp = tcp_sk(sk);
const int timeout = TCP_RTO_MAX * 2;
- u32 rcv_delta;
+ s32 rcv_delta;
+ /* Note: timer interrupt might have been delayed by at least one jiffy,
+ * and tp->rcv_tstamp might very well have been written recently.
+ * rcv_delta can thus be negative.
+ */
rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp;
if (rcv_delta <= timeout)
return false;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 53d2558..5d989d8 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -36,6 +36,7 @@ int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff
.flowi6_uid = sock_net_uid(net, sk),
.daddr = iph->daddr,
.saddr = iph->saddr,
+ .flowlabel = ip6_flowinfo(iph),
};
int err;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f083d9f..952c2bf 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6343,12 +6343,12 @@ static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write,
if (!write)
return -EINVAL;
- net = (struct net *)ctl->extra1;
- delay = net->ipv6.sysctl.flush_delay;
ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (ret)
return ret;
+ net = (struct net *)ctl->extra1;
+ delay = net->ipv6.sysctl.flush_delay;
fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0);
return 0;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8c577b65..729faf8 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1439,7 +1439,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
*/
newsk->sk_gso_type = SKB_GSO_TCPV6;
- ip6_dst_store(newsk, dst, NULL, NULL);
inet6_sk_rx_dst_set(newsk, skb);
inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
@@ -1450,6 +1449,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
+ ip6_dst_store(newsk, dst, NULL, NULL);
+
newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
newnp->saddr = ireq->ir_v6_loc_addr;
newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 7f53e02..ea9e581 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -677,6 +677,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
unsigned int add_addr_accept_max;
struct mptcp_addr_info remote;
unsigned int subflows_max;
+ bool sf_created = false;
int i, nr;
add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
@@ -704,15 +705,18 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
if (nr == 0)
return;
- msk->pm.add_addr_accepted++;
- if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
- msk->pm.subflows >= subflows_max)
- WRITE_ONCE(msk->pm.accept_addr, false);
-
spin_unlock_bh(&msk->pm.lock);
for (i = 0; i < nr; i++)
- __mptcp_subflow_connect(sk, &addrs[i], &remote);
+ if (__mptcp_subflow_connect(sk, &addrs[i], &remote) == 0)
+ sf_created = true;
spin_lock_bh(&msk->pm.lock);
+
+ if (sf_created) {
+ msk->pm.add_addr_accepted++;
+ if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
+ msk->pm.subflows >= subflows_max)
+ WRITE_ONCE(msk->pm.accept_addr, false);
+ }
}
void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
@@ -814,10 +818,13 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
spin_lock_bh(&msk->pm.lock);
removed = true;
- __MPTCP_INC_STATS(sock_net(sk), rm_type);
+ if (rm_type == MPTCP_MIB_RMSUBFLOW)
+ __MPTCP_INC_STATS(sock_net(sk), rm_type);
}
if (rm_type == MPTCP_MIB_RMSUBFLOW)
__set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
+ else if (rm_type == MPTCP_MIB_RMADDR)
+ __MPTCP_INC_STATS(sock_net(sk), rm_type);
if (!removed)
continue;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 96b1138..bb7dca8 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3740,6 +3740,7 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
WRITE_ONCE(msk->write_seq, subflow->idsn);
WRITE_ONCE(msk->snd_nxt, subflow->idsn);
+ WRITE_ONCE(msk->snd_una, subflow->idsn);
if (likely(!__mptcp_check_fallback(msk)))
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 3184cc6..c7ae4d9 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1172,23 +1172,50 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
.len = IPSET_MAXNAMELEN - 1 },
};
-static void
-ip_set_destroy_set(struct ip_set *set)
-{
- pr_debug("set: %s\n", set->name);
-
- /* Must call it without holding any lock */
- set->variant->destroy(set);
- module_put(set->type->me);
- kfree(set);
-}
+/* In order to return quickly when destroying a single set, it is split
+ * into two stages:
+ * - Cancel garbage collector
+ * - Destroy the set itself via call_rcu()
+ */
static void
ip_set_destroy_set_rcu(struct rcu_head *head)
{
struct ip_set *set = container_of(head, struct ip_set, rcu);
- ip_set_destroy_set(set);
+ set->variant->destroy(set);
+ module_put(set->type->me);
+ kfree(set);
+}
+
+static void
+_destroy_all_sets(struct ip_set_net *inst)
+{
+ struct ip_set *set;
+ ip_set_id_t i;
+ bool need_wait = false;
+
+ /* First cancel gc's: set:list sets are flushed as well */
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = ip_set(inst, i);
+ if (set) {
+ set->variant->cancel_gc(set);
+ if (set->type->features & IPSET_TYPE_NAME)
+ need_wait = true;
+ }
+ }
+ /* Must wait for flush to be really finished */
+ if (need_wait)
+ rcu_barrier();
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = ip_set(inst, i);
+ if (set) {
+ ip_set(inst, i) = NULL;
+ set->variant->destroy(set);
+ module_put(set->type->me);
+ kfree(set);
+ }
+ }
}
static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
@@ -1202,11 +1229,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
if (unlikely(protocol_min_failed(attr)))
return -IPSET_ERR_PROTOCOL;
-
/* Commands are serialized and references are
* protected by the ip_set_ref_lock.
* External systems (i.e. xt_set) must call
- * ip_set_put|get_nfnl_* functions, that way we
+ * ip_set_nfnl_get_* functions, that way we
* can safely check references here.
*
* list:set timer can only decrement the reference
@@ -1214,8 +1240,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
* without holding the lock.
*/
if (!attr[IPSET_ATTR_SETNAME]) {
- /* Must wait for flush to be really finished in list:set */
- rcu_barrier();
read_lock_bh(&ip_set_ref_lock);
for (i = 0; i < inst->ip_set_max; i++) {
s = ip_set(inst, i);
@@ -1226,15 +1250,7 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
}
inst->is_destroyed = true;
read_unlock_bh(&ip_set_ref_lock);
- for (i = 0; i < inst->ip_set_max; i++) {
- s = ip_set(inst, i);
- if (s) {
- ip_set(inst, i) = NULL;
- /* Must cancel garbage collectors */
- s->variant->cancel_gc(s);
- ip_set_destroy_set(s);
- }
- }
+ _destroy_all_sets(inst);
/* Modified by ip_set_destroy() only, which is serialized */
inst->is_destroyed = false;
} else {
@@ -1255,12 +1271,12 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
features = s->type->features;
ip_set(inst, i) = NULL;
read_unlock_bh(&ip_set_ref_lock);
+ /* Must cancel garbage collectors */
+ s->variant->cancel_gc(s);
if (features & IPSET_TYPE_NAME) {
/* Must wait for flush to be really finished */
rcu_barrier();
}
- /* Must cancel garbage collectors */
- s->variant->cancel_gc(s);
call_rcu(&s->rcu, ip_set_destroy_set_rcu);
}
return 0;
@@ -2365,30 +2381,25 @@ ip_set_net_init(struct net *net)
}
static void __net_exit
+ip_set_net_pre_exit(struct net *net)
+{
+ struct ip_set_net *inst = ip_set_pernet(net);
+
+ inst->is_deleted = true; /* flag for ip_set_nfnl_put */
+}
+
+static void __net_exit
ip_set_net_exit(struct net *net)
{
struct ip_set_net *inst = ip_set_pernet(net);
- struct ip_set *set = NULL;
- ip_set_id_t i;
-
- inst->is_deleted = true; /* flag for ip_set_nfnl_put */
-
- nfnl_lock(NFNL_SUBSYS_IPSET);
- for (i = 0; i < inst->ip_set_max; i++) {
- set = ip_set(inst, i);
- if (set) {
- ip_set(inst, i) = NULL;
- set->variant->cancel_gc(set);
- ip_set_destroy_set(set);
- }
- }
- nfnl_unlock(NFNL_SUBSYS_IPSET);
+ _destroy_all_sets(inst);
kvfree(rcu_dereference_protected(inst->ip_set_list, 1));
}
static struct pernet_operations ip_set_net_ops = {
.init = ip_set_net_init,
+ .pre_exit = ip_set_net_pre_exit,
.exit = ip_set_net_exit,
.id = &ip_set_net_id,
.size = sizeof(struct ip_set_net),
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 54e2a1d..bfae706 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -79,7 +79,7 @@ list_set_kadd(struct ip_set *set, const struct sk_buff *skb,
struct set_elem *e;
int ret;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -99,7 +99,7 @@ list_set_kdel(struct ip_set *set, const struct sk_buff *skb,
struct set_elem *e;
int ret;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -188,9 +188,10 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
struct list_set *map = set->data;
struct set_adt_elem *d = value;
struct set_elem *e, *next, *prev = NULL;
- int ret;
+ int ret = 0;
- list_for_each_entry(e, &map->members, list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -201,6 +202,7 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
if (d->before == 0) {
ret = 1;
+ goto out;
} else if (d->before > 0) {
next = list_next_entry(e, list);
ret = !list_is_last(&e->list, &map->members) &&
@@ -208,9 +210,11 @@ list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
} else {
ret = prev && prev->id == d->refid;
}
- return ret;
+ goto out;
}
- return 0;
+out:
+ rcu_read_unlock();
+ return ret;
}
static void
@@ -239,7 +243,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
/* Find where to add the new entry */
n = prev = next = NULL;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_rcu(e, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -316,9 +320,9 @@ list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext,
{
struct list_set *map = set->data;
struct set_adt_elem *d = value;
- struct set_elem *e, *next, *prev = NULL;
+ struct set_elem *e, *n, *next, *prev = NULL;
- list_for_each_entry(e, &map->members, list) {
+ list_for_each_entry_safe(e, n, &map->members, list) {
if (SET_WITH_TIMEOUT(set) &&
ip_set_timeout_expired(ext_timeout(e, set)))
continue;
@@ -424,14 +428,8 @@ static void
list_set_destroy(struct ip_set *set)
{
struct list_set *map = set->data;
- struct set_elem *e, *n;
- list_for_each_entry_safe(e, n, &map->members, list) {
- list_del(&e->list);
- ip_set_put_byindex(map->net, e->id);
- ip_set_ext_destroy(set, e);
- kfree(e);
- }
+ WARN_ON_ONCE(!list_empty(&map->members));
kfree(map);
set->data = NULL;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index ba0d368..9139ce3 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -839,6 +839,9 @@ static int nft_meta_inner_init(const struct nft_ctx *ctx,
struct nft_meta *priv = nft_expr_priv(expr);
unsigned int len;
+ if (!tb[NFTA_META_KEY] || !tb[NFTA_META_DREG])
+ return -EINVAL;
+
priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY]));
switch (priv->key) {
case NFT_META_PROTOCOL:
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 0c43d74..50429cb 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -650,6 +650,10 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx,
struct nft_payload *priv = nft_expr_priv(expr);
u32 base;
+ if (!tb[NFTA_PAYLOAD_BASE] || !tb[NFTA_PAYLOAD_OFFSET] ||
+ !tb[NFTA_PAYLOAD_LEN] || !tb[NFTA_PAYLOAD_DREG])
+ return -EINVAL;
+
base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE]));
switch (base) {
case NFT_PAYLOAD_TUN_HEADER:
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2a637a1..e22ff00 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -676,6 +676,7 @@ struct Qdisc noop_qdisc = {
.qlen = 0,
.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock),
},
+ .owner = -1,
};
EXPORT_SYMBOL(noop_qdisc);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 8084627..5e695a9 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2625,18 +2625,18 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
if (skb == u->oob_skb) {
if (copied) {
skb = NULL;
- } else if (sock_flag(sk, SOCK_URGINLINE)) {
- if (!(flags & MSG_PEEK)) {
+ } else if (!(flags & MSG_PEEK)) {
+ if (sock_flag(sk, SOCK_URGINLINE)) {
WRITE_ONCE(u->oob_skb, NULL);
consume_skb(skb);
+ } else {
+ __skb_unlink(skb, &sk->sk_receive_queue);
+ WRITE_ONCE(u->oob_skb, NULL);
+ unlinked_skb = skb;
+ skb = skb_peek(&sk->sk_receive_queue);
}
- } else if (flags & MSG_PEEK) {
- skb = NULL;
- } else {
- __skb_unlink(skb, &sk->sk_receive_queue);
- WRITE_ONCE(u->oob_skb, NULL);
- unlinked_skb = skb;
- skb = skb_peek(&sk->sk_receive_queue);
+ } else if (!sock_flag(sk, SOCK_URGINLINE)) {
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
}
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 2b66c5f..108aeeb 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -2249,9 +2249,10 @@
if reset "remove invalid addresses"; then
pm_nl_set_limits $ns1 3 3
pm_nl_add_endpoint $ns1 10.0.12.1 flags signal
+ # broadcast IP: no packet for this address will be received on ns1
+ pm_nl_add_endpoint $ns1 224.0.0.1 flags signal
pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
- pm_nl_add_endpoint $ns1 10.0.14.1 flags signal
- pm_nl_set_limits $ns2 3 3
+ pm_nl_set_limits $ns2 2 2
addr_nr_ns1=-3 speed=10 \
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
