diff options
| author |   Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-16 13:05:42 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-09-16 13:05:42 -0700 |
| commit | fc0c0548c1a2e676d3a928aaed70f2d4d254e395 (patch) | |
| tree | 6875da13286e88f0eee2b045ecde268c1dc10270 | |
| parent | net: 6pack: Fix tx timeout and slot time (diff) | |
| parent | mlxbf_gige: clear valid_polarity upon open (diff) | |
| download | linux-dev-fc0c0548c1a2e676d3a928aaed70f2d4d254e395.tar.xz linux-dev-fc0c0548c1a2e676d3a928aaed70f2d4d254e395.zip | |
Merge tag 'net-5.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf.
Current release - regressions:
- vhost_net: fix OoB on sendmsg() failure
- mlx5: bridge, fix uninitialized variable usage
- bnxt_en: fix error recovery regression
Current release - new code bugs:
- bpf, mm: fix lockdep warning triggered by stack_map_get_build_id_offset()
Previous releases - regressions:
- r6040: restore MDIO clock frequency after MAC reset
- tcp: fix tp->undo_retrans accounting in tcp_sacktag_one()
- dsa: flush switchdev workqueue before tearing down CPU/DSA ports
Previous releases - always broken:
- ptp: dp83640: don't define PAGE0, avoid compiler warning
- igc: fix tunnel segmentation offloads
- phylink: update SFP selected interface on advertising changes
- stmmac: fix system hang caused by eee_ctrl_timer during suspend/resume
- mlx5e: fix mutual exclusion between CQE compression and HW TS
Misc:
- bpf, cgroups: fix cgroup v2 fallback on v1/v2 mixed mode
- sfc: fallback for lack of xdp tx queues
- hns3: add option to turn off page pool feature"
* tag 'net-5.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (67 commits)
mlxbf_gige: clear valid_polarity upon open
igc: fix tunnel offloading
net/{mlx5|nfp|bnxt}: Remove unnecessary RTNL lock assert
net: wan: wanxl: define CROSS_COMPILE_M68K
selftests: nci: replace unsigned int with int
net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports
Revert "net: phy: Uniform PHY driver access"
net: dsa: destroy the phylink instance on any error in dsa_slave_phy_setup
ptp: dp83640: don't define PAGE0
bnx2x: Fix enabling network interfaces without VFs
Revert "Revert "ipv4: fix memory leaks in ip_cmsg_send() callers""
tcp: fix tp->undo_retrans accounting in tcp_sacktag_one()
net-caif: avoid user-triggerable WARN_ON(1)
bpf, selftests: Add test case for mixed cgroup v1/v2
bpf, selftests: Add cgroup v1 net_cls classid helpers
bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode
bpf: Add oversize check before call kvcalloc()
net: hns3: fix the timing issue of VF clearing interrupt sources
net: hns3: fix the exception when query imp info
net: hns3: disable mac in flr process
...
80 files changed, 770 insertions, 384 deletions
diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml index 7f2578d48e3f..9eb4bb529ad5 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml +++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml @@ -19,7 +19,9 @@ properties: - const: allwinner,sun8i-v3s-emac - const: allwinner,sun50i-a64-emac - items: - - const: allwinner,sun50i-h6-emac + - enum: + - allwinner,sun20i-d1-emac + - allwinner,sun50i-h6-emac - const: allwinner,sun50i-a64-emac reg: diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 64d6dfa83122..267324889dd6 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1885,6 +1885,12 @@ static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gph reset_control_assert(gphy_fw->reset); + /* The vendor BSP uses a 200ms delay after asserting the reset line. + * Without this some users are observing that the PHY is not coming up + * on the MDIO bus. + */ + msleep(200); + ret = request_firmware(&fw, gphy_fw->fw_name, dev); if (ret) { dev_err(dev, "failed to load firmware: %s, error: %i\n", diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 1f63f50f73f1..bda5a9bf4f52 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -643,10 +643,8 @@ qca8k_mdio_busy_wait(struct mii_bus *bus, u32 reg, u32 mask) } static int -qca8k_mdio_write(struct mii_bus *salve_bus, int phy, int regnum, u16 data) +qca8k_mdio_write(struct mii_bus *bus, int phy, int regnum, u16 data) { - struct qca8k_priv *priv = salve_bus->priv; - struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -682,10 +680,8 @@ exit: } static int -qca8k_mdio_read(struct mii_bus *salve_bus, int phy, int regnum) +qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) { - struct qca8k_priv *priv = salve_bus->priv; - struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -727,6 +723,24 @@ exit: } static int +qca8k_internal_mdio_write(struct mii_bus *slave_bus, int phy, int regnum, u16 data) +{ + struct qca8k_priv *priv = slave_bus->priv; + struct mii_bus *bus = priv->bus; + + return qca8k_mdio_write(bus, phy, regnum, data); +} + +static int +qca8k_internal_mdio_read(struct mii_bus *slave_bus, int phy, int regnum) +{ + struct qca8k_priv *priv = slave_bus->priv; + struct mii_bus *bus = priv->bus; + + return qca8k_mdio_read(bus, phy, regnum); +} + +static int qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) { struct qca8k_priv *priv = ds->priv; @@ -775,8 +789,8 @@ qca8k_mdio_register(struct qca8k_priv *priv, struct device_node *mdio) bus->priv = (void *)priv; bus->name = "qca8k slave mii"; - bus->read = qca8k_mdio_read; - bus->write = qca8k_mdio_write; + bus->read = qca8k_internal_mdio_read; + bus->write = qca8k_internal_mdio_write; snprintf(bus->id, MII_BUS_ID_SIZE, "qca8k-%d", ds->index); diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 53660bc8d6ff..9afc712f5948 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -922,13 +922,16 @@ static void __init ne_add_devices(void) } } -#ifdef MODULE static int __init ne_init(void) { int retval; - ne_add_devices(); + + if (IS_MODULE(CONFIG_NE2000)) + ne_add_devices(); + retval = platform_driver_probe(&ne_driver, ne_drv_probe); - if (retval) { + + if (IS_MODULE(CONFIG_NE2000) && retval) { if (io[0] == 0) pr_notice("ne.c: You must supply \"io=0xNNN\"" " value(s) for ISA cards.\n"); @@ -941,18 +944,8 @@ static int __init ne_init(void) return retval; } module_init(ne_init); -#else /* MODULE */ -static int __init ne_init(void) -{ - int retval = platform_driver_probe(&ne_driver, ne_drv_probe); - - /* Unregister unused platform_devices. */ - ne_loop_rm_unreg(0); - return retval; -} -module_init(ne_init); -#ifdef CONFIG_NETDEV_LEGACY_INIT +#if !defined(MODULE) && defined(CONFIG_NETDEV_LEGACY_INIT) struct net_device * __init ne_probe(int unit) { int this_dev; @@ -994,7 +987,6 @@ struct net_device * __init ne_probe(int unit) return ERR_PTR(-ENODEV); } #endif -#endif /* MODULE */ static void __exit ne_exit(void) { diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index b5df7ad5a83f..032e8922b482 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -748,7 +748,7 @@ static void ni65_stop_start(struct net_device *dev,struct priv *p) #ifdef XMT_VIA_SKB skb_save[i] = p->tmd_skb[i]; #endif - buffer[i] = (u32) isa_bus_to_virt(tmdp->u.buffer); + buffer[i] = (unsigned long)isa_bus_to_virt(tmdp->u.buffer); blen[i] = tmdp->blen; tmdp->u.s.status = 0x0; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index f255fd0b16db..6fbf735fca31 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -1224,7 +1224,7 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, /* SR-IOV capability was enabled but there are no VFs*/ if (iov->total == 0) { - err = -EINVAL; + err = 0; goto failed; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ea0c45d33814..037767b370d5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2213,12 +2213,11 @@ static int bnxt_async_event_process(struct bnxt *bp, DIV_ROUND_UP(fw_health->polling_dsecs * HZ, bp->current_interval * 10); fw_health->tmr_counter = fw_health->tmr_multiplier; - if (!fw_health->enabled) { + if (!fw_health->enabled) fw_health->last_fw_heartbeat = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); - fw_health->last_fw_reset_cnt = - bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); - } + fw_health->last_fw_reset_cnt = + bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); netif_info(bp, drv, bp->dev, "Error recovery info: error recovery[1], master[%d], reset count[%u], health status: 0x%x\n", fw_health->master, fw_health->last_fw_reset_cnt, @@ -2730,6 +2729,9 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; int j; + if (!txr->tx_buf_ring) + continue; + for (j = 0; j < max_idx;) { struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j]; struct sk_buff *skb; @@ -2814,6 +2816,9 @@ static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) } skip_rx_tpa_free: + if (!rxr->rx_buf_ring) + goto skip_rx_buf_free; + for (i = 0; i < max_idx; i++) { struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i]; dma_addr_t mapping = rx_buf->mapping; @@ -2836,6 +2841,11 @@ skip_rx_tpa_free: kfree(data); } } + +skip_rx_buf_free: + if (!rxr->rx_agg_ring) + goto skip_rx_agg_free; + for (i = 0; i < max_agg_idx; i++) { struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i]; struct page *page = rx_agg_buf->page; @@ -2852,6 +2862,8 @@ skip_rx_tpa_free: __free_page(page); } + +skip_rx_agg_free: if (rxr->rx_page) { __free_page(rxr->rx_page); rxr->rx_page = NULL; @@ -2900,6 +2912,9 @@ static void bnxt_free_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) struct pci_dev *pdev = bp->pdev; int i; + if (!rmem->pg_arr) + goto skip_pages; + for (i = 0; i < rmem->nr_pages; i++) { if (!rmem->pg_arr[i]) continue; @@ -2909,6 +2924,7 @@ static void bnxt_free_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) rmem->pg_arr[i] = NULL; } +skip_pages: if (rmem->pg_tbl) { size_t pg_tbl_size = rmem->nr_pages * 8; @@ -3228,10 +3244,14 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) static void bnxt_free_cp_arrays(struct bnxt_cp_ring_info *cpr) { + struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + kfree(cpr->cp_desc_ring); cpr->cp_desc_ring = NULL; + ring->ring_mem.pg_arr = NULL; kfree(cpr->cp_desc_mapping); cpr->cp_desc_mapping = NULL; + ring->ring_mem.dma_arr = NULL; } static int bnxt_alloc_cp_arrays(struct bnxt_cp_ring_info *cpr, int n) @@ -12207,6 +12227,11 @@ static void bnxt_fw_reset_task(struct work_struct *work) return; } + if ((bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) && + bp->fw_health->enabled) { + bp->fw_health->last_fw_reset_cnt = + bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + } bp->fw_reset_state = 0; /* Make sure fw_reset_state is 0 before clearing the flag */ smp_mb__before_atomic(); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 46fae1acbeed..e6a4a768b10b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1884,9 +1884,6 @@ bnxt_tc_indr_block_cb_lookup(struct bnxt *bp, struct net_device *netdev) { struct bnxt_flower_indr_block_cb_priv *cb_priv; - /* All callback list access should be protected by RTNL. */ - ASSERT_RTNL(); - list_for_each_entry(cb_priv, &bp->tc_indr_block_list, list) if (cb_priv->tunnel_netdev == netdev) return cb_priv; diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c index 8b7b59908a1a..f66d22de5168 100644 --- a/drivers/net/ethernet/cadence/macb_pci.c +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -111,9 +111,9 @@ static void macb_remove(struct pci_dev *pdev) struct platform_device *plat_dev = pci_get_drvdata(pdev); struct macb_platform_data *plat_data = dev_get_platdata(&plat_dev->dev); - platform_device_unregister(plat_dev); clk_unregister(plat_data->pclk); clk_unregister(plat_data->hclk); + platform_device_unregister(plat_dev); } static const struct pci_device_id dev_id_table[] = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 22af3d6ce178..adc54a726661 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -61,6 +61,9 @@ static unsigned int tx_sgl = 1; module_param(tx_sgl, uint, 0600); MODULE_PARM_DESC(tx_sgl, "Minimum number of frags when using dma_map_sg() to optimize the IOMMU mapping"); +static bool page_pool_enabled = true; +module_param(page_pool_enabled, bool, 0400); + #define HNS3_SGL_SIZE(nfrag) (sizeof(struct scatterlist) * (nfrag) + \ sizeof(struct sg_table)) #define HNS3_MAX_SGL_SIZE ALIGN(HNS3_SGL_SIZE(HNS3_MAX_TSO_BD_NUM), \ @@ -73,6 +76,7 @@ MODULE_PARM_DESC(tx_sgl, "Minimum number of frags when using dma_map_sg() to opt #define HNS3_OUTER_VLAN_TAG 2 #define HNS3_MIN_TX_LEN 33U +#define HNS3_MIN_TUN_PKT_LEN 65U /* hns3_pci_tbl - PCI Device ID Table * @@ -1424,8 +1428,11 @@ static int hns3_set_l2l3l4(struct sk_buff *skb, u8 ol4_proto, l4.tcp->doff); break; case IPPROTO_UDP: - if (hns3_tunnel_csum_bug(skb)) - return skb_checksum_help(skb); + if (hns3_tunnel_csum_bug(skb)) { + int ret = skb_put_padto(skb, HNS3_MIN_TUN_PKT_LEN); + + return ret ? ret : skb_checksum_help(skb); + } hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S, @@ -4753,7 +4760,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring) goto out_with_desc_cb; if (!HNAE3_IS_TX_RING(ring)) { - hns3_alloc_page_pool(ring); + if (page_pool_enabled) + hns3_alloc_page_pool(ring); ret = hns3_alloc_ring_buffers(ring); if (ret) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 68ed1715ac52..87d96f82c318 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -1724,6 +1724,10 @@ hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len) } bd_num = le32_to_cpu(req->bd_num); + if (!bd_num) { + dev_err(&hdev->pdev->dev, "imp statistics bd number is 0!\n"); + return -EINVAL; + } desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL); if (!desc_src) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e55ba2e511b1..f1e46ba799f9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1528,9 +1528,10 @@ static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev) static int hclge_configure(struct hclge_dev *hdev) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + const struct cpumask *cpumask = cpu_online_mask; struct hclge_cfg cfg; unsigned int i; - int ret; + int node, ret; ret = hclge_get_cfg(hdev, &cfg); if (ret) @@ -1595,11 +1596,12 @@ static int hclge_configure(struct hclge_dev *hdev) hclge_init_kdump_kernel_config(hdev); - /* Set the init affinity based on pci func number */ - i = cpumask_weight(cpumask_of_node(dev_to_node(&hdev->pdev->dev))); - i = i ? PCI_FUNC(hdev->pdev->devfn) % i : 0; - cpumask_set_cpu(cpumask_local_spread(i, dev_to_node(&hdev->pdev->dev)), - &hdev->affinity_mask); + /* Set the affinity based on numa node */ + node = dev_to_node(&hdev->pdev->dev); + if (node != NUMA_NO_NODE) + cpumask = cpumask_of_node(node); + + cpumask_copy(&hdev->affinity_mask, cpumask); return ret; } @@ -8125,11 +8127,12 @@ static void hclge_ae_stop(struct hnae3_handle *handle) hclge_clear_arfs_rules(hdev); spin_unlock_bh(&hdev->fd_rule_lock); - /* If it is not PF reset, the firmware will disable the MAC, + /* If it is not PF reset or FLR, the firmware will disable the MAC, * so it only need to stop phy here. */ if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && - hdev->reset_type != HNAE3_FUNC_RESET) { + hdev->reset_type != HNAE3_FUNC_RESET && + hdev->reset_type != HNAE3_FLR_RESET) { hclge_mac_stop_phy(hdev); hclge_update_link_status(hdev); return; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 82e727020120..a69e892277b3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2465,6 +2465,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) hclgevf_enable_vector(&hdev->misc_vector, false); event_cause = hclgevf_check_evt_cause(hdev, &clearval); + if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) + hclgevf_clear_event_cause(hdev, clearval); switch (event_cause) { case HCLGEVF_VECTOR0_EVENT_RST: @@ -2477,10 +2479,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) break; } - if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) { - hclgevf_clear_event_cause(hdev, clearval); + if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) hclgevf_enable_vector(&hdev->misc_vector, true); - } return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index a775c69e4fd7..a4579b340120 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4700,6 +4700,22 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, return 0; } + if (adapter->failover_pending) { + adapter->init_done_rc = -EAGAIN; + netdev_dbg(netdev, "Failover pending, ignoring login response\n"); + complete(&adapter->init_done); + /* login response buffer will be released on reset */ + return 0; + } + + if (adapter->failover_pending) { + adapter->init_done_rc = -EAGAIN; + netdev_dbg(netdev, "Failover pending, ignoring login response\n"); + complete(&adapter->init_done); + /* login response buffer will be released on reset */ + return 0; + } + netdev->mtu = adapter->req_mtu - ETH_HLEN; netdev_dbg(adapter->netdev, "Login Response Buffer:\n"); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index eadcb9958346..3c4f08d20414 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -695,6 +695,7 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) { if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) { set_bit(ICE_FLAG_RDMA_ENA, pf->flags); + set_bit(ICE_FLAG_AUX_ENA, pf->flags); ice_plug_aux_dev(pf); } } @@ -707,5 +708,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { ice_unplug_aux_dev(pf); clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + clear_bit(ICE_FLAG_AUX_ENA, pf->flags); } #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 1f2afdf6cd48..adcc9a251595 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -271,6 +271,12 @@ int ice_plug_aux_dev(struct ice_pf *pf) struct auxiliary_device *adev; int ret; + /* if this PF doesn't support a technology that requires auxiliary + * devices, then gracefully exit + */ + if (!ice_is_aux_ena(pf)) + return 0; + iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); if (!iadev) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index b877efae61df..0e19b4d02e62 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6350,7 +6350,9 @@ static int igc_probe(struct pci_dev *pdev, if (pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= netdev->features; + netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; + netdev->mpls_features |= NETIF_F_HW_CSUM; + netdev->hw_enc_features |= netdev->vlan_features; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index e84287ffc7ce..dcf9f27ba2ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -658,11 +658,10 @@ static const struct devlink_param enable_rdma_param = static int mlx5_devlink_rdma_param_register(struct devlink *devlink) { - struct mlx5_core_dev *dev = devlink_priv(devlink); union devlink_param_value value; int err; - if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev)) + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return 0; err = devlink_param_register(devlink, &enable_rdma_param); @@ -679,9 +678,7 @@ static int mlx5_devlink_rdma_param_register(struct devlink *devlink) static void mlx5_devlink_rdma_param_unregister(struct devlink *devlink) { - struct mlx5_core_dev *dev = devlink_priv(devlink); - - if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND) || MLX5_ESWITCH_MANAGER(dev)) + if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return; devlink_param_unpublish(devlink, &enable_rdma_param); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 3f8a98093f8c..f9cf9fb31547 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -1007,7 +1007,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn); if (err) { mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err); - return err; + goto err_cancel_work; } err = mlx5_fw_tracer_create_mkey(tracer); @@ -1031,6 +1031,7 @@ err_notifier_unregister: mlx5_core_destroy_mkey(dev, &tracer->buff.mkey); err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); +err_cancel_work: cancel_work_sync(&tracer->read_fw_strings_work); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 669a75f3537a..7b8c8187543a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -922,7 +922,7 @@ void mlx5e_set_rx_mode_work(struct work_struct *work); int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr); int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr); -int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val); +int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val, bool rx_filter); int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 0c38c2e319be..b5ddaa82755f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -137,7 +137,7 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr u16 vport_num, esw_owner_vhca_id; struct netlink_ext_ack *extack; int ifindex = upper->ifindex; - int err; + int err = 0; if (!netif_is_bridge_master(upper)) return 0; @@ -244,7 +244,7 @@ mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev, struct netlink_ext_ack *extack = switchdev_notifier_info_to_extack(&port_attr_info->info); const struct switchdev_attr *attr = port_attr_info->attr; u16 vport_num, esw_owner_vhca_id; - int err; + int err = 0; if (!mlx5_esw_bridge_lower_rep_vport_num_vhca_id_get(dev, br_offloads->esw, &vport_num, &esw_owner_vhca_id)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 51a4d80f7fa3..de03684528bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -300,9 +300,6 @@ mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv, { struct mlx5e_rep_indr_block_priv *cb_priv; - /* All callback list access should be protected by RTNL. */ - ASSERT_RTNL(); - list_for_each_entry(cb_priv, &rpriv->uplink_priv.tc_indr_block_priv_list, list) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index bf0313e2682b..13056cb9757d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -572,7 +572,7 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann if (res->features & MLX5E_RX_RES_FEATURE_PTP) { u32 rqn; - if (mlx5e_channels_get_ptp_rqn(chs, &rqn)) + if (!mlx5e_channels_get_ptp_rqn(chs, &rqn)) rqn = res->drop_rqn; err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 2cfd12953909..306fb5d6a36d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1884,7 +1884,7 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable) return set_pflag_cqe_based_moder(netdev, enable, true); } -int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val) +int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val, bool rx_filter) { bool curr_val = MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS); struct mlx5e_params new_params; @@ -1896,8 +1896,7 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val if (curr_val == new_val) return 0; - if (new_val && !priv->profile->rx_ptp_support && - priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) { + if (new_val && !priv->profile->rx_ptp_support && rx_filter) { netdev_err(priv->netdev, "Profile doesn't support enabling of CQE compression while hardware time-stamping is enabled.\n"); return -EINVAL; @@ -1905,7 +1904,7 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val new_params = priv->channels.params; MLX5E_SET_PFLAG(&new_params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val); - if (priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE) + if (rx_filter) new_params.ptp_rx = new_val; if (new_params.ptp_rx == priv->channels.params.ptp_rx) @@ -1928,12 +1927,14 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + bool rx_filter; int err; if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; - err = mlx5e_modify_rx_cqe_compression_locked(priv, enable); + rx_filter = priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE; + err = mlx5e_modify_rx_cqe_compression_locked(priv, enable, rx_filter); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 47efd858964d..3fd515e7bf30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3554,14 +3554,14 @@ static int mlx5e_hwstamp_config_no_ptp_rx(struct mlx5e_priv *priv, bool rx_filte if (!rx_filter) /* Reset CQE compression to Admin default */ - return mlx5e_modify_rx_cqe_compression_locked(priv, rx_cqe_compress_def); + return mlx5e_modify_rx_cqe_compression_locked(priv, rx_cqe_compress_def, false); if (!MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS)) return 0; /* Disable CQE compression */ netdev_warn(priv->netdev, "Disabling RX cqe compression\n"); - err = mlx5e_modify_rx_cqe_compression_locked(priv, false); + err = mlx5e_modify_rx_cqe_compression_locked(priv, false, true); if (err) netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9fe8e3c204d6..fe501ba88bea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1682,14 +1682,13 @@ static int build_match_list(struct match_list *match_head, curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); if (!curr_match) { + rcu_read_unlock(); free_match_list(match_head, ft_locked); - err = -ENOMEM; - goto out; + return -ENOMEM; } curr_match->g = g; list_add_tail(&curr_match->list, &match_head->list); } -out: rcu_read_unlock(); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 49ca57c6d31d..ca5690b0a7ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -927,9 +927,12 @@ void mlx5_lag_disable_change(struct mlx5_core_dev *dev) struct mlx5_core_dev *dev1; struct mlx5_lag *ldev; + ldev = mlx5_lag_dev(dev); + if (!ldev) + return; + mlx5_dev_list_lock(); - ldev = mlx5_lag_dev(dev); dev0 = ldev->pf[MLX5_LAG_P1].dev; dev1 = ldev->pf[MLX5_LAG_P2].dev; @@ -946,8 +949,11 @@ void mlx5_lag_enable_change(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev; - mlx5_dev_list_lock(); ldev = mlx5_lag_dev(dev); + if (!ldev) + return; + + mlx5_dev_list_lock(); ldev->mode_changes_in_progress--; mlx5_dev_list_unlock(); mlx5_queue_bond_work(ldev, 0); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 3e85b17f5857..6704f5c1aa32 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -142,6 +142,13 @@ static int mlxbf_gige_open(struct net_device *netdev) err = mlxbf_gige_clean_port(priv); if (err) goto free_irqs; + + /* Clear driver's valid_polarity to match hardware, + * since the above call to clean_port() resets the + * receive polarity used by hardware. + */ + priv->valid_polarity = 0; + err = mlxbf_gige_rx_init(priv); if (err) goto free_irqs; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index c1310ea1c216..d5c485a6d284 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -398,9 +398,7 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context *hwc, u16 q_depth, int err; u16 i; - dma_buf = kzalloc(sizeof(*dma_buf) + - q_depth * sizeof(struct hwc_work_request), - GFP_KERNEL); + dma_buf = kzalloc(struct_size(dma_buf, reqs, q_depth), GFP_KERNEL); if (!dma_buf) return -ENOMEM; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 556c3495211d..64c0ef57ad42 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1767,9 +1767,6 @@ nfp_flower_indr_block_cb_priv_lookup(struct nfp_app *app, struct nfp_flower_indr_block_cb_priv *cb_priv; struct nfp_flower_priv *priv = app->priv; - /* All callback list access should be protected by RTNL. */ - ASSERT_RTNL(); - list_for_each_entry(cb_priv, &priv->indr_block_cb_priv, list) if (cb_priv->netdev == netdev) return cb_priv; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 6e5a6cc97d0e..24cd41567775 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3367,6 +3367,7 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, struct qed_nvm_image_att *p_image_att) { enum nvm_image_type type; + int rc; u32 i; /* Translate image_id into MFW definitions */ @@ -3395,7 +3396,10 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, return -EINVAL; } - qed_mcp_nvm_info_populate(p_hwfn); + rc = qed_mcp_nvm_info_populate(p_hwfn); + if (rc) + return rc; + for (i = 0; i < p_hwfn->nvm_info.num_images; i++) if (type == p_hwfn->nvm_info.image_att[i].image_type) break; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 0a2f34fc8b24..27dffa299ca6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -1354,10 +1354,10 @@ static int qlcnic_83xx_copy_fw_file(struct qlcnic_adapter *adapter) struct qlc_83xx_fw_info *fw_info = adapter->ahw->fw_info; const struct firmware *fw = fw_info->fw; u32 dest, *p_cache, *temp; - int i, ret = -EIO; __le32 *temp_le; u8 data[16]; size_t size; + int i, ret; u64 addr; temp = vzalloc(fw->size); diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 4b2eca5e08e2..01ef5efd7bc2 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -119,6 +119,8 @@ #define PHY_ST 0x8A /* PHY status register */ #define MAC_SM 0xAC /* MAC status machine */ #define MAC_SM_RST 0x0002 /* MAC status machine reset */ +#define MD_CSC 0xb6 /* MDC speed control register */ +#define MD_CSC_DEFAULT 0x0030 #define MAC_ID 0xBE /* Identifier register */ #define TX_DCNT 0x80 /* TX descriptor count */ @@ -355,8 +357,9 @@ static void r6040_reset_mac(struct r6040_private *lp) { void __iomem *ioaddr = lp->base; int limit = MAC_DEF_TIMEOUT; - u16 cmd; + u16 cmd, md_csc; + md_csc = ioread16(ioaddr + MD_CSC); iowrite16(MAC_RST, ioaddr + MCR1); while (limit--) { cmd = ioread16(ioaddr + MCR1); @@ -368,6 +371,10 @@ static void r6040_reset_mac(struct r6040_private *lp) iowrite16(MAC_SM_RST, ioaddr + MAC_SM); iowrite16(0, ioaddr + MAC_SM); mdelay(5); + + /* Restore MDIO clock frequency */ + if (md_csc != MD_CSC_DEFAULT) + iowrite16(md_csc, ioaddr + MD_CSC); } static void r6040_init_mac_regs(struct net_device *dev) diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index e5b0d795c301..3dbea028b325 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -166,32 +166,46 @@ static int efx_allocate_msix_channels(struct efx_nic *efx, * We need a channel per event queue, plus a VI per tx queue. * This may be more pessimistic than it needs to be. */ - if (n_channels + n_xdp_ev > max_channels) { - netif_err(efx, drv, efx->net_dev, - "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", - n_xdp_ev, n_channels, max_channels); - netif_err(efx, drv, efx->net_dev, - "XDP_TX and XDP_REDIRECT will not work on this interface"); - efx->n_xdp_channels = 0; - efx->xdp_tx_per_channel = 0; - efx->xdp_tx_queue_count = 0; + if (n_channels >= max_channels) { + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; + netif_warn(efx, drv, efx->net_dev, + "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", + n_xdp_ev, n_channels, max_channels); + netif_warn(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT might decrease device's performance\n"); } else if (n_channels + n_xdp_tx > efx->max_vis) { - netif_err(efx, drv, efx->net_dev, - "Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n", - n_xdp_tx, n_channels, efx->max_vis); - netif_err(efx, drv, efx->net_dev, - "XDP_TX and XDP_REDIRECT will not work on this interface"); - efx->n_xdp_channels = 0; - efx->xdp_tx_per_channel = 0; - efx->xdp_tx_queue_count = 0; + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_BORROWED; + netif_warn(efx, drv, efx->net_dev, + "Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n", + n_xdp_tx, n_channels, efx->max_vis); + netif_warn(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT might decrease device's performance\n"); + } else if (n_channels + n_xdp_ev > max_channels) { + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_SHARED; + netif_warn(efx, drv, efx->net_dev, + "Insufficient resources for %d XDP event queues (%d other channels, max %d)\n", + n_xdp_ev, n_channels, max_channels); + + n_xdp_ev = max_channels - n_channels; + netif_warn(efx, drv, efx->net_dev, + "XDP_TX and XDP_REDIRECT will work with reduced performance (%d cpus/tx_queue)\n", + DIV_ROUND_UP(n_xdp_tx, tx_per_ev * n_xdp_ev)); } else { + efx->xdp_txq_queues_mode = EFX_XDP_TX_QUEUES_DEDICATED; + } + + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_BORROWED) { efx->n_xdp_channels = n_xdp_ev; efx->xdp_tx_per_channel = tx_per_ev; efx->xdp_tx_queue_count = n_xdp_tx; n_channels += n_xdp_ev; netif_dbg(efx, drv, efx->net_dev, "Allocating %d TX and %d event queues for XDP\n", - n_xdp_tx, n_xdp_ev); + n_xdp_ev * tx_per_ev, n_xdp_ev); + } else { + efx->n_xdp_channels = 0; + efx->xdp_tx_per_channel = 0; + efx->xdp_tx_queue_count = n_xdp_tx; } if (vec_count < n_channels) { @@ -858,6 +872,20 @@ rollback: goto out; } +static inline int +efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, + struct efx_tx_queue *tx_queue) +{ + if (xdp_queue_number >= efx->xdp_tx_queue_count) + return -EINVAL; + + netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", + tx_queue->channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); + efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + return 0; +} + int efx_set_channels(struct efx_nic *efx) { struct efx_tx_queue *tx_queue; @@ -896,20 +924,9 @@ int efx_set_channels(struct efx_nic *efx) if (efx_channel_is_xdp_tx(channel)) { efx_for_each_channel_tx_queue(tx_queue, channel) { tx_queue->queue = next_queue++; - - /* We may have a few left-over XDP TX - * queues owing to xdp_tx_queue_count - * not dividing evenly by EFX_MAX_TXQ_PER_CHANNEL. - * We still allocate and probe those - * TXQs, but never use them. - */ - if (xdp_queue_number < efx->xdp_tx_queue_count) { - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); - efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) xdp_queue_number++; - } } } else { efx_for_each_channel_tx_queue(tx_queue, channel) { @@ -918,10 +935,35 @@ int efx_set_channels(struct efx_nic *efx) channel->channel, tx_queue->label, tx_queue->queue); } + + /* If XDP is borrowing queues from net stack, it must use the queue + * with no csum offload, which is the first one of the channel + * (note: channel->tx_queue_by_type is not initialized yet) + */ + if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { + tx_queue = &channel->tx_queue[0]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; + } } } } - WARN_ON(xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number > efx->xdp_tx_queue_count); + + /* If we have more CPUs than assigned XDP TX queues, assign the already + * existing queues to the exceeding CPUs + */ + next_queue = 0; + while (xdp_queue_number < efx->xdp_tx_queue_count) { + tx_queue = efx->xdp_tx_queues[next_queue++]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; + } rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 9b4b25704271..f6981810039d 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -782,6 +782,12 @@ struct efx_async_filter_insertion { #define EFX_RPS_MAX_IN_FLIGHT 8 #endif /* CONFIG_RFS_ACCEL */ +enum efx_xdp_tx_queues_mode { + EFX_XDP_TX_QUEUES_DEDICATED, /* one queue per core, locking not needed */ + EFX_XDP_TX_QUEUES_SHARED, /* each queue used by more than 1 core */ + EFX_XDP_TX_QUEUES_BORROWED /* queues borrowed from net stack */ +}; + /** * struct efx_nic - an Efx NIC * @name: Device name (net device name or bus id before net device registered) @@ -820,6 +826,7 @@ struct efx_async_filter_insertion { * should be allocated for this NIC * @xdp_tx_queue_count: Number of entries in %xdp_tx_queues. * @xdp_tx_queues: Array of pointers to tx queues used for XDP transmit. + * @xdp_txq_queues_mode: XDP TX queues sharing strategy. * @rxq_entries: Size of receive queues requested by user. * @txq_entries: Size of transmit queues requested by user. * @txq_stop_thresh: TX queue fill level at or above which we stop it. @@ -979,6 +986,7 @@ struct efx_nic { unsigned int xdp_tx_queue_count; struct efx_tx_queue **xdp_tx_queues; + enum efx_xdp_tx_queues_mode xdp_txq_queues_mode; unsigned rxq_entries; unsigned txq_entries; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 0c6650d2e239..d16e031e95f4 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -428,23 +428,32 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, unsigned int len; int space; int cpu; - int i; + int i = 0; - cpu = raw_smp_processor_id(); + if (unlikely(n && !xdpfs)) + return -EINVAL; + if (unlikely(!n)) + return 0; - if (!efx->xdp_tx_queue_count || - unlikely(cpu >= efx->xdp_tx_queue_count)) + cpu = raw_smp_processor_id(); + if (unlikely(cpu >= efx->xdp_tx_queue_count)) return -EINVAL; tx_queue = efx->xdp_tx_queues[cpu]; if (unlikely(!tx_queue)) return -EINVAL; - if (unlikely(n && !xdpfs)) - return -EINVAL; + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) + HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu); - if (!n) - return 0; + /* If we're borrowing net stack queues we have to handle stop-restart + * or we might block the queue and it will be considered as frozen + */ + if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { + if (netif_tx_queue_stopped(tx_queue->core_txq)) + goto unlock; + efx_tx_maybe_stop_queue(tx_queue); + } /* Check for available space. We should never need multiple * descriptors per frame. @@ -484,6 +493,10 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (flush && i > 0) efx_nic_push_buffers(tx_queue); +unlock: + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) + HARD_TX_UNLOCK(efx->net_dev, tx_queue->core_txq); + return i == 0 ? -EIO : i; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ece02b35a6ce..553c4403258a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -309,7 +309,7 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv) priv->clk_csr = STMMAC_CSR_100_150M; else if ((clk_rate >= CSR_F_150M) && (clk_rate < CSR_F_250M)) priv->clk_csr = STMMAC_CSR_150_250M; - else if ((clk_rate >= CSR_F_250M) && (clk_rate < CSR_F_300M)) + else if ((clk_rate >= CSR_F_250M) && (clk_rate <= CSR_F_300M)) priv->clk_csr = STMMAC_CSR_250_300M; } @@ -7118,7 +7118,6 @@ int stmmac_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct stmmac_priv *priv = netdev_priv(ndev); u32 chan; - int ret; if (!ndev || !netif_running(ndev)) return 0; @@ -7150,13 +7149,6 @@ int stmmac_suspend(struct device *dev) } else { stmmac_mac_set(priv, priv->ioaddr, false); pinctrl_pm_select_sleep_state(priv->device); - /* Disable clock in case of PWM is off */ - clk_disable_unprepare(priv->plat->clk_ptp_ref); - ret = pm_runtime_force_suspend(dev); - if (ret) { - mutex_unlock(&priv->lock); - return ret; - } } mutex_unlock(&priv->lock); @@ -7242,12 +7234,6 @@ int stmmac_resume(struct device *dev) priv->irq_wake = 0; } else { pinctrl_pm_select_default_state(priv->device); - /* enable the clk previously disabled */ - ret = pm_runtime_force_resume(dev); - if (ret) - return ret; - if (priv->plat->clk_ptp_ref) - clk_prepare_enable(priv->plat->clk_ptp_ref); /* reset the phy so that it's ready */ if (priv->mii) stmmac_mdio_reset(priv->mii); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5ca710844cc1..62cec9bfcd33 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -9,6 +9,7 @@ *******************************************************************************/ #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/module.h> #include <linux/io.h> #include <linux/of.h> @@ -771,9 +772,52 @@ static int __maybe_unused stmmac_runtime_resume(struct device *dev) return stmmac_bus_clks_config(priv, true); } +static int __maybe_unused stmmac_pltfr_noirq_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + int ret; + + if (!netif_running(ndev)) + return 0; + + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { + /* Disable clock in case of PWM is off */ + clk_disable_unprepare(priv->plat->clk_ptp_ref); + + ret = pm_runtime_force_suspend(dev); + if (ret) + return ret; + } + + return 0; +} + +static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + int ret; + + if (!netif_running(ndev)) + return 0; + + if (!device_may_wakeup(priv->device) || !priv->plat->pmt) { + /* enable the clk previously disabled */ + ret = pm_runtime_force_resume(dev); + if (ret) + return ret; + + clk_prepare_enable(priv->plat->clk_ptp_ref); + } + + return 0; +} + const struct dev_pm_ops stmmac_pltfr_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_suspend, stmmac_pltfr_resume) SET_RUNTIME_PM_OPS(stmmac_runtime_suspend, stmmac_runtime_resume, NULL) + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(stmmac_pltfr_noirq_suspend, stmmac_pltfr_noirq_resume) }; EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops); diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 2324e1b93e37..1da334f54944 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -430,7 +430,8 @@ static void ipa_table_init_add(struct gsi_trans *trans, bool filter, * table region determines the number of entries it has. */ if (filter) { - count = hweight32(ipa->filter_map); + /* Include one extra "slot" to hold the filter map itself */ + count = 1 + hweight32(ipa->filter_map); hash_count = hash_mem->size ? count : 0; } else { count = mem->size / sizeof(__le64); diff --git a/drivers/net/phy/dp83640_reg.h b/drivers/net/phy/dp83640_reg.h index 21aa24c741b9..daae7fa58fb8 100644 --- a/drivers/net/phy/dp83640_reg.h +++ b/drivers/net/phy/dp83640_reg.h @@ -5,7 +5,7 @@ #ifndef HAVE_DP83640_REGISTERS #define HAVE_DP83640_REGISTERS -#define PAGE0 0x0000 +/* #define PAGE0 0x0000 */ #define PHYCR2 0x001c /* PHY Control Register 2 */ #define PAGE4 0x0004 diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 9e2891d8e8dd..ba5ad86ec826 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -233,9 +233,11 @@ static DEFINE_MUTEX(phy_fixup_lock); static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) { + struct device_driver *drv = phydev->mdio.dev.driver; + struct phy_driver *phydrv = to_phy_driver(drv); struct net_device *netdev = phydev->attached_dev; - if (!phydev->drv->suspend) + if (!drv || !phydrv->suspend) return false; /* PHY not attached? May suspend if the PHY has not already been diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index a1464b764d4d..0a0abe8e4be0 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1607,6 +1607,32 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, if (config.an_enabled && phylink_is_empty_linkmode(config.advertising)) return -EINVAL; + /* If this link is with an SFP, ensure that changes to advertised modes + * also cause the associated interface to be selected such that the + * link can be configured correctly. + */ + if (pl->sfp_port && pl->sfp_bus) { + config.interface = sfp_select_interface(pl->sfp_bus, + config.advertising); + if (config.interface == PHY_INTERFACE_MODE_NA) { + phylink_err(pl, + "selection of interface failed, advertisement %*pb\n", + __ETHTOOL_LINK_MODE_MASK_NBITS, + config.advertising); + return -EINVAL; + } + + /* Revalidate with the selected interface */ + linkmode_copy(support, pl->supported); + if (phylink_validate(pl, support, &config)) { + phylink_err(pl, "validation of %s/%s with support %*pb failed\n", + phylink_an_mode_str(pl->cur_link_an_mode), + phy_modes(config.interface), + __ETHTOOL_LINK_MODE_MASK_NBITS, support); + return -EINVAL; + } + } + mutex_lock(&pl->state_mutex); pl->link_config.speed = config.speed; pl->link_config.duplex = config.duplex; @@ -2186,7 +2212,9 @@ static int phylink_sfp_config(struct phylink *pl, u8 mode, if (phy_interface_mode_is_8023z(iface) && pl->phydev) return -EINVAL; - changed = !linkmode_equal(pl->supported, support); + changed = !linkmode_equal(pl->supported, support) || + !linkmode_equal(pl->link_config.advertising, + config.advertising); if (changed) { linkmode_copy(pl->supported, support); linkmode_copy(pl->link_config.advertising, config.advertising); diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile index f6b92efffc94..480bcd1f6c1c 100644 --- a/drivers/net/wan/Makefile +++ b/drivers/net/wan/Makefile @@ -34,6 +34,8 @@ obj-$(CONFIG_SLIC_DS26522) += slic_ds26522.o clean-files := wanxlfw.inc $(obj)/wanxl.o: $(obj)/wanxlfw.inc +CROSS_COMPILE_M68K = m68k-linux-gnu- + ifeq ($(CONFIG_WANXL_BUILD_FIRMWARE),y) ifeq ($(ARCH),m68k) M68KCC = $(CC) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 3a249ee7e144..28ef323882fb 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -467,7 +467,7 @@ static void vhost_tx_batch(struct vhost_net *net, .num = nvq->batched_xdp, .ptr = nvq->xdp, }; - int err; + int i, err; if (nvq->batched_xdp == 0) goto signal_used; @@ -476,6 +476,15 @@ static void vhost_tx_batch(struct vhost_net *net, err = sock->ops->sendmsg(sock, msghdr, 0); if (unlikely(err < 0)) { vq_err(&nvq->vq, "Fail to batch sending packets\n"); + + /* free pages owned by XDP; since this is an unlikely error path, + * keep it simple and avoid more complex bulk update for the + * used pages + */ + for (i = 0; i < nvq->batched_xdp; ++i) + put_page(virt_to_head_page(nvq->xdp[i].data)); + nvq->batched_xdp = 0; + nvq->done_idx = 0; return; } diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index e1c705fdfa7c..db2e147e069f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * - * On legacy hierarchies, net_prio and net_cls controllers directly set - * attributes on each sock which can then be tested by the network layer. - * On the default hierarchy, each sock is associated with the cgroup it was - * created in and the networking layer can match the cgroup directly. - * - * To avoid carrying all three cgroup related fields separately in sock, - * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. - * On boot, sock_cgroup_data records the cgroup that the sock was created - * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overridden to carry prioidx and/or - * classid. The two modes are distinguished by whether the lowest bit is - * set. Clear bit indicates cgroup pointer while set bit prioidx and - * classid. - * - * While userland may start using net_prio or net_cls at any time, once - * either is used, cgroup2 matching no longer works. There is no reason to - * mix the two and this is in line with how legacy and v2 compatibility is - * handled. On mode switch, cgroup references which are already being - * pointed to by socks may be leaked. While this can be remedied by adding - * synchronization around sock_cgroup_data, given that the number of leaked - * cgroups is bound and highly unlikely to be high, this seems to be the - * better trade-off. + * On legacy hierarchies, net_prio and net_cls controllers directly + * set attributes on each sock which can then be tested by the network + * layer. On the default hierarchy, each sock is associated with the + * cgroup it was created in and the networking layer can match the + * cgroup directly. */ struct sock_cgroup_data { - union { -#ifdef __LITTLE_ENDIAN - struct { - u8 is_data : 1; - u8 no_refcnt : 1; - u8 unused : 6; - u8 padding; - u16 prioidx; - u32 classid; - } __packed; -#else - struct { - u32 classid; - u16 prioidx; - u8 padding; - u8 unused : 6; - u8 no_refcnt : 1; - u8 is_data : 1; - } __packed; + struct cgroup *cgroup; /* v2 */ +#ifdef CONFIG_CGROUP_NET_CLASSID + u32 classid; /* v1 */ +#endif +#ifdef CONFIG_CGROUP_NET_PRIO + u16 prioidx; /* v1 */ #endif - u64 val; - }; }; -/* - * There's a theoretical window where the following accessors race with - * updaters and return part of the previous pointer as the prioidx or - * classid. Such races are short-lived and the result isn't critical. - */ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { - /* fallback to 1 which is always the ID of the root cgroup */ - return (skcd->is_data & 1) ? skcd->prioidx : 1; +#ifdef CONFIG_CGROUP_NET_PRIO + return READ_ONCE(skcd->prioidx); +#else + return 1; +#endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { - /* fallback to 0 which is the unconfigured default classid */ - return (skcd->is_data & 1) ? skcd->classid : 0; +#ifdef CONFIG_CGROUP_NET_CLASSID + return READ_ONCE(skcd->classid); +#else + return 0; +#endif } -/* - * If invoked concurrently, the updaters may clobber each other. The - * caller is responsible for synchronization. - */ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_prioidx(&skcd_buf) == prioidx) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.prioidx = prioidx; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_PRIO + WRITE_ONCE(skcd->prioidx, prioidx); +#endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_classid(&skcd_buf) == classid) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.classid = classid; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_CLASSID + WRITE_ONCE(skcd->classid, classid); +#endif } #else /* CONFIG_SOCK_CGROUP_DATA */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7bf60454a313..75c151413fda 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) -extern spinlock_t cgroup_sk_update_lock; -#endif - -void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - unsigned long v; - - /* - * @skcd->val is 64bit but the following is safe on 32bit too as we - * just need the lower ulong to be written and read atomically. - */ - v = READ_ONCE(skcd->val); - - if (v & 3) - return &cgrp_dfl_root.cgrp; - - return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; -#else - return (struct cgroup *)(unsigned long)skcd->val; -#endif + return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index b179f1e3541a..96e113e23d04 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm) up_read(&mm->mmap_lock); } -static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) -{ - if (mmap_read_trylock(mm)) { - rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); - return true; - } - return false; -} - static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { __mmap_lock_trace_released(mm, false); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6bdb0db3e825..841e2f0f5240 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk, WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); WRITE_ONCE(prev->next, newsk); - list->qlen++; + WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, diff --git a/include/net/dsa.h b/include/net/dsa.h index f9a17145255a..258867eff230 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -447,6 +447,11 @@ static inline bool dsa_port_is_user(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_USER; } +static inline bool dsa_port_is_unused(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_UNUSED; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index ca3cd9aaa6ce..7b4afb7d96db 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0-only +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h index e546b18d27da..a4b040793f44 100644 --- a/kernel/bpf/disasm.h +++ b/kernel/bpf/disasm.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index e8eefdf8cf3e..09a3fd97d329 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -179,7 +179,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, * with build_id. */ if (!user || !current || !current->mm || irq_work_busy || - !mmap_read_trylock_non_owner(current->mm)) { + !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; @@ -204,9 +204,15 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } if (!work) { - mmap_read_unlock_non_owner(current->mm); + mmap_read_unlock(current->mm); } else { work->mm = current->mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); irq_work_queue(&work->irq_work); } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 047ac4b4703b..e76b55917905 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -9912,6 +9912,8 @@ static int check_btf_line(struct bpf_verifier_env *env, nr_linfo = attr->line_info_cnt; if (!nr_linfo) return 0; + if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info)) + return -EINVAL; rec_size = attr->line_info_rec_size; if (rec_size < MIN_BPF_LINEINFO_SIZE || diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 881ce1470beb..8afa8690d288 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6572,74 +6572,44 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - -DEFINE_SPINLOCK(cgroup_sk_update_lock); -static bool cgroup_sk_alloc_disabled __read_mostly; - -void cgroup_sk_alloc_disable(void) -{ - if (cgroup_sk_alloc_disabled) - return; - pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n"); - cgroup_sk_alloc_disabled = true; -} - -#else - -#define cgroup_sk_alloc_disabled false - -#endif - void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) { - skcd->no_refcnt = 1; - return; - } - /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) return; rcu_read_lock(); - while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->val = (unsigned long)cset->dfl_cgrp; + skcd->cgroup = cset->dfl_cgrp; cgroup_bpf_get(cset->dfl_cgrp); break; } cpu_relax(); } - rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { - if (skcd->val) { - if (skcd->no_refcnt) - return; - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); - cgroup_bpf_get(sock_cgroup_ptr(skcd)); - } + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(cgrp); + cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); - if (skcd->no_refcnt) - return; cgroup_bpf_put(cgrp); cgroup_put(cgrp); } diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 37b67194c0df..414dc5671c45 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -53,20 +53,6 @@ struct chnl_net { enum caif_states state; }; -static void robust_list_del(struct list_head *delete_node) -{ - struct list_head *list_node; - struct list_head *n; - ASSERT_RTNL(); - list_for_each_safe(list_node, n, &chnl_net_list) { - if (list_node == delete_node) { - list_del(list_node); - return; - } - } - WARN_ON(1); -} - static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) { struct sk_buff *skb; @@ -364,6 +350,7 @@ static int chnl_net_init(struct net_device *dev) ASSERT_RTNL(); priv = netdev_priv(dev); strncpy(priv->name, dev->name, sizeof(priv->name)); + INIT_LIST_HEAD(&priv->list_field); return 0; } @@ -372,7 +359,7 @@ static void chnl_net_uninit(struct net_device *dev) struct chnl_net *priv; ASSERT_RTNL(); priv = netdev_priv(dev); - robust_list_del(&priv->list_field); + list_del_init(&priv->list_field); } static const struct net_device_ops netdev_ops = { @@ -537,7 +524,7 @@ static void __exit chnl_exit_module(void) rtnl_lock(); list_for_each_safe(list_node, _tmp, &chnl_net_list) { dev = list_entry(list_node, struct chnl_net, list_field); - list_del(list_node); + list_del_init(list_node); delete_device(dev); } rtnl_unlock(); diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index b49c57d35a88..1a6a86693b74 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -71,11 +71,8 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n) struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + if (sock) sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); - spin_unlock(&cgroup_sk_update_lock); - } if (--ctx->batch == 0) { ctx->batch = UPDATE_CLASSID_BATCH; return n + 1; @@ -121,8 +118,6 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, struct css_task_iter it; struct task_struct *p; - cgroup_sk_alloc_disable(); - cs->classid = (u32)value; css_task_iter_start(css, 0, &it); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 99a431c56f23..8456dfbe2eb4 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -207,8 +207,6 @@ static ssize_t write_priomap(struct kernfs_open_file *of, if (!dev) return -ENODEV; - cgroup_sk_alloc_disable(); - rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); @@ -221,12 +219,10 @@ static ssize_t write_priomap(struct kernfs_open_file *of, static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + + if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); - spin_unlock(&cgroup_sk_update_lock); - } return 0; } @@ -235,8 +231,6 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; - cgroup_sk_alloc_disable(); - cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index c5c74a34d139..91e7a2202697 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -94,6 +94,8 @@ struct sock *dccp_create_openreq_child(const struct sock *sk, newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; newdp->dccps_service_list = NULL; + newdp->dccps_hc_rx_ccid = NULL; + newdp->dccps_hc_tx_ccid = NULL; newdp->dccps_service = dreq->dreq_service; newdp->dccps_timestamp_echo = dreq->dreq_timestamp_echo; newdp->dccps_timestamp_time = dreq->dreq_timestamp_time; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1dc45e40f961..41f36ad8b0ec 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -345,6 +345,11 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } +void dsa_flush_workqueue(void) +{ + flush_workqueue(dsa_owq); +} + int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 1b2b25d7bd02..eef13cd20f19 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -897,6 +897,33 @@ static void dsa_switch_teardown(struct dsa_switch *ds) ds->setup = false; } +/* First tear down the non-shared, then the shared ports. This ensures that + * all work items scheduled by our switchdev handlers for user ports have + * completed before we destroy the refcounting kept on the shared ports. + */ +static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) + dsa_port_teardown(dp); + + dsa_flush_workqueue(); + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) + dsa_port_teardown(dp); +} + +static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + dsa_switch_teardown(dp->ds); +} + static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) { struct dsa_port *dp; @@ -923,26 +950,13 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) return 0; teardown: - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); + dsa_tree_teardown_ports(dst); - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); + dsa_tree_teardown_switches(dst); return err; } -static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); - - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); -} - static int dsa_tree_setup_master(struct dsa_switch_tree *dst) { struct dsa_port *dp; @@ -1052,6 +1066,8 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_master(dst); + dsa_tree_teardown_ports(dst); + dsa_tree_teardown_switches(dst); dsa_tree_teardown_cpu_ports(dst); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 33ab7d7af9eb..a5c9bc7b66c6 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -170,6 +170,7 @@ void dsa_tag_driver_put(const struct dsa_device_ops *ops); const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); +void dsa_flush_workqueue(void); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 662ff531d4e2..a2bf2d8ac65b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1854,13 +1854,11 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) * use the switch internal MDIO bus instead */ ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags); - if (ret) { - netdev_err(slave_dev, - "failed to connect to port %d: %d\n", - dp->index, ret); - phylink_destroy(dp->pl); - return ret; - } + } + if (ret) { + netdev_err(slave_dev, "failed to connect to PHY: %pe\n", + ERR_PTR(ret)); + phylink_destroy(dp->pl); } return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3f7bd7ae7d7a..141e85e6422b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1346,7 +1346,7 @@ static u8 tcp_sacktag_one(struct sock *sk, if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans > 0 && after(end_seq, tp->undo_marker)) - tp->undo_retrans--; + tp->undo_retrans = max_t(int, 0, tp->undo_retrans - pcount); if ((sacked & TCPCB_SACKED_ACKED) && before(start_seq, state->reord)) state->reord = start_seq; diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index 0d122edc368d..b91003538d87 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -935,7 +935,7 @@ static int __init udp_tunnel_nic_init_module(void) { int err; - udp_tunnel_nic_workqueue = alloc_workqueue("udp_tunnel_nic", 0, 0); + udp_tunnel_nic_workqueue = alloc_ordered_workqueue("udp_tunnel_nic", 0); if (!udp_tunnel_nic_workqueue) return -ENOMEM; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1bec5b22f80d..0371d2c14145 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1378,7 +1378,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, int err = -ENOMEM; int allow_create = 1; int replace_required = 0; - int sernum = fib6_new_sernum(info->nl_net); if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) @@ -1478,7 +1477,7 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (!err) { if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); - __fib6_update_sernum_upto_root(rt, sernum); + __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); fib6_start_gc(info->nl_net, rt); } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 53486b162f01..93271a2632b8 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -869,8 +869,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) } if (tunnel->version == L2TP_HDR_VER_3 && - l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { + l2tp_session_dec_refcount(session); goto invalid; + } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); diff --git a/net/mctp/route.c b/net/mctp/route.c index 5265525011ad..5ca186d53cb0 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -1083,8 +1083,10 @@ static void __net_exit mctp_routes_net_exit(struct net *net) { struct mctp_route *rt; + rcu_read_lock(); list_for_each_entry_rcu(rt, &net->mctp.routes, list) mctp_route_release(rt); + rcu_read_unlock(); } static struct pernet_operations mctp_net_ops = { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 543365f58e97..2a2bc64f75cf 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -46,6 +46,8 @@ * Copyright (C) 2011, <lokec@ccs.neu.edu> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/ethtool.h> #include <linux/types.h> #include <linux/mm.h> diff --git a/net/tipc/socket.c b/net/tipc/socket.c index a0a27d87f631..ad570c2450be 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2423,7 +2423,7 @@ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk, u32 dport, struct sk_buff_head *xmitq) { - unsigned long time_limit = jiffies + 2; + unsigned long time_limit = jiffies + usecs_to_jiffies(20000); struct sk_buff *skb; unsigned int lim; atomic_t *dcnt; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index eb47b9de2380..92345c9bb60c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3073,7 +3073,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, other = unix_peer(sk); if (other && unix_peer(other) != sk && - unix_recvq_full(other) && + unix_recvq_full_lockless(other) && unix_dgram_peer_wake_me(sk, other)) writable = 0; diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 033051717ba5..f3daa44a8266 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -12,27 +12,36 @@ #include <unistd.h> #include <ftw.h> - #include "cgroup_helpers.h" /* * To avoid relying on the system setup, when setup_cgroup_env is called - * we create a new mount namespace, and cgroup namespace. The cgroup2 - * root is mounted at CGROUP_MOUNT_PATH - * - * Unfortunately, most people don't have cgroupv2 enabled at this point in time. - * It's easier to create our own mount namespace and manage it ourselves. + * we create a new mount namespace, and cgroup namespace. The cgroupv2 + * root is mounted at CGROUP_MOUNT_PATH. Unfortunately, most people don't + * have cgroupv2 enabled at this point in time. It's easier to create our + * own mount namespace and manage it ourselves. We assume /mnt exists. * - * We assume /mnt exists. + * Related cgroupv1 helpers are named *classid*(), since we only use the + * net_cls controller for tagging net_cls.classid. We assume the default + * mount under /sys/fs/cgroup/net_cls, which should be the case for the + * vast majority of users. */ #define WALK_FD_LIMIT 16 + #define CGROUP_MOUNT_PATH "/mnt" +#define CGROUP_MOUNT_DFLT "/sys/fs/cgroup" +#define NETCLS_MOUNT_PATH CGROUP_MOUNT_DFLT "/net_cls" #define CGROUP_WORK_DIR "/cgroup-test-work-dir" + #define format_cgroup_path(buf, path) \ snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \ CGROUP_WORK_DIR, path) +#define format_classid_path(buf) \ + snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH, \ + CGROUP_WORK_DIR) + /** * enable_all_controllers() - Enable all available cgroup v2 controllers * @@ -139,8 +148,7 @@ static int nftwfunc(const char *filename, const struct stat *statptr, return 0; } - -static int join_cgroup_from_top(char *cgroup_path) +static int join_cgroup_from_top(const char *cgroup_path) { char cgroup_procs_path[PATH_MAX + 1]; pid_t pid = getpid(); @@ -313,3 +321,114 @@ int cgroup_setup_and_join(const char *path) { } return cg_fd; } + +/** + * setup_classid_environment() - Setup the cgroupv1 net_cls environment + * + * After calling this function, cleanup_classid_environment should be called + * once testing is complete. + * + * This function will print an error to stderr and return 1 if it is unable + * to setup the cgroup environment. If setup is successful, 0 is returned. + */ +int setup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + + if (mount("tmpfs", CGROUP_MOUNT_DFLT, "tmpfs", 0, NULL) && + errno != EBUSY) { + log_err("mount cgroup base"); + return 1; + } + + if (mkdir(NETCLS_MOUNT_PATH, 0777) && errno != EEXIST) { + log_err("mkdir cgroup net_cls"); + return 1; + } + + if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") && + errno != EBUSY) { + log_err("mount cgroup net_cls"); + return 1; + } + + cleanup_classid_environment(); + + if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) { + log_err("mkdir cgroup work dir"); + return 1; + } + + return 0; +} + +/** + * set_classid() - Set a cgroupv1 net_cls classid + * @id: the numeric classid + * + * Writes the passed classid into the cgroup work dir's net_cls.classid + * file in order to later on trigger socket tagging. + * + * On success, it returns 0, otherwise on failure it returns 1. If there + * is a failure, it prints the error to stderr. + */ +int set_classid(unsigned int id) +{ + char cgroup_workdir[PATH_MAX - 42]; + char cgroup_classid_path[PATH_MAX + 1]; + int fd, rc = 0; + + format_classid_path(cgroup_workdir); + snprintf(cgroup_classid_path, sizeof(cgroup_classid_path), + "%s/net_cls.classid", cgroup_workdir); + + fd = open(cgroup_classid_path, O_WRONLY); + if (fd < 0) { + log_err("Opening cgroup classid: %s", cgroup_classid_path); + return 1; + } + + if (dprintf(fd, "%u\n", id) < 0) { + log_err("Setting cgroup classid"); + rc = 1; + } + + close(fd); + return rc; +} + +/** + * join_classid() - Join a cgroupv1 net_cls classid + * + * This function expects the cgroup work dir to be already created, as we + * join it here. This causes the process sockets to be tagged with the given + * net_cls classid. + * + * On success, it returns 0, otherwise on failure it returns 1. + */ +int join_classid(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + return join_cgroup_from_top(cgroup_workdir); +} + +/** + * cleanup_classid_environment() - Cleanup the cgroupv1 net_cls environment + * + * At call time, it moves the calling process to the root cgroup, and then + * runs the deletion process. + * + * On failure, it will print an error to stderr, and try to continue. + */ +void cleanup_classid_environment(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + join_cgroup_from_top(NETCLS_MOUNT_PATH); + nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT); +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index 5fe3d88e4f0d..629da3854b3e 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_HELPERS_H #define __CGROUP_HELPERS_H + #include <errno.h> #include <string.h> @@ -8,12 +9,21 @@ #define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \ __FILE__, __LINE__, clean_errno(), ##__VA_ARGS__) - +/* cgroupv2 related */ int cgroup_setup_and_join(const char *path); int create_and_get_cgroup(const char *path); +unsigned long long get_cgroup_id(const char *path); + int join_cgroup(const char *path); + int setup_cgroup_environment(void); void cleanup_cgroup_environment(void); -unsigned long long get_cgroup_id(const char *path); -#endif +/* cgroupv1 related */ +int set_classid(unsigned int id); +int join_classid(void); + +int setup_classid_environment(void); +void cleanup_classid_environment(void); + +#endif /* __CGROUP_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 7e9f6375757a..6db1af8fdee7 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -208,11 +208,26 @@ error_close: static int connect_fd_to_addr(int fd, const struct sockaddr_storage *addr, - socklen_t addrlen) + socklen_t addrlen, const bool must_fail) { - if (connect(fd, (const struct sockaddr *)addr, addrlen)) { - log_err("Failed to connect to server"); - return -1; + int ret; + + errno = 0; + ret = connect(fd, (const struct sockaddr *)addr, addrlen); + if (must_fail) { + if (!ret) { + log_err("Unexpected success to connect to server"); + return -1; + } + if (errno != EPERM) { + log_err("Unexpected error from connect to server"); + return -1; + } + } else { + if (ret) { + log_err("Failed to connect to server"); + return -1; + } } return 0; @@ -257,7 +272,7 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts) strlen(opts->cc) + 1)) goto error_close; - if (connect_fd_to_addr(fd, &addr, addrlen)) + if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail)) goto error_close; return fd; @@ -289,7 +304,7 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms) return -1; } - if (connect_fd_to_addr(client_fd, &addr, len)) + if (connect_fd_to_addr(client_fd, &addr, len, false)) return -1; return 0; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index da7e132657d5..d198181a5648 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -20,6 +20,7 @@ typedef __u16 __sum16; struct network_helper_opts { const char *cc; int timeout_ms; + bool must_fail; }; /* ipv4 test vector */ diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c new file mode 100644 index 000000000000..ab3b9bc5e6d1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include "connect4_dropper.skel.h" + +#include "cgroup_helpers.h" +#include "network_helpers.h" + +static int run_test(int cgroup_fd, int server_fd, bool classid) +{ + struct network_helper_opts opts = { + .must_fail = true, + }; + struct connect4_dropper *skel; + int fd, err = 0; + + skel = connect4_dropper__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return -1; + + skel->links.connect_v4_dropper = + bpf_program__attach_cgroup(skel->progs.connect_v4_dropper, + cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.connect_v4_dropper, "prog_attach")) { + err = -1; + goto out; + } + + if (classid && !ASSERT_OK(join_classid(), "join_classid")) { + err = -1; + goto out; + } + + fd = connect_to_fd_opts(server_fd, &opts); + if (fd < 0) + err = -1; + else + close(fd); +out: + connect4_dropper__destroy(skel); + return err; +} + +void test_cgroup_v1v2(void) +{ + struct network_helper_opts opts = {}; + int server_fd, client_fd, cgroup_fd; + static const int port = 60123; + + /* Step 1: Check base connectivity works without any BPF. */ + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) + return; + client_fd = connect_to_fd_opts(server_fd, &opts); + if (!ASSERT_GE(client_fd, 0, "client_fd")) { + close(server_fd); + return; + } + close(client_fd); + close(server_fd); + + /* Step 2: Check BPF policy prog attached to cgroups drops connectivity. */ + cgroup_fd = test__join_cgroup("/connect_dropper"); + if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd")) + return; + server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0); + if (!ASSERT_GE(server_fd, 0, "server_fd")) { + close(cgroup_fd); + return; + } + ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only"); + setup_classid_environment(); + set_classid(42); + ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2"); + cleanup_classid_environment(); + close(server_fd); + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c index 53f0e0fa1a53..37c20b5ffa70 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c +++ b/tools/testing/selftests/bpf/prog_tests/task_pt_regs.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE #include <test_progs.h> -#include <linux/ptrace.h> #include "test_task_pt_regs.skel.h" void test_task_pt_regs(void) diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c new file mode 100644 index 000000000000..b565d997810a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> + +#include <sys/socket.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define VERDICT_REJECT 0 +#define VERDICT_PROCEED 1 + +SEC("cgroup/connect4") +int connect_v4_dropper(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_STREAM) + return VERDICT_PROCEED; + if (ctx->user_port == bpf_htons(60123)) + return VERDICT_REJECT; + return VERDICT_PROCEED; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c index 6c059f1cfa1b..e6cb09259408 100644 --- a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c +++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c @@ -1,12 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/ptrace.h> -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -struct pt_regs current_regs = {}; -struct pt_regs ctx_regs = {}; +#define PT_REGS_SIZE sizeof(struct pt_regs) + +/* + * The kernel struct pt_regs isn't exported in its entirety to userspace. + * Pass it as an array to task_pt_regs.c + */ +char current_regs[PT_REGS_SIZE] = {}; +char ctx_regs[PT_REGS_SIZE] = {}; int uprobe_res = 0; SEC("uprobe/trigger_func") @@ -17,8 +22,10 @@ int handle_uprobe(struct pt_regs *ctx) current = bpf_get_current_task_btf(); regs = (struct pt_regs *) bpf_task_pt_regs(current); - __builtin_memcpy(¤t_regs, regs, sizeof(*regs)); - __builtin_memcpy(&ctx_regs, ctx, sizeof(*ctx)); + if (bpf_probe_read_kernel(current_regs, PT_REGS_SIZE, regs)) + return 0; + if (bpf_probe_read_kernel(ctx_regs, PT_REGS_SIZE, ctx)) + return 0; /* Prove that uprobe was run */ uprobe_res = 1; diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c index e1bf55dabdf6..162c41e9bcae 100644 --- a/tools/testing/selftests/nci/nci_dev.c +++ b/tools/testing/selftests/nci/nci_dev.c @@ -746,7 +746,7 @@ int read_write_nci_cmd(int nfc_sock, int virtual_fd, const __u8 *cmd, __u32 cmd_ const __u8 *rsp, __u32 rsp_len) { char buf[256]; - unsigned int len; + int len; send(nfc_sock, &cmd[3], cmd_len - 3, 0); len = read(virtual_fd, buf, cmd_len); diff --git a/tools/testing/selftests/net/altnames.sh b/tools/testing/selftests/net/altnames.sh index 4254ddc3f70b..1ef9e4159bba 100755 --- a/tools/testing/selftests/net/altnames.sh +++ b/tools/testing/selftests/net/altnames.sh @@ -45,7 +45,7 @@ altnames_test() check_err $? "Got unexpected long alternative name from link show JSON" ip link property del $DUMMY_DEV altname $SHORT_NAME - check_err $? "Failed to add short alternative name" + check_err $? "Failed to delete short alternative name" ip -j -p link show $SHORT_NAME &>/dev/null check_fail $? "Unexpected success while trying to do link show with deleted short alternative name" |