diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-18 12:54:24 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-18 12:54:24 -0800 |
| commit | 8d0112ac6fd001f95aabb084ec2ccaa3637bc344 (patch) | |
| tree | 323894ea1e3cf60935b3ded0c5b5b8ca55610ca7 | |
| parent | 6fdf886424cf8c4fff96a20189c00606327e5df6 (diff) | |
| parent | c7521d3aa2fa7fc785682758c99b5bcae503f6be (diff) | |
Merge tag 'net-5.16-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf, mac80211.
Current release - regressions:
- devlink: don't throw an error if flash notification sent before
devlink visible
- page_pool: Revert "page_pool: disable dma mapping support...",
turns out there are active arches who need it
Current release - new code bugs:
- amt: cancel delayed_work synchronously in amt_fini()
Previous releases - regressions:
- xsk: fix crash on double free in buffer pool
- bpf: fix inner map state pruning regression causing program
rejections
- mac80211: drop check for DONT_REORDER in __ieee80211_select_queue,
preventing mis-selecting the best effort queue
- mac80211: do not access the IV when it was stripped
- mac80211: fix radiotap header generation, off-by-one
- nl80211: fix getting radio statistics in survey dump
- e100: fix device suspend/resume
Previous releases - always broken:
- tcp: fix uninitialized access in skb frags array for Rx 0cp
- bpf: fix toctou on read-only map's constant scalar tracking
- bpf: forbid bpf_ktime_get_coarse_ns and bpf_timer_* in tracing
progs
- tipc: only accept encrypted MSG_CRYPTO msgs
- smc: transfer remaining wait queue entries during fallback, fix
missing wake ups
- udp: validate checksum in udp_read_sock() (when sockmap is used)
- sched: act_mirred: drop dst for the direction from egress to
ingress
- virtio_net_hdr_to_skb: count transport header in UFO, prevent
allowing bad skbs into the stack
- nfc: reorder the logic in nfc_{un,}register_device, fix unregister
- ipsec: check return value of ipv6_skip_exthdr
- usb: r8152: add MAC passthrough support for more Lenovo Docks"
* tag 'net-5.16-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (96 commits)
ptp: ocp: Fix a couple NULL vs IS_ERR() checks
net: ethernet: dec: tulip: de4x5: fix possible array overflows in type3_infoblock()
net: tulip: de4x5: fix the problem that the array 'lp->phy[8]' may be out of bound
ipv6: check return value of ipv6_skip_exthdr
e100: fix device suspend/resume
devlink: Don't throw an error if flash notification sent before devlink visible
page_pool: Revert "page_pool: disable dma mapping support..."
ethernet: hisilicon: hns: hns_dsaf_misc: fix a possible array overflow in hns_dsaf_ge_srst_by_port()
octeontx2-af: debugfs: don't corrupt user memory
NFC: add NCI_UNREG flag to eliminate the race
NFC: reorder the logic in nfc_{un,}register_device
NFC: reorganize the functions in nci_request
tipc: check for null after calling kmemdup
i40e: Fix display error code in dmesg
i40e: Fix creation of first queue by omitting it if is not power of two
i40e: Fix warning message and call stack during rmmod i40e driver
i40e: Fix ping is lost after configuring ADq on VF
i40e: Fix changing previously set num_queue_pairs for PFs
i40e: Fix NULL ptr dereference on VSI filter sync
i40e: Fix correct max_pkt_size on VF RX queue
...
102 files changed, 1314 insertions, 507 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 7a2345ce8521..10c8ae3a8c73 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3733,7 +3733,7 @@ F: drivers/scsi/bnx2i/ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER M: Ariel Elior <aelior@marvell.com> M: Sudarsana Kalluru <skalluru@marvell.com> -M: GR-everest-linux-l2@marvell.com +M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/bnx2x/ @@ -15593,7 +15593,7 @@ F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER M: Ariel Elior <aelior@marvell.com> -M: GR-everest-linux-l2@marvell.com +M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/qlogic/qed/ diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 47a04c330885..b732ee9a50ef 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3286,7 +3286,7 @@ static void __exit amt_fini(void) { rtnl_link_unregister(&amt_link_ops); unregister_netdevice_notifier(&amt_notifier_block); - cancel_delayed_work(&source_gc_wq); + cancel_delayed_work_sync(&source_gc_wq); __amt_source_gc_work(); destroy_workqueue(amt_wq); } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index fc0e66006644..3f1704cbe1cb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -559,6 +559,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, goto err_exit; if (fw.len == 0xFFFFU) { + if (sw.len > sizeof(self->rpc)) { + printk(KERN_INFO "Invalid sw len: %x\n", sw.len); + err = -EINVAL; + goto err_exit; + } err = hw_atl_utils_fw_rpc_call(self, sw.len); if (err < 0) goto err_exit; @@ -567,6 +572,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, if (rpc) { if (fw.len) { + if (fw.len > sizeof(self->rpc)) { + printk(KERN_INFO "Invalid fw len: %x\n", fw.len); + err = -EINVAL; + goto err_exit; + } err = hw_atl_utils_fw_downld_dwords(self, self->rpc_addr, diff --git a/drivers/net/ethernet/asix/ax88796c_main.h b/drivers/net/ethernet/asix/ax88796c_main.h index 80263c3cef75..4a83c991dcbe 100644 --- a/drivers/net/ethernet/asix/ax88796c_main.h +++ b/drivers/net/ethernet/asix/ax88796c_main.h @@ -127,9 +127,9 @@ struct ax88796c_device { #define AX_PRIV_FLAGS_MASK (AX_CAP_COMP) unsigned long flags; - #define EVENT_INTR BIT(0) - #define EVENT_TX BIT(1) - #define EVENT_SET_MULTI BIT(2) + #define EVENT_INTR 0 + #define EVENT_TX 1 + #define EVENT_SET_MULTI 2 }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h index 1835d2e451c0..fc7fce642666 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h @@ -635,11 +635,13 @@ static int bnx2x_ilt_client_mem_op(struct bnx2x *bp, int cli_num, { int i, rc; struct bnx2x_ilt *ilt = BP_ILT(bp); - struct ilt_client_info *ilt_cli = &ilt->clients[cli_num]; + struct ilt_client_info *ilt_cli; if (!ilt || !ilt->lines) return -1; + ilt_cli = &ilt->clients[cli_num]; + if (ilt_cli->flags & (ILT_CLIENT_SKIP_INIT | ILT_CLIENT_SKIP_MEM)) return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index d0d5da9b78f8..4c9507d82fd0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2258,6 +2258,16 @@ static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db, } } +/* Must hold rtnl_lock */ +static inline bool bnxt_sriov_cfg(struct bnxt *bp) +{ +#if defined(CONFIG_BNXT_SRIOV) + return BNXT_PF(bp) && (bp->pf.active_vfs || bp->sriov_cfg); +#else + return false; +#endif +} + extern const u16 bnxt_lhint_arr[]; int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 5c464ea73576..951c4c569a9b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -360,7 +360,7 @@ bnxt_dl_livepatch_report_err(struct bnxt *bp, struct netlink_ext_ack *extack, NL_SET_ERR_MSG_MOD(extack, "Live patch already applied"); break; default: - netdev_err(bp->dev, "Unexpected live patch error: %hhd\n", err); + netdev_err(bp->dev, "Unexpected live patch error: %d\n", err); NL_SET_ERR_MSG_MOD(extack, "Failed to activate live patch"); break; } @@ -441,12 +441,13 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: { - if (BNXT_PF(bp) && bp->pf.active_vfs) { + rtnl_lock(); + if (bnxt_sriov_cfg(bp)) { NL_SET_ERR_MSG_MOD(extack, - "reload is unsupported when VFs are allocated"); + "reload is unsupported while VFs are allocated or being configured"); + rtnl_unlock(); return -EOPNOTSUPP; } - rtnl_lock(); if (bp->dev->reg_state == NETREG_UNREGISTERED) { rtnl_unlock(); return -ENODEV; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index e6a4a768b10b..1471b6130a2b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1868,7 +1868,7 @@ static int bnxt_tc_setup_indr_block_cb(enum tc_setup_type type, struct flow_cls_offload *flower = type_data; struct bnxt *bp = priv->bp; - if (flower->common.chain_index) + if (!tc_cls_can_offload_and_chain0(bp->dev, type_data)) return -EOPNOTSUPP; switch (type) { diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 13121c4dcfe6..71730ef4cd57 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -4709,6 +4709,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p) lp->ibn = 3; lp->active = *p++; if (MOTO_SROM_BUG) lp->active = 0; + /* if (MOTO_SROM_BUG) statement indicates lp->active could + * be 8 (i.e. the size of array lp->phy) */ + if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy))) + return -EINVAL; lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].mc = get_unaligned_le16(p); p += 2; @@ -5000,19 +5004,23 @@ mii_get_phy(struct net_device *dev) } if ((j == limit) && (i < DE4X5_MAX_MII)) { for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++); - lp->phy[k].addr = i; - lp->phy[k].id = id; - lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */ - lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */ - lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */ - lp->mii_cnt++; - lp->active++; - printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name); - j = de4x5_debug; - de4x5_debug |= DEBUG_MII; - de4x5_dbg_mii(dev, k); - de4x5_debug = j; - printk("\n"); + if (k < DE4X5_MAX_PHY) { + lp->phy[k].addr = i; + lp->phy[k].id = id; + lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */ + lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */ + lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */ + lp->mii_cnt++; + lp->active++; + printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name); + j = de4x5_debug; + de4x5_debug |= DEBUG_MII; + de4x5_dbg_mii(dev, k); + de4x5_debug = j; + printk("\n"); + } else { + goto purgatory; + } } } purgatory: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 714e961e7a77..6451c8383639 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4550,10 +4550,10 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) fsl_mc_portal_free(priv->mc_io); - free_netdev(net_dev); - dev_dbg(net_dev->dev.parent, "Removed interface %s\n", net_dev->name); + free_netdev(net_dev); + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 23d9cbf262c3..740850b64aff 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -400,6 +400,10 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, return; if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) { + /* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8. + We need check to prevent array overflow */ + if (port >= DSAF_MAX_PORT_NUM) + return; reg_val_1 = 0x1 << port; port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off; /* there is difference between V1 and V2 in register.*/ diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 5039a2536951..0bf3d47bb90d 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -3003,9 +3003,10 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) struct net_device *netdev = pci_get_drvdata(pdev); struct nic *nic = netdev_priv(netdev); + netif_device_detach(netdev); + if (netif_running(netdev)) e100_down(nic); - netif_device_detach(netdev); if ((nic->flags & wol_magic) | e100_asf(nic)) { /* enable reverse auto-negotiation */ @@ -3022,7 +3023,7 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) *enable_wake = false; } - pci_clear_master(pdev); + pci_disable_device(pdev); } static int __e100_power_off(struct pci_dev *pdev, bool wake) @@ -3042,8 +3043,6 @@ static int __maybe_unused e100_suspend(struct device *dev_d) __e100_shutdown(to_pci_dev(dev_d), &wake); - device_wakeup_disable(dev_d); - return 0; } @@ -3051,6 +3050,14 @@ static int __maybe_unused e100_resume(struct device *dev_d) { struct net_device *netdev = dev_get_drvdata(dev_d); struct nic *nic = netdev_priv(netdev); + int err; + + err = pci_enable_device(to_pci_dev(dev_d)); + if (err) { + netdev_err(netdev, "Resume cannot enable PCI device, aborting\n"); + return err; + } + pci_set_master(to_pci_dev(dev_d)); /* disable reverse auto-negotiation */ if (nic->phy == phy_82552_v) { @@ -3062,10 +3069,11 @@ static int __maybe_unused e100_resume(struct device *dev_d) smartspeed & ~(E100_82552_REV_ANEG)); } - netif_device_attach(netdev); if (netif_running(netdev)) e100_up(nic); + netif_device_attach(netdev); + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 3d528fba754b..4d939af0a626 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -161,6 +161,7 @@ enum i40e_vsi_state_t { __I40E_VSI_OVERFLOW_PROMISC, __I40E_VSI_REINIT_REQUESTED, __I40E_VSI_DOWN_REQUESTED, + __I40E_VSI_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_VSI_STATE_SIZE__, }; @@ -1247,6 +1248,7 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf); void i40e_ptp_init(struct i40e_pf *pf); void i40e_ptp_stop(struct i40e_pf *pf); int i40e_ptp_alloc_pins(struct i40e_pf *pf); +int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf); i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index ba862131b9bd..e118cf9265c7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1790,6 +1790,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, bool is_add) { struct i40e_pf *pf = vsi->back; + u16 num_tc_qps = 0; u16 sections = 0; u8 netdev_tc = 0; u16 numtc = 1; @@ -1797,13 +1798,33 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, u8 offset; u16 qmap; int i; - u16 num_tc_qps = 0; sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; offset = 0; + /* zero out queue mapping, it will get updated on the end of the function */ + memset(ctxt->info.queue_mapping, 0, sizeof(ctxt->info.queue_mapping)); + + if (vsi->type == I40E_VSI_MAIN) { + /* This code helps add more queue to the VSI if we have + * more cores than RSS can support, the higher cores will + * be served by ATR or other filters. Furthermore, the + * non-zero req_queue_pairs says that user requested a new + * queue count via ethtool's set_channels, so use this + * value for queues distribution across traffic classes + */ + if (vsi->req_queue_pairs > 0) + vsi->num_queue_pairs = vsi->req_queue_pairs; + else if (pf->flags & I40E_FLAG_MSIX_ENABLED) + vsi->num_queue_pairs = pf->num_lan_msix; + } /* Number of queues per enabled TC */ - num_tc_qps = vsi->alloc_queue_pairs; + if (vsi->type == I40E_VSI_MAIN || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs != 0)) + num_tc_qps = vsi->num_queue_pairs; + else + num_tc_qps = vsi->alloc_queue_pairs; + if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) { /* Find numtc from enabled TC bitmap */ for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { @@ -1881,15 +1902,11 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, } ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); } - - /* Set actual Tx/Rx queue pairs */ - vsi->num_queue_pairs = offset; - if ((vsi->type == I40E_VSI_MAIN) && (numtc == 1)) { - if (vsi->req_queue_pairs > 0) - vsi->num_queue_pairs = vsi->req_queue_pairs; - else if (pf->flags & I40E_FLAG_MSIX_ENABLED) - vsi->num_queue_pairs = pf->num_lan_msix; - } + /* Do not change previously set num_queue_pairs for PFs and VFs*/ + if ((vsi->type == I40E_VSI_MAIN && numtc != 1) || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs == 0) || + (vsi->type != I40E_VSI_MAIN && vsi->type != I40E_VSI_SRIOV)) + vsi->num_queue_pairs = offset; /* Scheduler section valid can only be set for ADD VSI */ if (is_add) { @@ -2623,7 +2640,8 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && - (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) { + (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED) && + !test_bit(__I40E_VSI_RELEASING, pf->vsi[v]->state)) { int ret = i40e_sync_vsi_filters(pf->vsi[v]); if (ret) { @@ -5427,6 +5445,58 @@ static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi, } /** + * i40e_update_adq_vsi_queues - update queue mapping for ADq VSI + * @vsi: the VSI being reconfigured + * @vsi_offset: offset from main VF VSI + */ +int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset) +{ + struct i40e_vsi_context ctxt = {}; + struct i40e_pf *pf; + struct i40e_hw *hw; + int ret; + + if (!vsi) + return I40E_ERR_PARAM; + pf = vsi->back; + hw = &pf->hw; + + ctxt.seid = vsi->seid; + ctxt.pf_num = hw->pf_id; + ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id + vsi_offset; + ctxt.uplink_seid = vsi->uplink_seid; + ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL; + ctxt.flags = I40E_AQ_VSI_TYPE_VF; + ctxt.info = vsi->info; + + i40e_vsi_setup_queue_map(vsi, &ctxt, vsi->tc_config.enabled_tc, + false); + if (vsi->reconfig_rss) { + vsi->rss_size = min_t(int, pf->alloc_rss_size, + vsi->num_queue_pairs); + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&pf->pdev->dev, "Failed to reconfig rss for num_queues\n"); + return ret; + } + vsi->reconfig_rss = false; + } + + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + /* update the local VSI info with updated queue map */ + i40e_vsi_update_queue_map(vsi, &ctxt); + vsi->info.valid_sections = 0; + + return ret; +} + +/** * i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map * @vsi: VSI to be configured * @enabled_tc: TC bitmap @@ -5717,24 +5787,6 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi) } /** - * i40e_is_any_channel - channel exist or not - * @vsi: ptr to VSI to which channels are associated with - * - * Returns true or false if channel(s) exist for associated VSI or not - **/ -static bool i40e_is_any_channel(struct i40e_vsi *vsi) -{ - struct i40e_channel *ch, *ch_tmp; - - list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { - if (ch->initialized) - return true; - } - - return false; -} - -/** * i40e_get_max_queues_for_channel * @vsi: ptr to VSI to which channels are associated with * @@ -6240,26 +6292,15 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi, /* By default we are in VEPA mode, if this is the first VF/VMDq * VSI to be added switch to VEB mode. */ - if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) || - (!i40e_is_any_channel(vsi))) { - if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) { - dev_dbg(&pf->pdev->dev, - "Failed to create channel. Override queues (%u) not power of 2\n", - vsi->tc_config.tc_info[0].qcount); - return -EINVAL; - } - if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { - pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; + if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { + pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - if (vsi->type == I40E_VSI_MAIN) { - if (pf->flags & I40E_FLAG_TC_MQPRIO) - i40e_do_reset(pf, I40E_PF_RESET_FLAG, - true); - else - i40e_do_reset_safe(pf, - I40E_PF_RESET_FLAG); - } + if (vsi->type == I40E_VSI_MAIN) { + if (pf->flags & I40E_FLAG_TC_MQPRIO) + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); + else + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } /* now onwards for main VSI, number of queues will be value * of TC0's queue count @@ -7912,12 +7953,20 @@ config_tc: vsi->seid); need_reset = true; goto exit; - } else { - dev_info(&vsi->back->pdev->dev, - "Setup channel (id:%u) utilizing num_queues %d\n", - vsi->seid, vsi->tc_config.tc_info[0].qcount); + } else if (enabled_tc && + (!is_power_of_2(vsi->tc_config.tc_info[0].qcount))) { + netdev_info(netdev, + "Failed to create channel. Override queues (%u) not power of 2\n", + vsi->tc_config.tc_info[0].qcount); + ret = -EINVAL; + need_reset = true; + goto exit; } + dev_info(&vsi->back->pdev->dev, + "Setup channel (id:%u) utilizing num_queues %d\n", + vsi->seid, vsi->tc_config.tc_info[0].qcount); + if (pf->flags & I40E_FLAG_TC_MQPRIO) { if (vsi->mqprio_qopt.max_rate[0]) { u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; @@ -8482,9 +8531,8 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi, err = i40e_add_del_cloud_filter(vsi, filter, true); if (err) { - dev_err(&pf->pdev->dev, - "Failed to add cloud filter, err %s\n", - i40e_stat_str(&pf->hw, err)); + dev_err(&pf->pdev->dev, "Failed to add cloud filter, err %d\n", + err); goto err; } @@ -13771,7 +13819,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) dev_info(&pf->pdev->dev, "Can't remove PF VSI\n"); return -ENODEV; } - + set_bit(__I40E_VSI_RELEASING, vsi->state); uplink_seid = vsi->uplink_seid; if (vsi->type != I40E_VSI_SRIOV) { if (vsi->netdev_registered) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 472f56b360b8..80ae264c99ba 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -183,17 +183,18 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) /***********************misc routines*****************************/ /** - * i40e_vc_disable_vf + * i40e_vc_reset_vf * @vf: pointer to the VF info - * - * Disable the VF through a SW reset. + * @notify_vf: notify vf about reset or not + * Reset VF handler. **/ -static inline void i40e_vc_disable_vf(struct i40e_vf *vf) +static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) { struct i40e_pf *pf = vf->pf; int i; - i40e_vc_notify_vf_reset(vf); + if (notify_vf) + i40e_vc_notify_vf_reset(vf); /* We want to ensure that an actual reset occurs initiated after this * function was called. However, we do not want to wait forever, so @@ -211,9 +212,14 @@ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) usleep_range(10000, 20000); } - dev_warn(&vf->pf->pdev->dev, - "Failed to initiate reset for VF %d after 200 milliseconds\n", - vf->vf_id); + if (notify_vf) + dev_warn(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); + else + dev_dbg(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); } /** @@ -674,14 +680,13 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, u16 vsi_queue_id, struct virtchnl_rxq_info *info) { + u16 pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx]; struct i40e_hw *hw = &pf->hw; struct i40e_hmc_obj_rxq rx_ctx; - u16 pf_queue_id; int ret = 0; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); - /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(struct i40e_hmc_obj_rxq)); @@ -719,6 +724,10 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, } rx_ctx.rxmax = info->max_pkt_size; + /* if port VLAN is configured increase the max packet size */ + if (vsi->info.pvid) + rx_ctx.rxmax += VLAN_HLEN; + /* enable 32bytes desc always */ rx_ctx.dsize = 1; @@ -2106,20 +2115,6 @@ err: } /** - * i40e_vc_reset_vf_msg - * @vf: pointer to the VF info - * - * called from the VF to reset itself, - * unlike other virtchnl messages, PF driver - * doesn't send the response back to the VF - **/ -static void i40e_vc_reset_vf_msg(struct i40e_vf *vf) -{ - if (test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) - i40e_reset_vf(vf, false); -} - -/** * i40e_vc_config_promiscuous_mode_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2217,11 +2212,12 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_vsi_queue_config_info *qci = (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; - struct i40e_pf *pf = vf->pf; u16 vsi_id, vsi_queue_id = 0; - u16 num_qps_all = 0; + struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; int i, j = 0, idx = 0; + struct i40e_vsi *vsi; + u16 num_qps_all = 0; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; @@ -2310,9 +2306,15 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = qci->num_queue_pairs; } else { - for (i = 0; i < vf->num_tc; i++) - pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs = - vf->ch[i].num_qps; + for (i = 0; i < vf->num_tc; i++) { + vsi = pf->vsi[vf->ch[i].vsi_idx]; + vsi->num_queue_pairs = vf->ch[i].num_qps; + + if (i40e_update_adq_vsi_queues(vsi, i)) { + aq_ret = I40E_ERR_CONFIG; + goto error_param; + } + } } error_param: @@ -2607,8 +2609,7 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) } else { /* successful request */ vf->num_req_queues = req_pairs; - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return 0; } @@ -3803,8 +3804,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) vf->num_req_queues = 0; /* reset the VF in order to allocate resources */ - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return I40E_SUCCESS; @@ -3844,8 +3844,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) } /* reset the VF in order to allocate resources */ - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return I40E_SUCCESS; @@ -3907,7 +3906,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, i40e_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - i40e_vc_reset_vf_msg(vf); + i40e_vc_reset_vf(vf, false); ret = 0; break; case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: @@ -4161,7 +4160,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* Force the VF interface down so it has to bring up with new MAC * address */ - i40e_vc_disable_vf(vf); + i40e_vc_reset_vf(vf, true); dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n"); error_param: @@ -4170,34 +4169,6 @@ error_param: } /** - * i40e_vsi_has_vlans - True if VSI has configured VLANs - * @vsi: pointer to the vsi - * - * Check if a VSI has configured any VLANs. False if we have a port VLAN or if - * we have no configured VLANs. Do not call while holding the - * mac_filter_hash_lock. - */ -static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi) -{ - bool have_vlans; - - /* If we have a port VLAN, then the VSI cannot have any VLANs - * configured, as all MAC/VLAN filters will be assigned to the PVID. - */ - if (vsi->info.pvid) - return false; - - /* Since we don't have a PVID, we know that if the device is in VLAN - * mode it must be because of a VLAN filter configured on this VSI. - */ - spin_lock_bh(&vsi->mac_filter_hash_lock); - have_vlans = i40e_is_vsi_in_vlan(vsi); - spin_unlock_bh(&vsi->mac_filter_hash_lock); - - return have_vlans; -} - -/** * i40e_ndo_set_vf_port_vlan * @netdev: network interface device structure * @vf_id: VF identifier @@ -4253,19 +4224,9 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, /* duplicate request, so just return success */ goto error_pvid; - if (i40e_vsi_has_vlans(vsi)) { - dev_err(&pf->pdev->dev, - "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", - vf_id); - /* Administrator Error - knock the VF offline until he does - * the right thing by reconfiguring his network correctly - * and then reloading the VF driver. - */ - i40e_vc_disable_vf(vf); - /* During reset the VF got a new VSI, so refresh the pointer. */ - vsi = pf->vsi[vf->lan_vsi_idx]; - } - + i40e_vc_reset_vf(vf, true); + /* During reset the VF got a new VSI, so refresh a pointer. */ + vsi = pf->vsi[vf->lan_vsi_idx]; /* Locked once because multiple functions below iterate list */ spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -4641,7 +4602,7 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) goto out; vf->trusted = setting; - i40e_vc_disable_vf(vf); + i40e_vc_reset_vf(vf, true); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e6e7c1da47fb..75635bd57cf6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -39,6 +39,7 @@ #include "iavf_txrx.h" #include "iavf_fdir.h" #include "iavf_adv_rss.h" +#include <linux/bitmap.h> #define DEFAULT_DEBUG_LEVEL_SHIFT 3 #define PFX "iavf: " diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 5a359a0a20ec..144a77679359 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1776,6 +1776,7 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; + int i; if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1786,7 +1787,7 @@ static int iavf_set_channels(struct net_device *netdev, /* All of these should have already been checked by ethtool before this * even gets to us, but just to be sure. */ - if (num_req > adapter->vsi_res->num_queue_pairs) + if (num_req == 0 || num_req > adapter->vsi_res->num_queue_pairs) return -EINVAL; if (num_req == adapter->num_active_queues) @@ -1798,6 +1799,20 @@ static int iavf_set_channels(struct net_device *netdev, adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; iavf_schedule_reset(adapter); + + /* wait for the reset is done */ + for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { + msleep(IAVF_RESET_WAIT_MS); + if (adapter->flags & IAVF_FLAG_RESET_PENDING) + continue; + break; + } + if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->num_active_queues = num_req; + return -EOPNOTSUPP; + } + return 0; } @@ -1844,14 +1859,13 @@ static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, if (hfunc) *hfunc = ETH_RSS_HASH_TOP; - if (!indir) - return 0; - - memcpy(key, adapter->rss_key, adapter->rss_key_size); + if (key) + memcpy(key, adapter->rss_key, adapter->rss_key_size); - /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - for (i = 0; i < adapter->rss_lut_size; i++) - indir[i] = (u32)adapter->rss_lut[i]; + if (indir) + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + indir[i] = (u32)adapter->rss_lut[i]; return 0; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 847d67e32a54..336e6bf95e48 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -697,6 +697,23 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) } /** + * iavf_restore_filters + * @adapter: board private structure + * + * Restore existing non MAC filters when VF netdev comes back up + **/ +static void iavf_restore_filters(struct iavf_adapter *adapter) +{ + /* re-add all VLAN filters */ + if (VLAN_ALLOWED(adapter)) { + u16 vid; + + for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) + iavf_add_vlan(adapter, vid); + } +} + +/** * iavf_vlan_rx_add_vid - Add a VLAN filter to a device * @netdev: network device struct * @proto: unused protocol data @@ -709,8 +726,11 @@ static int iavf_vlan_rx_add_vid(struct net_device *netdev, if (!VLAN_ALLOWED(adapter)) return -EIO; + if (iavf_add_vlan(adapter, vid) == NULL) return -ENOMEM; + + set_bit(vid, adapter->vsi.active_vlans); return 0; } @@ -725,11 +745,13 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (VLAN_ALLOWED(adapter)) { - iavf_del_vlan(adapter, vid); - return 0; - } - return -EIO; + if (!VLAN_ALLOWED(adapter)) + return -EIO; + + iavf_del_vlan(adapter, vid); + clear_bit(vid, adapter->vsi.active_vlans); + + return 0; } /** @@ -1639,8 +1661,7 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); return 0; } - - if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) && + if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) || (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { iavf_set_promiscuous(adapter, 0); return 0; @@ -2123,8 +2144,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); - iavf_free_queues(adapter); iavf_free_q_vectors(adapter); + iavf_free_queues(adapter); memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); adapter->netdev->flags &= ~IFF_UP; @@ -2410,7 +2431,7 @@ static void iavf_adminq_task(struct work_struct *work) /* check for error indications */ val = rd32(hw, hw->aq.arq.len); - if (val == 0xdeadbeef) /* indicates device in reset */ + if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */ goto freedom; oldval = val; if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) { @@ -3095,8 +3116,10 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, return -ENOMEM; while (!mutex_trylock(&adapter->crit_lock)) { - if (--count == 0) - goto err; + if (--count == 0) { + kfree(filter); + return err; + } udelay(1); } @@ -3107,11 +3130,11 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, /* start out with flow type and eth type IPv4 to begin with */ filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; err = iavf_parse_cls_flower(adapter, cls_flower, filter); - if (err < 0) + if (err) goto err; err = iavf_handle_tclass(adapter, tc, filter); - if (err < 0) + if (err) goto err; /* add filter to the list */ @@ -3308,6 +3331,9 @@ static int iavf_open(struct net_device *netdev) spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* Restore VLAN filters that were removed with IFF_DOWN */ + iavf_restore_filters(adapter); + iavf_configure(adapter); iavf_up_complete(adapter); @@ -3503,7 +3529,8 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) + if (adapter->vf_res && + !(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) features &= ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER); diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 6433c909c6b2..072391c494ce 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -25,6 +25,7 @@ #include <linux/io.h> #include <linux/dma-mapping.h> #include <linux/module.h> +#include <linux/property.h> #include <asm/checksum.h> @@ -239,6 +240,7 @@ ltq_etop_hw_init(struct net_device *dev) { struct ltq_etop_priv *priv = netdev_priv(dev); int i; + int err; ltq_pmu_enable(PMU_PPE); @@ -273,7 +275,13 @@ ltq_etop_hw_init(struct net_device *dev) if (IS_TX(i)) { ltq_dma_alloc_tx(&ch->dma); - request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv); + err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv); + if (err) { + netdev_err(dev, + "Unable to get Tx DMA IRQ %d\n", + irq); + return err; + } } else if (IS_RX(i)) { ltq_dma_alloc_rx(&ch->dma); for (ch->dma.desc = 0; ch->dma.desc < LTQ_DESC_NUM; @@ -281,7 +289,13 @@ ltq_etop_hw_init(struct net_device *dev) if (ltq_etop_alloc_skb(ch)) return -ENOMEM; ch->dma.desc = 0; - request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv); + err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv); + if (err) { + netdev_err(dev, + "Unable to get Rx DMA IRQ %d\n", + irq); + return err; + } } ch->dma.irq = irq; } @@ -726,7 +740,7 @@ static struct platform_driver ltq_mii_driver = { }, }; -int __init +static int __init init_ltq_etop(void) { int ret = platform_driver_probe(<q_mii_driver, ltq_etop_probe); diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 62a97c46fba0..ef878973b859 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -429,12 +429,14 @@ static const struct of_device_id orion_mdio_match[] = { }; MODULE_DEVICE_TABLE(of, orion_mdio_match); +#ifdef CONFIG_ACPI static const struct acpi_device_id orion_mdio_acpi_match[] = { { "MRVL0100", BUS_TYPE_SMI }, { "MRVL0101", BUS_TYPE_XSMI }, { }, }; MODULE_DEVICE_TABLE(acpi, orion_mdio_acpi_match); +#endif static struct platform_driver orion_mdio_driver = { .probe = orion_mdio_probe, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index c7fd466a0efd..a09a507369ac 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -236,10 +236,11 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, u64 lmt_addr, val, tbl_base; int pf, vf, num_vfs, hw_vfs; void __iomem *lmt_map_base; - int index = 0, off = 0; - int bytes_not_copied; int buf_size = 10240; + size_t off = 0; + int index = 0; char *buf; + int ret; /* don't allow partial reads */ if (*ppos != 0) @@ -303,15 +304,17 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, } off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); - bytes_not_copied = copy_to_user(buffer, buf, off); + ret = min(off, count); + if (copy_to_user(buffer, buf, ret)) + ret = -EFAULT; kfree(buf); iounmap(lmt_map_base); - if (bytes_not_copied) - return -EFAULT; + if (ret < 0) + return ret; - *ppos = off; - return off; + *ppos = ret; + return ret; } RVU_DEBUG_FOPS(lmtst_map_table, lmtst_map_table_display, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index f71ec4d9d68e..8eaa24d865c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -339,6 +339,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_PAGE_FAULT_RESUME: case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS: case MLX5_CMD_OP_DEALLOC_SF: + case MLX5_CMD_OP_DESTROY_UCTX: + case MLX5_CMD_OP_DESTROY_UMEM: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -464,9 +466,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT: case MLX5_CMD_OP_QUERY_GENERAL_OBJECT: case MLX5_CMD_OP_CREATE_UCTX: - case MLX5_CMD_OP_DESTROY_UCTX: case MLX5_CMD_OP_CREATE_UMEM: - case MLX5_CMD_OP_DESTROY_UMEM: case MLX5_CMD_OP_ALLOC_MEMIC: case MLX5_CMD_OP_MODIFY_XRQ: case MLX5_CMD_OP_RELEASE_XRQ_ERROR: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 02e77ffe5c3e..5371ad0a12eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -164,13 +164,14 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); MLX5_SET(destroy_cq_in, in, uid, cq->uid); err = mlx5_cmd_exec_in(dev, destroy_cq, in); + if (err) + return err; synchronize_irq(cq->irqn); - mlx5_cq_put(cq); wait_for_completion(&cq->free); - return err; + return 0; } EXPORT_SYMBOL(mlx5_core_destroy_cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 07c8d9811bc8..10d195042ab5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -507,6 +507,8 @@ void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) if (!mlx5_debugfs_root) return; - if (cq->dbg) + if (cq->dbg) { rem_res_tree(cq->dbg); + cq->dbg = NULL; + } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index c1c6e74c79c4..2445e2ae3324 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1356,9 +1356,13 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; + int err; + if (!priv) { NL_SET_ERR_MSG_MOD(extack, "offload of ct action isn't available"); @@ -1369,6 +1373,17 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.ct_action = act->ct.action; attr->ct_attr.nf_ft = act->ct.flow_table; + if (!clear_action) + goto out; + + err = mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to set registers for ct clear"); + return err; + } + attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + +out: return 0; } @@ -1898,23 +1913,16 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, memcpy(pre_ct_attr, attr, attr_sz); - err = mlx5_tc_ct_entry_set_registers(ct_priv, mod_acts, 0, 0, 0, 0); - if (err) { - ct_dbg("Failed to set register for ct clear"); - goto err_set_registers; - } - mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type, mod_acts->num_actions, mod_acts->actions); if (IS_ERR(mod_hdr)) { err = PTR_ERR(mod_hdr); ct_dbg("Failed to add create ct clear mod hdr"); - goto err_set_registers; + goto err_mod_hdr; } pre_ct_attr->modify_hdr = mod_hdr; - pre_ct_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr); if (IS_ERR(rule)) { @@ -1930,7 +1938,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, err_insert: mlx5_modify_header_dealloc(priv->mdev, mod_hdr); -err_set_registers: +err_mod_hdr: netdev_warn(priv->netdev, "Failed to offload ct clear flow, err %d\n", err); kfree(pre_ct_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 363329f4aac6..99662af1e41a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -110,6 +110,7 @@ int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec); int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack); @@ -172,6 +173,7 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec) static inline int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 8f64f2c8895a..b689701ac7d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -102,6 +102,7 @@ struct mlx5e_tc_flow { refcount_t refcnt; struct rcu_head rcu_head; struct completion init_done; + struct completion del_hw_done; int tunnel_id; /* the mapped tunnel id of this flow */ struct mlx5_flow_attr *attr; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 660cca73c36c..042b1abe1437 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -245,8 +245,14 @@ static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow, struct list_head *flow_list, int index) { - if (IS_ERR(mlx5e_flow_get(flow))) + if (IS_ERR(mlx5e_flow_get(flow))) { + /* Flow is being deleted concurrently. Wait for it to be + * unoffloaded from hardware, otherwise deleting encap will + * fail. + */ + wait_for_completion(&flow->del_hw_done); return; + } wait_for_completion(&flow->init_done); flow->tmp_entry_index = index; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 62abce008c7b..a2a9f68579dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -55,6 +55,7 @@ struct mlx5e_ktls_offload_context_rx { DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS); /* resync */ + spinlock_t lock; /* protects resync fields */ struct mlx5e_ktls_rx_resync_ctx resync; struct list_head list; }; @@ -386,14 +387,18 @@ static void resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_r struct mlx5e_icosq *sq; bool trigger_poll; - memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq)); - sq = &c->async_icosq; ktls_resync = sq->ktls_resync; + trigger_poll = false; spin_lock_bh(&ktls_resync->lock); - list_add_tail(&priv_rx->list, &ktls_resync->list); - trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state); + spin_lock_bh(&priv_rx->lock); + memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq)); + if (list_empty(&priv_rx->list)) { + list_add_tail(&priv_rx->list, &ktls_resync->list); + trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state); + } + spin_unlock_bh(&priv_rx->lock); spin_unlock_bh(&ktls_resync->lock); if (!trigger_poll) @@ -617,6 +622,8 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, if (err) goto err_create_key; + INIT_LIST_HEAD(&priv_rx->list); + spin_lock_init(&priv_rx->lock); priv_rx->crypto_info = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info; @@ -730,10 +737,14 @@ bool mlx5e_ktls_rx_handle_resync_list(struct mlx5e_channel *c, int budget) priv_rx = list_first_entry(&local_list, struct mlx5e_ktls_offload_context_rx, list); + spin_lock(&priv_rx->lock); cseg = post_static_params(sq, priv_rx); - if (IS_ERR(cseg)) + if (IS_ERR(cseg)) { + spin_unlock(&priv_rx->lock); break; - list_del(&priv_rx->list); + } + list_del_init(&priv_rx->list); + spin_unlock(&priv_rx->lock); db_cseg = cseg; } if (db_cseg) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 835caa1c7b74..3d45f4ae80c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1600,6 +1600,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, else mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); } + complete_all(&flow->del_hw_done); if (mlx5_flow_has_geneve_opt(flow)) mlx5_geneve_tlv_option_del(priv->mdev->geneve); @@ -3607,7 +3608,9 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, attr->dest_chain = act->chain_index; break; case FLOW_ACTION_CT: - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack); + err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, + &parse_attr->mod_hdr_acts, + act, extack); if (err) return err; @@ -4276,7 +4279,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported"); return -EOPNOTSUPP; } - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack); + err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, + &parse_attr->mod_hdr_acts, + act, extack); if (err) return err; @@ -4465,6 +4470,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, INIT_LIST_HEAD(&flow->l3_to_l2_reformat); refcount_set(&flow->refcnt, 1); init_completion(&flow->init_done); + init_completion(&flow->del_hw_done); *__flow = flow; *__parse_attr = parse_attr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index ec136b499204..51a8cecc4a7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1305,12 +1305,17 @@ abort: */ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { + bool toggle_lag; int ret; if (!mlx5_esw_allowed(esw)) return 0; - mlx5_lag_disable_change(esw->dev); + toggle_lag = esw->mode == MLX5_ESWITCH_NONE; + + if (toggle_lag) + mlx5_lag_disable_change(esw->dev); + down_write(&esw->mode_lock); if (esw->mode == MLX5_ESWITCH_NONE) { ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs); @@ -1324,7 +1329,10 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) esw->esw_funcs.num_vfs = num_vfs; } up_write(&esw->mode_lock); - mlx5_lag_enable_change(esw->dev); + + if (toggle_lag) + mlx5_lag_enable_change(esw->dev); + return ret; } @@ -1572,6 +1580,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->enabled_vports = 0; esw->mode = MLX5_ESWITCH_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) && + MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)) + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; + else + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; dev->priv.eswitch = esw; BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); @@ -1934,7 +1947,7 @@ free_out: return err; } -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1948,7 +1961,7 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) struct mlx5_eswitch *esw; esw = dev->priv.eswitch; - return mlx5_esw_allowed(esw) ? esw->offloads.encap : + return (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS) ? esw->offloads.encap : DEVLINK_ESWITCH_ENCAP_MODE_NONE; } EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f4eaa5893886..a46455694f7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3183,12 +3183,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) u64 mapping_id; int err; - if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) && - MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap)) - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; - else - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; - mutex_init(&esw->offloads.termtbl_mutex); mlx5_rdma_enable_roce(esw->dev); @@ -3286,7 +3280,6 @@ void esw_offloads_disable(struct mlx5_eswitch *esw) esw_offloads_metadata_uninit(esw); mlx5_rdma_disable_roce(esw->dev); mutex_destroy(&esw->offloads.termtbl_mutex); - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) @@ -3630,7 +3623,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, *encap = esw->offloads.encap; unlock: up_write(&esw->mode_lock); - return 0; + return err; } static bool diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 31c99d53faf7..7e0e04cf26f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,7 +40,7 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) -#define MLX5_SF_NUM_COUNTERS_BULK 6 +#define MLX5_SF_NUM_COUNTERS_BULK 8 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) #define MLX5_FC_POOL_USED_BUFF_RATIO 10 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 48d2ea690d7a..4ddf6b330a44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -615,6 +615,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, bool is_bonded, is_in_lag, mode_supported; int bond_status = 0; int num_slaves = 0; + int changed = 0; int idx; if (!netif_is_lag_master(upper)) @@ -653,27 +654,27 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, */ is_in_lag = num_slaves == MLX5_MAX_PORTS && bond_status == 0x3; - if (!mlx5_lag_is_ready(ldev) && is_in_lag) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Can't activate LAG offload, PF is configured with more than 64 VFs"); - return 0; - } - /* Lag mode must be activebackup or hash. */ mode_supported = tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP || tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH; - if (is_in_lag && !mode_supported) - NL_SET_ERR_MSG_MOD(info->info.extack, - "Can't activate LAG offload, TX type isn't supported"); - is_bonded = is_in_lag && mode_supported; if (tracker->is_bonded != is_bonded) { tracker->is_bonded = is_bonded; - return 1; + changed = 1; } - return 0; + if (!is_in_lag) + return changed; + + if (!mlx5_lag_is_ready(ldev)) + NL_SET_ERR_MSG_MOD(info->info.extack, + "Can't activate LAG offload, PF is configured with more than 64 VFs"); + else if (!mode_supported) + NL_SET_ERR_MSG_MOD(info->info.extack, + "Can't activate LAG offload, TX type isn't supported"); + + return changed; } static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev, @@ -716,9 +717,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, ldev = container_of(this, struct mlx5_lag, nb); - if (!mlx5_lag_is_ready(ldev) && event == NETDEV_CHANGELOWERSTATE) - return NOTIFY_DONE; - tracker = ldev->tracker; switch (event) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 49089cbe897c..8cbd36c82b3b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -135,25 +135,14 @@ static void dr_domain_fill_uplink_caps(struct mlx5dr_domain *dmn, static int dr_domain_query_vport(struct mlx5dr_domain *dmn, u16 vport_number, + bool other_vport, struct mlx5dr_cmd_vport_cap *vport_caps) { - u16 cmd_vport = vport_number; - bool other_vport = true; int ret; - if (vport_number == MLX5_VPORT_UPLINK) { - dr_domain_fill_uplink_caps(dmn, vport_caps); - return 0; - } - - if (dmn->info.caps.is_ecpf && vport_number == MLX5_VPORT_ECPF) { - other_vport = false; - cmd_vport = 0; - } - ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev, other_vport, - cmd_vport, + vport_number, &vport_caps->icm_address_rx, &vport_caps->icm_address_tx); if (ret) @@ -161,7 +150,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn, ret = mlx5dr_cmd_query_gvmi(dmn->mdev, other_vport, - cmd_vport, + vport_number, &vport_caps->vport_gvmi); if (ret) return ret; @@ -176,9 +165,15 @@ static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn) { return dr_domain_query_vport(dmn, dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0, + false, &dmn->info.caps.vports.esw_manager_caps); } +static void dr_domain_query_uplink(struct mlx5dr_domain *dmn) +{ + dr_domain_fill_uplink_caps(dmn, &dmn->info.caps.vports.uplink_caps); +} + static struct mlx5dr_cmd_vport_cap * dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) { @@ -190,7 +185,7 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) if (!vport_caps) return NULL; - ret = dr_domain_query_vport(dmn, vport, vport_caps); + ret = dr_domain_query_vport(dmn, vport, true, vport_caps); if (ret) { kvfree(vport_caps); return NULL; @@ -207,16 +202,26 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) return vport_caps; } +static bool dr_domain_is_esw_mgr_vport(struct mlx5dr_domain *dmn, u16 vport) +{ + struct mlx5dr_cmd_caps *caps = &dmn->info.caps; + + return (caps->is_ecpf && vport == MLX5_VPORT_ECPF) || + (!caps->is_ecpf && vport == 0); +} + struct mlx5dr_cmd_vport_cap * mlx5dr_domain_get_vport_cap(struct mlx5dr_domain *dmn, u16 vport) { struct mlx5dr_cmd_caps *caps = &dmn->info.caps; struct mlx5dr_cmd_vport_cap *vport_caps; - if ((caps->is_ecpf && vport == MLX5_VPORT_ECPF) || - (!caps->is_ecpf && vport == 0)) + if (dr_domain_is_esw_mgr_vport(dmn, vport)) return &caps->vports.esw_manager_caps; + if (vport == MLX5_VPORT_UPLINK) + return &caps->vports.uplink_caps; + vport_load: vport_caps = xa_load(&caps->vports.vports_caps_xa, vport); if (vport_caps) @@ -241,17 +246,6 @@ static void dr_domain_clear_vports(struct mlx5dr_domain *dmn) } } -static int dr_domain_query_uplink(struct mlx5dr_domain *dmn) -{ - struct mlx5dr_cmd_vport_cap *vport_caps; - - vport_caps = mlx5dr_domain_get_vport_cap(dmn, MLX5_VPORT_UPLINK); - if (!vport_caps) - return -EINVAL; - - return 0; -} - static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, struct mlx5dr_domain *dmn) { @@ -281,11 +275,7 @@ static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, goto free_vports_caps_xa; } - ret = dr_domain_query_uplink(dmn); - if (ret) { - mlx5dr_err(dmn, "Failed to query uplink vport caps (err: %d)", ret); - goto free_vports_caps_xa; - } + dr_domain_query_uplink(dmn); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 75c775bee351..793365242e85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -924,11 +924,12 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, /* Check that all mask data was consumed */ for (i = 0; i < consumed_mask.match_sz; i++) { - if (consumed_mask.match_buf[i]) { - mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n"); - ret = -EOPNOTSUPP; - goto free_consumed_mask; - } + if (!((u8 *)consumed_mask.match_buf)[i]) + continue; + + mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n"); + ret = -EOPNOTSUPP; + goto free_consumed_mask; } ret = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 3028b776da00..2333c2439c28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -764,6 +764,7 @@ struct mlx5dr_roce_cap { struct mlx5dr_vports { struct mlx5dr_cmd_vport_cap esw_manager_caps; + struct mlx5dr_cmd_vport_cap uplink_caps; struct xarray vports_caps_xa; }; diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index cc2d907c4c4b..23a336c5096e 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -392,7 +392,7 @@ static int sis96x_get_mac_addr(struct pci_dev *pci_dev, /* get MAC address from EEPROM */ for (i = 0; i < 3; i++) addr[i] = read_eeprom(ioaddr, i + EEPROMMACAddr); - eth_hw_addr_set(net_dev, (u8 *)addr); + eth_hw_addr_set(net_dev, (u8 *)addr); rc = 1; break; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 85208128f135..b7c2579c963b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -485,8 +485,28 @@ static int socfpga_dwmac_resume(struct device *dev) } #endif /* CONFIG_PM_SLEEP */ -static SIMPLE_DEV_PM_OPS(socfpga_dwmac_pm_ops, stmmac_suspend, - socfpga_dwmac_resume); +static int __maybe_unused socfpga_dwmac_runtime_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + + stmmac_bus_clks_config(priv, false); + + return 0; +} + +static int __maybe_unused socfpga_dwmac_runtime_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + + return stmmac_bus_clks_config(priv, true); +} + +static const struct dev_pm_ops socfpga_dwmac_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(stmmac_suspend, socfpga_dwmac_resume) + SET_RUNTIME_PM_OPS(socfpga_dwmac_runtime_suspend, socfpga_dwmac_runtime_resume, NULL) +}; static const struct socfpga_dwmac_ops socfpga_gen5_ops = { .set_phy_mode = socfpga_gen5_set_phy_mode, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d3f350c25b9b..2eb284576336 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -511,6 +511,14 @@ bool stmmac_eee_init(struct stmmac_priv *priv) return true; } +static inline u32 stmmac_cdc_adjust(struct stmmac_priv *priv) +{ + /* Correct the clk domain crossing(CDC) error */ + if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) + return (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate; + return 0; +} + /* stmmac_get_tx_hwtstamp - get HW TX timestamps * @priv: driver private structure * @p : descriptor pointer @@ -524,7 +532,6 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, { struct skb_shared_hwtstamps shhwtstamp; bool found = false; - s64 adjust = 0; u64 ns = 0; if (!priv->hwts_tx_en) @@ -543,12 +550,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, } if (found) { - /* Correct the clk domain crossing(CDC) error */ - if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) { - adjust += -(2 * (NSEC_PER_SEC / - priv->plat->clk_ptp_rate)); - ns += adjust; - } + ns -= stmmac_cdc_adjust(priv); memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp.hwtstamp = ns_to_ktime(ns); @@ -573,7 +575,6 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, { struct skb_shared_hwtstamps *shhwtstamp = NULL; struct dma_desc *desc = p; - u64 adjust = 0; u64 ns = 0; if (!priv->hwts_rx_en) @@ -586,11 +587,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, if (stmmac_get_rx_timestamp_status(priv, p, np, priv->adv_ts)) { stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns); - /* Correct the clk domain crossing(CDC) error */ - if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) { - adjust += 2 * (NSEC_PER_SEC / priv->plat->clk_ptp_rate); - ns -= adjust; - } + ns -= stmmac_cdc_adjust(priv); netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index bfdf89e54752..8a19a06b505d 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -306,7 +306,6 @@ static void sp_setup(struct net_device *dev) { /* Finish setting up the DEVICE info. */ dev->netdev_ops = &sp_netdev_ops; - dev->needs_free_netdev = true; dev->mtu = SIXP_MTU; dev->hard_header_len = AX25_MAX_HEADER_LEN; dev->header_ops = &ax25_header_ops; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 5528d97110d5..ef790fd0ab56 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -853,6 +853,7 @@ static void ipa_endpoint_init_hol_block_timer(struct ipa_endpoint *endpoint, u32 offset; u32 val; + /* This should only be changed when HOL_BLOCK_EN is disabled */ offset = IPA_REG_ENDP_INIT_HOL_BLOCK_TIMER_N_OFFSET(endpoint_id); val = hol_block_timer_val(ipa, microseconds); iowrite32(val, ipa->reg_virt + offset); @@ -868,6 +869,9 @@ ipa_endpoint_init_hol_block_enable(struct ipa_endpoint *endpoint, bool enable) val = enable ? HOL_BLOCK_EN_FMASK : 0; offset = IPA_REG_ENDP_INIT_HOL_BLOCK_EN_N_OFFSET(endpoint_id); iowrite32(val, endpoint->ipa->reg_virt + offset); + /* When enabling, the register must be written twice for IPA v4.5+ */ + if (enable && endpoint->ipa->version >= IPA_VERSION_4_5) + iowrite32(val, endpoint->ipa->reg_virt + offset); } void ipa_endpoint_modem_hol_block_clear_all(struct ipa *ipa) @@ -880,6 +884,7 @@ void ipa_endpoint_modem_hol_block_clear_all(struct ipa *ipa) if (endpoint->toward_ipa || endpoint->ee_id != GSI_EE_MODEM) continue; + ipa_endpoint_init_hol_block_enable(endpoint, false); ipa_endpoint_init_hol_block_timer(endpoint, 0); ipa_endpoint_init_hol_block_enable(endpoint, true); } diff --git a/drivers/net/ipa/ipa_resource.c b/drivers/net/ipa/ipa_resource.c index e3da95d69409..06cec7199382 100644 --- a/drivers/net/ipa/ipa_resource.c +++ b/drivers/net/ipa/ipa_resource.c @@ -52,7 +52,7 @@ static bool ipa_resource_limits_valid(struct ipa *ipa, return false; } - group_count = data->rsrc_group_src_count; + group_count = data->rsrc_group_dst_count; if (!group_count || group_count > IPA_RESOURCE_GROUP_MAX) return false; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index fecc9a1d293a..1572878c3403 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1010,6 +1010,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); int txq = skb->queue_mapping; + struct netdev_queue *queue; struct tun_file *tfile; int len = skb->len; @@ -1054,6 +1055,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) if (ptr_ring_produce(&tfile->tx_ring, skb)) goto drop; + /* NETIF_F_LLTX requires to do our own update of trans_start */ + queue = netdev_get_tx_queue(dev, txq); + queue->trans_start = jiffies; + /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 4a02f33f0643..f9877a3e83ac 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9603,12 +9603,9 @@ static int rtl8152_probe(struct usb_interface *intf, netdev->hw_features &= ~NETIF_F_RXCSUM; } - if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO) { - switch (le16_to_cpu(udev->descriptor.idProduct)) { - case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2: - case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2: - tp->lenovo_macpassthru = 1; - } + if (udev->parent && + le16_to_cpu(udev->parent->descriptor.idVendor) == VENDOR_ID_LENOVO) { + tp->lenovo_macpassthru = 1; } if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial && diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 6bc5791a7ec5..08e429a06922 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -1699,12 +1699,9 @@ static int initialize_dco_operating_mode(struct idtcm_channel *channel) /* PTP Hardware Clock interface */ -/** +/* * Maximum absolute value for write phase offset in picoseconds * - * @channel: channel - * @delta_ns: delta in nanoseconds - * * Destination signed register is 32-bit register in resolution of 50ps * * 0x7fffffff * 50 = 2147483647 * 50 = 107374182350 diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 34f943c8c9fd..0f1b5a7d2a89 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -1304,10 +1304,11 @@ ptp_ocp_register_ext(struct ptp_ocp *bp, struct ocp_resource *r) if (!ext) return -ENOMEM; - err = -EINVAL; ext->mem = ptp_ocp_get_mem(bp, r); - if (!ext->mem) + if (IS_ERR(ext->mem)) { + err = PTR_ERR(ext->mem); goto out; + } ext->bp = bp; ext->info = r->extra; @@ -1371,8 +1372,8 @@ ptp_ocp_register_mem(struct ptp_ocp *bp, struct ocp_resource *r) void __iomem *mem; mem = ptp_ocp_get_mem(bp, r); - if (!mem) - return -EINVAL; + if (IS_ERR(mem)) + return PTR_ERR(mem); bp_assign_entry(bp, r, mem); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f715e8863f4d..e7a163a3146b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -193,7 +193,7 @@ struct bpf_map { atomic64_t usercnt; struct work_struct work; struct mutex freeze_mutex; - u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ + atomic64_t writecnt; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -1419,6 +1419,7 @@ void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); +bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 97afcea39a7b..8b18fe9771f9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -145,13 +145,13 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { return MLX5_ESWITCH_NONE; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bb8c6f5f19bc..c3a6e6209600 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -105,7 +105,18 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - atomic_long_t pp_frag_count; + union { + /** + * dma_addr_upper: might require a 64-bit + * value on 32-bit architectures. + */ + unsigned long dma_addr_upper; + /** + * For frag page support, not supported in + * 32-bit architectures with 64-bit DMA. + */ + atomic_long_t pp_frag_count; + }; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 686a666d073d..c8cb7e697d47 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4226,7 +4226,7 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, return; } - if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index b465f8f3e554..04e87f4b9417 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -120,10 +120,15 @@ retry: if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); + /* UFO may not include transport header in gso_size. */ + if (gso_type & SKB_GSO_UDP) + nh_off -= thlen; + /* Too small packets are not really GSO ones. */ - if (skb->len - p_off > gso_size) { + if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index a964daedc17b..ea8595651c38 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -30,6 +30,7 @@ enum nci_flag { NCI_UP, NCI_DATA_EXCHANGE, NCI_DATA_EXCHANGE_TO, + NCI_UNREG, }; /* NCI device states */ diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 3855f069627f..a4082406a003 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,14 +216,24 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; + + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 2ca643af9a54..43eb3501721b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return cgroup_base_func_proto(func_id, prog); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1ffd469c217f..649f07623df6 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 50f96ea4452a..1033ee8c0caf 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static void bpf_map_write_active_inc(struct bpf_map *map) +{ + atomic64_inc(&map->writecnt); +} + +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} + +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; +} + static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) goto out; if (vma->vm_flags & VM_MAYWRITE) - map->writecnt++; + bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; @@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1174,6 +1184,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr) out: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; @@ -1597,6 +1611,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr) } mutex_lock(&map->freeze_mutex); - - if (map->writecnt) { + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; + bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; @@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); - err_put: + if (has_write) + bpf_map_write_active_dec(map); fdput(f); return err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 890b3ec375a3..50efda51515b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1151,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - reg->map_uid = reg->id; + if (map_value_has_timer(map->inner_map_meta)) + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -4055,7 +4056,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) static bool bpf_map_is_rdonly(const struct bpf_map *map) { - return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; + /* A map is considered read-only if the following condition are true: + * + * 1) BPF program side cannot change any of the map content. The + * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map + * and was set at map creation time. + * 2) The map value(s) have been initialized from user space by a + * loader and then "frozen", such that no new map update/delete + * operations from syscall side are possible for the rest of + * the map's lifetime from that point onwards. + * 3) Any parallel/pending map update/delete operations from syscall + * side have been completed. Only after that point, it's safe to + * assume that map value(s) are immutable. + */ + return (map->map_flags & BPF_F_RDONLY_PROG) && + READ_ONCE(map->frozen) && + !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) @@ -11631,6 +11647,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if (map_value_has_timer(map)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_timer yet\n"); + return -EINVAL; + } + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..ae9755037b7e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/net/core/devlink.c b/net/core/devlink.c index 5ba4f9434acd..5ad72dbfcd07 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4229,7 +4229,9 @@ static void __devlink_flash_update_notify(struct devlink *devlink, WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && cmd != DEVLINK_CMD_FLASH_UPDATE_END && cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) diff --git a/net/core/filter.c b/net/core/filter.c index e471c9b09670..6102f093d59a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7162,6 +7162,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -10327,6 +10329,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -10833,6 +10837,8 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b60e4301a44..1a6978427d6c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -49,12 +49,6 @@ static int page_pool_init(struct page_pool *pool, * which is the XDP_TX use-case. */ if (pool->p.flags & PP_FLAG_DMA_MAP) { - /* DMA-mapping is not supported on 32-bit systems with - * 64-bit DMA mapping. - */ - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - return -EOPNOTSUPP; - if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; @@ -75,6 +69,10 @@ static int page_pool_init(struct page_pool *pool, */ } + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && + pool->p.flags & PP_FLAG_PAGE_FRAG) + return -EINVAL; + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; diff --git a/net/core/sock.c b/net/core/sock.c index 8f2b2f2c0e7b..41e91d0f7061 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2124,8 +2124,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_prot_creator = prot; /* SANITY */ - if (likely(newsk->sk_net_refcnt)) + if (likely(newsk->sk_net_refcnt)) { get_net(sock_net(newsk)); + sock_inuse_add(sock_net(newsk), 1); + } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); @@ -2197,8 +2199,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); - if (likely(newsk->sk_net_refcnt)) - sock_inuse_add(sock_net(newsk), 1); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 2cf02b4d77fb..4bb9401b0a3f 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -205,6 +205,8 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, offsetof(struct tcp_congestion_ops, release)) return &bpf_sk_getsockopt_proto; return NULL; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ec73a0d52d3e..323e622ff9b7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2591,7 +2591,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, free: kfree(t); out: - return -ENOBUFS; + return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b7796b4cf0a0..bbb3d39c69af 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1758,6 +1758,9 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, { skb_frag_t *frag; + if (unlikely(offset_skb >= skb->len)) + return NULL; + offset_skb -= skb_headlen(skb); if ((int)offset_skb < 0 || skb_has_frag_list(skb)) return NULL; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 319dd7bbfe33..8bcecdd6aeda 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1807,6 +1807,17 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc, skb = skb_recv_udp(sk, 0, 1, &err); if (!skb) return err; + + if (udp_lib_checksum_complete(skb)) { + __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, + IS_UDPLITE(sk)); + __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + continue; + } + used = recv_actor(desc, skb, 0, skb->len); if (used <= 0) { if (!copied) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index ed2f061b8768..f0bac6f7ab6b 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -808,6 +808,12 @@ int esp6_input_done2(struct sk_buff *skb, int err) struct tcphdr *th; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); + + if (offset < 0) { + err = -EINVAL; + goto out; + } + uh = (void *)(skb->data + offset); th = (void *)(skb->data + offset); hdr_len += offset; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index e2b791c37591..bd3d3195097f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -80,7 +80,8 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, } /* also validate MU-MIMO change */ - monitor_sdata = rtnl_dereference(local->monitor_sdata); + monitor_sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (!monitor_sdata && (params->vht_mumimo_groups || params->vht_mumimo_follow_addr)) @@ -840,7 +841,8 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy, mutex_lock(&local->mtx); if (local->use_chanctx) { - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (sdata) { ieee80211_vif_release_channel(sdata); ret = ieee80211_vif_use_channel(sdata, chandef, @@ -2707,7 +2709,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (!sdata) return -EOPNOTSUPP; } @@ -2767,7 +2770,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, mutex_unlock(&local->iflist_mtx); if (has_monitor) { - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (sdata) { sdata->user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 9a2145c8192b..20aa5cc31f77 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -588,7 +588,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do */ if (local->suspended) { WARN_ON(local->wowlan); - WARN_ON(rtnl_dereference(local->monitor_sdata)); + WARN_ON(rcu_access_pointer(local->monitor_sdata)); return; } @@ -961,6 +961,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) return 0; ASSERT_RTNL(); + lockdep_assert_wiphy(local->hw.wiphy); if (local->monitor_sdata) return 0; @@ -1028,6 +1029,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) return; ASSERT_RTNL(); + lockdep_assert_wiphy(local->hw.wiphy); mutex_lock(&local->iflist_mtx); diff --git a/net/mac80211/led.h b/net/mac80211/led.h index fb3aaa3c5606..b71a1428d883 100644 --- a/net/mac80211/led.h +++ b/net/mac80211/led.h @@ -72,19 +72,19 @@ static inline void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, #endif static inline void -ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, __le16 fc, int bytes) +ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, int bytes) { #ifdef CONFIG_MAC80211_LEDS - if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active)) + if (atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->tx_bytes += bytes; #endif } static inline void -ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, __le16 fc, int bytes) +ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, int bytes) { #ifdef CONFIG_MAC80211_LEDS - if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active)) + if (atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->rx_bytes += bytes; #endif } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fc5c608d02e2..9541a4c30aca 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -364,7 +364,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, * the compiler to think we have walked past the end of the * struct member. */ - pos = (void *)&rthdr->it_optional[it_present - rthdr->it_optional]; + pos = (void *)&rthdr->it_optional[it_present + 1 - rthdr->it_optional]; /* the order of the following fields is important */ @@ -1952,7 +1952,8 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) int keyid = rx->sta->ptk_idx; sta_ptk = rcu_dereference(rx->sta->ptk[keyid]); - if (ieee80211_has_protected(fc)) { + if (ieee80211_has_protected(fc) && + !(status->flag & RX_FLAG_IV_STRIPPED)) { cs = rx->sta->cipher_scheme; keyid = ieee80211_get_keyid(rx->skb, cs); @@ -4863,6 +4864,7 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, struct ieee80211_rate *rate = NULL; struct ieee80211_supported_band *sband; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; WARN_ON_ONCE(softirq_count() == 0); @@ -4959,9 +4961,9 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, if (!(status->flag & RX_FLAG_8023)) skb = ieee80211_rx_monitor(local, skb, rate); if (skb) { - ieee80211_tpt_led_trig_rx(local, - ((struct ieee80211_hdr *)skb->data)->frame_control, - skb->len); + if ((status->flag & RX_FLAG_8023) || + ieee80211_is_data_present(hdr->frame_control)) + ieee80211_tpt_led_trig_rx(local, skb->len); if (status->flag & RX_FLAG_8023) __ieee80211_rx_handle_8023(hw, pubsta, skb, list); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a756a197c770..278945e3e08a 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1721,21 +1721,19 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local, * Returns false if the frame couldn't be transmitted but was queued instead. */ static bool __ieee80211_tx(struct ieee80211_local *local, - struct sk_buff_head *skbs, int led_len, - struct sta_info *sta, bool txpending) + struct sk_buff_head *skbs, struct sta_info *sta, + bool txpending) { struct ieee80211_tx_info *info; struct ieee80211_sub_if_data *sdata; struct ieee80211_vif *vif; struct sk_buff *skb; bool result; - __le16 fc; if (WARN_ON(skb_queue_empty(skbs))) return true; skb = skb_peek(skbs); - fc = ((struct ieee80211_hdr *)skb->data)->frame_control; info = IEEE80211_SKB_CB(skb); sdata = vif_to_sdata(info->control.vif); if (sta && !sta->uploaded) @@ -1769,8 +1767,6 @@ static bool __ieee80211_tx(struct ieee80211_local *local, result = ieee80211_tx_frags(local, vif, sta, skbs, txpending); - ieee80211_tpt_led_trig_tx(local, fc, led_len); - WARN_ON_ONCE(!skb_queue_empty(skbs)); return result; @@ -1920,7 +1916,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, ieee80211_tx_result res_prepare; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); bool result = true; - int led_len; if (unlikely(skb->len < 10)) { dev_kfree_skb(skb); @@ -1928,7 +1923,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, } /* initialises tx */ - led_len = skb->len; res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb); if (unlikely(res_prepare == TX_DROP)) { @@ -1951,8 +1945,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, return true; if (!invoke_tx_handlers_late(&tx)) - result = __ieee80211_tx(local, &tx.skbs, led_len, - tx.sta, txpending); + result = __ieee80211_tx(local, &tx.skbs, tx.sta, txpending); return result; } @@ -4175,6 +4168,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct sk_buff *next; + int len = skb->len; if (unlikely(skb->len < ETH_HLEN)) { kfree_skb(skb); @@ -4221,10 +4215,8 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, } } else { /* we cannot process non-linear frames on this path */ - if (skb_linearize(skb)) { - kfree_skb(skb); - goto out; - } + if (skb_linearize(skb)) + goto out_free; /* the frame could be fragmented, software-encrypted, and other * things so we cannot really handle checksum offload with it - @@ -4258,7 +4250,10 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, goto out; out_free: kfree_skb(skb); + len = 0; out: + if (len) + ieee80211_tpt_led_trig_tx(local, len); rcu_read_unlock(); } @@ -4396,8 +4391,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, } static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, int led_len, - struct sta_info *sta, + struct sk_buff *skb, struct sta_info *sta, bool txpending) { struct ieee80211_local *local = sdata->local; @@ -4410,6 +4404,8 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, if (sta) sk_pacing_shift_update(skb->sk, local->hw.tx_sk_pacing_shift); + ieee80211_tpt_led_trig_tx(local, skb->len); + if (ieee80211_queue_skb(local, sdata, sta, skb)) return true; @@ -4498,7 +4494,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, if (key) info->control.hw_key = &key->conf; - ieee80211_tx_8023(sdata, skb, skb->len, sta, false); + ieee80211_tx_8023(sdata, skb, sta, false); return; @@ -4637,7 +4633,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, if (IS_ERR(sta) || (sta && !sta->uploaded)) sta = NULL; - result = ieee80211_tx_8023(sdata, skb, skb->len, sta, true); + result = ieee80211_tx_8023(sdata, skb, sta, true); } else { struct sk_buff_head skbs; @@ -4647,7 +4643,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, hdr = (struct ieee80211_hdr *)skb->data; sta = sta_info_get(sdata, hdr->addr1); - result = __ieee80211_tx(local, &skbs, skb->len, sta, true); + result = __ieee80211_tx(local, &skbs, sta, true); } return result; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 39fa2a50385d..43df2f0c5db9 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -796,7 +796,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || - lockdep_rtnl_is_held()); + lockdep_is_held(&local->hw.wiphy->mtx)); if (sdata && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) @@ -2381,7 +2381,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); /* add interfaces */ - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata) { /* in HW restart it exists already */ WARN_ON(local->resuming); @@ -2426,7 +2426,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN_ON(drv_add_chanctx(local, ctx)); mutex_unlock(&local->chanctx_mtx); - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (sdata && ieee80211_sdata_running(sdata)) ieee80211_assign_chanctx(local, sdata); } diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 9ea6004abe1b..62c6733e0792 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -143,7 +143,6 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct mac80211_qos_map *qos_map; bool qos; @@ -156,7 +155,7 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, else qos = false; - if (!qos || (info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) { + if (!qos) { skb->priority = 0; /* required for correct WPA/11i MIC */ return IEEE80211_AC_BE; } diff --git a/net/nfc/core.c b/net/nfc/core.c index 3c645c1d99c9..dc7a2404efdf 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -94,13 +94,13 @@ int nfc_dev_up(struct nfc_dev *dev) device_lock(&dev->dev); - if (dev->rfkill && rfkill_blocked(dev->rfkill)) { - rc = -ERFKILL; + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; goto error; } - if (!device_is_registered(&dev->dev)) { - rc = -ENODEV; + if (dev->rfkill && rfkill_blocked(dev->rfkill)) { + rc = -ERFKILL; goto error; } @@ -1125,11 +1125,7 @@ int nfc_register_device(struct nfc_dev *dev) if (rc) pr_err("Could not register llcp device\n"); - rc = nfc_genl_device_added(dev); - if (rc) - pr_debug("The userspace won't be notified that the device %s was added\n", - dev_name(&dev->dev)); - + device_lock(&dev->dev); dev->rfkill = rfkill_alloc(dev_name(&dev->dev), &dev->dev, RFKILL_TYPE_NFC, &nfc_rfkill_ops, dev); if (dev->rfkill) { @@ -1138,6 +1134,12 @@ int nfc_register_device(struct nfc_dev *dev) dev->rfkill = NULL; } } + device_unlock(&dev->dev); + + rc = nfc_genl_device_added(dev); + if (rc) + pr_debug("The userspace won't be notified that the device %s was added\n", + dev_name(&dev->dev)); return 0; } @@ -1154,10 +1156,17 @@ void nfc_unregister_device(struct nfc_dev *dev) pr_debug("dev_name=%s\n", dev_name(&dev->dev)); + rc = nfc_genl_device_removed(dev); + if (rc) + pr_debug("The userspace won't be notified that the device %s " + "was removed\n", dev_name(&dev->dev)); + + device_lock(&dev->dev); if (dev->rfkill) { rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); } + device_unlock(&dev->dev); if (dev->ops->check_presence) { device_lock(&dev->dev); @@ -1167,11 +1176,6 @@ void nfc_unregister_device(struct nfc_dev *dev) cancel_work_sync(&dev->check_pres_work); } - rc = nfc_genl_device_removed(dev); - if (rc) - pr_debug("The userspace won't be notified that the device %s " - "was removed\n", dev_name(&dev->dev)); - nfc_llcp_unregister_device(dev); mutex_lock(&nfc_devlist_mutex); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6fd873aa86be..d2537383a3e8 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -144,12 +144,15 @@ inline int nci_request(struct nci_dev *ndev, { int rc; - if (!test_bit(NCI_UP, &ndev->flags)) - return -ENETDOWN; - /* Serialize all requests */ mutex_lock(&ndev->req_lock); - rc = __nci_request(ndev, req, opt, timeout); + /* check the state after obtaing the lock against any races + * from nci_close_device when the device gets removed. + */ + if (test_bit(NCI_UP, &ndev->flags)) + rc = __nci_request(ndev, req, opt, timeout); + else + rc = -ENETDOWN; mutex_unlock(&ndev->req_lock); return rc; @@ -473,6 +476,11 @@ static int nci_open_device(struct nci_dev *ndev) mutex_lock(&ndev->req_lock); + if (test_bit(NCI_UNREG, &ndev->flags)) { + rc = -ENODEV; + goto done; + } + if (test_bit(NCI_UP, &ndev->flags)) { rc = -EALREADY; goto done; @@ -545,6 +553,10 @@ done: static int nci_close_device(struct nci_dev *ndev) { nci_req_cancel(ndev, ENODEV); + + /* This mutex needs to be held as a barrier for + * caller nci_unregister_device + */ mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { @@ -582,8 +594,8 @@ static int nci_close_device(struct nci_dev *ndev) del_timer_sync(&ndev->cmd_timer); - /* Clear flags */ - ndev->flags = 0; + /* Clear flags except NCI_UNREG */ + ndev->flags &= BIT(NCI_UNREG); mutex_unlock(&ndev->req_lock); @@ -1266,6 +1278,12 @@ void nci_unregister_device(struct nci_dev *ndev) { struct nci_conn_info *conn_info, *n; + /* This set_bit is not protected with specialized barrier, + * However, it is fine because the mutex_lock(&ndev->req_lock); + * in nci_close_device() will help to emit one. + */ + set_bit(NCI_UNREG, &ndev->flags); + nci_close_device(ndev); destroy_workqueue(ndev->cmd_wq); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index d64b0eeccbe4..efc963ab995a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -19,6 +19,7 @@ #include <linux/if_arp.h> #include <net/net_namespace.h> #include <net/netlink.h> +#include <net/dst.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_mirred.h> @@ -228,6 +229,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool want_ingress; bool is_redirect; bool expects_nh; + bool at_ingress; int m_eaction; int mac_len; bool at_nh; @@ -263,7 +265,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, * ingress - that covers the TC S/W datapath. */ is_redirect = tcf_mirred_is_act_redirect(m_eaction); - use_reinsert = skb_at_tc_ingress(skb) && is_redirect && + at_ingress = skb_at_tc_ingress(skb); + use_reinsert = at_ingress && is_redirect && tcf_mirred_can_reinsert(retval); if (!use_reinsert) { skb2 = skb_clone(skb, GFP_ATOMIC); @@ -271,10 +274,12 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + /* All mirred/redirected skbs should clear previous ct info */ nf_reset_ct(skb2); - - want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ + skb_dst_drop(skb2); expects_nh = want_ingress || !m_mac_header_xmit; at_nh = skb->data == skb_network_header(skb); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 59284da9116d..b61c802e3bf3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -566,6 +566,10 @@ static void smc_stat_fallback(struct smc_sock *smc) static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { + wait_queue_head_t *smc_wait = sk_sleep(&smc->sk); + wait_queue_head_t *clc_wait = sk_sleep(smc->clcsock->sk); + unsigned long flags; + smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -575,6 +579,16 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) smc->clcsock->file->private_data = smc->clcsock; smc->clcsock->wq.fasync_list = smc->sk.sk_socket->wq.fasync_list; + + /* There may be some entries remaining in + * smc socket->wq, which should be removed + * to clcsocket->wq during the fallback. + */ + spin_lock_irqsave(&smc_wait->lock, flags); + spin_lock(&clc_wait->lock); + list_splice_init(&smc_wait->head, &clc_wait->head); + spin_unlock(&clc_wait->lock); + spin_unlock_irqrestore(&smc_wait->lock, flags); } } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 49b8ba3bb683..25ebd30feecd 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -708,13 +708,14 @@ static u8 smcr_next_link_id(struct smc_link_group *lgr) int i; while (1) { +again: link_id = ++lgr->next_link_id; if (!link_id) /* skip zero as link_id */ link_id = ++lgr->next_link_id; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (smc_link_usable(&lgr->lnk[i]) && lgr->lnk[i].link_id == link_id) - continue; + goto again; } break; } diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index dc60c32bb70d..b4d9419a015b 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -524,7 +524,7 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey, return -EEXIST; /* Allocate a new AEAD */ - tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC); + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); if (unlikely(!tmp)) return -ENOMEM; @@ -597,6 +597,10 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey, tmp->cloned = NULL; tmp->authsize = TIPC_AES_GCM_TAG_SIZE; tmp->key = kmemdup(ukey, tipc_aead_key_size(ukey), GFP_KERNEL); + if (!tmp->key) { + tipc_aead_free(&tmp->rcu); + return -ENOMEM; + } memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE); atomic_set(&tmp->users, 0); atomic64_set(&tmp->seqno, 0); @@ -1470,7 +1474,7 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net, return -EEXIST; /* Allocate crypto */ - c = kzalloc(sizeof(*c), GFP_ATOMIC); + c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; @@ -1484,7 +1488,7 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net, } /* Allocate statistic structure */ - c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC); + c->stats = alloc_percpu(struct tipc_crypto_stats); if (!c->stats) { if (c->wq) destroy_workqueue(c->wq); @@ -2457,7 +2461,7 @@ static void tipc_crypto_work_tx(struct work_struct *work) } /* Lets duplicate it first */ - skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_ATOMIC); + skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_KERNEL); rcu_read_unlock(); /* Now, generate new key, initiate & distribute it */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 1b7a487c8841..09ae8448f394 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1298,8 +1298,11 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, return false; #ifdef CONFIG_TIPC_CRYPTO case MSG_CRYPTO: - tipc_crypto_msg_rcv(l->net, skb); - return true; + if (TIPC_SKB_CB(skb)->decrypted) { + tipc_crypto_msg_rcv(l->net, skb); + return true; + } + fallthrough; #endif default: pr_warn("Dropping received illegal msg type\n"); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 81232b73df8f..a27b3b5fa210 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -936,33 +936,37 @@ nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = { [NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 }, }; -int nl80211_prepare_wdev_dump(struct netlink_callback *cb, - struct cfg80211_registered_device **rdev, - struct wireless_dev **wdev) +static int nl80211_prepare_wdev_dump(struct netlink_callback *cb, + struct cfg80211_registered_device **rdev, + struct wireless_dev **wdev, + struct nlattr **attrbuf) { int err; if (!cb->args[0]) { - struct nlattr **attrbuf; + struct nlattr **attrbuf_free = NULL; - attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), - GFP_KERNEL); - if (!attrbuf) - return -ENOMEM; + if (!attrbuf) { + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), + GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + attrbuf_free = attrbuf; + } err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, attrbuf, nl80211_fam.maxattr, nl80211_policy, NULL); if (err) { - kfree(attrbuf); + kfree(attrbuf_free); return err; } rtnl_lock(); *wdev = __cfg80211_wdev_from_attrs(NULL, sock_net(cb->skb->sk), attrbuf); - kfree(attrbuf); + kfree(attrbuf_free); if (IS_ERR(*wdev)) { rtnl_unlock(); return PTR_ERR(*wdev); @@ -6197,7 +6201,7 @@ static int nl80211_dump_station(struct sk_buff *skb, int sta_idx = cb->args[2]; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -7092,7 +7096,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, int path_idx = cb->args[2]; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -7292,7 +7296,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb, int path_idx = cb->args[2]; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -9718,7 +9722,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) int start = cb->args[2], idx = 0; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -9851,7 +9855,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) if (!attrbuf) return -ENOMEM; - res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf); if (res) { kfree(attrbuf); return res; diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index a3f387770f1b..d642e3be4ee7 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file - * Copyright (C) 2018, 2020 Intel Corporation + * Copyright (C) 2018, 2020-2021 Intel Corporation */ #ifndef __NET_WIRELESS_NL80211_H #define __NET_WIRELESS_NL80211_H @@ -22,10 +22,6 @@ static inline u64 wdev_id(struct wireless_dev *wdev) ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32); } -int nl80211_prepare_wdev_dump(struct netlink_callback *cb, - struct cfg80211_registered_device **rdev, - struct wireless_dev **wdev); - int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, struct genl_info *info, struct cfg80211_chan_def *chandef); diff --git a/net/wireless/util.c b/net/wireless/util.c index 5ff1f8726faf..41ea65deb6e1 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1046,6 +1046,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, switch (otype) { case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, dev, true); break; case NL80211_IFTYPE_ADHOC: diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 90c4e1e819d3..bc4ad48ea4f0 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -500,7 +500,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) pool->free_list_cnt--; xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); - list_del(&xskb->free_list_node); + list_del_init(&xskb->free_list_node); } xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM; @@ -568,7 +568,7 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3 i = nb_entries; while (i--) { xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); - list_del(&xskb->free_list_node); + list_del_init(&xskb->free_list_node); *xdp = &xskb->xdp; xdp++; @@ -615,6 +615,9 @@ EXPORT_SYMBOL(xp_can_alloc); void xp_free(struct xdp_buff_xsk *xskb) { + if (!list_empty(&xskb->free_list_node)) + return; + xskb->pool->free_list_cnt++; list_add(&xskb->free_list_node, &xskb->pool->free_list); } diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h index 722b3fadb467..1752a46a2b05 100644 --- a/samples/bpf/hbm_kern.h +++ b/samples/bpf/hbm_kern.h @@ -9,8 +9,6 @@ * Include file for sample Host Bandwidth Manager (HBM) BPF programs */ #define KBUILD_MODNAME "foo" -#include <stddef.h> -#include <stdbool.h> #include <uapi/linux/bpf.h> #include <uapi/linux/if_ether.h> #include <uapi/linux/if_packet.h> diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index d84e6949007c..a81704d3317b 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -309,7 +309,6 @@ int main(int argc, char **argv) const char *mprog_filename = NULL, *mprog_name = NULL; struct xdp_redirect_cpu *skel; struct bpf_map_info info = {}; - char ifname_buf[IF_NAMESIZE]; struct bpf_cpumap_val value; __u32 infosz = sizeof(info); int ret = EXIT_FAIL_OPTION; @@ -390,10 +389,10 @@ int main(int argc, char **argv) case 'd': if (strlen(optarg) >= IF_NAMESIZE) { fprintf(stderr, "-d/--dev name too long\n"); + usage(argv, long_options, __doc__, mask, true, skel->obj); goto end_cpu; } - safe_strncpy(ifname_buf, optarg, strlen(ifname_buf)); - ifindex = if_nametoindex(ifname_buf); + ifindex = if_nametoindex(optarg); if (!ifindex) ifindex = strtoul(optarg, NULL, 0); if (!ifindex) { diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c index b32d82178199..8740838e7767 100644 --- a/samples/bpf/xdp_sample_user.c +++ b/samples/bpf/xdp_sample_user.c @@ -120,7 +120,10 @@ struct sample_output { __u64 xmit; } totals; struct { - __u64 pps; + union { + __u64 pps; + __u64 num; + }; __u64 drop; __u64 err; } rx_cnt; @@ -1322,7 +1325,7 @@ int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, static void sample_summary_print(void) { - double period = sample_out.rx_cnt.pps; + double num = sample_out.rx_cnt.num; if (sample_out.totals.rx) { double pkts = sample_out.totals.rx; @@ -1330,7 +1333,7 @@ static void sample_summary_print(void) print_always(" Packets received : %'-10llu\n", sample_out.totals.rx); print_always(" Average packets/s : %'-10.0f\n", - sample_round(pkts / period)); + sample_round(pkts / num)); } if (sample_out.totals.redir) { double pkts = sample_out.totals.redir; @@ -1338,7 +1341,7 @@ static void sample_summary_print(void) print_always(" Packets redirected : %'-10llu\n", sample_out.totals.redir); print_always(" Average redir/s : %'-10.0f\n", - sample_round(pkts / period)); + sample_round(pkts / num)); } if (sample_out.totals.drop) print_always(" Rx dropped : %'-10llu\n", @@ -1355,7 +1358,7 @@ static void sample_summary_print(void) print_always(" Packets transmitted : %'-10llu\n", sample_out.totals.xmit); print_always(" Average transmit/s : %'-10.0f\n", - sample_round(pkts / period)); + sample_round(pkts / num)); } } @@ -1422,7 +1425,7 @@ static int sample_stats_collect(struct stats_record *rec) return 0; } -static void sample_summary_update(struct sample_output *out, int interval) +static void sample_summary_update(struct sample_output *out) { sample_out.totals.rx += out->totals.rx; sample_out.totals.redir += out->totals.redir; @@ -1430,12 +1433,11 @@ static void sample_summary_update(struct sample_output *out, int interval) sample_out.totals.drop_xmit += out->totals.drop_xmit; sample_out.totals.err += out->totals.err; sample_out.totals.xmit += out->totals.xmit; - sample_out.rx_cnt.pps += interval; + sample_out.rx_cnt.num++; } static void sample_stats_print(int mask, struct stats_record *cur, - struct stats_record *prev, char *prog_name, - int interval) + struct stats_record *prev, char *prog_name) { struct sample_output out = {}; @@ -1452,7 +1454,7 @@ static void sample_stats_print(int mask, struct stats_record *cur, else if (mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI) stats_get_devmap_xmit_multi(cur, prev, 0, &out, mask & SAMPLE_DEVMAP_XMIT_CNT); - sample_summary_update(&out, interval); + sample_summary_update(&out); stats_print(prog_name, mask, cur, prev, &out); } @@ -1495,7 +1497,7 @@ static void swap(struct stats_record **a, struct stats_record **b) } static int sample_timer_cb(int timerfd, struct stats_record **rec, - struct stats_record **prev, int interval) + struct stats_record **prev) { char line[64] = "Summary"; int ret; @@ -1524,7 +1526,7 @@ static int sample_timer_cb(int timerfd, struct stats_record **rec, snprintf(line, sizeof(line), "%s->%s", f ?: "?", t ?: "?"); } - sample_stats_print(sample_mask, *rec, *prev, line, interval); + sample_stats_print(sample_mask, *rec, *prev, line); return 0; } @@ -1579,7 +1581,7 @@ int sample_run(int interval, void (*post_cb)(void *), void *ctx) if (pfd[0].revents & POLLIN) ret = sample_signal_cb(); else if (pfd[1].revents & POLLIN) - ret = sample_timer_cb(timerfd, &rec, &prev, interval); + ret = sample_timer_cb(timerfd, &rec, &prev); if (ret) break; diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index bbd1150578f7..8791d0e2762b 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -88,5 +88,4 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU $(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \ - LIBBPF_OUTPUT=$(BPFOBJ_OUTPUT) \ - LIBBPF_DESTDIR=$(BPF_DESTDIR) CC=$(HOSTCC) LD=$(HOSTLD) + CC=$(HOSTCC) LD=$(HOSTLD) diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index d26e5472fe50..6f3df004479b 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -45,8 +45,8 @@ struct bpf_gen { int nr_fd_array; }; -void bpf_gen__init(struct bpf_gen *gen, int log_level); -int bpf_gen__finish(struct bpf_gen *gen); +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps); +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps); void bpf_gen__free(struct bpf_gen *gen); void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 502dea53a742..9934851ccde7 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -18,7 +18,7 @@ #define MAX_USED_MAPS 64 #define MAX_USED_PROGS 32 #define MAX_KFUNC_DESCS 256 -#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS) +#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS) /* The following structure describes the stack layout of the loader program. * In addition R6 contains the pointer to context. @@ -33,8 +33,8 @@ */ struct loader_stack { __u32 btf_fd; - __u32 prog_fd[MAX_USED_PROGS]; __u32 inner_map_fd; + __u32 prog_fd[MAX_USED_PROGS]; }; #define stack_off(field) \ @@ -42,6 +42,11 @@ struct loader_stack { #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field)) +static int blob_fd_array_off(struct bpf_gen *gen, int index) +{ + return gen->fd_array + index * sizeof(int); +} + static int realloc_insn_buf(struct bpf_gen *gen, __u32 size) { size_t off = gen->insn_cur - gen->insn_start; @@ -102,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in emit(gen, insn2); } -void bpf_gen__init(struct bpf_gen *gen, int log_level) +static int add_data(struct bpf_gen *gen, const void *data, __u32 size); +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off); + +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps) { - size_t stack_sz = sizeof(struct loader_stack); + size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz; int i; + gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); gen->log_level = log_level; /* save ctx pointer into R6 */ emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1)); @@ -118,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + /* amount of stack actually used, only used to calculate iterations, not stack offset */ + nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]); /* jump over cleanup code */ emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, - /* size of cleanup code below */ - (stack_sz / 4) * 3 + 2)); + /* size of cleanup code below (including map fd cleanup) */ + (nr_progs_sz / 4) * 3 + 2 + + /* 6 insns for emit_sys_close_blob, + * 6 insns for debug_regs in emit_sys_close_blob + */ + nr_maps * (6 + (gen->log_level ? 6 : 0)))); /* remember the label where all error branches will jump to */ gen->cleanup_label = gen->insn_cur - gen->insn_start; /* emit cleanup code: close all temp FDs */ - for (i = 0; i < stack_sz; i += 4) { + for (i = 0; i < nr_progs_sz; i += 4) { emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i)); emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); } + for (i = 0; i < nr_maps; i++) + emit_sys_close_blob(gen, blob_fd_array_off(gen, i)); /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); emit(gen, BPF_EXIT_INSN()); @@ -160,8 +177,6 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size) */ static int add_map_fd(struct bpf_gen *gen) { - if (!gen->fd_array) - gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); if (gen->nr_maps == MAX_USED_MAPS) { pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS); gen->error = -E2BIG; @@ -174,8 +189,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen) { int cur; - if (!gen->fd_array) - gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); if (gen->nr_fd_array == MAX_KFUNC_DESCS) { cur = add_data(gen, NULL, sizeof(int)); return (cur - gen->fd_array) / sizeof(int); @@ -183,11 +196,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen) return MAX_USED_MAPS + gen->nr_fd_array++; } -static int blob_fd_array_off(struct bpf_gen *gen, int index) -{ - return gen->fd_array + index * sizeof(int); -} - static int insn_bytes_to_bpf_size(__u32 sz) { switch (sz) { @@ -359,10 +367,15 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) __emit_sys_close(gen); } -int bpf_gen__finish(struct bpf_gen *gen) +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) { int i; + if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) { + pr_warn("progs/maps mismatch\n"); + gen->error = -EFAULT; + return gen->error; + } emit_sys_close_stack(gen, stack_off(btf_fd)); for (i = 0; i < gen->nr_progs; i++) move_stack2ctx(gen, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a1bea1953df6..7c74342bb668 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7258,7 +7258,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) } if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, attr->log_level); + bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps); err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); @@ -7277,7 +7277,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) for (i = 0; i < obj->nr_maps; i++) obj->maps[i].fd = -1; if (!err) - err = bpf_gen__finish(obj->gen_loader); + err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); } /* clean up fd_array */ diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 54b0a41a3775..62fafbeb4672 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -187,7 +187,7 @@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ - BPFTOOL_OUTPUT=$(BUILD_DIR)/bpftool/ \ + BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ cp $(RUNQSLOWER_OUTPUT)runqslower $@ diff --git a/tools/testing/selftests/bpf/prog_tests/helper_restricted.c b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c new file mode 100644 index 000000000000..e1de5f80c3b2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_helper_restricted.skel.h" + +void test_helper_restricted(void) +{ + int prog_i = 0, prog_cnt; + int duration = 0; + + do { + struct test_helper_restricted *test; + int maybeOK; + + test = test_helper_restricted__open(); + if (!ASSERT_OK_PTR(test, "open")) + return; + + prog_cnt = test->skeleton->prog_cnt; + + for (int j = 0; j < prog_cnt; ++j) { + struct bpf_program *prog = *test->skeleton->progs[j].prog; + + maybeOK = bpf_program__set_autoload(prog, prog_i == j); + ASSERT_OK(maybeOK, "set autoload"); + } + + maybeOK = test_helper_restricted__load(test); + CHECK(!maybeOK, test->skeleton->progs[prog_i].name, "helper isn't restricted"); + + test_helper_restricted__destroy(test); + } while (++prog_i < prog_cnt); +} diff --git a/tools/testing/selftests/bpf/progs/test_helper_restricted.c b/tools/testing/selftests/bpf/progs/test_helper_restricted.c new file mode 100644 index 000000000000..68d64c365f90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_helper_restricted.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <time.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct timer { + struct bpf_timer t; +}; + +struct lock { + struct bpf_spin_lock l; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct timer); +} timers SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct lock); +} locks SEC(".maps"); + +static int timer_cb(void *map, int *key, struct timer *timer) +{ + return 0; +} + +static void timer_work(void) +{ + struct timer *timer; + const int key = 0; + + timer = bpf_map_lookup_elem(&timers, &key); + if (timer) { + bpf_timer_init(&timer->t, &timers, CLOCK_MONOTONIC); + bpf_timer_set_callback(&timer->t, timer_cb); + bpf_timer_start(&timer->t, 10E9, 0); + bpf_timer_cancel(&timer->t); + } +} + +static void spin_lock_work(void) +{ + const int key = 0; + struct lock *lock; + + lock = bpf_map_lookup_elem(&locks, &key); + if (lock) { + bpf_spin_lock(&lock->l); + bpf_spin_unlock(&lock->l); + } +} + +SEC("raw_tp/sys_enter") +int raw_tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("kprobe/sys_nanosleep") +int kprobe_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("perf_event") +int perf_event_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("raw_tp/sys_enter") +int raw_tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("kprobe/sys_nanosleep") +int kprobe_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("perf_event") +int perf_event_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +const char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 25afe423b3f0..465ef3f112c0 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -92,6 +92,7 @@ struct bpf_test { int fixup_map_event_output[MAX_FIXUPS]; int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; + int fixup_map_timer[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -604,8 +605,15 @@ static int create_cgroup_storage(bool percpu) * int cnt; * struct bpf_spin_lock l; * }; + * struct bpf_timer { + * __u64 :64; + * __u64 :64; + * } __attribute__((aligned(8))); + * struct timer { + * struct bpf_timer t; + * }; */ -static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; +static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t"; static __u32 btf_raw_types[] = { /* int */ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ @@ -616,6 +624,11 @@ static __u32 btf_raw_types[] = { BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + /* struct bpf_timer */ /* [4] */ + BTF_TYPE_ENC(25, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0), 16), + /* struct timer */ /* [5] */ + BTF_TYPE_ENC(35, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 16), + BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */ }; static int load_btf(void) @@ -696,6 +709,29 @@ static int create_sk_storage_map(void) return fd; } +static int create_map_timer(void) +{ + struct bpf_create_map_attr attr = { + .name = "test_map", + .map_type = BPF_MAP_TYPE_ARRAY, + .key_size = 4, + .value_size = 16, + .max_entries = 1, + .btf_key_type_id = 1, + .btf_value_type_id = 5, + }; + int fd, btf_fd; + + btf_fd = load_btf(); + if (btf_fd < 0) + return -1; + attr.btf_fd = btf_fd; + fd = bpf_create_map_xattr(&attr); + if (fd < 0) + printf("Failed to create map with timer\n"); + return fd; +} + static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, @@ -722,6 +758,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_event_output = test->fixup_map_event_output; int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; + int *fixup_map_timer = test->fixup_map_timer; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -907,6 +944,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_ringbuf++; } while (*fixup_map_ringbuf); } + if (*fixup_map_timer) { + map_fds[21] = create_map_timer(); + do { + prog[*fixup_map_timer].imm = map_fds[21]; + fixup_map_timer++; + } while (*fixup_map_timer); + } } struct libcap { diff --git a/tools/testing/selftests/bpf/verifier/helper_restricted.c b/tools/testing/selftests/bpf/verifier/helper_restricted.c new file mode 100644 index 000000000000..a067b7098b97 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/helper_restricted.c @@ -0,0 +1,196 @@ +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, +{ + "bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c index 2798927ee9ff..128a348b762d 100644 --- a/tools/testing/selftests/bpf/verifier/map_in_map.c +++ b/tools/testing/selftests/bpf/verifier/map_in_map.c @@ -19,6 +19,40 @@ .result = ACCEPT, }, { + "map in map state pruning", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 4, 14 }, + .flags = BPF_F_TEST_STATE_FREQ, + .result = VERBOSE_ACCEPT, + .errstr = "processed 25 insns", + .prog_type = BPF_PROG_TYPE_XDP, +}, +{ "invalid inner map pointer", .insns = { BPF_ST_MEM(0, BPF_REG_10, -4, 0), diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index a4bd1b087303..697994a9278b 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -6,6 +6,7 @@ CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_VRF=m CONFIG_BPF_SYSCALL=y CONFIG_CGROUP_BPF=y +CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m CONFIG_NET_ACT_VLAN=m diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index d9eca227136b..de19eb6c38f0 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,7 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test" + gact_trap_test mirred_egress_to_ingress_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -13,10 +13,12 @@ tcflags="skip_hw" h1_create() { simple_if_init $h1 192.0.2.1/24 + tc qdisc add dev $h1 clsact } h1_destroy() { + tc qdisc del dev $h1 clsact simple_if_fini $h1 192.0.2.1/24 } @@ -153,6 +155,49 @@ gact_trap_test() log_test "trap ($tcflags)" } +mirred_egress_to_ingress_test() +{ + RET=0 + + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action \ + ct commit nat src addr 192.0.2.2 pipe \ + ct clear pipe \ + ct commit nat dst addr 192.0.2.1 pipe \ + mirred ingress redirect dev $h1 + + tc filter add dev $swp1 protocol ip pref 11 handle 111 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action drop + tc filter add dev $swp1 protocol ip pref 12 handle 112 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 0 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t icmp "ping,id=42,seq=10" -q + + tc_check_packets "dev $h1 egress" 100 1 + check_err $? "didn't mirror first packet" + + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect first packet" + tc_check_packets "dev $swp1 ingress" 112 1 + check_err $? "didn't receive reply to first packet" + + ping 192.0.2.2 -I$h1 -c1 -w1 -q 1>/dev/null 2>&1 + + tc_check_packets "dev $h1 egress" 100 2 + check_err $? "didn't mirror second packet" + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect second packet" + tc_check_packets "dev $swp1 ingress" 112 2 + check_err $? "didn't receive reply to second packet" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $swp1 ingress protocol ip pref 11 handle 111 flower + tc filter del dev $swp1 ingress protocol ip pref 12 handle 112 flower + + log_test "mirred_egress_to_ingress ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh index fdeb44d621eb..3224651db97b 100755 --- a/tools/testing/selftests/net/gre_gso.sh +++ b/tools/testing/selftests/net/gre_gso.sh @@ -118,16 +118,18 @@ gre_gst_test_checks() local addr=$2 local proto=$3 - $NS_EXEC nc $proto -kl $port >/dev/null & + [ "$proto" == 6 ] && addr="[$addr]" + + $NS_EXEC socat - tcp${proto}-listen:$port,reuseaddr,fork >/dev/null & PID=$! while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done - cat $TMPFILE | timeout 1 nc $proto -N $addr $port + cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port log_test $? 0 "$name - copy file w/ TSO" ethtool -K veth0 tso off - cat $TMPFILE | timeout 1 nc $proto -N $addr $port + cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port log_test $? 0 "$name - copy file w/ GSO" ethtool -K veth0 tso on @@ -155,8 +157,8 @@ gre6_gso_test() sleep 2 - gre_gst_test_checks GREv6/v4 172.16.2.2 - gre_gst_test_checks GREv6/v6 2001:db8:1::2 -6 + gre_gst_test_checks GREv6/v4 172.16.2.2 4 + gre_gst_test_checks GREv6/v6 2001:db8:1::2 6 cleanup } @@ -212,8 +214,8 @@ if [ ! -x "$(command -v ip)" ]; then exit $ksft_skip fi -if [ ! -x "$(command -v nc)" ]; then - echo "SKIP: Could not run test without nc tool" +if [ ! -x "$(command -v socat)" ]; then + echo "SKIP: Could not run test without socat tool" exit $ksft_skip fi |