diff options
37 files changed, 561 insertions, 255 deletions
diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst index 9232cd7da301..5d0b68f752c0 100644 --- a/Documentation/networking/devlink/devlink-region.rst +++ b/Documentation/networking/devlink/devlink-region.rst @@ -49,7 +49,7 @@ example usage $ devlink region show [ DEV/REGION ] $ devlink region del DEV/REGION snapshot SNAPSHOT_ID $ devlink region dump DEV/REGION [ snapshot SNAPSHOT_ID ] - $ devlink region read DEV/REGION [ snapshot SNAPSHOT_ID ] address ADDRESS length length + $ devlink region read DEV/REGION [ snapshot SNAPSHOT_ID ] address ADDRESS length LENGTH # Show all of the exposed regions with region sizes: $ devlink region show diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 02f07b870f10..268949939636 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1047,31 +1047,31 @@ static int lan9303_get_sset_count(struct dsa_switch *ds, int port, int sset) return ARRAY_SIZE(lan9303_mib); } -static int lan9303_phy_read(struct dsa_switch *ds, int phy, int regnum) +static int lan9303_phy_read(struct dsa_switch *ds, int port, int regnum) { struct lan9303 *chip = ds->priv; int phy_base = chip->phy_addr_base; - if (phy == phy_base) + if (port == 0) return lan9303_virt_phy_reg_read(chip, regnum); - if (phy > phy_base + 2) + if (port > 2) return -ENODEV; - return chip->ops->phy_read(chip, phy, regnum); + return chip->ops->phy_read(chip, phy_base + port, regnum); } -static int lan9303_phy_write(struct dsa_switch *ds, int phy, int regnum, +static int lan9303_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val) { struct lan9303 *chip = ds->priv; int phy_base = chip->phy_addr_base; - if (phy == phy_base) + if (port == 0) return lan9303_virt_phy_reg_write(chip, regnum, val); - if (phy > phy_base + 2) + if (port > 2) return -ENODEV; - return chip->ops->phy_write(chip, phy, regnum, val); + return chip->ops->phy_write(chip, phy_base + port, regnum, val); } static int lan9303_port_enable(struct dsa_switch *ds, int port, @@ -1099,7 +1099,7 @@ static void lan9303_port_disable(struct dsa_switch *ds, int port) vlan_vid_del(dsa_port_to_conduit(dp), htons(ETH_P_8021Q), port); lan9303_disable_processing_port(chip, port); - lan9303_phy_write(ds, chip->phy_addr_base + port, MII_BMCR, BMCR_PDOWN); + lan9303_phy_write(ds, port, MII_BMCR, BMCR_PDOWN); } static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, @@ -1374,8 +1374,6 @@ static const struct dsa_switch_ops lan9303_switch_ops = { static int lan9303_register_switch(struct lan9303 *chip) { - int base; - chip->ds = devm_kzalloc(chip->dev, sizeof(*chip->ds), GFP_KERNEL); if (!chip->ds) return -ENOMEM; @@ -1385,8 +1383,7 @@ static int lan9303_register_switch(struct lan9303 *chip) chip->ds->priv = chip; chip->ds->ops = &lan9303_switch_ops; chip->ds->phylink_mac_ops = &lan9303_phylink_mac_ops; - base = chip->phy_addr_base; - chip->ds->phys_mii_mask = GENMASK(LAN9303_NUM_PORTS - 1 + base, base); + chip->ds->phys_mii_mask = GENMASK(LAN9303_NUM_PORTS - 1, 0); return dsa_register_switch(chip->ds); } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index a806dadc4196..20c6529ec135 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -1380,6 +1380,7 @@ static int bcmasp_probe(struct platform_device *pdev) dev_err(dev, "Cannot create eth interface %d\n", i); bcmasp_remove_intfs(priv); of_node_put(intf_node); + ret = -ENOMEM; goto of_put_exit; } list_add_tail(&intf->list, &priv->intfs); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 53085058100c..64b61a8d426d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6146,6 +6146,21 @@ static u16 bnxt_get_max_rss_ring(struct bnxt *bp) return max_ring; } +u16 bnxt_get_max_rss_ctx_ring(struct bnxt *bp) +{ + u16 i, tbl_size, max_ring = 0; + struct bnxt_rss_ctx *rss_ctx; + + tbl_size = bnxt_get_rxfh_indir_size(bp->dev); + + list_for_each_entry(rss_ctx, &bp->rss_ctx_list, list) { + for (i = 0; i < tbl_size; i++) + max_ring = max(max_ring, rss_ctx->rss_indir_tbl[i]); + } + + return max_ring; +} + int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings) { if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9cf0acfa04e5..6b10a09ee1af 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2776,6 +2776,7 @@ int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, struct bnxt_vnic_info *vnic, void bnxt_fill_ipv6_mask(__be32 mask[4]); int bnxt_alloc_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx); void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx); +u16 bnxt_get_max_rss_ctx_ring(struct bnxt *bp); int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings); int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic); int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 8763f8a01457..79c09c1cdf93 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -961,6 +961,12 @@ static int bnxt_set_channels(struct net_device *dev, return rc; } + if (req_rx_rings < bp->rx_nr_rings && + req_rx_rings <= bnxt_get_max_rss_ctx_ring(bp)) { + netdev_warn(dev, "Can't deactivate rings used by RSS contexts\n"); + return -EINVAL; + } + if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) && netif_is_rxfh_configured(dev)) { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 2e98a2a0bead..ce227b56cf72 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1109,6 +1109,46 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) } /** + * e1000e_force_smbus - Force interfaces to transition to SMBUS mode. + * @hw: pointer to the HW structure + * + * Force the MAC and the PHY to SMBUS mode. Assumes semaphore already + * acquired. + * + * Return: 0 on success, negative errno on failure. + **/ +static s32 e1000e_force_smbus(struct e1000_hw *hw) +{ + u16 smb_ctrl = 0; + u32 ctrl_ext; + s32 ret_val; + + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + + /* Force SMBus mode in the PHY */ + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &smb_ctrl); + if (ret_val) { + e1000e_enable_phy_retry(hw); + return ret_val; + } + + smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS; + e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, smb_ctrl); + + e1000e_enable_phy_retry(hw); + + /* Force SMBus mode in the MAC */ + ctrl_ext = er32(CTRL_EXT); + ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, ctrl_ext); + + return 0; +} + +/** * e1000_enable_ulp_lpt_lp - configure Ultra Low Power mode for LynxPoint-LP * @hw: pointer to the HW structure * @to_sx: boolean indicating a system power state transition to Sx @@ -1165,6 +1205,14 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) if (ret_val) goto out; + if (hw->mac.type != e1000_pch_mtp) { + ret_val = e1000e_force_smbus(hw); + if (ret_val) { + e_dbg("Failed to force SMBUS: %d\n", ret_val); + goto release; + } + } + /* Si workaround for ULP entry flow on i127/rev6 h/w. Enable * LPLU and disable Gig speed when entering ULP */ @@ -1225,27 +1273,12 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) } release: - /* Switching PHY interface always returns MDI error - * so disable retry mechanism to avoid wasting time - */ - e1000e_disable_phy_retry(hw); - - /* Force SMBus mode in PHY */ - ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); - if (ret_val) { - e1000e_enable_phy_retry(hw); - hw->phy.ops.release(hw); - goto out; + if (hw->mac.type == e1000_pch_mtp) { + ret_val = e1000e_force_smbus(hw); + if (ret_val) + e_dbg("Failed to force SMBUS over MTL system: %d\n", + ret_val); } - phy_reg |= CV_SMB_CTRL_FORCE_SMBUS; - e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); - - e1000e_enable_phy_retry(hw); - - /* Force SMBus mode in MAC */ - mac_reg = er32(CTRL_EXT); - mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, mac_reg); hw->phy.ops.release(hw); out: diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 284c3fad5a6e..310513d9321b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13293,6 +13293,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, bool need_reset; int i; + /* VSI shall be deleted in a moment, block loading new programs */ + if (prog && test_bit(__I40E_IN_REMOVE, pf->state)) + return -EINVAL; + /* Don't allow frames that span over multiple buffers */ if (vsi->netdev->mtu > frame_size - I40E_PACKET_HDR_PAD) { NL_SET_ERR_MSG_MOD(extack, "MTU too large for linear frames and XDP prog does not support frags"); @@ -13301,14 +13305,9 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, /* When turning XDP on->off/off->on we reset and rebuild the rings. */ need_reset = (i40e_enabled_xdp_vsi(vsi) != !!prog); - if (need_reset) i40e_prep_for_reset(pf); - /* VSI shall be deleted in a moment, just return EINVAL */ - if (test_bit(__I40E_IN_REMOVE, pf->state)) - return -EINVAL; - old_prog = xchg(&vsi->xdp_prog, prog); if (need_reset) { diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 5352fee62d2b..0b9982804370 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -217,9 +217,9 @@ ltq_etop_free_channel(struct net_device *dev, struct ltq_etop_chan *ch) if (ch->dma.irq) free_irq(ch->dma.irq, priv); if (IS_RX(ch->idx)) { - int desc; + struct ltq_dma_channel *dma = &ch->dma; - for (desc = 0; desc < LTQ_DESC_NUM; desc++) + for (dma->desc = 0; dma->desc < LTQ_DESC_NUM; dma->desc++) dev_kfree_skb_any(ch->skb[ch->dma.desc]); } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index ff78251f92d4..5f661e67ccbc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1643,7 +1643,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, if (req->ssow > block->lf.max) { dev_err(&rvu->pdev->dev, "Func 0x%x: Invalid SSOW req, %d > max %d\n", - pcifunc, req->sso, block->lf.max); + pcifunc, req->ssow, block->lf.max); return -EINVAL; } mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 31aebeb2e285..25989c79c92e 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -1524,6 +1524,7 @@ static int mtk_star_probe(struct platform_device *pdev) { struct device_node *of_node; struct mtk_star_priv *priv; + struct phy_device *phydev; struct net_device *ndev; struct device *dev; void __iomem *base; @@ -1649,6 +1650,12 @@ static int mtk_star_probe(struct platform_device *pdev) netif_napi_add(ndev, &priv->rx_napi, mtk_star_rx_poll); netif_napi_add_tx(ndev, &priv->tx_napi, mtk_star_tx_poll); + phydev = of_phy_find_device(priv->phy_node); + if (phydev) { + phydev->mac_managed_pm = true; + put_device(&phydev->mdio.dev); + } + return devm_register_netdev(dev, ndev); } diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 6453c92f0fa7..7fa1820db9cc 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -352,11 +352,11 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) netif_dbg(ks, intr, ks->netdev, "%s: txspace %d\n", __func__, tx_space); - spin_lock(&ks->statelock); + spin_lock_bh(&ks->statelock); ks->tx_space = tx_space; if (netif_queue_stopped(ks->netdev)) netif_wake_queue(ks->netdev); - spin_unlock(&ks->statelock); + spin_unlock_bh(&ks->statelock); } if (status & IRQ_SPIBEI) { @@ -482,6 +482,7 @@ static int ks8851_net_open(struct net_device *dev) ks8851_wrreg16(ks, KS_IER, ks->rc_ier); ks->queued_len = 0; + ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR); netif_start_queue(ks->netdev); netif_dbg(ks, ifup, ks->netdev, "network device up\n"); @@ -635,14 +636,14 @@ static void ks8851_set_rx_mode(struct net_device *dev) /* schedule work to do the actual set of the data if needed */ - spin_lock(&ks->statelock); + spin_lock_bh(&ks->statelock); if (memcmp(&rxctrl, &ks->rxctrl, sizeof(rxctrl)) != 0) { memcpy(&ks->rxctrl, &rxctrl, sizeof(ks->rxctrl)); schedule_work(&ks->rxctrl_work); } - spin_unlock(&ks->statelock); + spin_unlock_bh(&ks->statelock); } static int ks8851_set_mac_address(struct net_device *dev, void *addr) @@ -1101,7 +1102,6 @@ int ks8851_probe_common(struct net_device *netdev, struct device *dev, int ret; ks->netdev = netdev; - ks->tx_space = 6144; ks->gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); ret = PTR_ERR_OR_ZERO(ks->gpio); diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 670c1de966db..3062cc0f9199 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -340,10 +340,10 @@ static void ks8851_tx_work(struct work_struct *work) tx_space = ks8851_rdreg16_spi(ks, KS_TXMIR); - spin_lock(&ks->statelock); + spin_lock_bh(&ks->statelock); ks->queued_len -= dequeued_len; ks->tx_space = tx_space; - spin_unlock(&ks->statelock); + spin_unlock_bh(&ks->statelock); ks8851_unlock_spi(ks, &flags); } diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index a838b61cd844..a35528497a57 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -748,7 +748,7 @@ static int lan87xx_cable_test_report(struct phy_device *phydev) ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A, lan87xx_cable_test_report_trans(detect)); - return 0; + return phy_init_hw(phydev); } static int lan87xx_cable_test_get_status(struct phy_device *phydev, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 0a65b6d690fe..eb9acfcaeb09 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -70,6 +70,7 @@ #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */ #define PPP_PROTO_LEN 2 +#define PPP_LCP_HDRLEN 4 /* * An instance of /dev/ppp can be associated with either a ppp @@ -493,6 +494,15 @@ static ssize_t ppp_read(struct file *file, char __user *buf, return ret; } +static bool ppp_check_packet(struct sk_buff *skb, size_t count) +{ + /* LCP packets must include LCP header which 4 bytes long: + * 1-byte code, 1-byte identifier, and 2-byte length. + */ + return get_unaligned_be16(skb->data) != PPP_LCP || + count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN; +} + static ssize_t ppp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -515,6 +525,11 @@ static ssize_t ppp_write(struct file *file, const char __user *buf, kfree_skb(skb); goto out; } + ret = -EINVAL; + if (unlikely(!ppp_check_packet(skb, count))) { + kfree_skb(skb); + goto out; + } switch (pf->kind) { case INTERFACE: diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 0ba714ca5185..4b8528206cc8 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -15,8 +15,8 @@ static void swap_endian(u8 *dst, const u8 *src, u8 bits) if (bits == 32) { *(u32 *)dst = be32_to_cpu(*(const __be32 *)src); } else if (bits == 128) { - ((u64 *)dst)[0] = be64_to_cpu(((const __be64 *)src)[0]); - ((u64 *)dst)[1] = be64_to_cpu(((const __be64 *)src)[1]); + ((u64 *)dst)[0] = get_unaligned_be64(src); + ((u64 *)dst)[1] = get_unaligned_be64(src + 8); } } diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index 1ea4f874e367..7eb76724b3ed 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -124,10 +124,10 @@ static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) */ static inline int wg_cpumask_next_online(int *last_cpu) { - int cpu = cpumask_next(*last_cpu, cpu_online_mask); + int cpu = cpumask_next(READ_ONCE(*last_cpu), cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(cpu_online_mask); - *last_cpu = cpu; + WRITE_ONCE(*last_cpu, cpu); return cpu; } diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 0d48e0f4a1ba..26e09c30d596 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -222,7 +222,7 @@ void wg_packet_send_keepalive(struct wg_peer *peer) { struct sk_buff *skb; - if (skb_queue_empty(&peer->staged_packet_queue)) { + if (skb_queue_empty_lockless(&peer->staged_packet_queue)) { skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH, GFP_ATOMIC); if (unlikely(!skb)) diff --git a/include/net/tcx.h b/include/net/tcx.h index 72a3e75e539f..5ce0ce9e0c02 100644 --- a/include/net/tcx.h +++ b/include/net/tcx.h @@ -13,7 +13,7 @@ struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; - bool miniq_active; + u32 miniq_active; struct rcu_head rcu; }; @@ -125,11 +125,16 @@ static inline void tcx_skeys_dec(bool ingress) tcx_dec(); } -static inline void tcx_miniq_set_active(struct bpf_mprog_entry *entry, - const bool active) +static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); - tcx_entry(entry)->miniq_active = active; + tcx_entry(entry)->miniq_active++; +} + +static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) +{ + ASSERT_RTNL(); + tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 976cb258a0ed..c938dea5ddbf 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -782,8 +782,8 @@ bpf_local_storage_map_alloc(union bpf_attr *attr, nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); - smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets), - nbuckets, GFP_USER | __GFP_NOWARN); + smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets, + sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN); if (!smap->buckets) { err = -ENOMEM; goto free_smap; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 2a69a9a36c0f..3243c83ef3e3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1084,7 +1084,10 @@ struct bpf_async_cb { struct bpf_prog *prog; void __rcu *callback_fn; void *value; - struct rcu_head rcu; + union { + struct rcu_head rcu; + struct work_struct delete_work; + }; u64 flags; }; @@ -1107,6 +1110,7 @@ struct bpf_async_cb { struct bpf_hrtimer { struct bpf_async_cb cb; struct hrtimer timer; + atomic_t cancelling; }; struct bpf_work { @@ -1219,6 +1223,21 @@ static void bpf_wq_delete_work(struct work_struct *work) kfree_rcu(w, cb.rcu); } +static void bpf_timer_delete_work(struct work_struct *work) +{ + struct bpf_hrtimer *t = container_of(work, struct bpf_hrtimer, cb.delete_work); + + /* Cancel the timer and wait for callback to complete if it was running. + * If hrtimer_cancel() can be safely called it's safe to call + * kfree_rcu(t) right after for both preallocated and non-preallocated + * maps. The async->cb = NULL was already done and no code path can see + * address 't' anymore. Timer if armed for existing bpf_hrtimer before + * bpf_timer_cancel_and_free will have been cancelled. + */ + hrtimer_cancel(&t->timer); + kfree_rcu(t, cb.rcu); +} + static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u64 flags, enum bpf_async_type type) { @@ -1262,6 +1281,8 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u clockid = flags & (MAX_CLOCKS - 1); t = (struct bpf_hrtimer *)cb; + atomic_set(&t->cancelling, 0); + INIT_WORK(&t->cb.delete_work, bpf_timer_delete_work); hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT); t->timer.function = bpf_timer_cb; cb->value = (void *)async - map->record->timer_off; @@ -1440,7 +1461,8 @@ static void drop_prog_refcnt(struct bpf_async_cb *async) BPF_CALL_1(bpf_timer_cancel, struct bpf_async_kern *, timer) { - struct bpf_hrtimer *t; + struct bpf_hrtimer *t, *cur_t; + bool inc = false; int ret = 0; if (in_nmi()) @@ -1452,14 +1474,41 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_async_kern *, timer) ret = -EINVAL; goto out; } - if (this_cpu_read(hrtimer_running) == t) { + + cur_t = this_cpu_read(hrtimer_running); + if (cur_t == t) { /* If bpf callback_fn is trying to bpf_timer_cancel() * its own timer the hrtimer_cancel() will deadlock - * since it waits for callback_fn to finish + * since it waits for callback_fn to finish. */ ret = -EDEADLK; goto out; } + + /* Only account in-flight cancellations when invoked from a timer + * callback, since we want to avoid waiting only if other _callbacks_ + * are waiting on us, to avoid introducing lockups. Non-callback paths + * are ok, since nobody would synchronously wait for their completion. + */ + if (!cur_t) + goto drop; + atomic_inc(&t->cancelling); + /* Need full barrier after relaxed atomic_inc */ + smp_mb__after_atomic(); + inc = true; + if (atomic_read(&cur_t->cancelling)) { + /* We're cancelling timer t, while some other timer callback is + * attempting to cancel us. In such a case, it might be possible + * that timer t belongs to the other callback, or some other + * callback waiting upon it (creating transitive dependencies + * upon us), and we will enter a deadlock if we continue + * cancelling and waiting for it synchronously, since it might + * do the same. Bail! + */ + ret = -EDEADLK; + goto out; + } +drop: drop_prog_refcnt(&t->cb); out: __bpf_spin_unlock_irqrestore(&timer->lock); @@ -1467,6 +1516,8 @@ out: * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); + if (inc) + atomic_dec(&t->cancelling); rcu_read_unlock(); return ret; } @@ -1512,25 +1563,39 @@ void bpf_timer_cancel_and_free(void *val) if (!t) return; - /* Cancel the timer and wait for callback to complete if it was running. - * If hrtimer_cancel() can be safely called it's safe to call kfree(t) - * right after for both preallocated and non-preallocated maps. - * The async->cb = NULL was already done and no code path can - * see address 't' anymore. - * - * Check that bpf_map_delete/update_elem() wasn't called from timer - * callback_fn. In such case don't call hrtimer_cancel() (since it will - * deadlock) and don't call hrtimer_try_to_cancel() (since it will just - * return -1). Though callback_fn is still running on this cpu it's + /* We check that bpf_map_delete/update_elem() was called from timer + * callback_fn. In such case we don't call hrtimer_cancel() (since it + * will deadlock) and don't call hrtimer_try_to_cancel() (since it will + * just return -1). Though callback_fn is still running on this cpu it's * safe to do kfree(t) because bpf_timer_cb() read everything it needed * from 't'. The bpf subprog callback_fn won't be able to access 't', * since async->cb = NULL was already done. The timer will be * effectively cancelled because bpf_timer_cb() will return * HRTIMER_NORESTART. + * + * However, it is possible the timer callback_fn calling us armed the + * timer _before_ calling us, such that failing to cancel it here will + * cause it to possibly use struct hrtimer after freeing bpf_hrtimer. + * Therefore, we _need_ to cancel any outstanding timers before we do + * kfree_rcu, even though no more timers can be armed. + * + * Moreover, we need to schedule work even if timer does not belong to + * the calling callback_fn, as on two different CPUs, we can end up in a + * situation where both sides run in parallel, try to cancel one + * another, and we end up waiting on both sides in hrtimer_cancel + * without making forward progress, since timer1 depends on time2 + * callback to finish, and vice versa. + * + * CPU 1 (timer1_cb) CPU 2 (timer2_cb) + * bpf_timer_cancel_and_free(timer2) bpf_timer_cancel_and_free(timer1) + * + * To avoid these issues, punt to workqueue context when we are in a + * timer callback. */ - if (this_cpu_read(hrtimer_running) != t) - hrtimer_cancel(&t->timer); - kfree_rcu(t, cb.rcu); + if (this_cpu_read(hrtimer_running)) + queue_work(system_unbound_wq, &t->cb.delete_work); + else + bpf_timer_delete_work(&t->cb.delete_work); } /* This function is called by map_delete/update_elem for individual element and diff --git a/net/core/datagram.c b/net/core/datagram.c index e9ba4c7b449d..e72dd78471a6 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -423,11 +423,12 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, if (copy > len) copy = len; + n = 0; skb_frag_foreach_page(frag, skb_frag_off(frag) + offset - start, copy, p, p_off, p_len, copied) { vaddr = kmap_local_page(p); - n = INDIRECT_CALL_1(cb, simple_copy_to_iter, + n += INDIRECT_CALL_1(cb, simple_copy_to_iter, vaddr + p_off, p_len, data, to); kunmap_local(vaddr); } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index fd20aae30be2..bbf40b999713 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -434,7 +434,8 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (copy) + copy = copy_page_to_iter(page, sge->offset, copy, iter); if (!copy) { copied = copied ? copied : -EFAULT; goto out; diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index b2de2108b356..34d76e87847d 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -37,6 +37,8 @@ static int linkstate_get_sqi(struct net_device *dev) mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi) ret = -EOPNOTSUPP; + else if (!phydev->link) + ret = -ENETDOWN; else ret = phydev->drv->get_sqi(phydev); mutex_unlock(&phydev->lock); @@ -55,6 +57,8 @@ static int linkstate_get_sqi_max(struct net_device *dev) mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi_max) ret = -EOPNOTSUPP; + else if (!phydev->link) + ret = -ENETDOWN; else ret = phydev->drv->get_sqi_max(phydev); mutex_unlock(&phydev->lock); @@ -62,6 +66,17 @@ static int linkstate_get_sqi_max(struct net_device *dev) return ret; }; +static bool linkstate_sqi_critical_error(int sqi) +{ + return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN; +} + +static bool linkstate_sqi_valid(struct linkstate_reply_data *data) +{ + return data->sqi >= 0 && data->sqi_max >= 0 && + data->sqi <= data->sqi_max; +} + static int linkstate_get_link_ext_state(struct net_device *dev, struct linkstate_reply_data *data) { @@ -93,12 +108,12 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, data->link = __ethtool_get_link(dev); ret = linkstate_get_sqi(dev); - if (ret < 0 && ret != -EOPNOTSUPP) + if (linkstate_sqi_critical_error(ret)) goto out; data->sqi = ret; ret = linkstate_get_sqi_max(dev); - if (ret < 0 && ret != -EOPNOTSUPP) + if (linkstate_sqi_critical_error(ret)) goto out; data->sqi_max = ret; @@ -136,11 +151,10 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + 0; - if (data->sqi != -EOPNOTSUPP) - len += nla_total_size(sizeof(u32)); - - if (data->sqi_max != -EOPNOTSUPP) - len += nla_total_size(sizeof(u32)); + if (linkstate_sqi_valid(data)) { + len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */ + len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */ + } if (data->link_ext_state_provided) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */ @@ -164,13 +178,14 @@ static int linkstate_fill_reply(struct sk_buff *skb, nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) return -EMSGSIZE; - if (data->sqi != -EOPNOTSUPP && - nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) - return -EMSGSIZE; + if (linkstate_sqi_valid(data)) { + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) + return -EMSGSIZE; - if (data->sqi_max != -EOPNOTSUPP && - nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max)) - return -EMSGSIZE; + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, + data->sqi_max)) + return -EMSGSIZE; + } if (data->link_ext_state_provided) { if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 77294fd5fd3e..38da23f991d6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2129,8 +2129,16 @@ void tcp_clear_retrans(struct tcp_sock *tp) static inline void tcp_init_undo(struct tcp_sock *tp) { tp->undo_marker = tp->snd_una; + /* Retransmission still in flight may cause DSACKs later. */ - tp->undo_retrans = tp->retrans_out ? : -1; + /* First, account for regular retransmits in flight: */ + tp->undo_retrans = tp->retrans_out; + /* Next, account for TLP retransmits in flight: */ + if (tp->tlp_high_seq && tp->tlp_retrans) + tp->undo_retrans++; + /* Finally, avoid 0, because undo_retrans==0 means "can undo now": */ + if (!tp->undo_retrans) + tp->undo_retrans = -1; } static bool tcp_is_rack(const struct sock *sk) @@ -2209,6 +2217,7 @@ void tcp_enter_loss(struct sock *sk) tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; + tp->tlp_high_seq = 0; tcp_ecn_queue_cwr(tp); /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5bfd76a31af6..892c86657fbc 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -483,15 +483,26 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb, u32 rtx_delta) { + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); - const int timeout = TCP_RTO_MAX * 2; + int timeout = TCP_RTO_MAX * 2; s32 rcv_delta; + if (user_timeout) { + /* If user application specified a TCP_USER_TIMEOUT, + * it does not want win 0 packets to 'reset the timer' + * while retransmits are not making progress. + */ + if (rtx_delta > user_timeout) + return true; + timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); + } /* Note: timer interrupt might have been delayed by at least one jiffy, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ - rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; @@ -536,8 +547,6 @@ void tcp_retransmit_timer(struct sock *sk) if (WARN_ON_ONCE(!skb)) return; - tp->tlp_high_seq = 0; - if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { /* Receiver dastardly shrinks window. Our retransmits diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 189c9113fe9a..578668878a85 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -326,6 +326,8 @@ found: goto fail_unlock; } + sock_set_flag(sk, SOCK_RCU_FREE); + sk_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -342,7 +344,7 @@ found: hslot2->count++; spin_unlock(&hslot2->lock); } - sock_set_flag(sk, SOCK_RCU_FREE); + error = 0; fail_unlock: spin_unlock_bh(&hslot->lock); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 081c08536d0f..91cc3a81ba8f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3823,6 +3823,15 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r nf_tables_rule_destroy(ctx, rule); } +/** nft_chain_validate - loop detection and hook validation + * + * @ctx: context containing call depth and base chain + * @chain: chain to validate + * + * Walk through the rules of the given chain and chase all jumps/gotos + * and set lookups until either the jump limit is hit or all reachable + * chains have been validated. + */ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) { struct nft_expr *expr, *last; @@ -3844,6 +3853,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (!expr->ops->validate) continue; + /* This may call nft_chain_validate() recursively, + * callers that do so must increment ctx->level. + */ err = expr->ops->validate(ctx, expr, &data); if (err < 0) return err; @@ -10809,150 +10821,6 @@ int nft_chain_validate_hooks(const struct nft_chain *chain, } EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); -/* - * Loop detection - walk through the ruleset beginning at the destination chain - * of a new jump until either the source chain is reached (loop) or all - * reachable chains have been traversed. - * - * The loop check is performed whenever a new jump verdict is added to an - * expression or verdict map or a verdict map is bound to a new chain. - */ - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain); - -static int nft_check_loops(const struct nft_ctx *ctx, - const struct nft_set_ext *ext) -{ - const struct nft_data *data; - int ret; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - ret = nf_tables_check_loops(ctx, data->verdict.chain); - break; - default: - ret = 0; - break; - } - - return ret; -} - -static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_elem_priv *elem_priv) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); - - if (!nft_set_elem_active(ext, iter->genmask)) - return 0; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - return nft_check_loops(ctx, ext); -} - -static int nft_set_catchall_loops(const struct nft_ctx *ctx, - struct nft_set *set) -{ - u8 genmask = nft_genmask_next(ctx->net); - struct nft_set_elem_catchall *catchall; - struct nft_set_ext *ext; - int ret = 0; - - list_for_each_entry_rcu(catchall, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) - continue; - - ret = nft_check_loops(ctx, ext); - if (ret < 0) - return ret; - } - - return ret; -} - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain) -{ - const struct nft_rule *rule; - const struct nft_expr *expr, *last; - struct nft_set *set; - struct nft_set_binding *binding; - struct nft_set_iter iter; - - if (ctx->chain == chain) - return -ELOOP; - - if (fatal_signal_pending(current)) - return -EINTR; - - list_for_each_entry(rule, &chain->rules, list) { - nft_rule_for_each_expr(expr, last, rule) { - struct nft_immediate_expr *priv; - const struct nft_data *data; - int err; - - if (strcmp(expr->ops->type->name, "immediate")) - continue; - - priv = nft_expr_priv(expr); - if (priv->dreg != NFT_REG_VERDICT) - continue; - - data = &priv->data; - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - err = nf_tables_check_loops(ctx, - data->verdict.chain); - if (err < 0) - return err; - break; - default: - break; - } - } - } - - list_for_each_entry(set, &ctx->table->sets, list) { - if (!nft_is_active_next(ctx->net, set)) - continue; - if (!(set->flags & NFT_SET_MAP) || - set->dtype != NFT_DATA_VERDICT) - continue; - - list_for_each_entry(binding, &set->bindings, list) { - if (!(binding->flags & NFT_SET_MAP) || - binding->chain != chain) - continue; - - iter.genmask = nft_genmask_next(ctx->net); - iter.type = NFT_ITER_UPDATE; - iter.skip = 0; - iter.count = 0; - iter.err = 0; - iter.fn = nf_tables_loop_check_setelem; - - set->ops->walk(ctx, set, &iter); - if (!iter.err) - iter.err = nft_set_catchall_loops(ctx, set); - - if (iter.err < 0) - return iter.err; - } - } - - return 0; -} - /** * nft_parse_u32_check - fetch u32 attribute and check for maximum value * @@ -11065,7 +10933,7 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, if (data != NULL && (data->verdict.code == NFT_GOTO || data->verdict.code == NFT_JUMP)) { - err = nf_tables_check_loops(ctx, data->verdict.chain); + err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f1c31757e496..55e28e1da66e 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -325,7 +325,7 @@ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) hooks = nf_hook_entries_head(net, pf, entry->state.hook); i = entry->hook_index; - if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { + if (!hooks || i >= hooks->num_hook_entries) { kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); nf_queue_entry_free(entry); return; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 2a96d9c1db65..6fa3cca87d34 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1077,6 +1077,14 @@ do_nat: */ if (nf_conntrack_confirm(skb) != NF_ACCEPT) goto drop; + + /* The ct may be dropped if a clash has been resolved, + * so it's necessary to retrieve it from skb again to + * prevent UAF. + */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + skip_add = true; } if (!skip_add) diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index c2ef9dcf91d2..cc6051d4f2ef 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -91,7 +91,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, true, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, true); @@ -121,7 +121,7 @@ static void ingress_destroy(struct Qdisc *sch) tcf_block_put_ext(q->block, sch, &q->block_info); if (entry) { - tcx_miniq_set_active(entry, false); + tcx_miniq_dec(entry); if (!tcx_entry_is_active(entry)) { tcx_entry_update(dev, NULL, true); tcx_entry_free(entry); @@ -257,7 +257,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, true, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, true); @@ -276,7 +276,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, false, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, false); @@ -302,7 +302,7 @@ static void clsact_destroy(struct Qdisc *sch) tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); if (ingress_entry) { - tcx_miniq_set_active(ingress_entry, false); + tcx_miniq_dec(ingress_entry); if (!tcx_entry_is_active(ingress_entry)) { tcx_entry_update(dev, NULL, true); tcx_entry_free(ingress_entry); @@ -310,7 +310,7 @@ static void clsact_destroy(struct Qdisc *sch) } if (egress_entry) { - tcx_miniq_set_active(egress_entry, false); + tcx_miniq_dec(egress_entry); if (!tcx_entry_is_active(egress_entry)) { tcx_entry_update(dev, NULL, false); tcx_entry_free(egress_entry); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index dfc353eea8ed..0e1691316f42 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2441,6 +2441,13 @@ static void xs_tcp_setup_socket(struct work_struct *work) transport->srcport = 0; status = -EAGAIN; break; + case -EPERM: + /* Happens, for instance, if a BPF program is preventing + * the connect. Remap the error so upper layers can better + * deal with it. + */ + status = -ECONNREFUSED; + fallthrough; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index eeabd798bc3a..98b6b6a886ce 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -58,9 +58,12 @@ CONFIG_MPLS=y CONFIG_MPLS_IPTUNNEL=y CONFIG_MPLS_ROUTING=y CONFIG_MPTCP=y +CONFIG_NET_ACT_SKBMOD=y +CONFIG_NET_CLS=y CONFIG_NET_CLS_ACT=y CONFIG_NET_CLS_BPF=y CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_CLS_MATCHALL=y CONFIG_NET_FOU=y CONFIG_NET_FOU_IP_TUNNELS=y CONFIG_NET_IPGRE=y diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c index bc9841144685..1af9ec1149aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_links.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c @@ -9,6 +9,8 @@ #define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null" #include "test_tc_link.skel.h" + +#include "netlink_helpers.h" #include "tc_helpers.h" void serial_test_tc_links_basic(void) @@ -1787,6 +1789,65 @@ void serial_test_tc_links_ingress(void) test_tc_links_ingress(BPF_TCX_INGRESS, false, false); } +struct qdisc_req { + struct nlmsghdr n; + struct tcmsg t; + char buf[1024]; +}; + +static int qdisc_replace(int ifindex, const char *kind, bool block) +{ + struct rtnl_handle rth = { .fd = -1 }; + struct qdisc_req req; + int err; + + err = rtnl_open(&rth, 0); + if (!ASSERT_OK(err, "open_rtnetlink")) + return err; + + memset(&req, 0, sizeof(req)); + req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.n.nlmsg_flags = NLM_F_CREATE | NLM_F_REPLACE | NLM_F_REQUEST; + req.n.nlmsg_type = RTM_NEWQDISC; + req.t.tcm_family = AF_UNSPEC; + req.t.tcm_ifindex = ifindex; + req.t.tcm_parent = 0xfffffff1; + + addattr_l(&req.n, sizeof(req), TCA_KIND, kind, strlen(kind) + 1); + if (block) + addattr32(&req.n, sizeof(req), TCA_INGRESS_BLOCK, 1); + + err = rtnl_talk(&rth, &req.n, NULL); + ASSERT_OK(err, "talk_rtnetlink"); + rtnl_close(&rth); + return err; +} + +void serial_test_tc_links_dev_chain0(void) +{ + int err, ifindex; + + ASSERT_OK(system("ip link add dev foo type veth peer name bar"), "add veth"); + ifindex = if_nametoindex("foo"); + ASSERT_NEQ(ifindex, 0, "non_zero_ifindex"); + err = qdisc_replace(ifindex, "ingress", true); + if (!ASSERT_OK(err, "attaching ingress")) + goto cleanup; + ASSERT_OK(system("tc filter add block 1 matchall action skbmod swap mac"), "add block"); + err = qdisc_replace(ifindex, "clsact", false); + if (!ASSERT_OK(err, "attaching clsact")) + goto cleanup; + /* Heuristic: kern_sync_rcu() alone does not work; a wait-time of ~5s + * triggered the issue without the fix reliably 100% of the time. + */ + sleep(5); + ASSERT_OK(system("tc filter add dev foo ingress matchall action skbmod swap mac"), "add filter"); +cleanup: + ASSERT_OK(system("ip link del dev foo"), "del veth"); + ASSERT_EQ(if_nametoindex("foo"), 0, "foo removed"); + ASSERT_EQ(if_nametoindex("bar"), 0, "bar removed"); +} + static void test_tc_links_dev_mixed(int target) { LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c new file mode 100644 index 000000000000..871d16cb95cf --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <sched.h> +#include <test_progs.h> +#include <pthread.h> +#include <network_helpers.h> + +#include "timer_lockup.skel.h" + +static long cpu; +static int *timer1_err; +static int *timer2_err; +static bool skip; + +volatile int k = 0; + +static void *timer_lockup_thread(void *arg) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1000, + ); + int i, prog_fd = *(int *)arg; + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset); + ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset), + &cpuset), + "cpu affinity"); + + for (i = 0; !READ_ONCE(*timer1_err) && !READ_ONCE(*timer2_err); i++) { + bpf_prog_test_run_opts(prog_fd, &opts); + /* Skip the test if we can't reproduce the race in a reasonable + * amount of time. + */ + if (i > 50) { + WRITE_ONCE(skip, true); + break; + } + } + + return NULL; +} + +void test_timer_lockup(void) +{ + int timer1_prog, timer2_prog; + struct timer_lockup *skel; + pthread_t thrds[2]; + void *ret; + + skel = timer_lockup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load")) + return; + + timer1_prog = bpf_program__fd(skel->progs.timer1_prog); + timer2_prog = bpf_program__fd(skel->progs.timer2_prog); + + timer1_err = &skel->bss->timer1_err; + timer2_err = &skel->bss->timer2_err; + + if (!ASSERT_OK(pthread_create(&thrds[0], NULL, timer_lockup_thread, + &timer1_prog), + "pthread_create thread1")) + goto out; + if (!ASSERT_OK(pthread_create(&thrds[1], NULL, timer_lockup_thread, + &timer2_prog), + "pthread_create thread2")) { + pthread_exit(&thrds[0]); + goto out; + } + + pthread_join(thrds[1], &ret); + pthread_join(thrds[0], &ret); + + if (skip) { + test__skip(); + goto out; + } + + if (*timer1_err != -EDEADLK && *timer1_err != 0) + ASSERT_FAIL("timer1_err bad value"); + if (*timer2_err != -EDEADLK && *timer2_err != 0) + ASSERT_FAIL("timer2_err bad value"); +out: + timer_lockup__destroy(skel); + return; +} diff --git a/tools/testing/selftests/bpf/progs/timer_lockup.c b/tools/testing/selftests/bpf/progs/timer_lockup.c new file mode 100644 index 000000000000..3e520133281e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_lockup.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <time.h> +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct elem { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} timer1_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} timer2_map SEC(".maps"); + +int timer1_err; +int timer2_err; + +static int timer_cb1(void *map, int *k, struct elem *v) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer2_map, &key); + if (timer) + timer2_err = bpf_timer_cancel(timer); + + return 0; +} + +static int timer_cb2(void *map, int *k, struct elem *v) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer1_map, &key); + if (timer) + timer1_err = bpf_timer_cancel(timer); + + return 0; +} + +SEC("tc") +int timer1_prog(void *ctx) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer1_map, &key); + if (timer) { + bpf_timer_init(timer, &timer1_map, CLOCK_BOOTTIME); + bpf_timer_set_callback(timer, timer_cb1); + bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN); + } + + return 0; +} + +SEC("tc") +int timer2_prog(void *ctx) +{ + struct bpf_timer *timer; + int key = 0; + + timer = bpf_map_lookup_elem(&timer2_map, &key); + if (timer) { + bpf_timer_init(timer, &timer2_map, CLOCK_BOOTTIME); + bpf_timer_set_callback(timer, timer_cb2); + bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN); + } + + return 0; +} diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index e95bd56b332f..35856b11c143 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -109,9 +109,9 @@ KERNEL_ARCH := x86_64 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(HOST_ARCH),$(ARCH)) -QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off -no-acpi +QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off,acpi=off else -QEMU_MACHINE := -cpu max -machine microvm -no-acpi +QEMU_MACHINE := -cpu max -machine microvm,acpi=off endif else ifeq ($(ARCH),i686) CHOST := i686-linux-musl @@ -120,9 +120,9 @@ KERNEL_ARCH := x86 KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage QEMU_VPORT_RESULT := virtio-serial-device ifeq ($(subst x86_64,i686,$(HOST_ARCH)),$(ARCH)) -QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off -no-acpi +QEMU_MACHINE := -cpu host -machine microvm,accel=kvm,pit=off,pic=off,rtc=off,acpi=off else -QEMU_MACHINE := -cpu coreduo -machine microvm -no-acpi +QEMU_MACHINE := -cpu coreduo -machine microvm,acpi=off endif else ifeq ($(ARCH),mips64) CHOST := mips64-linux-musl |