diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-02-22 09:57:58 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-02-22 09:57:58 -0800 |
| commit | 6714ebb922ab15a209dfc3c1ed29d4bb0abc9f02 (patch) | |
| tree | 4c8c92b7a4ded99e9ad8f66c2d369032825d81ee | |
| parent | efa80dcbb7a3ecc4a1b2f54624c49b5a612f92b3 (diff) | |
| parent | 359e54a93ab43d32ee1bff3c2f9f10cb9f6b6e79 (diff) | |
Merge tag 'net-6.8.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from bpf and netfilter.
Current release - regressions:
- af_unix: fix another unix GC hangup
Previous releases - regressions:
- core: fix a possible AF_UNIX deadlock
- bpf: fix NULL pointer dereference in sk_psock_verdict_data_ready()
- netfilter: nft_flow_offload: release dst in case direct xmit path
is used
- bridge: switchdev: ensure MDB events are delivered exactly once
- l2tp: pass correct message length to ip6_append_data
- dccp/tcp: unhash sk from ehash for tb2 alloc failure after
check_estalblished()
- tls: fixes for record type handling with PEEK
- devlink: fix possible use-after-free and memory leaks in
devlink_init()
Previous releases - always broken:
- bpf: fix an oops when attempting to read the vsyscall page through
bpf_probe_read_kernel
- sched: act_mirred: use the backlog for mirred ingress
- netfilter: nft_flow_offload: fix dst refcount underflow
- ipv6: sr: fix possible use-after-free and null-ptr-deref
- mptcp: fix several data races
- phonet: take correct lock to peek at the RX queue
Misc:
- handful of fixes and reliability improvements for selftests"
* tag 'net-6.8.0-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (72 commits)
l2tp: pass correct message length to ip6_append_data
net: phy: realtek: Fix rtl8211f_config_init() for RTL8211F(D)(I)-VD-CG PHY
selftests: ioam: refactoring to align with the fix
Fix write to cloned skb in ipv6_hop_ioam()
phonet/pep: fix racy skb_queue_empty() use
phonet: take correct lock to peek at the RX queue
net: sparx5: Add spinlock for frame transmission from CPU
net/sched: flower: Add lock protection when remove filter handle
devlink: fix port dump cmd type
net: stmmac: Fix EST offset for dwmac 5.10
tools: ynl: don't leak mcast_groups on init error
tools: ynl: make sure we always pass yarg to mnl_cb_run
net: mctp: put sock on tag allocation failure
netfilter: nf_tables: use kzalloc for hook allocation
netfilter: nf_tables: register hooks last when adding new chain/flowtable
netfilter: nft_flow_offload: release dst in case direct xmit path is used
netfilter: nft_flow_offload: reset dst in route object after setting up flow
netfilter: nf_tables: set dormant flag on hook register failure
selftests: tls: add test for peeking past a record of a different type
selftests: tls: add test for merging of same-type control messages
...
75 files changed, 870 insertions, 378 deletions
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 84ee60fceef2..fd96e4a3cef9 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -431,7 +431,7 @@ patchwork checks Checks in patchwork are mostly simple wrappers around existing kernel scripts, the sources are available at: -https://github.com/kuba-moo/nipa/tree/master/tests +https://github.com/linux-netdev/nipa/tree/master/tests **Do not** post your patches just to run them through the checks. You must ensure that your patches are ready by testing them locally diff --git a/MAINTAINERS b/MAINTAINERS index 9ed4d3868539..bf77be03fb2b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15242,6 +15242,8 @@ F: Documentation/networking/ F: Documentation/networking/net_cachelines/ F: Documentation/process/maintainer-netdev.rst F: Documentation/userspace-api/netlink/ +F: include/linux/framer/framer-provider.h +F: include/linux/framer/framer.h F: include/linux/in.h F: include/linux/indirect_call_wrapper.h F: include/linux/net.h diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8dcb..472f0263dbc6 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> +#include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 679b09cfe241..d6375b3c633b 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -798,15 +798,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 6993f026adec..42115ac079cf 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,6 +3,8 @@ #include <linux/uaccess.h> #include <linux/kernel.h> +#include <asm/vsyscall.h> + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { @@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) return false; /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. + */ + if (is_vsyscall_vaddr(vaddr)) + return false; + + /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. diff --git a/drivers/net/ethernet/adi/Kconfig b/drivers/net/ethernet/adi/Kconfig index da3bdd302502..c91b4dcef4ec 100644 --- a/drivers/net/ethernet/adi/Kconfig +++ b/drivers/net/ethernet/adi/Kconfig @@ -7,6 +7,7 @@ config NET_VENDOR_ADI bool "Analog Devices devices" default y depends on SPI + select PHYLIB help If you have a network (Ethernet) card belonging to this class, say Y. diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index 29b04a274d07..80245c65cc90 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -535,9 +535,6 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs, int j = 0, i; for (i = 0; i < NUM_NET_FILTERS; i++) { - if (j == *rule_cnt) - return -EMSGSIZE; - if (!priv->net_filters[i].claimed || priv->net_filters[i].port != intf->port) continue; @@ -547,6 +544,9 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs, priv->net_filters[i - 1].wake_filter) continue; + if (j == *rule_cnt) + return -EMSGSIZE; + rule_locs[j++] = priv->net_filters[i].fs.location; } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index f59557b0cd51..6ad1366270f7 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -1050,6 +1050,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect) netdev_err(dev, "could not attach to PHY\n"); goto err_phy_disable; } + + /* Indicate that the MAC is responsible for PHY PM */ + phydev->mac_managed_pm = true; } else if (!intf->wolopts) { ret = phy_resume(dev->phydev); if (ret) diff --git a/drivers/net/ethernet/cisco/enic/vnic_vic.c b/drivers/net/ethernet/cisco/enic/vnic_vic.c index 20fcb20b42ed..66b577835338 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_vic.c +++ b/drivers/net/ethernet/cisco/enic/vnic_vic.c @@ -49,7 +49,8 @@ int vic_provinfo_add_tlv(struct vic_provinfo *vp, u16 type, u16 length, tlv->type = htons(type); tlv->length = htons(length); - memcpy(tlv->value, value, length); + unsafe_memcpy(tlv->value, value, length, + /* Flexible array of flexible arrays */); vp->num_tlvs = htonl(ntohl(vp->num_tlvs) + 1); vp->length = htonl(ntohl(vp->length) + diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index e5d6156655ba..516adb50f9f6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -415,6 +415,10 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, return; } + /* AF modifies given action iff PF/VF has requested for it */ + if ((entry->action & 0xFULL) != NIX_RX_ACTION_DEFAULT) + return; + /* copy VF default entry action to the VF mcam entry */ rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr, target_func); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index d1f7fc8b1b71..3c066b62e689 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -757,6 +757,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) platform_set_drvdata(pdev, sparx5); sparx5->pdev = pdev; sparx5->dev = &pdev->dev; + spin_lock_init(&sparx5->tx_lock); /* Do switch core reset if available */ reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch"); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 6f565c0c0c3d..316fed5f2735 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -280,6 +280,7 @@ struct sparx5 { int xtr_irq; /* Frame DMA */ int fdma_irq; + spinlock_t tx_lock; /* lock for frame transmission */ struct sparx5_rx rx; struct sparx5_tx tx; /* PTP */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index 6db6ac6a3bbc..ac7e1cffbcec 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -244,10 +244,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) } skb_tx_timestamp(skb); + spin_lock(&sparx5->tx_lock); if (sparx5->fdma_irq > 0) ret = sparx5_fdma_xmit(sparx5, ifh, skb); else ret = sparx5_inject(sparx5, ifh, skb, dev); + spin_unlock(&sparx5->tx_lock); if (ret == -EBUSY) goto busy; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index c49aa358e424..10a9d80db32c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -223,7 +223,7 @@ static void ionic_clear_pci(struct ionic *ionic) ionic_unmap_bars(ionic); pci_release_regions(ionic->pdev); - if (atomic_read(&ionic->pdev->enable_cnt) > 0) + if (pci_is_enabled(ionic->pdev)) pci_disable_device(ionic->pdev); } diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 1bd34b2a47e8..29367105df54 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -224,7 +224,7 @@ static const struct stmmac_hwif_entry { .regs = { .ptp_off = PTP_GMAC4_OFFSET, .mmc_off = MMC_GMAC4_OFFSET, - .est_off = EST_XGMAC_OFFSET, + .est_off = EST_GMAC4_OFFSET, }, .desc = &dwmac4_desc_ops, .dma = &dwmac410_dma_ops, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 75d029704503..e80d77bd9f1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6059,11 +6059,6 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -6079,11 +6074,6 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -6105,11 +6095,6 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data) dma_conf = container_of(tx_q, struct stmmac_dma_conf, tx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -6136,11 +6121,6 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data) dma_conf = container_of(rx_q, struct stmmac_dma_conf, rx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index b1919278e931..2129ae42c703 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1907,20 +1907,20 @@ static int __init gtp_init(void) if (err < 0) goto error_out; - err = genl_register_family(>p_genl_family); + err = register_pernet_subsys(>p_net_ops); if (err < 0) goto unreg_rtnl_link; - err = register_pernet_subsys(>p_net_ops); + err = genl_register_family(>p_genl_family); if (err < 0) - goto unreg_genl_family; + goto unreg_pernet_subsys; pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0; -unreg_genl_family: - genl_unregister_family(>p_genl_family); +unreg_pernet_subsys: + unregister_pernet_subsys(>p_net_ops); unreg_rtnl_link: rtnl_link_unregister(>p_link_ops); error_out: diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index 4bc05948f772..a78c692f2d3c 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -212,7 +212,7 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt) u32 unit_count; u32 unit; - unit_count = roundup(ipa->endpoint_count, 32); + unit_count = DIV_ROUND_UP(ipa->endpoint_count, 32); for (unit = 0; unit < unit_count; unit++) { const struct reg *reg; u32 val; diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 894172a3e15f..337899c69738 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -421,9 +421,11 @@ static int rtl8211f_config_init(struct phy_device *phydev) ERR_PTR(ret)); return ret; } + + return genphy_soft_reset(phydev); } - return genphy_soft_reset(phydev); + return 0; } static int rtl821x_suspend(struct phy_device *phydev) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 956c752ceb31..a763dd327c6e 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -276,7 +276,7 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, } void flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route); + struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index a43062d4c734..8346b0d29542 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -308,6 +308,9 @@ void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack); +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack); diff --git a/include/net/tcp.h b/include/net/tcp.h index dd78a1181031..f6eba9652d01 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2506,7 +2506,7 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(const struct sock *sk, struct sk_buff *skb); + int (*get_info)(struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index be72824f32b2..d19cd863d294 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1101,6 +1101,7 @@ struct bpf_hrtimer { struct bpf_prog *prog; void __rcu *callback_fn; void *value; + struct rcu_head rcu; }; /* the actual struct hidden inside uapi struct bpf_timer */ @@ -1332,6 +1333,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) if (in_nmi()) return -EOPNOTSUPP; + rcu_read_lock(); __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { @@ -1353,6 +1355,7 @@ out: * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); + rcu_read_unlock(); return ret; } @@ -1407,7 +1410,7 @@ out: */ if (this_cpu_read(hrtimer_running) != t) hrtimer_cancel(&t->timer); - kfree(t); + kfree_rcu(t, rcu); } BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index e5c3500443c6..ec4e97c61eef 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -978,6 +978,8 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != __alignof__(struct bpf_iter_task)); + kit->pos = NULL; + switch (flags) { case BPF_TASK_ITER_ALL_THREADS: case BPF_TASK_ITER_ALL_PROCS: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 65f598694d55..b263f093ee76 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5227,7 +5227,9 @@ BTF_ID(struct, prog_test_ref_kfunc) #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) #endif +#ifdef CONFIG_BPF_JIT BTF_ID(struct, bpf_cpumask) +#endif BTF_ID(struct, task_struct) BTF_SET_END(rcu_protected_types) diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index ee84e783e1df..7b41ee8740cb 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -595,21 +595,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, } static int br_switchdev_mdb_queue_one(struct list_head *mdb_list, + struct net_device *dev, + unsigned long action, enum switchdev_obj_id id, const struct net_bridge_mdb_entry *mp, struct net_device *orig_dev) { - struct switchdev_obj_port_mdb *mdb; + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = id, + .orig_dev = orig_dev, + }, + }; + struct switchdev_obj_port_mdb *pmdb; - mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); - if (!mdb) - return -ENOMEM; + br_switchdev_mdb_populate(&mdb, mp); + + if (action == SWITCHDEV_PORT_OBJ_ADD && + switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) { + /* This event is already in the deferred queue of + * events, so this replay must be elided, lest the + * driver receives duplicate events for it. This can + * only happen when replaying additions, since + * modifications are always immediately visible in + * br->mdb_list, whereas actual event delivery may be + * delayed. + */ + return 0; + } - mdb->obj.id = id; - mdb->obj.orig_dev = orig_dev; - br_switchdev_mdb_populate(mdb, mp); - list_add_tail(&mdb->obj.list, mdb_list); + pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC); + if (!pmdb) + return -ENOMEM; + list_add_tail(&pmdb->obj.list, mdb_list); return 0; } @@ -677,51 +696,50 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev, if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return 0; - /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, - * because the write-side protection is br->multicast_lock. But we - * need to emulate the [ blocking ] calling context of a regular - * switchdev event, so since both br->multicast_lock and RCU read side - * critical sections are atomic, we have no choice but to pick the RCU - * read side lock, queue up all our events, leave the critical section - * and notify switchdev from blocking context. + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + /* br_switchdev_mdb_queue_one() will take care to not queue a + * replay of an event that is already pending in the switchdev + * deferred queue. In order to safely determine that, there + * must be no new deferred MDB notifications enqueued for the + * duration of the MDB scan. Therefore, grab the write-side + * lock to avoid racing with any concurrent IGMP/MLD snooping. */ - rcu_read_lock(); + spin_lock_bh(&br->multicast_lock); - hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { + hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group __rcu * const *pp; const struct net_bridge_port_group *p; if (mp->host_joined) { - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_HOST_MDB, mp, br_dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } - for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->key.port->dev != dev) continue; - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_PORT_MDB, mp, dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } } - rcu_read_unlock(); - - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; + spin_unlock_bh(&br->multicast_lock); list_for_each_entry(obj, &mdb_list, list) { err = br_switchdev_mdb_replay_one(nb, dev, @@ -786,6 +804,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL); + + /* Make sure that the device leaving this bridge has seen all + * relevant events before it is disassociated. In the normal + * case, when the device is directly attached to the bridge, + * this is covered by del_nbp(). If the association was indirect + * however, e.g. via a team or bond, and the device is leaving + * that intermediate device, then the bridge port remains in + * place. + */ + switchdev_deferred_process(); } /* Let the bridge know that this port is offloaded, so that it can assign a diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93ecfceac1bc..4d75ef9d24bf 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,8 +1226,11 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) - psock->saved_data_ready(sk); + if (psock) { + read_lock_bh(&sk->sk_callback_lock); + sk_psock_data_ready(sk, psock); + read_unlock_bh(&sk->sk_callback_lock); + } rcu_read_unlock(); } } diff --git a/net/core/sock.c b/net/core/sock.c index 0a7f46c37f0c..5e78798456fd 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1188,6 +1188,17 @@ int sk_setsockopt(struct sock *sk, int level, int optname, */ WRITE_ONCE(sk->sk_txrehash, (u8)val); return 0; + case SO_PEEK_OFF: + { + int (*set_peek_off)(struct sock *sk, int val); + + set_peek_off = READ_ONCE(sock->ops)->set_peek_off; + if (set_peek_off) + ret = set_peek_off(sk, val); + else + ret = -EOPNOTSUPP; + return ret; + } } sockopt_lock_sock(sk); @@ -1430,18 +1441,6 @@ set_sndbuf: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; - case SO_PEEK_OFF: - { - int (*set_peek_off)(struct sock *sk, int val); - - set_peek_off = READ_ONCE(sock->ops)->set_peek_off; - if (set_peek_off) - ret = set_peek_off(sk, val); - else - ret = -EOPNOTSUPP; - break; - } - case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; diff --git a/net/devlink/core.c b/net/devlink/core.c index 6a58342752b4..7f0b093208d7 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -529,14 +529,20 @@ static int __init devlink_init(void) { int err; - err = genl_register_family(&devlink_nl_family); - if (err) - goto out; err = register_pernet_subsys(&devlink_pernet_ops); if (err) goto out; + err = genl_register_family(&devlink_nl_family); + if (err) + goto out_unreg_pernet_subsys; err = register_netdevice_notifier(&devlink_port_netdevice_nb); + if (!err) + return 0; + + genl_unregister_family(&devlink_nl_family); +out_unreg_pernet_subsys: + unregister_pernet_subsys(&devlink_pernet_ops); out: WARN_ON(err); return err; diff --git a/net/devlink/port.c b/net/devlink/port.c index 78592912f657..4b2d46ccfe48 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -583,7 +583,7 @@ devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) { err = devlink_nl_port_fill(msg, devlink_port, - DEVLINK_CMD_NEW, + DEVLINK_CMD_PORT_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9456f5bb35e5..0d0d725b46ad 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) if (neigh) { if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); r->arp_ha.sa_family = dev->type; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ca0ff15dc8fa..bc74f131fe4d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1825,6 +1825,21 @@ done: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; @@ -1876,8 +1891,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ - tgt_net->dev_base_seq; + cb->seq = inet_base_seq(tgt_net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2278,8 +2292,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 93e9193df544..308ff34002ea 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1130,10 +1130,33 @@ ok: return 0; error: + if (sk_hashed(sk)) { + spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash); + + sock_prot_inuse_add(net, sk->sk_prot, -1); + + spin_lock(lock); + sk_nulls_del_node_init_rcu(sk); + spin_unlock(lock); + + sk->sk_hash = 0; + inet_sk(sk)->inet_sport = 0; + inet_sk(sk)->inet_num = 0; + + if (tw) + inet_twsk_bind_unhash(tw, hinfo); + } + spin_unlock(&head2->lock); if (tb_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - spin_unlock_bh(&head->lock); + spin_unlock(&head->lock); + + if (tw) + inet_twsk_deschedule_put(tw); + + local_bh_enable(); + return -ENOMEM; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f631b0a21af4..e474b201900f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1589,12 +1589,7 @@ int udp_init_sock(struct sock *sk) void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { - if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) { - bool slow = lock_sock_fast(sk); - - sk_peek_offset_bwd(sk, len); - unlock_sock_fast(sk, slow); - } + sk_peek_offset_bwd(sk, len); if (!skb_unref(skb)) return; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 733ace18806c..5a839c5fb1a5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -708,6 +708,22 @@ errout: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet6_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv6.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + + static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { @@ -741,8 +757,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -5362,7 +5377,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; + cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 4952ae792450..02e9ffb63af1 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -177,6 +177,8 @@ static bool ip6_parse_tlv(bool hopbyhop, case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; + + nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) @@ -943,6 +945,14 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) if (!skb_valid_dst(skb)) ip6_route_input(skb); + /* About to mangle packet header */ + if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) + goto drop; + + /* Trace pointer may have changed */ + trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + + optoff + sizeof(*hdr)); + ioam6_fill_trace_data(skb, ns, trace, true); break; default: diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 29346a6eec9f..35508abd76f4 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -512,22 +512,24 @@ int __init seg6_init(void) { int err; - err = genl_register_family(&seg6_genl_family); + err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; - err = register_pernet_subsys(&ip6_segments_ops); + err = genl_register_family(&seg6_genl_family); if (err) - goto out_unregister_genl; + goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) - goto out_unregister_pernet; + goto out_unregister_genl; err = seg6_local_init(); - if (err) - goto out_unregister_pernet; + if (err) { + seg6_iptunnel_exit(); + goto out_unregister_genl; + } #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -548,11 +550,11 @@ out_unregister_iptun: #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL -out_unregister_pernet: - unregister_pernet_subsys(&ip6_segments_ops); -#endif out_unregister_genl: genl_unregister_family(&seg6_genl_family); +#endif +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); goto out; } diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 6334f64f04d5..b0b3e9c5af44 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID"; static LIST_HEAD(iucv_handler_list); /* - * iucv_path_table: an array of iucv_path structures. + * iucv_path_table: array of pointers to iucv_path structures. */ static struct iucv_path **iucv_path_table; static unsigned long iucv_max_pathid; @@ -544,7 +544,7 @@ static int iucv_enable(void) cpus_read_lock(); rc = -ENOMEM; - alloc_size = iucv_max_pathid * sizeof(struct iucv_path); + alloc_size = iucv_max_pathid * sizeof(*iucv_path_table); iucv_path_table = kzalloc(alloc_size, GFP_KERNEL); if (!iucv_path_table) goto out; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index dd3153966173..7bf14cf9ffaa 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -627,7 +627,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); - ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; + ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/mctp/route.c b/net/mctp/route.c index 7a47a58aa54b..6218dcd07e18 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -663,7 +663,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, spin_unlock_irqrestore(&mns->keys_lock, flags); if (!tagbits) { - kfree(key); + mctp_key_unref(key); return ERR_PTR(-EBUSY); } diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a536586742f2..6ff6f14674aa 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,19 @@ #include <uapi/linux/mptcp.h> #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -63,17 +65,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) sf->map_data_len) || nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) || nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) || - nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) { + nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) { err = -EMSGSIZE; goto nla_failure; } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 287a60381eae..58d17d9604e7 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -396,19 +396,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } -static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, - const struct mptcp_addr_info *addr) -{ - int i; - - for (i = 0; i < nr; i++) { - if (addrs[i].id == addr->id) - return true; - } - - return false; -} - /* Fill all the remote addresses into the array addrs[], * and return the array size. */ @@ -440,18 +427,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, msk->pm.subflows++; addrs[i++] = remote; } else { + DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + + /* Forbid creation of new subflows matching existing + * ones, possibly already created by incoming ADD_ADDR + */ + bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + mptcp_for_each_subflow(msk, subflow) + if (READ_ONCE(subflow->local_id) == local->id) + __set_bit(subflow->remote_id, unavail_id); + mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); remote_address((struct sock_common *)ssk, &addrs[i]); - addrs[i].id = subflow->remote_id; + addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue; + if (test_bit(addrs[i].id, unavail_id)) + continue; + if (!mptcp_pm_addr_families_match(sk, local, &addrs[i])) continue; - if (!lookup_address_in_vec(addrs, i, &addrs[i]) && - msk->pm.subflows < subflows_max) { + if (msk->pm.subflows < subflows_max) { + /* forbid creating multiple address towards + * this id + */ + __set_bit(addrs[i].id, unavail_id); msk->pm.subflows++; i++; } @@ -799,18 +802,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + u8 remote_id = READ_ONCE(subflow->remote_id); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - u8 id = subflow->local_id; + u8 id = subflow_get_local_id(subflow); - if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id) + if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) continue; pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", - i, rm_id, subflow->local_id, subflow->remote_id, - msk->mpc_endpoint_id); + i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); @@ -901,7 +904,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -949,7 +953,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -960,7 +964,7 @@ find_next: } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1092,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1285,6 +1289,18 @@ next: return 0; } +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) +{ + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_address_nl_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; @@ -1326,7 +1342,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; @@ -1980,7 +1997,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) if (WARN_ON_ONCE(!sf)) return -EINVAL; - if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 4f3901d5b8ef..d396a5973429 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -26,7 +26,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); struct mptcp_pm_addr_entry *match = NULL; @@ -41,7 +42,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); - if (addr_match && entry->addr.id == 0) + if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; id_match = (e->addr.id == entry->addr.id); if (addr_match && id_match) { @@ -64,7 +65,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } *e = *entry; - if (!e->addr.id) + if (!e->addr.id && needs_id) e->addr.id = find_next_zero_bit(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 1); @@ -153,7 +154,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, if (new_entry.addr.port == msk_sport) new_entry.addr.port = 0; - return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); + return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) @@ -198,7 +199,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val); + err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto announce_err; @@ -233,7 +234,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->local_id == 0) { + if (READ_ONCE(subflow->local_id) == 0) { has_id_0 = true; break; } @@ -378,7 +379,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) } local.addr = addr_l; - err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto create_err; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8ef2927ebca2..948606a537da 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -85,7 +85,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ - subflow->local_id_valid = 1; + WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ed50f2015dc3..631a7f445f34 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -491,10 +491,9 @@ struct mptcp_subflow_context { remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 9; + __unused : 10; bool data_avail; bool scheduled; u32 remote_nonce; @@ -505,7 +504,7 @@ struct mptcp_subflow_context { u8 hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */ u64 iasn; /* initial ack sequence number, MPC subflows only */ }; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -556,6 +555,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; + WRITE_ONCE(subflow->local_id, -1); } static inline u64 @@ -1022,6 +1022,15 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) +{ + int local_id = READ_ONCE(subflow->local_id); + + if (local_id < 0) + return 0; + return local_id; +} + void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c34ecadee120..71ba86246ff8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -535,7 +535,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; - subflow->remote_id = mp_opt.join_id; + WRITE_ONCE(subflow->remote_id, mp_opt.join_id); pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -577,8 +577,8 @@ do_reset: static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { - subflow->local_id = local_id; - subflow->local_id_valid = 1; + WARN_ON_ONCE(local_id < 0 || local_id > 255); + WRITE_ONCE(subflow->local_id, local_id); } static int subflow_chk_local_id(struct sock *sk) @@ -587,7 +587,7 @@ static int subflow_chk_local_id(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err; - if (likely(subflow->local_id_valid)) + if (likely(subflow->local_id >= 0)) return 0; err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); @@ -1567,7 +1567,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; - subflow->remote_id = remote_id; + WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); subflow->subflow_id = msk->subflow_id++; @@ -1731,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, pr_debug("subflow=%p", ctx); ctx->tcp_sock = sk; + WRITE_ONCE(ctx->local_id, -1); return ctx; } @@ -1966,14 +1967,14 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->idsn = subflow_req->idsn; /* this is the first subflow, id is always 0 */ - new_ctx->local_id_valid = 1; + subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; - new_ctx->remote_id = subflow_req->remote_id; + WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 920a5a29ae1d..a0571339239c 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) return 0; } +static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct dst_entry *dst = route->tuple[dir].dst; + + route->tuple[dir].dst = NULL; + + return dst; +} + static int flow_offload_fill_route(struct flow_offload *flow, - const struct nf_flow_route *route, + struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *dst = route->tuple[dir].dst; + struct dst_entry *dst = nft_route_dst_fetch(route, dir); int i, j = 0; switch (flow_tuple->l3proto) { @@ -122,6 +132,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; + dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: @@ -146,7 +157,7 @@ static void nft_flow_dst_release(struct flow_offload *flow, } void flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) + struct nf_flow_route *route) { flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f8e3f70c35bd..7e938c7397dd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -684,15 +684,16 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; } -static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, - struct nft_flowtable *flowtable) +static struct nft_trans * +nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, + struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_flowtable)); if (trans == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); @@ -701,22 +702,22 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); - return 0; + return trans; } static int nft_delflowtable(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { - int err; + struct nft_trans *trans; - err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); - if (err < 0) - return err; + trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); + if (IS_ERR(trans)) + return PTR_ERR(trans); nft_deactivate_next(ctx->net, flowtable); nft_use_dec(&ctx->table->use); - return err; + return 0; } static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) @@ -1251,6 +1252,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; err_register_hooks: + ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } @@ -2080,7 +2082,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, struct nft_hook *hook; int err; - hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); + hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) { err = -ENOMEM; goto err_hook_alloc; @@ -2503,19 +2505,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, RCU_INIT_POINTER(chain->blob_gen_0, blob); RCU_INIT_POINTER(chain->blob_gen_1, blob); - err = nf_tables_register_hook(net, table, chain); - if (err < 0) - goto err_destroy_chain; - if (!nft_use_inc(&table->use)) { err = -EMFILE; - goto err_use; + goto err_destroy_chain; } trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - goto err_unregister_hook; + goto err_trans; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; @@ -2523,17 +2521,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, nft_trans_chain_policy(trans) = policy; err = nft_chain_add(table, chain); - if (err < 0) { - nft_trans_destroy(trans); - goto err_unregister_hook; - } + if (err < 0) + goto err_chain_add; + + /* This must be LAST to ensure no packets are walking over this chain. */ + err = nf_tables_register_hook(net, table, chain); + if (err < 0) + goto err_register_hook; return 0; -err_unregister_hook: +err_register_hook: + nft_chain_del(chain); +err_chain_add: + nft_trans_destroy(trans); +err_trans: nft_use_dec_restore(&table->use); -err_use: - nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -8455,9 +8458,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb, u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; struct nft_flowtable *flowtable; - struct nft_hook *hook, *next; struct net *net = info->net; struct nft_table *table; + struct nft_trans *trans; struct nft_ctx ctx; int err; @@ -8537,34 +8540,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb, err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable, extack, true); if (err < 0) - goto err4; + goto err_flowtable_parse_hooks; list_splice(&flowtable_hook.list, &flowtable->hook_list); flowtable->data.priority = flowtable_hook.priority; flowtable->hooknum = flowtable_hook.num; + trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto err_flowtable_trans; + } + + /* This must be LAST to ensure no packets are walking over this flowtable. */ err = nft_register_flowtable_net_hooks(ctx.net, table, &flowtable->hook_list, flowtable); - if (err < 0) { - nft_hooks_destroy(&flowtable->hook_list); - goto err4; - } - - err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err5; + goto err_flowtable_hooks; list_add_tail_rcu(&flowtable->list, &table->flowtables); return 0; -err5: - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } -err4: + +err_flowtable_hooks: + nft_trans_destroy(trans); +err_flowtable_trans: + nft_hooks_destroy(&flowtable->hook_list); +err_flowtable_parse_hooks: flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 3aa50dc7535b..976fe250b509 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -34,10 +34,10 @@ static int pn_ioctl(struct sock *sk, int cmd, int *karg) switch (cmd) { case SIOCINQ: - lock_sock(sk); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); *karg = skb ? skb->len : 0; - release_sock(sk); + spin_unlock_bh(&sk->sk_receive_queue.lock); return 0; case SIOCPNADDRESOURCE: diff --git a/net/phonet/pep.c b/net/phonet/pep.c index faba31f2eff2..3dd5f52bc1b5 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -917,6 +917,37 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) return 0; } +static unsigned int pep_first_packet_length(struct sock *sk) +{ + struct pep_sock *pn = pep_sk(sk); + struct sk_buff_head *q; + struct sk_buff *skb; + unsigned int len = 0; + bool found = false; + + if (sock_flag(sk, SOCK_URGINLINE)) { + q = &pn->ctrlreq_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) { + len = skb->len; + found = true; + } + spin_unlock_bh(&q->lock); + } + + if (likely(!found)) { + q = &sk->sk_receive_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) + len = skb->len; + spin_unlock_bh(&q->lock); + } + + return len; +} + static int pep_ioctl(struct sock *sk, int cmd, int *karg) { struct pep_sock *pn = pep_sk(sk); @@ -929,15 +960,7 @@ static int pep_ioctl(struct sock *sk, int cmd, int *karg) break; } - lock_sock(sk); - if (sock_flag(sk, SOCK_URGINLINE) && - !skb_queue_empty(&pn->ctrlreq_queue)) - *karg = skb_peek(&pn->ctrlreq_queue)->len; - else if (!skb_queue_empty(&sk->sk_receive_queue)) - *karg = skb_peek(&sk->sk_receive_queue)->len; - else - *karg = 0; - release_sock(sk); + *karg = pep_first_packet_length(sk); ret = 0; break; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 0a1a9e40f237..6faa7d00da09 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -232,18 +232,14 @@ release_idr: return err; } -static bool is_mirred_nested(void) -{ - return unlikely(__this_cpu_read(mirred_nest_level) > 1); -} - -static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) +static int +tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = tcf_dev_queue_xmit(skb, dev_queue_xmit); - else if (is_mirred_nested()) + else if (!at_ingress) err = netif_rx(skb); else err = netif_receive_skb(skb); @@ -270,8 +266,7 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); - err = -ENODEV; - goto out; + goto err_cant_do; } /* we could easily avoid the clone only if called by ingress and clsact; @@ -283,10 +278,8 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, tcf_mirred_can_reinsert(retval); if (!dont_clone) { skb_to_send = skb_clone(skb, GFP_ATOMIC); - if (!skb_to_send) { - err = -ENOMEM; - goto out; - } + if (!skb_to_send) + goto err_cant_do; } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); @@ -319,19 +312,20 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress); - err = tcf_mirred_forward(want_ingress, skb_to_send); + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } else { - err = tcf_mirred_forward(want_ingress, skb_to_send); + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } - - if (err) { -out: + if (err) tcf_action_inc_overlimit_qstats(&m->common); - if (is_redirect) - retval = TC_ACT_SHOT; - } return retval; + +err_cant_do: + if (is_redirect) + retval = TC_ACT_SHOT; + tcf_action_inc_overlimit_qstats(&m->common); + return retval; } static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index efb9d2811b73..6ee7064c82fc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2460,8 +2460,11 @@ unbind_filter: } errout_idr: - if (!fold) + if (!fold) { + spin_lock(&tp->lock); idr_remove(&head->handle_idr, fnew->handle); + spin_unlock(&tp->lock); + } __fl_put(fnew); errout_tb: kfree(tb); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5b045284849e..c9189a970eec 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,6 +19,35 @@ #include <linux/rtnetlink.h> #include <net/switchdev.h> +static bool switchdev_obj_eq(const struct switchdev_obj *a, + const struct switchdev_obj *b) +{ + const struct switchdev_obj_port_vlan *va, *vb; + const struct switchdev_obj_port_mdb *ma, *mb; + + if (a->id != b->id || a->orig_dev != b->orig_dev) + return false; + + switch (a->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + va = SWITCHDEV_OBJ_PORT_VLAN(a); + vb = SWITCHDEV_OBJ_PORT_VLAN(b); + return va->flags == vb->flags && + va->vid == vb->vid && + va->changed == vb->changed; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + ma = SWITCHDEV_OBJ_PORT_MDB(a); + mb = SWITCHDEV_OBJ_PORT_MDB(b); + return ma->vid == mb->vid && + ether_addr_equal(ma->addr, mb->addr); + default: + break; + } + + BUG(); +} + static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); @@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); +/** + * switchdev_port_obj_act_is_deferred - Is object action pending? + * + * @dev: port device + * @nt: type of action; add or delete + * @obj: object to test + * + * Returns true if a deferred item is pending, which is + * equivalent to the action @nt on an object @obj. + * + * rtnl_lock must be held. + */ +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj) +{ + struct switchdev_deferred_item *dfitem; + bool found = false; + + ASSERT_RTNL(); + + spin_lock_bh(&deferred_lock); + + list_for_each_entry(dfitem, &deferred, list) { + if (dfitem->dev != dev) + continue; + + if ((dfitem->func == switchdev_port_obj_add_deferred && + nt == SWITCHDEV_PORT_OBJ_ADD) || + (dfitem->func == switchdev_port_obj_del_deferred && + nt == SWITCHDEV_PORT_OBJ_DEL)) { + if (switchdev_obj_eq((const void *)dfitem->data, obj)) { + found = true; + break; + } + } + } + + spin_unlock_bh(&deferred_lock); + + return found; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); + static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 1c2c6800949d..b4674f03d71a 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -1003,7 +1003,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx) return 0; } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9fbc70200cd0..de96959336c4 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1772,7 +1772,8 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, u8 *control, size_t skip, size_t len, - bool is_peek) + bool is_peek, + bool *more) { struct sk_buff *skb = skb_peek(&ctx->rx_list); struct tls_msg *tlm; @@ -1785,7 +1786,7 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; if (skip < rxm->full_len) break; @@ -1803,12 +1804,12 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; err = skb_copy_datagram_msg(skb, rxm->offset + skip, msg, chunk); if (err < 0) - goto out; + goto more; len = len - chunk; copied = copied + chunk; @@ -1844,6 +1845,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, out: return copied ? : err; +more: + if (more) + *more = true; + goto out; } static bool @@ -1947,6 +1952,7 @@ int tls_sw_recvmsg(struct sock *sk, int target, err; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; + bool rx_more = false; bool released = true; bool bpf_strp_enabled; bool zc_capable; @@ -1966,12 +1972,12 @@ int tls_sw_recvmsg(struct sock *sk, goto end; /* Process pending decrypted records. It must be non-zero-copy */ - err = process_rx_list(ctx, msg, &control, 0, len, is_peek); + err = process_rx_list(ctx, msg, &control, 0, len, is_peek, &rx_more); if (err < 0) goto end; copied = err; - if (len <= copied) + if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); @@ -2064,6 +2070,8 @@ put_on_rx_list: decrypted += chunk; len -= chunk; __skb_queue_tail(&ctx->rx_list, skb); + if (unlikely(control != TLS_RECORD_TYPE_DATA)) + break; continue; } @@ -2128,10 +2136,10 @@ recv_end: /* Drain records from the rx_list & copy if required */ if (is_peek || is_kvec) err = process_rx_list(ctx, msg, &control, copied, - decrypted, is_peek); + decrypted, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, - async_copy_bytes, is_peek); + async_copy_bytes, is_peek, NULL); } copied += decrypted; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 30b178ebba60..0748e7ea5210 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -782,19 +782,6 @@ static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t, int); -static int unix_set_peek_off(struct sock *sk, int val) -{ - struct unix_sock *u = unix_sk(sk); - - if (mutex_lock_interruptible(&u->iolock)) - return -EINTR; - - WRITE_ONCE(sk->sk_peek_off, val); - mutex_unlock(&u->iolock); - - return 0; -} - #ifdef CONFIG_PROC_FS static int unix_count_nr_fds(struct sock *sk) { @@ -862,7 +849,7 @@ static const struct proto_ops unix_stream_ops = { .read_skb = unix_stream_read_skb, .mmap = sock_no_mmap, .splice_read = unix_stream_splice_read, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -886,7 +873,7 @@ static const struct proto_ops unix_dgram_ops = { .read_skb = unix_read_skb, .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -909,7 +896,7 @@ static const struct proto_ops unix_seqpacket_ops = { .sendmsg = unix_seqpacket_sendmsg, .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2ff7ddbaa782..2a81880dac7b 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -284,9 +284,17 @@ void unix_gc(void) * which are creating the cycle(s). */ skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) + list_for_each_entry(u, &gc_candidates, link) { scan_children(&u->sk, inc_inflight, &hitlist); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + } + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ @@ -314,18 +322,6 @@ void unix_gc(void) /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - while (!list_empty(&gc_candidates)) { - u = list_entry(gc_candidates.next, struct unix_sock, link); - if (u->oob_skb) { - struct sk_buff *skb = u->oob_skb; - - u->oob_skb = NULL; - kfree_skb(skb); - } - } -#endif - spin_lock(&unix_gc_lock); /* There could be io_uring registered files, just push them back to diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 1eadfac03cc4..b78c0e095e22 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -722,7 +722,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, memcpy(vaddr, buffer, len); kunmap_local(vaddr); - skb_add_rx_frag(skb, nr_frags, page, 0, len, 0); + skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); + refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); } if (first_frag && desc->options & XDP_TX_METADATA) { diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 61b7dddedc46..0669bac5e900 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -513,7 +513,7 @@ eBPF programs can have an associated license, passed along with the bytecode instructions to the kernel when the programs are loaded. The format for that string is identical to the one in use for kernel modules (Dual licenses, such as "Dual BSD/GPL", may be used). Some helper functions are only accessible to -programs that are compatible with the GNU Privacy License (GPL). +programs that are compatible with the GNU General Public License (GNU GPL). In order to use such helpers, the eBPF program must be loaded with the correct license string passed (via **attr**) to the **bpf**\\ () system call, and this diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index c82a7f41b31c..6e6d474c8366 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -466,6 +466,8 @@ ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) int ynl_recv_ack(struct ynl_sock *ys, int ret) { + struct ynl_parse_arg yarg = { .ys = ys, }; + if (!ret) { yerr(ys, YNL_ERROR_EXPECT_ACK, "Expecting an ACK but nothing received"); @@ -478,7 +480,7 @@ int ynl_recv_ack(struct ynl_sock *ys, int ret) return ret; } return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid, - ynl_cb_null, ys); + ynl_cb_null, &yarg); } int ynl_cb_null(const struct nlmsghdr *nlh, void *data) @@ -586,7 +588,13 @@ static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name) return err; } - return ynl_recv_ack(ys, err); + err = ynl_recv_ack(ys, err); + if (err < 0) { + free(ys->mcast_groups); + return err; + } + + return 0; } struct ynl_sock * @@ -741,11 +749,14 @@ err_free: static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data) { - return ynl_ntf_parse((struct ynl_sock *)data, nlh); + struct ynl_parse_arg *yarg = data; + + return ynl_ntf_parse(yarg->ys, nlh); } int ynl_ntf_check(struct ynl_sock *ys) { + struct ynl_parse_arg yarg = { .ys = ys, }; ssize_t len; int err; @@ -767,7 +778,7 @@ int ynl_ntf_check(struct ynl_sock *ys) return len; err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, - ynl_ntf_trampoline, ys, + ynl_ntf_trampoline, &yarg, ynl_cb_array, NLMSG_MIN_TYPE); if (err < 0) return err; diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c index bf84d4a1d9ae..3c440370c1f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/iters.c +++ b/tools/testing/selftests/bpf/prog_tests/iters.c @@ -193,6 +193,7 @@ static void subtest_task_iters(void) ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt"); ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt"); ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt"); + ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt"); pthread_mutex_unlock(&do_nothing_mutex); for (int i = 0; i < thread_num; i++) ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join"); diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c new file mode 100644 index 000000000000..3405923fe4e6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024. Huawei Technologies Co., Ltd */ +#include "test_progs.h" +#include "read_vsyscall.skel.h" + +#if defined(__x86_64__) +/* For VSYSCALL_ADDR */ +#include <asm/vsyscall.h> +#else +/* To prevent build failure on non-x86 arch */ +#define VSYSCALL_ADDR 0UL +#endif + +struct read_ret_desc { + const char *name; + int ret; +} all_read[] = { + { .name = "probe_read_kernel", .ret = -ERANGE }, + { .name = "probe_read_kernel_str", .ret = -ERANGE }, + { .name = "probe_read", .ret = -ERANGE }, + { .name = "probe_read_str", .ret = -ERANGE }, + { .name = "probe_read_user", .ret = -EFAULT }, + { .name = "probe_read_user_str", .ret = -EFAULT }, + { .name = "copy_from_user", .ret = -EFAULT }, + { .name = "copy_from_user_task", .ret = -EFAULT }, +}; + +void test_read_vsyscall(void) +{ + struct read_vsyscall *skel; + unsigned int i; + int err; + +#if !defined(__x86_64__) + test__skip(); + return; +#endif + skel = read_vsyscall__open_and_load(); + if (!ASSERT_OK_PTR(skel, "read_vsyscall open_load")) + return; + + skel->bss->target_pid = getpid(); + err = read_vsyscall__attach(skel); + if (!ASSERT_EQ(err, 0, "read_vsyscall attach")) + goto out; + + /* userspace may don't have vsyscall page due to LEGACY_VSYSCALL_NONE, + * but it doesn't affect the returned error codes. + */ + skel->bss->user_ptr = (void *)VSYSCALL_ADDR; + usleep(1); + + for (i = 0; i < ARRAY_SIZE(all_read); i++) + ASSERT_EQ(skel->bss->read_ret[i], all_read[i].ret, all_read[i].name); +out: + read_vsyscall__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index 760ad96b4be0..d66687f1ee6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -4,10 +4,29 @@ #include "timer.skel.h" #include "timer_failure.skel.h" +#define NUM_THR 8 + +static void *spin_lock_thread(void *arg) +{ + int i, err, prog_fd = *(int *)arg; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + for (i = 0; i < 10000; i++) { + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err") || + !ASSERT_OK(topts.retval, "test_run_opts retval")) + break; + } + + pthread_exit(arg); +} + static int timer(struct timer *timer_skel) { - int err, prog_fd; + int i, err, prog_fd; LIBBPF_OPTS(bpf_test_run_opts, topts); + pthread_t thread_id[NUM_THR]; + void *ret; err = timer__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) @@ -43,6 +62,20 @@ static int timer(struct timer *timer_skel) /* check that code paths completed */ ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok"); + prog_fd = bpf_program__fd(timer_skel->progs.race); + for (i = 0; i < NUM_THR; i++) { + err = pthread_create(&thread_id[i], NULL, + &spin_lock_thread, &prog_fd); + if (!ASSERT_OK(err, "pthread_create")) + break; + } + + while (i) { + err = pthread_join(thread_id[--i], &ret); + if (ASSERT_OK(err, "pthread_join")) + ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join"); + } + return 0; } diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c index c9b4055cd410..e4d53e40ff20 100644 --- a/tools/testing/selftests/bpf/progs/iters_task.c +++ b/tools/testing/selftests/bpf/progs/iters_task.c @@ -10,7 +10,7 @@ char _license[] SEC("license") = "GPL"; pid_t target_pid; -int procs_cnt, threads_cnt, proc_threads_cnt; +int procs_cnt, threads_cnt, proc_threads_cnt, invalid_cnt; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; @@ -26,6 +26,16 @@ int iter_task_for_each_sleep(void *ctx) procs_cnt = threads_cnt = proc_threads_cnt = 0; bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, ~0U) { + /* Below instructions shouldn't be executed for invalid flags */ + invalid_cnt++; + } + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_PROC_THREADS) { + /* Below instructions shouldn't be executed for invalid task__nullable */ + invalid_cnt++; + } + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) if (pos->pid == target_pid) procs_cnt++; diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c new file mode 100644 index 000000000000..986f96687ae1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024. Huawei Technologies Co., Ltd */ +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +int target_pid = 0; +void *user_ptr = 0; +int read_ret[8]; + +char _license[] SEC("license") = "GPL"; + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int do_probe_read(void *ctx) +{ + char buf[8]; + + if ((bpf_get_current_pid_tgid() >> 32) != target_pid) + return 0; + + read_ret[0] = bpf_probe_read_kernel(buf, sizeof(buf), user_ptr); + read_ret[1] = bpf_probe_read_kernel_str(buf, sizeof(buf), user_ptr); + read_ret[2] = bpf_probe_read(buf, sizeof(buf), user_ptr); + read_ret[3] = bpf_probe_read_str(buf, sizeof(buf), user_ptr); + read_ret[4] = bpf_probe_read_user(buf, sizeof(buf), user_ptr); + read_ret[5] = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr); + + return 0; +} + +SEC("fentry.s/" SYS_PREFIX "sys_nanosleep") +int do_copy_from_user(void *ctx) +{ + char buf[8]; + + if ((bpf_get_current_pid_tgid() >> 32) != target_pid) + return 0; + + read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr); + read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr, + bpf_get_current_task_btf(), 0); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c index 8b946c8188c6..f615da97df26 100644 --- a/tools/testing/selftests/bpf/progs/timer.c +++ b/tools/testing/selftests/bpf/progs/timer.c @@ -51,7 +51,8 @@ struct { __uint(max_entries, 1); __type(key, int); __type(value, struct elem); -} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"); +} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"), + race_array SEC(".maps"); __u64 bss_data; __u64 abs_data; @@ -390,3 +391,34 @@ int BPF_PROG2(test5, int, a) return 0; } + +static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer *timer) +{ + bpf_timer_start(timer, 1000000, 0); + return 0; +} + +SEC("syscall") +int race(void *ctx) +{ + struct bpf_timer *timer; + int err, race_key = 0; + struct elem init; + + __builtin_memset(&init, 0, sizeof(struct elem)); + bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY); + + timer = bpf_map_lookup_elem(&race_array, &race_key); + if (!timer) + return 1; + + err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC); + if (err && err != -EBUSY) + return 1; + + bpf_timer_set_callback(timer, race_timer_callback); + bpf_timer_start(timer, 0, 0); + bpf_timer_cancel(timer); + + return 0; +} diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index d508486cc0bd..9a3d3c389dad 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -62,6 +62,8 @@ prio_test() # create bond bond_reset "${param}" + # set active_slave to primary eth1 specifically + ip -n ${s_ns} link set bond0 type bond active_slave eth1 # check bonding member prio value ip -n ${s_ns} link set eth0 type bond_slave prio 0 diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index b0f5e55d2d0b..589629636502 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -235,9 +235,6 @@ mirred_egress_to_ingress_tcp_test() check_err $? "didn't mirred redirect ICMP" tc_check_packets "dev $h1 ingress" 102 10 check_err $? "didn't drop mirred ICMP" - local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits) - test ${overlimits} = 10 - check_err $? "wrong overlimits, expected 10 got ${overlimits}" tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index fe59ca3e5596..12491850ae98 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -367,14 +367,12 @@ run_test() local desc=$2 local node_src=$3 local node_dst=$4 - local ip6_src=$5 - local ip6_dst=$6 - local if_dst=$7 - local trace_type=$8 - local ioam_ns=$9 - - ip netns exec $node_dst ./ioam6_parser $if_dst $name $ip6_src $ip6_dst \ - $trace_type $ioam_ns & + local ip6_dst=$5 + local trace_type=$6 + local ioam_ns=$7 + local type=$8 + + ip netns exec $node_dst ./ioam6_parser $name $trace_type $ioam_ns $type & local spid=$! sleep 0.1 @@ -489,7 +487,7 @@ out_undef_ns() trace prealloc type 0x800000 ns 0 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0x800000 0 + db01::1 0x800000 0 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -509,7 +507,7 @@ out_no_room() trace prealloc type 0xc00000 ns 123 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xc00000 123 + db01::1 0xc00000 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -543,14 +541,14 @@ out_bits() if [ $cmd_res != 0 ] then npassed=$((npassed+1)) - log_test_passed "$descr" + log_test_passed "$descr ($1 mode)" else nfailed=$((nfailed+1)) - log_test_failed "$descr" + log_test_failed "$descr ($1 mode)" fi else run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \ - $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 + $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1 fi done @@ -574,7 +572,7 @@ out_full_supp_trace() trace prealloc type 0xfff002 ns 123 size 100 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xfff002 123 + db01::1 0xfff002 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -604,7 +602,7 @@ in_undef_ns() trace prealloc type 0x800000 ns 0 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0x800000 0 + db01::1 0x800000 0 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -624,7 +622,7 @@ in_no_room() trace prealloc type 0xc00000 ns 123 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xc00000 123 + db01::1 0xc00000 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -651,7 +649,7 @@ in_bits() dev veth0 run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \ - $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 + $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1 done [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down @@ -679,7 +677,7 @@ in_oflag() trace prealloc type 0xc00000 ns 123 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xc00000 123 + db01::1 0xc00000 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down @@ -703,7 +701,7 @@ in_full_supp_trace() trace prealloc type 0xfff002 ns 123 size 80 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xfff002 123 + db01::1 0xfff002 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -731,7 +729,7 @@ fwd_full_supp_trace() trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_gamma \ - db01::2 db02::2 veth0 0xfff002 123 + db02::2 0xfff002 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down } diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index d9d1d4190126..895e5bb5044b 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -8,7 +8,6 @@ #include <errno.h> #include <limits.h> #include <linux/const.h> -#include <linux/if_ether.h> #include <linux/ioam6.h> #include <linux/ipv6.h> #include <stdlib.h> @@ -512,14 +511,6 @@ static int str2id(const char *tname) return -1; } -static int ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) -{ - return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | - (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | - (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | - (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; -} - static int get_u32(__u32 *val, const char *arg, int base) { unsigned long res; @@ -603,70 +594,80 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { int main(int argc, char **argv) { - int fd, size, hoplen, tid, ret = 1; - struct in6_addr src, dst; + int fd, size, hoplen, tid, ret = 1, on = 1; struct ioam6_hdr *opt; - struct ipv6hdr *ip6h; - __u8 buffer[400], *p; - __u16 ioam_ns; + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec iov; + __u8 buffer[512]; __u32 tr_type; + __u16 ioam_ns; + __u8 *ptr; - if (argc != 7) + if (argc != 5) goto out; - tid = str2id(argv[2]); + tid = str2id(argv[1]); if (tid < 0 || !func[tid]) goto out; - if (inet_pton(AF_INET6, argv[3], &src) != 1 || - inet_pton(AF_INET6, argv[4], &dst) != 1) + if (get_u32(&tr_type, argv[2], 16) || + get_u16(&ioam_ns, argv[3], 0)) goto out; - if (get_u32(&tr_type, argv[5], 16) || - get_u16(&ioam_ns, argv[6], 0)) + fd = socket(PF_INET6, SOCK_RAW, + !strcmp(argv[4], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6); + if (fd < 0) goto out; - fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6)); - if (!fd) - goto out; + setsockopt(fd, IPPROTO_IPV6, IPV6_RECVHOPOPTS, &on, sizeof(on)); - if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE, - argv[1], strlen(argv[1]))) + iov.iov_len = 1; + iov.iov_base = malloc(CMSG_SPACE(sizeof(buffer))); + if (!iov.iov_base) goto close; - recv: - size = recv(fd, buffer, sizeof(buffer), 0); + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = buffer; + msg.msg_controllen = CMSG_SPACE(sizeof(buffer)); + + size = recvmsg(fd, &msg, 0); if (size <= 0) goto close; - ip6h = (struct ipv6hdr *)buffer; + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level != IPPROTO_IPV6 || + cmsg->cmsg_type != IPV6_HOPOPTS || + cmsg->cmsg_len < sizeof(struct ipv6_hopopt_hdr)) + continue; - if (!ipv6_addr_equal(&ip6h->saddr, &src) || - !ipv6_addr_equal(&ip6h->daddr, &dst)) - goto recv; + ptr = (__u8 *)CMSG_DATA(cmsg); - if (ip6h->nexthdr != IPPROTO_HOPOPTS) - goto close; + hoplen = (ptr[1] + 1) << 3; + ptr += sizeof(struct ipv6_hopopt_hdr); - p = buffer + sizeof(*ip6h); - hoplen = (p[1] + 1) << 3; - p += sizeof(struct ipv6_hopopt_hdr); + while (hoplen > 0) { + opt = (struct ioam6_hdr *)ptr; - while (hoplen > 0) { - opt = (struct ioam6_hdr *)p; + if (opt->opt_type == IPV6_TLV_IOAM && + opt->type == IOAM6_TYPE_PREALLOC) { + ptr += sizeof(*opt); + ret = func[tid](tid, + (struct ioam6_trace_hdr *)ptr, + tr_type, ioam_ns); + goto close; + } - if (opt->opt_type == IPV6_TLV_IOAM && - opt->type == IOAM6_TYPE_PREALLOC) { - p += sizeof(*opt); - ret = func[tid](tid, (struct ioam6_trace_hdr *)p, - tr_type, ioam_ns); - break; + ptr += opt->opt_len + 2; + hoplen -= opt->opt_len + 2; } - - p += opt->opt_len + 2; - hoplen -= opt->opt_len + 2; } + + goto recv; close: + free(iov.iov_base); close(fd); out: return ret; diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 04fcb8a077c9..0a58ebb8b04c 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -62,8 +62,8 @@ __chk_nr() nr=$(eval $command) printf "%-50s" "$msg" - if [ $nr != $expected ]; then - if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then + if [ "$nr" != "$expected" ]; then + if [ "$nr" = "$skip" ] && ! mptcp_lib_expect_all_features; then echo "[ skip ] Feature probably not supported" mptcp_lib_result_skip "${msg}" else @@ -166,9 +166,13 @@ chk_msk_listen() chk_msk_inuse() { local expected=$1 - local msg="$2" + local msg="....chk ${2:-${expected}} msk in use" local listen_nr + if [ "${expected}" -eq 0 ]; then + msg+=" after flush" + fi + listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) expected=$((expected + listen_nr)) @@ -179,16 +183,21 @@ chk_msk_inuse() sleep 0.1 done - __chk_nr get_msk_inuse $expected "$msg" 0 + __chk_nr get_msk_inuse $expected "${msg}" 0 } # $1: cestab nr chk_msk_cestab() { - local cestab=$1 + local expected=$1 + local msg="....chk ${2:-${expected}} cestab" + + if [ "${expected}" -eq 0 ]; then + msg+=" after flush" + fi __chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \ - "${cestab}" "....chk ${cestab} cestab" "" + "${expected}" "${msg}" "" } wait_connected() @@ -227,12 +236,12 @@ wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" -chk_msk_inuse 2 "....chk 2 msk in use" +chk_msk_inuse 2 chk_msk_cestab 2 flush_pids -chk_msk_inuse 0 "....chk 0 msk in use after flush" -chk_msk_cestab 0 +chk_msk_inuse 0 "2->0" +chk_msk_cestab 0 "2->0" echo "a" | \ timeout ${timeout_test} \ @@ -247,12 +256,12 @@ echo "b" | \ 127.0.0.1 >/dev/null & wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" -chk_msk_inuse 1 "....chk 1 msk in use" +chk_msk_inuse 1 chk_msk_cestab 1 flush_pids -chk_msk_inuse 0 "....chk 0 msk in use after flush" -chk_msk_cestab 0 +chk_msk_inuse 0 "1->0" +chk_msk_cestab 0 "1->0" NR_CLIENTS=100 for I in `seq 1 $NR_CLIENTS`; do @@ -273,12 +282,12 @@ for I in `seq 1 $NR_CLIENTS`; do done wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present" -chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use" -chk_msk_cestab $((NR_CLIENTS*2)) +chk_msk_inuse $((NR_CLIENTS*2)) "many" +chk_msk_cestab $((NR_CLIENTS*2)) "many" flush_pids -chk_msk_inuse 0 "....chk 0 msk in use after flush" -chk_msk_cestab 0 +chk_msk_inuse 0 "many->0" +chk_msk_cestab 0 "many->0" mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 8f4ff123a7eb..71899a3ffa7a 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -183,7 +183,7 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nobackup)" # fullmesh support has been added later -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh 2>/dev/null if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || mptcp_lib_expect_all_features; then check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ @@ -194,6 +194,12 @@ subflow 10.0.1.1" " (nofullmesh)" ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +else + for st in fullmesh nofullmesh backup,fullmesh; do + st=" (${st})" + printf "%-50s%s\n" "${st}" "[SKIP]" + mptcp_lib_result_skip "${st}" + done fi mptcp_lib_result_print_all_tap diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 0cc964e6f2c1..8f9ddb3ad4fe 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -250,7 +250,8 @@ run_test() [ $bail -eq 0 ] || exit $ret fi - printf "%-60s" "$msg - reverse direction" + msg+=" - reverse direction" + printf "%-60s" "${msg}" do_transfer $large $small $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 6167837f48e1..1b94a75604fe 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -75,7 +75,7 @@ print_test() { test_name="${1}" - _printf "%-63s" "${test_name}" + _printf "%-68s" "${test_name}" } print_results() @@ -542,7 +542,7 @@ verify_subflow_events() local remid local info - info="${e_saddr} (${e_from}) => ${e_daddr} (${e_to})" + info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})" if [ "$e_type" = "$SUB_ESTABLISHED" ] then diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 49c84602707f..b95c249f81c2 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1485,6 +1485,51 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, control_msg_nomerge) +{ + char *rec1 = "1111"; + char *rec2 = "2222"; + int send_len = 5; + char buf[15]; + + if (self->notls) + SKIP(return, "no TLS support"); + + EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec1, send_len, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, rec1, send_len), 0); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, rec1, send_len), 0); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len); + EXPECT_EQ(memcmp(buf, rec1, send_len), 0); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len); + EXPECT_EQ(memcmp(buf, rec2, send_len), 0); +} + +TEST_F(tls, data_control_data) +{ + char *rec1 = "1111"; + char *rec2 = "2222"; + char *rec3 = "3333"; + int send_len = 5; + char buf[15]; + + if (self->notls) + SKIP(return, "no TLS support"); + + EXPECT_EQ(send(self->fd, rec1, send_len, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len); + EXPECT_EQ(send(self->fd, rec3, send_len, 0), send_len); + + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); +} + TEST_F(tls, shutdown) { char const *test_str = "test_read"; |