From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- .../testing/selftests/bpf/prog_tests/lsm_cgroup.c | 323 +++++++++++++++++++++ 1 file changed, 323 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c (limited to 'tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c') diff --git a/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c b/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c new file mode 100644 index 000000000..130a3b21e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include + +#include "lsm_cgroup.skel.h" +#include "lsm_cgroup_nonvoid.skel.h" +#include "cgroup_helpers.h" +#include "network_helpers.h" + +#ifndef ENOTSUPP +#define ENOTSUPP 524 +#endif + +static struct btf *btf; + +static __u32 query_prog_cnt(int cgroup_fd, const char *attach_func) +{ + LIBBPF_OPTS(bpf_prog_query_opts, p); + int cnt = 0; + int i; + + ASSERT_OK(bpf_prog_query_opts(cgroup_fd, BPF_LSM_CGROUP, &p), "prog_query"); + + if (!attach_func) + return p.prog_cnt; + + /* When attach_func is provided, count the number of progs that + * attach to the given symbol. + */ + + if (!btf) + btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK(libbpf_get_error(btf), "btf_vmlinux")) + return -1; + + p.prog_ids = malloc(sizeof(u32) * p.prog_cnt); + p.prog_attach_flags = malloc(sizeof(u32) * p.prog_cnt); + ASSERT_OK(bpf_prog_query_opts(cgroup_fd, BPF_LSM_CGROUP, &p), "prog_query"); + + for (i = 0; i < p.prog_cnt; i++) { + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int fd; + + fd = bpf_prog_get_fd_by_id(p.prog_ids[i]); + ASSERT_GE(fd, 0, "prog_get_fd_by_id"); + ASSERT_OK(bpf_prog_get_info_by_fd(fd, &info, &info_len), + "prog_info_by_fd"); + close(fd); + + if (info.attach_btf_id == + btf__find_by_name_kind(btf, attach_func, BTF_KIND_FUNC)) + cnt++; + } + + free(p.prog_ids); + free(p.prog_attach_flags); + + return cnt; +} + +static void test_lsm_cgroup_functional(void) +{ + DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, attach_opts); + DECLARE_LIBBPF_OPTS(bpf_link_update_opts, update_opts); + int cgroup_fd = -1, cgroup_fd2 = -1, cgroup_fd3 = -1; + int listen_fd, client_fd, accepted_fd; + struct lsm_cgroup *skel = NULL; + int post_create_prog_fd2 = -1; + int post_create_prog_fd = -1; + int bind_link_fd2 = -1; + int bind_prog_fd2 = -1; + int alloc_prog_fd = -1; + int bind_prog_fd = -1; + int bind_link_fd = -1; + int clone_prog_fd = -1; + int err, fd, prio; + socklen_t socklen; + + cgroup_fd3 = test__join_cgroup("/sock_policy_empty"); + if (!ASSERT_GE(cgroup_fd3, 0, "create empty cgroup")) + goto close_cgroup; + + cgroup_fd2 = test__join_cgroup("/sock_policy_reuse"); + if (!ASSERT_GE(cgroup_fd2, 0, "create cgroup for reuse")) + goto close_cgroup; + + cgroup_fd = test__join_cgroup("/sock_policy"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup")) + goto close_cgroup; + + skel = lsm_cgroup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto close_cgroup; + + post_create_prog_fd = bpf_program__fd(skel->progs.socket_post_create); + post_create_prog_fd2 = bpf_program__fd(skel->progs.socket_post_create2); + bind_prog_fd = bpf_program__fd(skel->progs.socket_bind); + bind_prog_fd2 = bpf_program__fd(skel->progs.socket_bind2); + alloc_prog_fd = bpf_program__fd(skel->progs.socket_alloc); + clone_prog_fd = bpf_program__fd(skel->progs.socket_clone); + + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_sk_alloc_security"), 0, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 0, "total prog count"); + err = bpf_prog_attach(alloc_prog_fd, cgroup_fd, BPF_LSM_CGROUP, 0); + if (err == -ENOTSUPP) { + test__skip(); + goto close_cgroup; + } + if (!ASSERT_OK(err, "attach alloc_prog_fd")) + goto detach_cgroup; + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_sk_alloc_security"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 1, "total prog count"); + + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_inet_csk_clone"), 0, "prog count"); + err = bpf_prog_attach(clone_prog_fd, cgroup_fd, BPF_LSM_CGROUP, 0); + if (!ASSERT_OK(err, "attach clone_prog_fd")) + goto detach_cgroup; + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_inet_csk_clone"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 2, "total prog count"); + + /* Make sure replacing works. */ + + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_socket_post_create"), 0, "prog count"); + err = bpf_prog_attach(post_create_prog_fd, cgroup_fd, + BPF_LSM_CGROUP, 0); + if (!ASSERT_OK(err, "attach post_create_prog_fd")) + goto detach_cgroup; + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_socket_post_create"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 3, "total prog count"); + + attach_opts.replace_prog_fd = post_create_prog_fd; + err = bpf_prog_attach_opts(post_create_prog_fd2, cgroup_fd, + BPF_LSM_CGROUP, &attach_opts); + if (!ASSERT_OK(err, "prog replace post_create_prog_fd")) + goto detach_cgroup; + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_socket_post_create"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 3, "total prog count"); + + /* Try the same attach/replace via link API. */ + + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_socket_bind"), 0, "prog count"); + bind_link_fd = bpf_link_create(bind_prog_fd, cgroup_fd, + BPF_LSM_CGROUP, NULL); + if (!ASSERT_GE(bind_link_fd, 0, "link create bind_prog_fd")) + goto detach_cgroup; + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_socket_bind"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 4, "total prog count"); + + update_opts.old_prog_fd = bind_prog_fd; + update_opts.flags = BPF_F_REPLACE; + + err = bpf_link_update(bind_link_fd, bind_prog_fd2, &update_opts); + if (!ASSERT_OK(err, "link update bind_prog_fd")) + goto detach_cgroup; + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_socket_bind"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 4, "total prog count"); + + /* Attach another instance of bind program to another cgroup. + * This should trigger the reuse of the trampoline shim (two + * programs attaching to the same btf_id). + */ + + ASSERT_EQ(query_prog_cnt(cgroup_fd, "bpf_lsm_socket_bind"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd2, "bpf_lsm_socket_bind"), 0, "prog count"); + bind_link_fd2 = bpf_link_create(bind_prog_fd2, cgroup_fd2, + BPF_LSM_CGROUP, NULL); + if (!ASSERT_GE(bind_link_fd2, 0, "link create bind_prog_fd2")) + goto detach_cgroup; + ASSERT_EQ(query_prog_cnt(cgroup_fd2, "bpf_lsm_socket_bind"), 1, "prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd, NULL), 4, "total prog count"); + ASSERT_EQ(query_prog_cnt(cgroup_fd2, NULL), 1, "total prog count"); + + fd = socket(AF_UNIX, SOCK_STREAM, 0); + if (!(skel->kconfig->CONFIG_SECURITY_APPARMOR + || skel->kconfig->CONFIG_SECURITY_SELINUX + || skel->kconfig->CONFIG_SECURITY_SMACK)) + /* AF_UNIX is prohibited. */ + ASSERT_LT(fd, 0, "socket(AF_UNIX)"); + close(fd); + + /* AF_INET6 gets default policy (sk_priority). */ + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (!ASSERT_GE(fd, 0, "socket(SOCK_STREAM)")) + goto detach_cgroup; + + prio = 0; + socklen = sizeof(prio); + ASSERT_GE(getsockopt(fd, SOL_SOCKET, SO_PRIORITY, &prio, &socklen), 0, + "getsockopt"); + ASSERT_EQ(prio, 123, "sk_priority"); + + close(fd); + + /* TX-only AF_PACKET is allowed. */ + + ASSERT_LT(socket(AF_PACKET, SOCK_RAW, htons(ETH_P_ALL)), 0, + "socket(AF_PACKET, ..., ETH_P_ALL)"); + + fd = socket(AF_PACKET, SOCK_RAW, 0); + ASSERT_GE(fd, 0, "socket(AF_PACKET, ..., 0)"); + + /* TX-only AF_PACKET can not be rebound. */ + + struct sockaddr_ll sa = { + .sll_family = AF_PACKET, + .sll_protocol = htons(ETH_P_ALL), + }; + ASSERT_LT(bind(fd, (struct sockaddr *)&sa, sizeof(sa)), 0, + "bind(ETH_P_ALL)"); + + close(fd); + + /* Trigger passive open. */ + + listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + ASSERT_GE(listen_fd, 0, "start_server"); + client_fd = connect_to_fd(listen_fd, 0); + ASSERT_GE(client_fd, 0, "connect_to_fd"); + accepted_fd = accept(listen_fd, NULL, NULL); + ASSERT_GE(accepted_fd, 0, "accept"); + + prio = 0; + socklen = sizeof(prio); + ASSERT_GE(getsockopt(accepted_fd, SOL_SOCKET, SO_PRIORITY, &prio, &socklen), 0, + "getsockopt"); + ASSERT_EQ(prio, 234, "sk_priority"); + + /* These are replaced and never called. */ + ASSERT_EQ(skel->bss->called_socket_post_create, 0, "called_create"); + ASSERT_EQ(skel->bss->called_socket_bind, 0, "called_bind"); + + /* AF_INET6+SOCK_STREAM + * AF_PACKET+SOCK_RAW + * AF_UNIX+SOCK_RAW if already have non-bpf lsms installed + * listen_fd + * client_fd + * accepted_fd + */ + if (skel->kconfig->CONFIG_SECURITY_APPARMOR + || skel->kconfig->CONFIG_SECURITY_SELINUX + || skel->kconfig->CONFIG_SECURITY_SMACK) + /* AF_UNIX+SOCK_RAW if already have non-bpf lsms installed */ + ASSERT_EQ(skel->bss->called_socket_post_create2, 6, "called_create2"); + else + ASSERT_EQ(skel->bss->called_socket_post_create2, 5, "called_create2"); + + /* start_server + * bind(ETH_P_ALL) + */ + ASSERT_EQ(skel->bss->called_socket_bind2, 2, "called_bind2"); + /* Single accept(). */ + ASSERT_EQ(skel->bss->called_socket_clone, 1, "called_clone"); + + /* AF_UNIX+SOCK_STREAM (failed) + * AF_INET6+SOCK_STREAM + * AF_PACKET+SOCK_RAW (failed) + * AF_PACKET+SOCK_RAW + * listen_fd + * client_fd + * accepted_fd + */ + ASSERT_EQ(skel->bss->called_socket_alloc, 7, "called_alloc"); + + close(listen_fd); + close(client_fd); + close(accepted_fd); + + /* Make sure other cgroup doesn't trigger the programs. */ + + if (!ASSERT_OK(join_cgroup("/sock_policy_empty"), "join root cgroup")) + goto detach_cgroup; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (!ASSERT_GE(fd, 0, "socket(SOCK_STREAM)")) + goto detach_cgroup; + + prio = 0; + socklen = sizeof(prio); + ASSERT_GE(getsockopt(fd, SOL_SOCKET, SO_PRIORITY, &prio, &socklen), 0, + "getsockopt"); + ASSERT_EQ(prio, 0, "sk_priority"); + + close(fd); + +detach_cgroup: + ASSERT_GE(bpf_prog_detach2(post_create_prog_fd2, cgroup_fd, + BPF_LSM_CGROUP), 0, "detach_create"); + close(bind_link_fd); + /* Don't close bind_link_fd2, exercise cgroup release cleanup. */ + ASSERT_GE(bpf_prog_detach2(alloc_prog_fd, cgroup_fd, + BPF_LSM_CGROUP), 0, "detach_alloc"); + ASSERT_GE(bpf_prog_detach2(clone_prog_fd, cgroup_fd, + BPF_LSM_CGROUP), 0, "detach_clone"); + +close_cgroup: + close(cgroup_fd); + close(cgroup_fd2); + close(cgroup_fd3); + lsm_cgroup__destroy(skel); +} + +static void test_lsm_cgroup_nonvoid(void) +{ + struct lsm_cgroup_nonvoid *skel = NULL; + + skel = lsm_cgroup_nonvoid__open_and_load(); + ASSERT_NULL(skel, "open succeeds"); + lsm_cgroup_nonvoid__destroy(skel); +} + +void test_lsm_cgroup(void) +{ + if (test__start_subtest("functional")) + test_lsm_cgroup_functional(); + if (test__start_subtest("nonvoid")) + test_lsm_cgroup_nonvoid(); + btf__free(btf); +} -- cgit v1.2.3