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(). ... --- .../selftests/bpf/prog_tests/unpriv_bpf_disabled.c | 312 +++++++++++++++++++++ 1 file changed, 312 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c (limited to 'tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c') diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c new file mode 100644 index 000000000..8383a99f6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022, Oracle and/or its affiliates. */ + +#include +#include + +#include "test_unpriv_bpf_disabled.skel.h" + +#include "cap_helpers.h" + +/* Using CAP_LAST_CAP is risky here, since it can get pulled in from + * an old /usr/include/linux/capability.h and be < CAP_BPF; as a result + * CAP_BPF would not be included in ALL_CAPS. Instead use CAP_BPF as + * we know its value is correct since it is explicitly defined in + * cap_helpers.h. + */ +#define ALL_CAPS ((2ULL << CAP_BPF) - 1) + +#define PINPATH "/sys/fs/bpf/unpriv_bpf_disabled_" +#define NUM_MAPS 7 + +static __u32 got_perfbuf_val; +static __u32 got_ringbuf_val; + +static int process_ringbuf(void *ctx, void *data, size_t len) +{ + if (ASSERT_EQ(len, sizeof(__u32), "ringbuf_size_valid")) + got_ringbuf_val = *(__u32 *)data; + return 0; +} + +static void process_perfbuf(void *ctx, int cpu, void *data, __u32 len) +{ + if (ASSERT_EQ(len, sizeof(__u32), "perfbuf_size_valid")) + got_perfbuf_val = *(__u32 *)data; +} + +static int sysctl_set(const char *sysctl_path, char *old_val, const char *new_val) +{ + int ret = 0; + FILE *fp; + + fp = fopen(sysctl_path, "r+"); + if (!fp) + return -errno; + if (old_val && fscanf(fp, "%s", old_val) <= 0) { + ret = -ENOENT; + } else if (!old_val || strcmp(old_val, new_val) != 0) { + fseek(fp, 0, SEEK_SET); + if (fprintf(fp, "%s", new_val) < 0) + ret = -errno; + } + fclose(fp); + + return ret; +} + +static void test_unpriv_bpf_disabled_positive(struct test_unpriv_bpf_disabled *skel, + __u32 prog_id, int prog_fd, int perf_fd, + char **map_paths, int *map_fds) +{ + struct perf_buffer *perfbuf = NULL; + struct ring_buffer *ringbuf = NULL; + int i, nr_cpus, link_fd = -1; + + nr_cpus = bpf_num_possible_cpus(); + + skel->bss->perfbuf_val = 1; + skel->bss->ringbuf_val = 2; + + /* Positive tests for unprivileged BPF disabled. Verify we can + * - retrieve and interact with pinned maps; + * - set up and interact with perf buffer; + * - set up and interact with ring buffer; + * - create a link + */ + perfbuf = perf_buffer__new(bpf_map__fd(skel->maps.perfbuf), 8, process_perfbuf, NULL, NULL, + NULL); + if (!ASSERT_OK_PTR(perfbuf, "perf_buffer__new")) + goto cleanup; + + ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf), process_ringbuf, NULL, NULL); + if (!ASSERT_OK_PTR(ringbuf, "ring_buffer__new")) + goto cleanup; + + /* trigger & validate perf event, ringbuf output */ + usleep(1); + + ASSERT_GT(perf_buffer__poll(perfbuf, 100), -1, "perf_buffer__poll"); + ASSERT_EQ(got_perfbuf_val, skel->bss->perfbuf_val, "check_perfbuf_val"); + ASSERT_EQ(ring_buffer__consume(ringbuf), 1, "ring_buffer__consume"); + ASSERT_EQ(got_ringbuf_val, skel->bss->ringbuf_val, "check_ringbuf_val"); + + for (i = 0; i < NUM_MAPS; i++) { + map_fds[i] = bpf_obj_get(map_paths[i]); + if (!ASSERT_GT(map_fds[i], -1, "obj_get")) + goto cleanup; + } + + for (i = 0; i < NUM_MAPS; i++) { + bool prog_array = strstr(map_paths[i], "prog_array") != NULL; + bool array = strstr(map_paths[i], "array") != NULL; + bool buf = strstr(map_paths[i], "buf") != NULL; + __u32 key = 0, vals[nr_cpus], lookup_vals[nr_cpus]; + __u32 expected_val = 1; + int j; + + /* skip ringbuf, perfbuf */ + if (buf) + continue; + + for (j = 0; j < nr_cpus; j++) + vals[j] = expected_val; + + if (prog_array) { + /* need valid prog array value */ + vals[0] = prog_fd; + /* prog array lookup returns prog id, not fd */ + expected_val = prog_id; + } + ASSERT_OK(bpf_map_update_elem(map_fds[i], &key, vals, 0), "map_update_elem"); + ASSERT_OK(bpf_map_lookup_elem(map_fds[i], &key, &lookup_vals), "map_lookup_elem"); + ASSERT_EQ(lookup_vals[0], expected_val, "map_lookup_elem_values"); + if (!array) + ASSERT_OK(bpf_map_delete_elem(map_fds[i], &key), "map_delete_elem"); + } + + link_fd = bpf_link_create(bpf_program__fd(skel->progs.handle_perf_event), perf_fd, + BPF_PERF_EVENT, NULL); + ASSERT_GT(link_fd, 0, "link_create"); + +cleanup: + if (link_fd) + close(link_fd); + if (perfbuf) + perf_buffer__free(perfbuf); + if (ringbuf) + ring_buffer__free(ringbuf); +} + +static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *skel, + __u32 prog_id, int prog_fd, int perf_fd, + char **map_paths, int *map_fds) +{ + const struct bpf_insn prog_insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn); + LIBBPF_OPTS(bpf_prog_load_opts, load_opts); + struct bpf_map_info map_info = {}; + __u32 map_info_len = sizeof(map_info); + struct bpf_link_info link_info = {}; + __u32 link_info_len = sizeof(link_info); + struct btf *btf = NULL; + __u32 attach_flags = 0; + __u32 prog_ids[3] = {}; + __u32 prog_cnt = 3; + __u32 next; + int i; + + /* Negative tests for unprivileged BPF disabled. Verify we cannot + * - load BPF programs; + * - create BPF maps; + * - get a prog/map/link fd by id; + * - get next prog/map/link id + * - query prog + * - BTF load + */ + ASSERT_EQ(bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "simple_prog", "GPL", + prog_insns, prog_insn_cnt, &load_opts), + -EPERM, "prog_load_fails"); + + for (i = BPF_MAP_TYPE_HASH; i <= BPF_MAP_TYPE_BLOOM_FILTER; i++) + ASSERT_EQ(bpf_map_create(i, NULL, sizeof(int), sizeof(int), 1, NULL), + -EPERM, "map_create_fails"); + + ASSERT_EQ(bpf_prog_get_fd_by_id(prog_id), -EPERM, "prog_get_fd_by_id_fails"); + ASSERT_EQ(bpf_prog_get_next_id(prog_id, &next), -EPERM, "prog_get_next_id_fails"); + ASSERT_EQ(bpf_prog_get_next_id(0, &next), -EPERM, "prog_get_next_id_fails"); + + if (ASSERT_OK(bpf_map_get_info_by_fd(map_fds[0], &map_info, &map_info_len), + "obj_get_info_by_fd")) { + ASSERT_EQ(bpf_map_get_fd_by_id(map_info.id), -EPERM, "map_get_fd_by_id_fails"); + ASSERT_EQ(bpf_map_get_next_id(map_info.id, &next), -EPERM, + "map_get_next_id_fails"); + } + ASSERT_EQ(bpf_map_get_next_id(0, &next), -EPERM, "map_get_next_id_fails"); + + if (ASSERT_OK(bpf_link_get_info_by_fd(bpf_link__fd(skel->links.sys_nanosleep_enter), + &link_info, &link_info_len), + "obj_get_info_by_fd")) { + ASSERT_EQ(bpf_link_get_fd_by_id(link_info.id), -EPERM, "link_get_fd_by_id_fails"); + ASSERT_EQ(bpf_link_get_next_id(link_info.id, &next), -EPERM, + "link_get_next_id_fails"); + } + ASSERT_EQ(bpf_link_get_next_id(0, &next), -EPERM, "link_get_next_id_fails"); + + ASSERT_EQ(bpf_prog_query(prog_fd, BPF_TRACE_FENTRY, 0, &attach_flags, prog_ids, + &prog_cnt), -EPERM, "prog_query_fails"); + + btf = btf__new_empty(); + if (ASSERT_OK_PTR(btf, "empty_btf") && + ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "unpriv_int_type")) { + const void *raw_btf_data; + __u32 raw_btf_size; + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (ASSERT_OK_PTR(raw_btf_data, "raw_btf_data_good")) + ASSERT_EQ(bpf_btf_load(raw_btf_data, raw_btf_size, NULL), -EPERM, + "bpf_btf_load_fails"); + } + btf__free(btf); +} + +void test_unpriv_bpf_disabled(void) +{ + char *map_paths[NUM_MAPS] = { PINPATH "array", + PINPATH "percpu_array", + PINPATH "hash", + PINPATH "percpu_hash", + PINPATH "perfbuf", + PINPATH "ringbuf", + PINPATH "prog_array" }; + int map_fds[NUM_MAPS]; + struct test_unpriv_bpf_disabled *skel; + char unprivileged_bpf_disabled_orig[32] = {}; + char perf_event_paranoid_orig[32] = {}; + struct bpf_prog_info prog_info = {}; + __u32 prog_info_len = sizeof(prog_info); + struct perf_event_attr attr = {}; + int prog_fd, perf_fd = -1, i, ret; + __u64 save_caps = 0; + __u32 prog_id; + + skel = test_unpriv_bpf_disabled__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->bss->test_pid = getpid(); + + map_fds[0] = bpf_map__fd(skel->maps.array); + map_fds[1] = bpf_map__fd(skel->maps.percpu_array); + map_fds[2] = bpf_map__fd(skel->maps.hash); + map_fds[3] = bpf_map__fd(skel->maps.percpu_hash); + map_fds[4] = bpf_map__fd(skel->maps.perfbuf); + map_fds[5] = bpf_map__fd(skel->maps.ringbuf); + map_fds[6] = bpf_map__fd(skel->maps.prog_array); + + for (i = 0; i < NUM_MAPS; i++) + ASSERT_OK(bpf_obj_pin(map_fds[i], map_paths[i]), "pin map_fd"); + + /* allow user without caps to use perf events */ + if (!ASSERT_OK(sysctl_set("/proc/sys/kernel/perf_event_paranoid", perf_event_paranoid_orig, + "-1"), + "set_perf_event_paranoid")) + goto cleanup; + /* ensure unprivileged bpf disabled is set */ + ret = sysctl_set("/proc/sys/kernel/unprivileged_bpf_disabled", + unprivileged_bpf_disabled_orig, "2"); + if (ret == -EPERM) { + /* if unprivileged_bpf_disabled=1, we get -EPERM back; that's okay. */ + if (!ASSERT_OK(strcmp(unprivileged_bpf_disabled_orig, "1"), + "unprivileged_bpf_disabled_on")) + goto cleanup; + } else { + if (!ASSERT_OK(ret, "set unprivileged_bpf_disabled")) + goto cleanup; + } + + prog_fd = bpf_program__fd(skel->progs.sys_nanosleep_enter); + ASSERT_OK(bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len), + "obj_get_info_by_fd"); + prog_id = prog_info.id; + ASSERT_GT(prog_id, 0, "valid_prog_id"); + + attr.size = sizeof(attr); + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_CPU_CLOCK; + attr.freq = 1; + attr.sample_freq = 1000; + perf_fd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); + if (!ASSERT_GE(perf_fd, 0, "perf_fd")) + goto cleanup; + + if (!ASSERT_OK(test_unpriv_bpf_disabled__attach(skel), "skel_attach")) + goto cleanup; + + if (!ASSERT_OK(cap_disable_effective(ALL_CAPS, &save_caps), "disable caps")) + goto cleanup; + + if (test__start_subtest("unpriv_bpf_disabled_positive")) + test_unpriv_bpf_disabled_positive(skel, prog_id, prog_fd, perf_fd, map_paths, + map_fds); + + if (test__start_subtest("unpriv_bpf_disabled_negative")) + test_unpriv_bpf_disabled_negative(skel, prog_id, prog_fd, perf_fd, map_paths, + map_fds); + +cleanup: + close(perf_fd); + if (save_caps) + cap_enable_effective(save_caps, NULL); + if (strlen(perf_event_paranoid_orig) > 0) + sysctl_set("/proc/sys/kernel/perf_event_paranoid", NULL, perf_event_paranoid_orig); + if (strlen(unprivileged_bpf_disabled_orig) > 0) + sysctl_set("/proc/sys/kernel/unprivileged_bpf_disabled", NULL, + unprivileged_bpf_disabled_orig); + for (i = 0; i < NUM_MAPS; i++) + unlink(map_paths[i]); + test_unpriv_bpf_disabled__destroy(skel); +} -- cgit v1.2.3