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/attach_probe.c | 228 +++++++++++++++++++++ 1 file changed, 228 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/attach_probe.c (limited to 'tools/testing/selftests/bpf/prog_tests/attach_probe.c') diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c new file mode 100644 index 000000000..56374c8b5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include "test_attach_probe.skel.h" + +/* this is how USDT semaphore is actually defined, except volatile modifier */ +volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes"))); + +/* uprobe attach point */ +static noinline void trigger_func(void) +{ + asm volatile (""); +} + +/* attach point for byname uprobe */ +static noinline void trigger_func2(void) +{ + asm volatile (""); +} + +/* attach point for byname sleepable uprobe */ +static noinline void trigger_func3(void) +{ + asm volatile (""); +} + +static char test_data[] = "test_data"; + +void test_attach_probe(void) +{ + DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts); + struct bpf_link *kprobe_link, *kretprobe_link; + struct bpf_link *uprobe_link, *uretprobe_link; + struct test_attach_probe* skel; + ssize_t uprobe_offset, ref_ctr_offset; + struct bpf_link *uprobe_err_link; + FILE *devnull; + bool legacy; + + /* Check if new-style kprobe/uprobe API is supported. + * Kernels that support new FD-based kprobe and uprobe BPF attachment + * through perf_event_open() syscall expose + * /sys/bus/event_source/devices/kprobe/type and + * /sys/bus/event_source/devices/uprobe/type files, respectively. They + * contain magic numbers that are passed as "type" field of + * perf_event_attr. Lack of such file in the system indicates legacy + * kernel with old-style kprobe/uprobe attach interface through + * creating per-probe event through tracefs. For such cases + * ref_ctr_offset feature is not supported, so we don't test it. + */ + legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0; + + uprobe_offset = get_uprobe_offset(&trigger_func); + if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset")) + return; + + ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr); + if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset")) + return; + + skel = test_attach_probe__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + /* sleepable kprobe test case needs flags set before loading */ + if (!ASSERT_OK(bpf_program__set_flags(skel->progs.handle_kprobe_sleepable, + BPF_F_SLEEPABLE), "kprobe_sleepable_flags")) + goto cleanup; + + if (!ASSERT_OK(test_attach_probe__load(skel), "skel_load")) + goto cleanup; + if (!ASSERT_OK_PTR(skel->bss, "check_bss")) + goto cleanup; + + /* manual-attach kprobe/kretprobe */ + kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe, + false /* retprobe */, + SYS_NANOSLEEP_KPROBE_NAME); + if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe")) + goto cleanup; + skel->links.handle_kprobe = kprobe_link; + + kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe, + true /* retprobe */, + SYS_NANOSLEEP_KPROBE_NAME); + if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe")) + goto cleanup; + skel->links.handle_kretprobe = kretprobe_link; + + /* auto-attachable kprobe and kretprobe */ + skel->links.handle_kprobe_auto = bpf_program__attach(skel->progs.handle_kprobe_auto); + ASSERT_OK_PTR(skel->links.handle_kprobe_auto, "attach_kprobe_auto"); + + skel->links.handle_kretprobe_auto = bpf_program__attach(skel->progs.handle_kretprobe_auto); + ASSERT_OK_PTR(skel->links.handle_kretprobe_auto, "attach_kretprobe_auto"); + + if (!legacy) + ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before"); + + uprobe_opts.retprobe = false; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; + uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe, + 0 /* self pid */, + "/proc/self/exe", + uprobe_offset, + &uprobe_opts); + if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe")) + goto cleanup; + skel->links.handle_uprobe = uprobe_link; + + if (!legacy) + ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after"); + + /* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */ + uprobe_opts.retprobe = true; + uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset; + uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe, + -1 /* any pid */, + "/proc/self/exe", + uprobe_offset, &uprobe_opts); + if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe")) + goto cleanup; + skel->links.handle_uretprobe = uretprobe_link; + + /* verify auto-attach fails for old-style uprobe definition */ + uprobe_err_link = bpf_program__attach(skel->progs.handle_uprobe_byname); + if (!ASSERT_EQ(libbpf_get_error(uprobe_err_link), -EOPNOTSUPP, + "auto-attach should fail for old-style name")) + goto cleanup; + + uprobe_opts.func_name = "trigger_func2"; + uprobe_opts.retprobe = false; + uprobe_opts.ref_ctr_offset = 0; + skel->links.handle_uprobe_byname = + bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname, + 0 /* this pid */, + "/proc/self/exe", + 0, &uprobe_opts); + if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname, "attach_uprobe_byname")) + goto cleanup; + + /* verify auto-attach works */ + skel->links.handle_uretprobe_byname = + bpf_program__attach(skel->progs.handle_uretprobe_byname); + if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname, "attach_uretprobe_byname")) + goto cleanup; + + /* test attach by name for a library function, using the library + * as the binary argument. libc.so.6 will be resolved via dlopen()/dlinfo(). + */ + uprobe_opts.func_name = "fopen"; + uprobe_opts.retprobe = false; + skel->links.handle_uprobe_byname2 = + bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname2, + 0 /* this pid */, + "libc.so.6", + 0, &uprobe_opts); + if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname2, "attach_uprobe_byname2")) + goto cleanup; + + uprobe_opts.func_name = "fclose"; + uprobe_opts.retprobe = true; + skel->links.handle_uretprobe_byname2 = + bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe_byname2, + -1 /* any pid */, + "libc.so.6", + 0, &uprobe_opts); + if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname2, "attach_uretprobe_byname2")) + goto cleanup; + + /* sleepable kprobes should not attach successfully */ + skel->links.handle_kprobe_sleepable = bpf_program__attach(skel->progs.handle_kprobe_sleepable); + if (!ASSERT_ERR_PTR(skel->links.handle_kprobe_sleepable, "attach_kprobe_sleepable")) + goto cleanup; + + /* test sleepable uprobe and uretprobe variants */ + skel->links.handle_uprobe_byname3_sleepable = bpf_program__attach(skel->progs.handle_uprobe_byname3_sleepable); + if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname3_sleepable, "attach_uprobe_byname3_sleepable")) + goto cleanup; + + skel->links.handle_uprobe_byname3 = bpf_program__attach(skel->progs.handle_uprobe_byname3); + if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname3, "attach_uprobe_byname3")) + goto cleanup; + + skel->links.handle_uretprobe_byname3_sleepable = bpf_program__attach(skel->progs.handle_uretprobe_byname3_sleepable); + if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname3_sleepable, "attach_uretprobe_byname3_sleepable")) + goto cleanup; + + skel->links.handle_uretprobe_byname3 = bpf_program__attach(skel->progs.handle_uretprobe_byname3); + if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname3, "attach_uretprobe_byname3")) + goto cleanup; + + skel->bss->user_ptr = test_data; + + /* trigger & validate kprobe && kretprobe */ + usleep(1); + + /* trigger & validate shared library u[ret]probes attached by name */ + devnull = fopen("/dev/null", "r"); + fclose(devnull); + + /* trigger & validate uprobe & uretprobe */ + trigger_func(); + + /* trigger & validate uprobe attached by name */ + trigger_func2(); + + /* trigger & validate sleepable uprobe attached by name */ + trigger_func3(); + + ASSERT_EQ(skel->bss->kprobe_res, 1, "check_kprobe_res"); + ASSERT_EQ(skel->bss->kprobe2_res, 11, "check_kprobe_auto_res"); + ASSERT_EQ(skel->bss->kretprobe_res, 2, "check_kretprobe_res"); + ASSERT_EQ(skel->bss->kretprobe2_res, 22, "check_kretprobe_auto_res"); + ASSERT_EQ(skel->bss->uprobe_res, 3, "check_uprobe_res"); + ASSERT_EQ(skel->bss->uretprobe_res, 4, "check_uretprobe_res"); + ASSERT_EQ(skel->bss->uprobe_byname_res, 5, "check_uprobe_byname_res"); + ASSERT_EQ(skel->bss->uretprobe_byname_res, 6, "check_uretprobe_byname_res"); + ASSERT_EQ(skel->bss->uprobe_byname2_res, 7, "check_uprobe_byname2_res"); + ASSERT_EQ(skel->bss->uretprobe_byname2_res, 8, "check_uretprobe_byname2_res"); + ASSERT_EQ(skel->bss->uprobe_byname3_sleepable_res, 9, "check_uprobe_byname3_sleepable_res"); + ASSERT_EQ(skel->bss->uprobe_byname3_res, 10, "check_uprobe_byname3_res"); + ASSERT_EQ(skel->bss->uretprobe_byname3_sleepable_res, 11, "check_uretprobe_byname3_sleepable_res"); + ASSERT_EQ(skel->bss->uretprobe_byname3_res, 12, "check_uretprobe_byname3_res"); + +cleanup: + test_attach_probe__destroy(skel); + ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_cleanup"); +} -- cgit v1.2.3