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(). ... --- tools/bpf/bpftool/jit_disasm.c | 403 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 403 insertions(+) create mode 100644 tools/bpf/bpftool/jit_disasm.c (limited to 'tools/bpf/bpftool/jit_disasm.c') diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c new file mode 100644 index 000000000..7b8d9ec89 --- /dev/null +++ b/tools/bpf/bpftool/jit_disasm.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Based on: + * + * Minimal BPF JIT image disassembler + * + * Disassembles BPF JIT compiler emitted opcodes back to asm insn's for + * debugging or verification purposes. + * + * Copyright 2013 Daniel Borkmann + * Licensed under the GNU General Public License, version 2.0 (GPLv2) + */ + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef HAVE_LLVM_SUPPORT +#include +#include +#include +#include +#endif + +#ifdef HAVE_LIBBFD_SUPPORT +#include +#include +#include +#endif + +#include "json_writer.h" +#include "main.h" + +static int oper_count; + +#ifdef HAVE_LLVM_SUPPORT +#define DISASM_SPACER + +typedef LLVMDisasmContextRef disasm_ctx_t; + +static int printf_json(char *s) +{ + s = strtok(s, " \t"); + jsonw_string_field(json_wtr, "operation", s); + + jsonw_name(json_wtr, "operands"); + jsonw_start_array(json_wtr); + oper_count = 1; + + while ((s = strtok(NULL, " \t,()")) != 0) { + jsonw_string(json_wtr, s); + oper_count++; + } + return 0; +} + +/* This callback to set the ref_type is necessary to have the LLVM disassembler + * print PC-relative addresses instead of byte offsets for branch instruction + * targets. + */ +static const char * +symbol_lookup_callback(__maybe_unused void *disasm_info, + __maybe_unused uint64_t ref_value, + uint64_t *ref_type, __maybe_unused uint64_t ref_PC, + __maybe_unused const char **ref_name) +{ + *ref_type = LLVMDisassembler_ReferenceType_InOut_None; + return NULL; +} + +static int +init_context(disasm_ctx_t *ctx, const char *arch, + __maybe_unused const char *disassembler_options, + __maybe_unused unsigned char *image, __maybe_unused ssize_t len) +{ + char *triple; + + if (arch) + triple = LLVMNormalizeTargetTriple(arch); + else + triple = LLVMGetDefaultTargetTriple(); + if (!triple) { + p_err("Failed to retrieve triple"); + return -1; + } + *ctx = LLVMCreateDisasm(triple, NULL, 0, NULL, symbol_lookup_callback); + LLVMDisposeMessage(triple); + + if (!*ctx) { + p_err("Failed to create disassembler"); + return -1; + } + + return 0; +} + +static void destroy_context(disasm_ctx_t *ctx) +{ + LLVMDisposeMessage(*ctx); +} + +static int +disassemble_insn(disasm_ctx_t *ctx, unsigned char *image, ssize_t len, int pc) +{ + char buf[256]; + int count; + + count = LLVMDisasmInstruction(*ctx, image + pc, len - pc, pc, + buf, sizeof(buf)); + if (json_output) + printf_json(buf); + else + printf("%s", buf); + + return count; +} + +int disasm_init(void) +{ + LLVMInitializeAllTargetInfos(); + LLVMInitializeAllTargetMCs(); + LLVMInitializeAllDisassemblers(); + return 0; +} +#endif /* HAVE_LLVM_SUPPORT */ + +#ifdef HAVE_LIBBFD_SUPPORT +#define DISASM_SPACER "\t" + +typedef struct { + struct disassemble_info *info; + disassembler_ftype disassemble; + bfd *bfdf; +} disasm_ctx_t; + +static int get_exec_path(char *tpath, size_t size) +{ + const char *path = "/proc/self/exe"; + ssize_t len; + + len = readlink(path, tpath, size - 1); + if (len <= 0) + return -1; + + tpath[len] = 0; + + return 0; +} + +static int printf_json(void *out, const char *fmt, va_list ap) +{ + char *s; + int err; + + err = vasprintf(&s, fmt, ap); + if (err < 0) + return -1; + + if (!oper_count) { + int i; + + /* Strip trailing spaces */ + i = strlen(s) - 1; + while (s[i] == ' ') + s[i--] = '\0'; + + jsonw_string_field(json_wtr, "operation", s); + jsonw_name(json_wtr, "operands"); + jsonw_start_array(json_wtr); + oper_count++; + } else if (!strcmp(fmt, ",")) { + /* Skip */ + } else { + jsonw_string(json_wtr, s); + oper_count++; + } + free(s); + return 0; +} + +static int fprintf_json(void *out, const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int fprintf_json_styled(void *out, + enum disassembler_style style __maybe_unused, + const char *fmt, ...) +{ + va_list ap; + int r; + + va_start(ap, fmt); + r = printf_json(out, fmt, ap); + va_end(ap); + + return r; +} + +static int init_context(disasm_ctx_t *ctx, const char *arch, + const char *disassembler_options, + unsigned char *image, ssize_t len) +{ + struct disassemble_info *info; + char tpath[PATH_MAX]; + bfd *bfdf; + + memset(tpath, 0, sizeof(tpath)); + if (get_exec_path(tpath, sizeof(tpath))) { + p_err("failed to create disassembler (get_exec_path)"); + return -1; + } + + ctx->bfdf = bfd_openr(tpath, NULL); + if (!ctx->bfdf) { + p_err("failed to create disassembler (bfd_openr)"); + return -1; + } + if (!bfd_check_format(ctx->bfdf, bfd_object)) { + p_err("failed to create disassembler (bfd_check_format)"); + goto err_close; + } + bfdf = ctx->bfdf; + + ctx->info = malloc(sizeof(struct disassemble_info)); + if (!ctx->info) { + p_err("mem alloc failed"); + goto err_close; + } + info = ctx->info; + + if (json_output) + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf_json, + fprintf_json_styled); + else + init_disassemble_info_compat(info, stdout, + (fprintf_ftype) fprintf, + fprintf_styled); + + /* Update architecture info for offload. */ + if (arch) { + const bfd_arch_info_type *inf = bfd_scan_arch(arch); + + if (inf) { + bfdf->arch_info = inf; + } else { + p_err("No libbfd support for %s", arch); + goto err_free; + } + } + + info->arch = bfd_get_arch(bfdf); + info->mach = bfd_get_mach(bfdf); + if (disassembler_options) + info->disassembler_options = disassembler_options; + info->buffer = image; + info->buffer_length = len; + + disassemble_init_for_target(info); + +#ifdef DISASM_FOUR_ARGS_SIGNATURE + ctx->disassemble = disassembler(info->arch, + bfd_big_endian(bfdf), + info->mach, + bfdf); +#else + ctx->disassemble = disassembler(bfdf); +#endif + if (!ctx->disassemble) { + p_err("failed to create disassembler"); + goto err_free; + } + return 0; + +err_free: + free(info); +err_close: + bfd_close(ctx->bfdf); + return -1; +} + +static void destroy_context(disasm_ctx_t *ctx) +{ + free(ctx->info); + bfd_close(ctx->bfdf); +} + +static int +disassemble_insn(disasm_ctx_t *ctx, __maybe_unused unsigned char *image, + __maybe_unused ssize_t len, int pc) +{ + return ctx->disassemble(pc, ctx->info); +} + +int disasm_init(void) +{ + bfd_init(); + return 0; +} +#endif /* HAVE_LIBBPFD_SUPPORT */ + +int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, + const char *arch, const char *disassembler_options, + const struct btf *btf, + const struct bpf_prog_linfo *prog_linfo, + __u64 func_ksym, unsigned int func_idx, + bool linum) +{ + const struct bpf_line_info *linfo = NULL; + unsigned int nr_skip = 0; + int count, i, pc = 0; + disasm_ctx_t ctx; + + if (!len) + return -1; + + if (init_context(&ctx, arch, disassembler_options, image, len)) + return -1; + + if (json_output) + jsonw_start_array(json_wtr); + do { + if (prog_linfo) { + linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo, + func_ksym + pc, + func_idx, + nr_skip); + if (linfo) + nr_skip++; + } + + if (json_output) { + jsonw_start_object(json_wtr); + oper_count = 0; + if (linfo) + btf_dump_linfo_json(btf, linfo, linum); + jsonw_name(json_wtr, "pc"); + jsonw_printf(json_wtr, "\"0x%x\"", pc); + } else { + if (linfo) + btf_dump_linfo_plain(btf, linfo, "; ", + linum); + printf("%4x:" DISASM_SPACER, pc); + } + + count = disassemble_insn(&ctx, image, len, pc); + + if (json_output) { + /* Operand array, was started in fprintf_json. Before + * that, make sure we have a _null_ value if no operand + * other than operation code was present. + */ + if (oper_count == 1) + jsonw_null(json_wtr); + jsonw_end_array(json_wtr); + } + + if (opcodes) { + if (json_output) { + jsonw_name(json_wtr, "opcodes"); + jsonw_start_array(json_wtr); + for (i = 0; i < count; ++i) + jsonw_printf(json_wtr, "\"0x%02hhx\"", + (uint8_t)image[pc + i]); + jsonw_end_array(json_wtr); + } else { + printf("\n\t"); + for (i = 0; i < count; ++i) + printf("%02x ", + (uint8_t)image[pc + i]); + } + } + if (json_output) + jsonw_end_object(json_wtr); + else + printf("\n"); + + pc += count; + } while (count > 0 && pc < len); + if (json_output) + jsonw_end_array(json_wtr); + + destroy_context(&ctx); + + return 0; +} -- cgit v1.2.3