diff options
Diffstat (limited to 'tools')
220 files changed, 15581 insertions, 5467 deletions
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 062bbd6cd048..fd2585af1252 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -32,7 +32,7 @@ FEATURE_TESTS = libbfd disassembler-four-args disassembler-init-styled FEATURE_DISPLAY = libbfd check_feat := 1 -NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean resolve_btfids_clean +NON_CHECK_FEAT_TARGETS := clean bpftool_clean resolve_btfids_clean ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) check_feat := 0 @@ -70,7 +70,7 @@ $(OUTPUT)%.lex.o: $(OUTPUT)%.lex.c PROGS = $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg $(OUTPUT)bpf_asm -all: $(PROGS) bpftool runqslower +all: $(PROGS) bpftool $(OUTPUT)bpf_jit_disasm: CFLAGS += -DPACKAGE='bpf_jit_disasm' $(OUTPUT)bpf_jit_disasm: $(OUTPUT)bpf_jit_disasm.o @@ -86,7 +86,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c -clean: bpftool_clean runqslower_clean resolve_btfids_clean +clean: bpftool_clean resolve_btfids_clean $(call QUIET_CLEAN, bpf-progs) $(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.* @@ -112,12 +112,6 @@ bpftool_install: bpftool_clean: $(call descend,bpftool,clean) -runqslower: - $(call descend,runqslower) - -runqslower_clean: - $(call descend,runqslower,clean) - resolve_btfids: $(call descend,resolve_btfids) @@ -125,5 +119,4 @@ resolve_btfids_clean: $(call descend,resolve_btfids,clean) .PHONY: all install clean bpftool bpftool_install bpftool_clean \ - runqslower runqslower_clean \ resolve_btfids resolve_btfids_clean diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 252e4c538edb..1af3305ea2b2 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -55,7 +55,8 @@ MAP COMMANDS | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** -| | **task_storage** | **bloom_filter** | **user_ringbuf** | **cgrp_storage** | **arena** } +| | **task_storage** | **bloom_filter** | **user_ringbuf** | **cgrp_storage** | **arena** +| | **insn_array** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index ff12628593ae..def297e879f4 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -590,7 +590,7 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id, case BTF_KIND_DATASEC: return btf_dumper_datasec(d, type_id, data); default: - jsonw_printf(d->jw, "(unsupported-kind"); + jsonw_printf(d->jw, "(unsupported-kind)"); return -EINVAL; } } diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index c9de44a45778..7ebf7dbcfba4 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1477,7 +1477,8 @@ static int do_help(int argc, char **argv) " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" - " task_storage | bloom_filter | user_ringbuf | cgrp_storage | arena }\n" + " task_storage | bloom_filter | user_ringbuf | cgrp_storage | arena |\n" + " insn_array }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-n|--nomount} }\n" "", diff --git a/tools/bpf/bpftool/sign.c b/tools/bpf/bpftool/sign.c index b34f74d210e9..f9b742f4bb10 100644 --- a/tools/bpf/bpftool/sign.c +++ b/tools/bpf/bpftool/sign.c @@ -28,6 +28,12 @@ #define OPEN_SSL_ERR_BUF_LEN 256 +/* Use deprecated in 3.0 ERR_get_error_line_data for openssl < 3 */ +#if !defined(OPENSSL_VERSION_MAJOR) || (OPENSSL_VERSION_MAJOR < 3) +#define ERR_get_error_all(file, line, func, data, flags) \ + ERR_get_error_line_data(file, line, data, flags) +#endif + static void display_openssl_errors(int l) { char buf[OPEN_SSL_ERR_BUF_LEN]; diff --git a/tools/bpf/runqslower/.gitignore b/tools/bpf/runqslower/.gitignore deleted file mode 100644 index ffdb70230c8b..000000000000 --- a/tools/bpf/runqslower/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -/.output diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile deleted file mode 100644 index 78a436c4072e..000000000000 --- a/tools/bpf/runqslower/Makefile +++ /dev/null @@ -1,91 +0,0 @@ -# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) -include ../../scripts/Makefile.include - -OUTPUT ?= $(abspath .output)/ - -BPFTOOL_OUTPUT := $(OUTPUT)bpftool/ -DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)bootstrap/bpftool -BPFTOOL ?= $(DEFAULT_BPFTOOL) -BPF_TARGET_ENDIAN ?= --target=bpf -LIBBPF_SRC := $(abspath ../../lib/bpf) -BPFOBJ_OUTPUT := $(OUTPUT)libbpf/ -BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a -BPF_DESTDIR := $(BPFOBJ_OUTPUT) -BPF_INCLUDE := $(BPF_DESTDIR)/include -INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi) -CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS) -CFLAGS += $(EXTRA_CFLAGS) -LDFLAGS += $(EXTRA_LDFLAGS) -LDLIBS += -lelf -lz - -# Try to detect best kernel BTF source -KERNEL_REL := $(shell uname -r) -VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux) \ - $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ - ../../../vmlinux /sys/kernel/btf/vmlinux \ - /boot/vmlinux-$(KERNEL_REL) -VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword \ - $(wildcard $(VMLINUX_BTF_PATHS)))) - -ifneq ($(V),1) -MAKEFLAGS += --no-print-directory -submake_extras := feature_display=0 -endif - -.DELETE_ON_ERROR: - -.PHONY: all clean runqslower libbpf_hdrs -all: runqslower - -runqslower: $(OUTPUT)/runqslower - -clean: - $(call QUIET_CLEAN, runqslower) - $(Q)$(RM) -r $(BPFOBJ_OUTPUT) $(BPFTOOL_OUTPUT) - $(Q)$(RM) $(OUTPUT)*.o $(OUTPUT)*.d - $(Q)$(RM) $(OUTPUT)*.skel.h $(OUTPUT)vmlinux.h - $(Q)$(RM) $(OUTPUT)runqslower - $(Q)$(RM) -r .output - -libbpf_hdrs: $(BPFOBJ) - -$(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ) - $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LDLIBS) -o $@ - -$(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \ - $(OUTPUT)/runqslower.bpf.o | libbpf_hdrs - -$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h | libbpf_hdrs - -$(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL) - $(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@ - -$(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT) - $(QUIET_GEN)$(CLANG) -g -O2 $(BPF_TARGET_ENDIAN) $(INCLUDES) \ - -c $(filter %.c,$^) -o $@ && \ - $(LLVM_STRIP) -g $@ - -$(OUTPUT)/%.o: %.c | $(OUTPUT) - $(QUIET_CC)$(CC) $(CFLAGS) $(INCLUDES) -c $(filter %.c,$^) -o $@ - -$(OUTPUT) $(BPFOBJ_OUTPUT) $(BPFTOOL_OUTPUT): - $(QUIET_MKDIR)mkdir -p $@ - -$(OUTPUT)/vmlinux.h: $(VMLINUX_BTF_PATH) | $(OUTPUT) $(BPFTOOL) -ifeq ($(VMLINUX_H),) - $(Q)if [ ! -e "$(VMLINUX_BTF_PATH)" ] ; then \ - echo "Couldn't find kernel BTF; set VMLINUX_BTF to" \ - "specify its location." >&2; \ - exit 1;\ - fi - $(QUIET_GEN)$(BPFTOOL) btf dump file $(VMLINUX_BTF_PATH) format c > $@ -else - $(Q)cp "$(VMLINUX_H)" $@ -endif - -$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OUTPUT) - $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) \ - DESTDIR=$(BPFOBJ_OUTPUT) prefix= $(abspath $@) install_headers - -$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT) - $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) bootstrap diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c deleted file mode 100644 index fced54a3adf6..000000000000 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ /dev/null @@ -1,106 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2019 Facebook -#include "vmlinux.h" -#include <bpf/bpf_helpers.h> -#include "runqslower.h" - -#define TASK_RUNNING 0 -#define BPF_F_CURRENT_CPU 0xffffffffULL - -const volatile __u64 min_us = 0; -const volatile pid_t targ_pid = 0; - -struct { - __uint(type, BPF_MAP_TYPE_TASK_STORAGE); - __uint(map_flags, BPF_F_NO_PREALLOC); - __type(key, int); - __type(value, u64); -} start SEC(".maps"); - -struct { - __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); - __uint(key_size, sizeof(u32)); - __uint(value_size, sizeof(u32)); -} events SEC(".maps"); - -/* record enqueue timestamp */ -__always_inline -static int trace_enqueue(struct task_struct *t) -{ - u32 pid = t->pid; - u64 *ptr; - - if (!pid || (targ_pid && targ_pid != pid)) - return 0; - - ptr = bpf_task_storage_get(&start, t, 0, - BPF_LOCAL_STORAGE_GET_F_CREATE); - if (!ptr) - return 0; - - *ptr = bpf_ktime_get_ns(); - return 0; -} - -SEC("tp_btf/sched_wakeup") -int handle__sched_wakeup(u64 *ctx) -{ - /* TP_PROTO(struct task_struct *p) */ - struct task_struct *p = (void *)ctx[0]; - - return trace_enqueue(p); -} - -SEC("tp_btf/sched_wakeup_new") -int handle__sched_wakeup_new(u64 *ctx) -{ - /* TP_PROTO(struct task_struct *p) */ - struct task_struct *p = (void *)ctx[0]; - - return trace_enqueue(p); -} - -SEC("tp_btf/sched_switch") -int handle__sched_switch(u64 *ctx) -{ - /* TP_PROTO(bool preempt, struct task_struct *prev, - * struct task_struct *next) - */ - struct task_struct *prev = (struct task_struct *)ctx[1]; - struct task_struct *next = (struct task_struct *)ctx[2]; - struct runq_event event = {}; - u64 *tsp, delta_us; - u32 pid; - - /* ivcsw: treat like an enqueue event and store timestamp */ - if (prev->__state == TASK_RUNNING) - trace_enqueue(prev); - - pid = next->pid; - - /* For pid mismatch, save a bpf_task_storage_get */ - if (!pid || (targ_pid && targ_pid != pid)) - return 0; - - /* fetch timestamp and calculate delta */ - tsp = bpf_task_storage_get(&start, next, 0, 0); - if (!tsp) - return 0; /* missed enqueue */ - - delta_us = (bpf_ktime_get_ns() - *tsp) / 1000; - if (min_us && delta_us <= min_us) - return 0; - - event.pid = pid; - event.delta_us = delta_us; - bpf_get_current_comm(&event.task, sizeof(event.task)); - - /* output */ - bpf_perf_event_output(ctx, &events, BPF_F_CURRENT_CPU, - &event, sizeof(event)); - - bpf_task_storage_delete(&start, next); - return 0; -} - -char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c deleted file mode 100644 index 83c5993a139a..000000000000 --- a/tools/bpf/runqslower/runqslower.c +++ /dev/null @@ -1,171 +0,0 @@ -// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) -// Copyright (c) 2019 Facebook -#include <argp.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <time.h> -#include <bpf/libbpf.h> -#include <bpf/bpf.h> -#include "runqslower.h" -#include "runqslower.skel.h" - -struct env { - pid_t pid; - __u64 min_us; - bool verbose; -} env = { - .min_us = 10000, -}; - -const char *argp_program_version = "runqslower 0.1"; -const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; -const char argp_program_doc[] = -"runqslower Trace long process scheduling delays.\n" -" For Linux, uses eBPF, BPF CO-RE, libbpf, BTF.\n" -"\n" -"This script traces high scheduling delays between tasks being\n" -"ready to run and them running on CPU after that.\n" -"\n" -"USAGE: runqslower [-p PID] [min_us]\n" -"\n" -"EXAMPLES:\n" -" runqslower # trace run queue latency higher than 10000 us (default)\n" -" runqslower 1000 # trace run queue latency higher than 1000 us\n" -" runqslower -p 123 # trace pid 123 only\n"; - -static const struct argp_option opts[] = { - { "pid", 'p', "PID", 0, "Process PID to trace"}, - { "verbose", 'v', NULL, 0, "Verbose debug output" }, - {}, -}; - -static error_t parse_arg(int key, char *arg, struct argp_state *state) -{ - static int pos_args; - int pid; - long long min_us; - - switch (key) { - case 'v': - env.verbose = true; - break; - case 'p': - errno = 0; - pid = strtol(arg, NULL, 10); - if (errno || pid <= 0) { - fprintf(stderr, "Invalid PID: %s\n", arg); - argp_usage(state); - } - env.pid = pid; - break; - case ARGP_KEY_ARG: - if (pos_args++) { - fprintf(stderr, - "Unrecognized positional argument: %s\n", arg); - argp_usage(state); - } - errno = 0; - min_us = strtoll(arg, NULL, 10); - if (errno || min_us <= 0) { - fprintf(stderr, "Invalid delay (in us): %s\n", arg); - argp_usage(state); - } - env.min_us = min_us; - break; - default: - return ARGP_ERR_UNKNOWN; - } - return 0; -} - -int libbpf_print_fn(enum libbpf_print_level level, - const char *format, va_list args) -{ - if (level == LIBBPF_DEBUG && !env.verbose) - return 0; - return vfprintf(stderr, format, args); -} - -void handle_event(void *ctx, int cpu, void *data, __u32 data_sz) -{ - const struct runq_event *e = data; - struct tm *tm; - char ts[32]; - time_t t; - - time(&t); - tm = localtime(&t); - strftime(ts, sizeof(ts), "%H:%M:%S", tm); - printf("%-8s %-16s %-6d %14llu\n", ts, e->task, e->pid, e->delta_us); -} - -void handle_lost_events(void *ctx, int cpu, __u64 lost_cnt) -{ - printf("Lost %llu events on CPU #%d!\n", lost_cnt, cpu); -} - -int main(int argc, char **argv) -{ - static const struct argp argp = { - .options = opts, - .parser = parse_arg, - .doc = argp_program_doc, - }; - struct perf_buffer *pb = NULL; - struct runqslower_bpf *obj; - int err; - - err = argp_parse(&argp, argc, argv, 0, NULL, NULL); - if (err) - return err; - - libbpf_set_print(libbpf_print_fn); - - /* Use libbpf 1.0 API mode */ - libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - - obj = runqslower_bpf__open(); - if (!obj) { - fprintf(stderr, "failed to open and/or load BPF object\n"); - return 1; - } - - /* initialize global data (filtering options) */ - obj->rodata->targ_pid = env.pid; - obj->rodata->min_us = env.min_us; - - err = runqslower_bpf__load(obj); - if (err) { - fprintf(stderr, "failed to load BPF object: %d\n", err); - goto cleanup; - } - - err = runqslower_bpf__attach(obj); - if (err) { - fprintf(stderr, "failed to attach BPF programs\n"); - goto cleanup; - } - - printf("Tracing run queue latency higher than %llu us\n", env.min_us); - printf("%-8s %-16s %-6s %14s\n", "TIME", "COMM", "PID", "LAT(us)"); - - pb = perf_buffer__new(bpf_map__fd(obj->maps.events), 64, - handle_event, handle_lost_events, NULL, NULL); - err = libbpf_get_error(pb); - if (err) { - pb = NULL; - fprintf(stderr, "failed to open perf buffer: %d\n", err); - goto cleanup; - } - - while ((err = perf_buffer__poll(pb, 100)) >= 0) - ; - printf("Error polling perf buffer: %d\n", err); - -cleanup: - perf_buffer__free(pb); - runqslower_bpf__destroy(obj); - - return err != 0; -} diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h deleted file mode 100644 index 4f70f07200c2..000000000000 --- a/tools/bpf/runqslower/runqslower.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ -#ifndef __RUNQSLOWER_H -#define __RUNQSLOWER_H - -#define TASK_COMM_LEN 16 - -struct runq_event { - char task[TASK_COMM_LEN]; - __u64 delta_us; - pid_t pid; -}; - -#endif /* __RUNQSLOWER_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6829936d33f5..be7d8e060e10 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1026,6 +1026,7 @@ enum bpf_map_type { BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, BPF_MAP_TYPE_ARENA, + BPF_MAP_TYPE_INSN_ARRAY, __MAX_BPF_MAP_TYPE }; @@ -1430,6 +1431,9 @@ enum { /* Do not translate kernel bpf_arena pointers to user pointers */ BPF_F_NO_USER_CONV = (1U << 18), + +/* Enable BPF ringbuf overwrite mode */ + BPF_F_RB_OVERWRITE = (1U << 19), }; /* Flags for BPF_PROG_QUERY. */ @@ -5618,7 +5622,7 @@ union bpf_attr { * Return * *sk* if casting is valid, or **NULL** otherwise. * - * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr) + * long bpf_dynptr_from_mem(void *data, u64 size, u64 flags, struct bpf_dynptr *ptr) * Description * Get a dynptr to local memory *data*. * @@ -5661,7 +5665,7 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) + * long bpf_dynptr_read(void *dst, u64 len, const struct bpf_dynptr *src, u64 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. @@ -5671,7 +5675,7 @@ union bpf_attr { * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if * *flags* is not 0. * - * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u64 offset, void *src, u64 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. @@ -5692,7 +5696,7 @@ union bpf_attr { * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs, * other errors correspond to errors returned by **bpf_skb_store_bytes**\ (). * - * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u64 offset, u64 len) * Description * Get a pointer to the underlying dynptr data. * @@ -6231,6 +6235,7 @@ enum { BPF_RB_RING_SIZE = 1, BPF_RB_CONS_POS = 2, BPF_RB_PROD_POS = 3, + BPF_RB_OVERWRITE_POS = 4, }; /* BPF ring buffer constants */ @@ -7200,6 +7205,7 @@ enum { TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ + SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */ }; enum { @@ -7645,4 +7651,24 @@ enum bpf_kfunc_flags { BPF_F_PAD_ZEROS = (1ULL << 0), }; +/* + * Values of a BPF_MAP_TYPE_INSN_ARRAY entry must be of this type. + * + * Before the map is used the orig_off field should point to an + * instruction inside the program being loaded. The other fields + * must be set to 0. + * + * After the program is loaded, the xlated_off will be adjusted + * by the verifier to point to the index of the original instruction + * in the xlated program. If the instruction is deleted, it will + * be set to (u32)-1. The jitted_off will be set to the corresponding + * offset in the jitted image of the program. + */ +struct bpf_insn_array_value { + __u32 orig_off; + __u32 xlated_off; + __u32 jitted_off; + __u32 :32; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 48eb49aa03d4..e0b579a1df4f 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NETDEV_H #define _UAPI_LINUX_NETDEV_H @@ -80,6 +81,7 @@ enum netdev_qstats_scope { enum netdev_napi_threaded { NETDEV_NAPI_THREADED_DISABLED, NETDEV_NAPI_THREADED_ENABLED, + NETDEV_NAPI_THREADED_BUSY_POLL, }; enum { diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 339b19797237..b66f5fbfbbb2 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -154,7 +154,7 @@ int bump_rlimit_memlock(void) memlock_bumped = true; - /* zero memlock_rlim_max disables auto-bumping RLIMIT_MEMLOCK */ + /* zero memlock_rlim disables auto-bumping RLIMIT_MEMLOCK */ if (memlock_rlim == 0) return 0; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 18907f0fcf9f..84a4b0abc8be 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1061,7 +1061,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf, b if (base_btf) { btf->base_btf = base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; } if (is_mmap) { @@ -3901,6 +3901,20 @@ err_out: return err; } +/* + * Calculate type signature hash of TYPEDEF, ignoring referenced type IDs, + * as referenced type IDs equivalence is established separately during type + * graph equivalence check algorithm. + */ +static long btf_hash_typedef(struct btf_type *t) +{ + long h; + + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info); + return h; +} + static long btf_hash_common(struct btf_type *t) { long h; @@ -3918,6 +3932,13 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } +/* Check structural compatibility of two TYPEDEF. */ +static bool btf_equal_typedef(struct btf_type *t1, struct btf_type *t2) +{ + return t1->name_off == t2->name_off && + t1->info == t2->info; +} + /* Calculate type signature hash of INT or TAG. */ static long btf_hash_int_decl_tag(struct btf_type *t) { @@ -4844,13 +4865,30 @@ static void btf_dedup_merge_hypot_map(struct btf_dedup *d) } } +static inline long btf_hash_by_kind(struct btf_type *t, __u16 kind) +{ + if (kind == BTF_KIND_TYPEDEF) + return btf_hash_typedef(t); + else + return btf_hash_struct(t); +} + +static inline bool btf_equal_by_kind(struct btf_type *t1, struct btf_type *t2, __u16 kind) +{ + if (kind == BTF_KIND_TYPEDEF) + return btf_equal_typedef(t1, t2); + else + return btf_shallow_equal_struct(t1, t2); +} + /* - * Deduplicate struct/union types. + * Deduplicate struct/union and typedef types. * * For each struct/union type its type signature hash is calculated, taking * into account type's name, size, number, order and names of fields, but * ignoring type ID's referenced from fields, because they might not be deduped - * completely until after reference types deduplication phase. This type hash + * completely until after reference types deduplication phase. For each typedef + * type, the hash is computed based on the type’s name and size. This type hash * is used to iterate over all potential canonical types, sharing same hash. * For each canonical candidate we check whether type graphs that they form * (through referenced types in fields and so on) are equivalent using algorithm @@ -4882,18 +4920,20 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) t = btf_type_by_id(d->btf, type_id); kind = btf_kind(t); - if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) + if (kind != BTF_KIND_STRUCT && + kind != BTF_KIND_UNION && + kind != BTF_KIND_TYPEDEF) return 0; - h = btf_hash_struct(t); + h = btf_hash_by_kind(t, kind); for_each_dedup_cand(d, hash_entry, h) { __u32 cand_id = hash_entry->value; int eq; /* * Even though btf_dedup_is_equiv() checks for - * btf_shallow_equal_struct() internally when checking two - * structs (unions) for equivalence, we need to guard here + * btf_equal_by_kind() internally when checking two + * structs (unions) or typedefs for equivalence, we need to guard here * from picking matching FWD type as a dedup candidate. * This can happen due to hash collision. In such case just * relying on btf_dedup_is_equiv() would lead to potentially @@ -4901,7 +4941,7 @@ static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) * FWD and compatible STRUCT/UNION are considered equivalent. */ cand_type = btf_type_by_id(d->btf, cand_id); - if (!btf_shallow_equal_struct(t, cand_type)) + if (!btf_equal_by_kind(t, cand_type, kind)) continue; btf_dedup_clear_hypot_map(d); @@ -4939,18 +4979,18 @@ static int btf_dedup_struct_types(struct btf_dedup *d) /* * Deduplicate reference type. * - * Once all primitive and struct/union types got deduplicated, we can easily + * Once all primitive, struct/union and typedef types got deduplicated, we can easily * deduplicate all other (reference) BTF types. This is done in two steps: * * 1. Resolve all referenced type IDs into their canonical type IDs. This - * resolution can be done either immediately for primitive or struct/union types - * (because they were deduped in previous two phases) or recursively for + * resolution can be done either immediately for primitive, struct/union, and typedef + * types (because they were deduped in previous two phases) or recursively for * reference types. Recursion will always terminate at either primitive or - * struct/union type, at which point we can "unwind" chain of reference types - * one by one. There is no danger of encountering cycles because in C type - * system the only way to form type cycle is through struct/union, so any chain - * of reference types, even those taking part in a type cycle, will inevitably - * reach struct/union at some point. + * struct/union and typedef types, at which point we can "unwind" chain of reference + * types one by one. There is no danger of encountering cycles in C, as the only way to + * form a type cycle is through struct or union types. Go can form such cycles through + * typedef. Thus, any chain of reference types, even those taking part in a type cycle, + * will inevitably reach a struct/union or typedef type at some point. * * 2. Once all referenced type IDs are resolved into canonical ones, BTF type * becomes "stable", in the sense that no further deduplication will cause @@ -4982,7 +5022,6 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_VOLATILE: case BTF_KIND_RESTRICT: case BTF_KIND_PTR: - case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_TYPE_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); @@ -5818,7 +5857,7 @@ void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) { btf->base_btf = (struct btf *)base_btf; btf->start_id = btf__type_cnt(base_btf); - btf->start_str_off = base_btf->hdr->str_len; + btf->start_str_off = base_btf->hdr->str_len + base_btf->start_str_off; } int btf__relocate(struct btf *btf, const struct btf *base_btf) diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index ccfd905f03df..cc01494d6210 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -94,6 +94,7 @@ LIBBPF_API struct btf *btf__new_empty(void); * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an * ELF BTF section except with a base BTF on top of which split BTF should be * based + * @param base_btf base BTF object * @return new BTF object instance which has to be eventually freed with * **btf__free()** * @@ -115,6 +116,10 @@ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); * When that split BTF is loaded against a (possibly changed) base, this * distilled base BTF will help update references to that (possibly changed) * base BTF. + * @param src_btf source split BTF object + * @param new_base_btf pointer to where the new base BTF object pointer will be stored + * @param new_split_btf pointer to where the new split BTF object pointer will be stored + * @return 0 on success; negative error code, otherwise * * Both the new split and its associated new base BTF must be freed by * the caller. @@ -264,6 +269,9 @@ LIBBPF_API int btf__dedup(struct btf *btf, const struct btf_dedup_opts *opts); * to base BTF kinds, and verify those references are compatible with * *base_btf*; if they are, *btf* is adjusted such that is re-parented to * *base_btf* and type ids and strings are adjusted to accommodate this. + * @param btf split BTF object to relocate + * @param base_btf base BTF object + * @return 0 on success; negative error code, otherwise * * If successful, 0 is returned and **btf** now has **base_btf** as its * base. diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 85abc357da31..3dc8a8078815 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -190,6 +190,7 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf", [BPF_MAP_TYPE_CGRP_STORAGE] = "cgrp_storage", [BPF_MAP_TYPE_ARENA] = "arena", + [BPF_MAP_TYPE_INSN_ARRAY] = "insn_array", }; static const char * const prog_type_name[] = { @@ -369,6 +370,7 @@ enum reloc_type { RELO_EXTERN_CALL, RELO_SUBPROG_ADDR, RELO_CORE, + RELO_INSN_ARRAY, }; struct reloc_desc { @@ -379,7 +381,16 @@ struct reloc_desc { struct { int map_idx; int sym_off; - int ext_idx; + /* + * The following two fields can be unionized, as the + * ext_idx field is used for extern symbols, and the + * sym_size is used for jump tables, which are never + * extern + */ + union { + int ext_idx; + int sym_size; + }; }; }; }; @@ -421,6 +432,11 @@ struct bpf_sec_def { libbpf_prog_attach_fn_t prog_attach_fn; }; +struct bpf_light_subprog { + __u32 sec_insn_off; + __u32 sub_insn_off; +}; + /* * bpf_prog should be a better name but it has been used in * linux/filter.h. @@ -494,6 +510,9 @@ struct bpf_program { __u32 line_info_cnt; __u32 prog_flags; __u8 hash[SHA256_DIGEST_LENGTH]; + + struct bpf_light_subprog *subprogs; + __u32 subprog_cnt; }; struct bpf_struct_ops { @@ -667,6 +686,7 @@ struct elf_state { int symbols_shndx; bool has_st_ops; int arena_data_shndx; + int jumptables_data_shndx; }; struct usdt_manager; @@ -738,6 +758,16 @@ struct bpf_object { void *arena_data; size_t arena_data_sz; + void *jumptables_data; + size_t jumptables_data_sz; + + struct { + struct bpf_program *prog; + int sym_off; + int fd; + } *jumptable_maps; + size_t jumptable_map_cnt; + struct kern_feature_cache *feat_cache; char *token_path; int token_fd; @@ -764,6 +794,7 @@ void bpf_program__unload(struct bpf_program *prog) zfree(&prog->func_info); zfree(&prog->line_info); + zfree(&prog->subprogs); } static void bpf_program__exit(struct bpf_program *prog) @@ -2996,7 +3027,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, scn = elf_sec_by_idx(obj, obj->efile.btf_maps_shndx); data = elf_sec_data(obj, scn); - if (!scn || !data) { + if (!data) { pr_warn("elf: failed to get %s map definitions for %s\n", MAPS_ELF_SEC, obj->path); return -EINVAL; @@ -3942,6 +3973,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } else if (strcmp(name, ARENA_SEC) == 0) { obj->efile.arena_data = data; obj->efile.arena_data_shndx = idx; + } else if (strcmp(name, JUMPTABLES_SEC) == 0) { + obj->jumptables_data = malloc(data->d_size); + if (!obj->jumptables_data) + return -ENOMEM; + memcpy(obj->jumptables_data, data->d_buf, data->d_size); + obj->jumptables_data_sz = data->d_size; + obj->efile.jumptables_data_shndx = idx; } else { pr_info("elf: skipping unrecognized data section(%d) %s\n", idx, name); @@ -4634,6 +4672,16 @@ static int bpf_program__record_reloc(struct bpf_program *prog, return 0; } + /* jump table data relocation */ + if (shdr_idx == obj->efile.jumptables_data_shndx) { + reloc_desc->type = RELO_INSN_ARRAY; + reloc_desc->insn_idx = insn_idx; + reloc_desc->map_idx = -1; + reloc_desc->sym_off = sym->st_value; + reloc_desc->sym_size = sym->st_size; + return 0; + } + /* generic map reference relocation */ if (type == LIBBPF_MAP_UNSPEC) { if (!bpf_object__shndx_is_maps(obj, shdr_idx)) { @@ -6144,6 +6192,157 @@ static void poison_kfunc_call(struct bpf_program *prog, int relo_idx, insn->imm = POISON_CALL_KFUNC_BASE + ext_idx; } +static int find_jt_map(struct bpf_object *obj, struct bpf_program *prog, int sym_off) +{ + size_t i; + + for (i = 0; i < obj->jumptable_map_cnt; i++) { + /* + * This might happen that same offset is used for two different + * programs (as jump tables can be the same). However, for + * different programs different maps should be created. + */ + if (obj->jumptable_maps[i].sym_off == sym_off && + obj->jumptable_maps[i].prog == prog) + return obj->jumptable_maps[i].fd; + } + + return -ENOENT; +} + +static int add_jt_map(struct bpf_object *obj, struct bpf_program *prog, int sym_off, int map_fd) +{ + size_t cnt = obj->jumptable_map_cnt; + size_t size = sizeof(obj->jumptable_maps[0]); + void *tmp; + + tmp = libbpf_reallocarray(obj->jumptable_maps, cnt + 1, size); + if (!tmp) + return -ENOMEM; + + obj->jumptable_maps = tmp; + obj->jumptable_maps[cnt].prog = prog; + obj->jumptable_maps[cnt].sym_off = sym_off; + obj->jumptable_maps[cnt].fd = map_fd; + obj->jumptable_map_cnt++; + + return 0; +} + +static int find_subprog_idx(struct bpf_program *prog, int insn_idx) +{ + int i; + + for (i = prog->subprog_cnt - 1; i >= 0; i--) { + if (insn_idx >= prog->subprogs[i].sub_insn_off) + return i; + } + + return -1; +} + +static int create_jt_map(struct bpf_object *obj, struct bpf_program *prog, struct reloc_desc *relo) +{ + const __u32 jt_entry_size = 8; + int sym_off = relo->sym_off; + int jt_size = relo->sym_size; + __u32 max_entries = jt_size / jt_entry_size; + __u32 value_size = sizeof(struct bpf_insn_array_value); + struct bpf_insn_array_value val = {}; + int subprog_idx; + int map_fd, err; + __u64 insn_off; + __u64 *jt; + __u32 i; + + map_fd = find_jt_map(obj, prog, sym_off); + if (map_fd >= 0) + return map_fd; + + if (sym_off % jt_entry_size) { + pr_warn("map '.jumptables': jumptable start %d should be multiple of %u\n", + sym_off, jt_entry_size); + return -EINVAL; + } + + if (jt_size % jt_entry_size) { + pr_warn("map '.jumptables': jumptable size %d should be multiple of %u\n", + jt_size, jt_entry_size); + return -EINVAL; + } + + map_fd = bpf_map_create(BPF_MAP_TYPE_INSN_ARRAY, ".jumptables", + 4, value_size, max_entries, NULL); + if (map_fd < 0) + return map_fd; + + if (!obj->jumptables_data) { + pr_warn("map '.jumptables': ELF file is missing jump table data\n"); + err = -EINVAL; + goto err_close; + } + if (sym_off + jt_size > obj->jumptables_data_sz) { + pr_warn("map '.jumptables': jumptables_data size is %zd, trying to access %d\n", + obj->jumptables_data_sz, sym_off + jt_size); + err = -EINVAL; + goto err_close; + } + + subprog_idx = -1; /* main program */ + if (relo->insn_idx < 0 || relo->insn_idx >= prog->insns_cnt) { + pr_warn("map '.jumptables': invalid instruction index %d\n", relo->insn_idx); + err = -EINVAL; + goto err_close; + } + if (prog->subprogs) + subprog_idx = find_subprog_idx(prog, relo->insn_idx); + + jt = (__u64 *)(obj->jumptables_data + sym_off); + for (i = 0; i < max_entries; i++) { + /* + * The offset should be made to be relative to the beginning of + * the main function, not the subfunction. + */ + insn_off = jt[i]/sizeof(struct bpf_insn); + if (subprog_idx >= 0) { + insn_off -= prog->subprogs[subprog_idx].sec_insn_off; + insn_off += prog->subprogs[subprog_idx].sub_insn_off; + } else { + insn_off -= prog->sec_insn_off; + } + + /* + * LLVM-generated jump tables contain u64 records, however + * should contain values that fit in u32. + */ + if (insn_off > UINT32_MAX) { + pr_warn("map '.jumptables': invalid jump table value 0x%llx at offset %d\n", + (long long)jt[i], sym_off + i * jt_entry_size); + err = -EINVAL; + goto err_close; + } + + val.orig_off = insn_off; + err = bpf_map_update_elem(map_fd, &i, &val, 0); + if (err) + goto err_close; + } + + err = bpf_map_freeze(map_fd); + if (err) + goto err_close; + + err = add_jt_map(obj, prog, sym_off, map_fd); + if (err) + goto err_close; + + return map_fd; + +err_close: + close(map_fd); + return err; +} + /* Relocate data references within program code: * - map references; * - global variable references; @@ -6235,6 +6434,20 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_CORE: /* will be handled by bpf_program_record_relos() */ break; + case RELO_INSN_ARRAY: { + int map_fd; + + map_fd = create_jt_map(obj, prog, relo); + if (map_fd < 0) { + pr_warn("prog '%s': relo #%d: can't create jump table: sym_off %u\n", + prog->name, i, relo->sym_off); + return map_fd; + } + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn->imm = map_fd; + insn->off = 0; + } + break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", prog->name, i, relo->type); @@ -6432,36 +6645,62 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra return 0; } +static int save_subprog_offsets(struct bpf_program *main_prog, struct bpf_program *subprog) +{ + size_t size = sizeof(main_prog->subprogs[0]); + int cnt = main_prog->subprog_cnt; + void *tmp; + + tmp = libbpf_reallocarray(main_prog->subprogs, cnt + 1, size); + if (!tmp) + return -ENOMEM; + + main_prog->subprogs = tmp; + main_prog->subprogs[cnt].sec_insn_off = subprog->sec_insn_off; + main_prog->subprogs[cnt].sub_insn_off = subprog->sub_insn_off; + main_prog->subprog_cnt++; + + return 0; +} + static int bpf_object__append_subprog_code(struct bpf_object *obj, struct bpf_program *main_prog, struct bpf_program *subprog) { - struct bpf_insn *insns; - size_t new_cnt; - int err; + struct bpf_insn *insns; + size_t new_cnt; + int err; - subprog->sub_insn_off = main_prog->insns_cnt; + subprog->sub_insn_off = main_prog->insns_cnt; - new_cnt = main_prog->insns_cnt + subprog->insns_cnt; - insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); - if (!insns) { - pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); - return -ENOMEM; - } - main_prog->insns = insns; - main_prog->insns_cnt = new_cnt; + new_cnt = main_prog->insns_cnt + subprog->insns_cnt; + insns = libbpf_reallocarray(main_prog->insns, new_cnt, sizeof(*insns)); + if (!insns) { + pr_warn("prog '%s': failed to realloc prog code\n", main_prog->name); + return -ENOMEM; + } + main_prog->insns = insns; + main_prog->insns_cnt = new_cnt; - memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, - subprog->insns_cnt * sizeof(*insns)); + memcpy(main_prog->insns + subprog->sub_insn_off, subprog->insns, + subprog->insns_cnt * sizeof(*insns)); - pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", - main_prog->name, subprog->insns_cnt, subprog->name); + pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", + main_prog->name, subprog->insns_cnt, subprog->name); - /* The subprog insns are now appended. Append its relos too. */ - err = append_subprog_relos(main_prog, subprog); - if (err) - return err; - return 0; + /* The subprog insns are now appended. Append its relos too. */ + err = append_subprog_relos(main_prog, subprog); + if (err) + return err; + + err = save_subprog_offsets(main_prog, subprog); + if (err) { + pr_warn("prog '%s': failed to add subprog offsets: %s\n", + main_prog->name, errstr(err)); + return err; + } + + return 0; } static int @@ -9228,6 +9467,13 @@ void bpf_object__close(struct bpf_object *obj) zfree(&obj->arena_data); + zfree(&obj->jumptables_data); + obj->jumptables_data_sz = 0; + + for (i = 0; i < obj->jumptable_map_cnt; i++) + close(obj->jumptable_maps[i].fd); + zfree(&obj->jumptable_maps); + free(obj); } @@ -13854,8 +14100,8 @@ int bpf_program__set_attach_target(struct bpf_program *prog, return libbpf_err(-EINVAL); if (attach_prog_fd && !attach_func_name) { - /* remember attach_prog_fd and let bpf_program__load() find - * BTF ID during the program load + /* Store attach_prog_fd. The BTF ID will be resolved later during + * the normal object/program load phase. */ prog->attach_prog_fd = attach_prog_fd; return 0; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 5118d0a90e24..65e68e964b89 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -448,7 +448,7 @@ LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); /** * @brief **bpf_program__unpin()** unpins the BPF program from a file - * in the BPFFS specified by a path. This decrements the programs + * in the BPFFS specified by a path. This decrements program's in-kernel * reference count. * * The file pinning the BPF program can also be unlinked by a different @@ -481,14 +481,12 @@ LIBBPF_API int bpf_link__pin(struct bpf_link *link, const char *path); /** * @brief **bpf_link__unpin()** unpins the BPF link from a file - * in the BPFFS specified by a path. This decrements the links - * reference count. + * in the BPFFS. This decrements link's in-kernel reference count. * * The file pinning the BPF link can also be unlinked by a different * process in which case this function will return an error. * - * @param prog BPF program to unpin - * @param path file path to the pin in a BPF file system + * @param link BPF link to unpin * @return 0, on success; negative error code, otherwise */ LIBBPF_API int bpf_link__unpin(struct bpf_link *link); @@ -995,8 +993,13 @@ LIBBPF_API __u32 bpf_program__line_info_cnt(const struct bpf_program *prog); * - fentry/fexit/fmod_ret; * - lsm; * - freplace. - * @param prog BPF program to set the attach type for - * @param type attach type to set the BPF map to have + * @param prog BPF program to configure; must be not yet loaded. + * @param attach_prog_fd FD of target BPF program (for freplace/extension). + * If >0 and func name omitted, defers BTF ID resolution. + * @param attach_func_name Target function name. Used either with + * attach_prog_fd to find destination BTF type ID in that BPF program, or + * alone (no attach_prog_fd) to resolve kernel (vmlinux/module) BTF ID. + * Must be provided if attach_prog_fd is 0. * @return error code; or 0 if no error occurred. */ LIBBPF_API int @@ -1098,6 +1101,7 @@ LIBBPF_API __u32 bpf_map__value_size(const struct bpf_map *map); /** * @brief **bpf_map__set_value_size()** sets map value size. * @param map the BPF map instance + * @param size the new value size * @return 0, on success; negative error, otherwise * * There is a special case for maps with associated memory-mapped regions, like @@ -1202,7 +1206,7 @@ LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map); * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__lookup_elem()** is high-level equivalent of @@ -1226,7 +1230,7 @@ LIBBPF_API int bpf_map__lookup_elem(const struct bpf_map *map, * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__update_elem()** is high-level equivalent of @@ -1242,7 +1246,7 @@ LIBBPF_API int bpf_map__update_elem(const struct bpf_map *map, * @param map BPF map to delete element from * @param key pointer to memory containing bytes of the key * @param key_sz size in bytes of key data, needs to match BPF map definition's **key_size** - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__delete_elem()** is high-level equivalent of @@ -1265,7 +1269,7 @@ LIBBPF_API int bpf_map__delete_elem(const struct bpf_map *map, * per-CPU values value size has to be aligned up to closest 8 bytes for * alignment reasons, so expected size is: `round_up(value_size, 8) * * libbpf_num_possible_cpus()`. - * @flags extra flags passed to kernel for this operation + * @param flags extra flags passed to kernel for this operation * @return 0, on success; negative error, otherwise * * **bpf_map__lookup_and_delete_elem()** is high-level equivalent of @@ -1637,6 +1641,7 @@ struct perf_buffer_opts { * @param sample_cb function called on each received data record * @param lost_cb function called when record loss has occurred * @param ctx user-provided extra context passed into *sample_cb* and *lost_cb* + * @param opts optional parameters for the perf buffer, can be null * @return a new instance of struct perf_buffer on success, NULL on error with * *errno* containing an error code */ diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 35b2527bedec..fc59b21b51b5 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -74,6 +74,8 @@ #define ELF64_ST_VISIBILITY(o) ((o) & 0x03) #endif +#define JUMPTABLES_SEC ".jumptables" + #define BTF_INFO_ENC(kind, kind_flag, vlen) \ ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) #define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 9dfbe7750f56..bccf4bb747e1 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -364,6 +364,10 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: break; + case BPF_MAP_TYPE_INSN_ARRAY: + key_size = sizeof(__u32); + value_size = sizeof(struct bpf_insn_array_value); + break; case BPF_MAP_TYPE_UNSPEC: default: return -EOPNOTSUPP; diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 56ae77047bc3..f4403e3cf994 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -2025,6 +2025,9 @@ static int linker_append_elf_sym(struct bpf_linker *linker, struct src_obj *obj, obj->sym_map[src_sym_idx] = dst_sec->sec_sym_idx; return 0; } + + if (strcmp(src_sec->sec_name, JUMPTABLES_SEC) == 0) + goto add_sym; } if (sym_bind == STB_LOCAL) diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index 211df5a93ad9..7736b492f559 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -12,10 +12,13 @@ endif libdir ?= $(prefix)/$(libdir_relative) includedir ?= $(prefix)/include -SUBDIRS = lib generated samples +SPECDIR=../../../Documentation/netlink/specs + +SUBDIRS = lib generated samples ynltool tests all: $(SUBDIRS) libynl.a +ynltool: | lib generated libynl.a samples: | lib generated libynl.a: | lib generated @echo -e "\tAR $@" @@ -48,5 +51,27 @@ install: libynl.a lib/*.h @echo -e "\tINSTALL pyynl" @pip install --prefix=$(DESTDIR)$(prefix) . @make -C generated install + @make -C tests install + +run_tests: + @$(MAKE) -C tests run_tests + +lint: + yamllint $(SPECDIR) + +schema_check: + @N=1; \ + for spec in $(SPECDIR)/*.yaml ; do \ + NAME=$$(basename $$spec) ; \ + OUTPUT=$$(./pyynl/cli.py --spec $$spec --validate) ; \ + if [ $$? -eq 0 ] ; then \ + echo "ok $$N $$NAME schema validation" ; \ + else \ + echo "not ok $$N $$NAME schema validation" ; \ + echo "$$OUTPUT" ; \ + echo ; \ + fi ; \ + N=$$((N+1)) ; \ + done -.PHONY: all clean distclean install $(SUBDIRS) +.PHONY: all clean distclean install run_tests lint schema_check $(SUBDIRS) diff --git a/tools/net/ynl/pyynl/cli.py b/tools/net/ynl/pyynl/cli.py index 8c192e900bd3..af02a5b7e5a2 100755 --- a/tools/net/ynl/pyynl/cli.py +++ b/tools/net/ynl/pyynl/cli.py @@ -7,9 +7,10 @@ import os import pathlib import pprint import sys +import textwrap sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix()) -from lib import YnlFamily, Netlink, NlError +from lib import YnlFamily, Netlink, NlError, SpecFamily sys_schema_dir='/usr/share/ynl' relative_schema_dir='../../../../Documentation/netlink' @@ -39,6 +40,60 @@ class YnlEncoder(json.JSONEncoder): return json.JSONEncoder.default(self, obj) +def print_attr_list(ynl, attr_names, attr_set, indent=2): + """Print a list of attributes with their types and documentation.""" + prefix = ' ' * indent + for attr_name in attr_names: + if attr_name in attr_set.attrs: + attr = attr_set.attrs[attr_name] + attr_info = f'{prefix}- {attr_name}: {attr.type}' + if 'enum' in attr.yaml: + enum_name = attr.yaml['enum'] + attr_info += f" (enum: {enum_name})" + # Print enum values if available + if enum_name in ynl.consts: + const = ynl.consts[enum_name] + enum_values = list(const.entries.keys()) + attr_info += f"\n{prefix} {const.type.capitalize()}: {', '.join(enum_values)}" + + # Show nested attributes reference and recursively display them + nested_set_name = None + if attr.type == 'nest' and 'nested-attributes' in attr.yaml: + nested_set_name = attr.yaml['nested-attributes'] + attr_info += f" -> {nested_set_name}" + + if attr.yaml.get('doc'): + doc_text = textwrap.indent(attr.yaml['doc'], prefix + ' ') + attr_info += f"\n{doc_text}" + print(attr_info) + + # Recursively show nested attributes + if nested_set_name in ynl.attr_sets: + nested_set = ynl.attr_sets[nested_set_name] + # Filter out 'unspec' and other unused attrs + nested_names = [n for n in nested_set.attrs.keys() + if nested_set.attrs[n].type != 'unused'] + if nested_names: + print_attr_list(ynl, nested_names, nested_set, indent + 4) + + +def print_mode_attrs(ynl, mode, mode_spec, attr_set, print_request=True): + """Print a given mode (do/dump/event/notify).""" + mode_title = mode.capitalize() + + if print_request and 'request' in mode_spec and 'attributes' in mode_spec['request']: + print(f'\n{mode_title} request attributes:') + print_attr_list(ynl, mode_spec['request']['attributes'], attr_set) + + if 'reply' in mode_spec and 'attributes' in mode_spec['reply']: + print(f'\n{mode_title} reply attributes:') + print_attr_list(ynl, mode_spec['reply']['attributes'], attr_set) + + if 'attributes' in mode_spec: + print(f'\n{mode_title} attributes:') + print_attr_list(ynl, mode_spec['attributes'], attr_set) + + def main(): description = """ YNL CLI utility - a general purpose netlink utility that uses YAML @@ -70,6 +125,9 @@ def main(): group.add_argument('--dump', dest='dump', metavar='DUMP-OPERATION', type=str) group.add_argument('--list-ops', action='store_true') group.add_argument('--list-msgs', action='store_true') + group.add_argument('--list-attrs', dest='list_attrs', metavar='OPERATION', type=str, + help='List attributes for an operation') + group.add_argument('--validate', action='store_true') parser.add_argument('--duration', dest='duration', type=int, help='when subscribed, watch for DURATION seconds') @@ -111,15 +169,25 @@ def main(): if args.family: spec = f"{spec_dir()}/{args.family}.yaml" - if args.schema is None and spec.startswith(sys_schema_dir): - args.schema = '' # disable schema validation when installed - if args.process_unknown is None: - args.process_unknown = True else: spec = args.spec if not os.path.isfile(spec): raise Exception(f"Spec file {spec} does not exist") + if args.validate: + try: + SpecFamily(spec, args.schema) + except Exception as error: + print(error) + exit(1) + return + + if args.family: # set behaviour when using installed specs + if args.schema is None and spec.startswith(sys_schema_dir): + args.schema = '' # disable schema validation when installed + if args.process_unknown is None: + args.process_unknown = True + ynl = YnlFamily(spec, args.schema, args.process_unknown, recv_size=args.dbg_small_recv) if args.dbg_small_recv: @@ -135,6 +203,28 @@ def main(): for op_name, op in ynl.msgs.items(): print(op_name, " [", ", ".join(op.modes), "]") + if args.list_attrs: + op = ynl.msgs.get(args.list_attrs) + if not op: + print(f'Operation {args.list_attrs} not found') + exit(1) + + print(f'Operation: {op.name}') + print(op.yaml['doc']) + + for mode in ['do', 'dump', 'event']: + if mode in op.yaml: + print_mode_attrs(ynl, mode, op.yaml[mode], op.attr_set, True) + + if 'notify' in op.yaml: + mode_spec = op.yaml['notify'] + ref_spec = ynl.msgs.get(mode_spec).yaml.get('do') + if ref_spec: + print_mode_attrs(ynl, 'notify', ref_spec, op.attr_set, False) + + if 'mcgrp' in op.yaml: + print(f"\nMulticast group: {op.yaml['mcgrp']}") + try: if args.do: reply = ynl.do(args.do, attrs, args.flags) diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 62383c70ebb9..36d36eb7e3b8 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -100,12 +100,21 @@ class Netlink: 'bitfield32', 'sint', 'uint']) class NlError(Exception): - def __init__(self, nl_msg): - self.nl_msg = nl_msg - self.error = -nl_msg.error - - def __str__(self): - return f"Netlink error: {os.strerror(self.error)}\n{self.nl_msg}" + def __init__(self, nl_msg): + self.nl_msg = nl_msg + self.error = -nl_msg.error + + def __str__(self): + msg = "Netlink error: " + + extack = self.nl_msg.extack.copy() if self.nl_msg.extack else {} + if 'msg' in extack: + msg += extack['msg'] + ': ' + del extack['msg'] + msg += os.strerror(self.error) + if extack: + msg += ' ' + str(extack) + return msg class ConfigError(Exception): @@ -976,6 +985,15 @@ class YnlFamily(SpecFamily): raw = bytes.fromhex(string) else: raw = int(string, 16) + elif attr_spec.display_hint == 'mac': + # Parse MAC address in format "00:11:22:33:44:55" or "001122334455" + if ':' in string: + mac_bytes = [int(x, 16) for x in string.split(':')] + else: + if len(string) % 2 != 0: + raise Exception(f"Invalid MAC address format: {string}") + mac_bytes = [int(string[i:i+2], 16) for i in range(0, len(string), 2)] + raw = bytes(mac_bytes) else: raise Exception(f"Display hint '{attr_spec.display_hint}' not implemented" f" when parsing '{attr_spec['name']}'") @@ -1039,15 +1057,15 @@ class YnlFamily(SpecFamily): self.check_ntf() def operation_do_attributes(self, name): - """ - For a given operation name, find and return a supported - set of attributes (as a dict). - """ - op = self.find_operation(name) - if not op: - return None - - return op['do']['request']['attributes'].copy() + """ + For a given operation name, find and return a supported + set of attributes (as a dict). + """ + op = self.find_operation(name) + if not op: + return None + + return op['do']['request']['attributes'].copy() def _encode_message(self, op, vals, flags, req_seq): nl_flags = Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index aadeb3abcad8..b517d0c605ad 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -1205,7 +1205,7 @@ class SubMessage(SpecSubMessage): class Family(SpecFamily): - def __init__(self, file_name, exclude_ops): + def __init__(self, file_name, exclude_ops, fn_prefix): # Added by resolve: self.c_name = None delattr(self, "c_name") @@ -1237,6 +1237,8 @@ class Family(SpecFamily): else: self.uapi_header_name = self.ident_name + self.fn_prefix = fn_prefix if fn_prefix else f'{self.ident_name}-nl' + def resolve(self): self.resolve_up(super()) @@ -2911,12 +2913,12 @@ def print_kernel_op_table_fwd(family, cw, terminate): continue if 'do' in op: - name = c_lower(f"{family.ident_name}-nl-{op_name}-doit") + name = c_lower(f"{family.fn_prefix}-{op_name}-doit") cw.write_func_prot('int', name, ['struct sk_buff *skb', 'struct genl_info *info'], suffix=';') if 'dump' in op: - name = c_lower(f"{family.ident_name}-nl-{op_name}-dumpit") + name = c_lower(f"{family.fn_prefix}-{op_name}-dumpit") cw.write_func_prot('int', name, ['struct sk_buff *skb', 'struct netlink_callback *cb'], suffix=';') cw.nl() @@ -2942,7 +2944,7 @@ def print_kernel_op_table(family, cw): for x in op['dont-validate']])), ) for op_mode in ['do', 'dump']: if op_mode in op: - name = c_lower(f"{family.ident_name}-nl-{op_name}-{op_mode}it") + name = c_lower(f"{family.fn_prefix}-{op_name}-{op_mode}it") members.append((op_mode + 'it', name)) if family.kernel_policy == 'per-op': struct = Struct(family, op['attribute-set'], @@ -2980,7 +2982,7 @@ def print_kernel_op_table(family, cw): members.append(('validate', ' | '.join([c_upper('genl-dont-validate-' + x) for x in dont_validate])), ) - name = c_lower(f"{family.ident_name}-nl-{op_name}-{op_mode}it") + name = c_lower(f"{family.fn_prefix}-{op_name}-{op_mode}it") if 'pre' in op[op_mode]: members.append((cb_names[op_mode]['pre'], c_lower(op[op_mode]['pre']))) members.append((op_mode + 'it', name)) @@ -3402,6 +3404,7 @@ def main(): help='Do not overwrite the output file if the new output is identical to the old') parser.add_argument('--exclude-op', action='append', default=[]) parser.add_argument('-o', dest='out_file', type=str, default=None) + parser.add_argument('--function-prefix', dest='fn_prefix', type=str) args = parser.parse_args() if args.header is None: @@ -3410,7 +3413,7 @@ def main(): exclude_ops = [re.compile(expr) for expr in args.exclude_op] try: - parsed = Family(args.spec, exclude_ops) + parsed = Family(args.spec, exclude_ops, args.fn_prefix) if parsed.license != '((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)': print('Spec license:', parsed.license) print('License must be: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)') @@ -3430,11 +3433,16 @@ def main(): cw.p("/* Do not edit directly, auto-generated from: */") cw.p(f"/*\t{spec_kernel} */") cw.p(f"/* YNL-GEN {args.mode} {'header' if args.header else 'source'} */") - if args.exclude_op or args.user_header: + if args.exclude_op or args.user_header or args.fn_prefix: line = '' - line += ' --user-header '.join([''] + args.user_header) - line += ' --exclude-op '.join([''] + args.exclude_op) + if args.user_header: + line += ' --user-header '.join([''] + args.user_header) + if args.exclude_op: + line += ' --exclude-op '.join([''] + args.exclude_op) + if args.fn_prefix: + line += f' --function-prefix {args.fn_prefix}' cw.p(f'/* YNL-ARG{line} */') + cw.p('/* To regenerate run: tools/net/ynl/ynl-regen.sh */') cw.nl() if args.mode == 'uapi': diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore index 7f5fca7682d7..05087ee323ba 100644 --- a/tools/net/ynl/samples/.gitignore +++ b/tools/net/ynl/samples/.gitignore @@ -7,3 +7,4 @@ rt-addr rt-link rt-route tc +tc-filter-add diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile index c9494a564da4..d76cbd41cbb1 100644 --- a/tools/net/ynl/samples/Makefile +++ b/tools/net/ynl/samples/Makefile @@ -19,6 +19,7 @@ include $(wildcard *.d) all: $(BINS) CFLAGS_page-pool=$(CFLAGS_netdev) +CFLAGS_tc-filter-add:=$(CFLAGS_tc) $(BINS): ../lib/ynl.a ../generated/protos.a $(SRCS) @echo -e '\tCC sample $@' diff --git a/tools/net/ynl/samples/page-pool.c b/tools/net/ynl/samples/page-pool.c deleted file mode 100644 index e5d521320fbf..000000000000 --- a/tools/net/ynl/samples/page-pool.c +++ /dev/null @@ -1,149 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE - -#include <stdio.h> -#include <string.h> - -#include <ynl.h> - -#include <net/if.h> - -#include "netdev-user.h" - -struct stat { - unsigned int ifc; - - struct { - unsigned int cnt; - size_t refs, bytes; - } live[2]; - - size_t alloc_slow, alloc_fast, recycle_ring, recycle_cache; -}; - -struct stats_array { - unsigned int i, max; - struct stat *s; -}; - -static struct stat *find_ifc(struct stats_array *a, unsigned int ifindex) -{ - unsigned int i; - - for (i = 0; i < a->i; i++) { - if (a->s[i].ifc == ifindex) - return &a->s[i]; - } - - a->i++; - if (a->i == a->max) { - a->max *= 2; - a->s = reallocarray(a->s, a->max, sizeof(*a->s)); - } - a->s[i].ifc = ifindex; - return &a->s[i]; -} - -static void count(struct stat *s, unsigned int l, - struct netdev_page_pool_get_rsp *pp) -{ - s->live[l].cnt++; - if (pp->_present.inflight) - s->live[l].refs += pp->inflight; - if (pp->_present.inflight_mem) - s->live[l].bytes += pp->inflight_mem; -} - -int main(int argc, char **argv) -{ - struct netdev_page_pool_stats_get_list *pp_stats; - struct netdev_page_pool_get_list *pools; - struct stats_array a = {}; - struct ynl_error yerr; - struct ynl_sock *ys; - - ys = ynl_sock_create(&ynl_netdev_family, &yerr); - if (!ys) { - fprintf(stderr, "YNL: %s\n", yerr.msg); - return 1; - } - - a.max = 128; - a.s = calloc(a.max, sizeof(*a.s)); - if (!a.s) - goto err_close; - - pools = netdev_page_pool_get_dump(ys); - if (!pools) - goto err_free; - - ynl_dump_foreach(pools, pp) { - struct stat *s = find_ifc(&a, pp->ifindex); - - count(s, 1, pp); - if (pp->_present.detach_time) - count(s, 0, pp); - } - netdev_page_pool_get_list_free(pools); - - pp_stats = netdev_page_pool_stats_get_dump(ys); - if (!pp_stats) - goto err_free; - - ynl_dump_foreach(pp_stats, pp) { - struct stat *s = find_ifc(&a, pp->info.ifindex); - - if (pp->_present.alloc_fast) - s->alloc_fast += pp->alloc_fast; - if (pp->_present.alloc_refill) - s->alloc_fast += pp->alloc_refill; - if (pp->_present.alloc_slow) - s->alloc_slow += pp->alloc_slow; - if (pp->_present.recycle_ring) - s->recycle_ring += pp->recycle_ring; - if (pp->_present.recycle_cached) - s->recycle_cache += pp->recycle_cached; - } - netdev_page_pool_stats_get_list_free(pp_stats); - - for (unsigned int i = 0; i < a.i; i++) { - char ifname[IF_NAMESIZE]; - struct stat *s = &a.s[i]; - const char *name; - double recycle; - - if (!s->ifc) { - name = "<orphan>\t"; - } else { - name = if_indextoname(s->ifc, ifname); - if (name) - printf("%8s", name); - printf("[%u]\t", s->ifc); - } - - printf("page pools: %u (zombies: %u)\n", - s->live[1].cnt, s->live[0].cnt); - printf("\t\trefs: %zu bytes: %zu (refs: %zu bytes: %zu)\n", - s->live[1].refs, s->live[1].bytes, - s->live[0].refs, s->live[0].bytes); - - /* We don't know how many pages are sitting in cache and ring - * so we will under-count the recycling rate a bit. - */ - recycle = (double)(s->recycle_ring + s->recycle_cache) / - (s->alloc_fast + s->alloc_slow) * 100; - printf("\t\trecycling: %.1lf%% (alloc: %zu:%zu recycle: %zu:%zu)\n", - recycle, s->alloc_slow, s->alloc_fast, - s->recycle_ring, s->recycle_cache); - } - - ynl_sock_destroy(ys); - return 0; - -err_free: - free(a.s); -err_close: - fprintf(stderr, "YNL: %s\n", ys->err.msg); - ynl_sock_destroy(ys); - return 2; -} diff --git a/tools/net/ynl/samples/tc-filter-add.c b/tools/net/ynl/samples/tc-filter-add.c new file mode 100644 index 000000000000..97871e9e9edc --- /dev/null +++ b/tools/net/ynl/samples/tc-filter-add.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> +#include <stdlib.h> +#include <arpa/inet.h> +#include <linux/pkt_sched.h> +#include <linux/tc_act/tc_vlan.h> +#include <linux/tc_act/tc_gact.h> +#include <linux/if_ether.h> +#include <net/if.h> + +#include <ynl.h> + +#include "tc-user.h" + +#define TC_HANDLE (0xFFFF << 16) + +const char *vlan_act_name(struct tc_vlan *p) +{ + switch (p->v_action) { + case TCA_VLAN_ACT_POP: + return "pop"; + case TCA_VLAN_ACT_PUSH: + return "push"; + case TCA_VLAN_ACT_MODIFY: + return "modify"; + default: + break; + } + + return "not supported"; +} + +const char *gact_act_name(struct tc_gact *p) +{ + switch (p->action) { + case TC_ACT_SHOT: + return "drop"; + case TC_ACT_OK: + return "ok"; + case TC_ACT_PIPE: + return "pipe"; + default: + break; + } + + return "not supported"; +} + +static void print_vlan(struct tc_act_vlan_attrs *vlan) +{ + printf("%s ", vlan_act_name(vlan->parms)); + if (vlan->_present.push_vlan_id) + printf("id %u ", vlan->push_vlan_id); + if (vlan->_present.push_vlan_protocol) + printf("protocol %#x ", ntohs(vlan->push_vlan_protocol)); + if (vlan->_present.push_vlan_priority) + printf("priority %u ", vlan->push_vlan_priority); +} + +static void print_gact(struct tc_act_gact_attrs *gact) +{ + struct tc_gact *p = gact->parms; + + printf("%s ", gact_act_name(p)); +} + +static void flower_print(struct tc_flower_attrs *flower, const char *kind) +{ + struct tc_act_attrs *a; + unsigned int i; + + printf("%s:\n", kind); + + if (flower->_present.key_vlan_id) + printf(" vlan_id: %u\n", flower->key_vlan_id); + if (flower->_present.key_vlan_prio) + printf(" vlan_prio: %u\n", flower->key_vlan_prio); + if (flower->_present.key_num_of_vlans) + printf(" num_of_vlans: %u\n", flower->key_num_of_vlans); + + for (i = 0; i < flower->_count.act; i++) { + a = &flower->act[i]; + printf("action order: %i %s ", i + 1, a->kind); + if (a->options._present.vlan) + print_vlan(&a->options.vlan); + else if (a->options._present.gact) + print_gact(&a->options.gact); + printf("\n"); + } + printf("\n"); +} + +static void tc_filter_print(struct tc_gettfilter_rsp *f) +{ + struct tc_options_msg *opt = &f->options; + + if (opt->_present.flower) + flower_print(&opt->flower, f->kind); + else if (f->_len.kind) + printf("%s pref %u proto: %#x\n", f->kind, + (f->_hdr.tcm_info >> 16), + ntohs(TC_H_MIN(f->_hdr.tcm_info))); +} + +static int tc_filter_add(struct ynl_sock *ys, int ifi) +{ + struct tc_newtfilter_req *req; + struct tc_act_attrs *acts; + struct tc_vlan p = { + .action = TC_ACT_PIPE, + .v_action = TCA_VLAN_ACT_PUSH + }; + __u16 flags = NLM_F_REQUEST | NLM_F_EXCL | NLM_F_CREATE; + int ret; + + req = tc_newtfilter_req_alloc(); + if (!req) { + fprintf(stderr, "tc_newtfilter_req_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + acts = tc_act_attrs_alloc(3); + if (!acts) { + fprintf(stderr, "tc_act_attrs_alloc\n"); + tc_newtfilter_req_free(req); + return -1; + } + memset(acts, 0, sizeof(*acts) * 3); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + req->_hdr.tcm_info = TC_H_MAKE(1 << 16, htons(ETH_P_8021Q)); + req->chain = 0; + + tc_newtfilter_req_set_nlflags(req, flags); + tc_newtfilter_req_set_kind(req, "flower"); + tc_newtfilter_req_set_options_flower_key_vlan_id(req, 100); + tc_newtfilter_req_set_options_flower_key_vlan_prio(req, 5); + tc_newtfilter_req_set_options_flower_key_num_of_vlans(req, 3); + + __tc_newtfilter_req_set_options_flower_act(req, acts, 3); + + /* Skip action at index 0 because in TC, the action array + * index starts at 1, with each index defining the action's + * order. In contrast, in YNL indexed arrays start at index 0. + */ + tc_act_attrs_set_kind(&acts[1], "vlan"); + tc_act_attrs_set_options_vlan_parms(&acts[1], &p, sizeof(p)); + tc_act_attrs_set_options_vlan_push_vlan_id(&acts[1], 200); + tc_act_attrs_set_kind(&acts[2], "vlan"); + tc_act_attrs_set_options_vlan_parms(&acts[2], &p, sizeof(p)); + tc_act_attrs_set_options_vlan_push_vlan_id(&acts[2], 300); + + tc_newtfilter_req_set_options_flower_flags(req, 0); + tc_newtfilter_req_set_options_flower_key_eth_type(req, htons(0x8100)); + + ret = tc_newtfilter(ys, req); + if (ret) + fprintf(stderr, "tc_newtfilter: %s\n", ys->err.msg); + + tc_newtfilter_req_free(req); + + return ret; +} + +static int tc_filter_show(struct ynl_sock *ys, int ifi) +{ + struct tc_gettfilter_req_dump *req; + struct tc_gettfilter_list *rsp; + + req = tc_gettfilter_req_dump_alloc(); + if (!req) { + fprintf(stderr, "tc_gettfilter_req_dump_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + req->_present.chain = 1; + req->chain = 0; + + rsp = tc_gettfilter_dump(ys, req); + tc_gettfilter_req_dump_free(req); + if (!rsp) { + fprintf(stderr, "YNL: %s\n", ys->err.msg); + return -1; + } + + if (ynl_dump_empty(rsp)) + fprintf(stderr, "Error: no filters reported\n"); + else + ynl_dump_foreach(rsp, flt) tc_filter_print(flt); + + tc_gettfilter_list_free(rsp); + + return 0; +} + +static int tc_filter_del(struct ynl_sock *ys, int ifi) +{ + struct tc_deltfilter_req *req; + __u16 flags = NLM_F_REQUEST; + int ret; + + req = tc_deltfilter_req_alloc(); + if (!req) { + fprintf(stderr, "tc_deltfilter_req_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + req->_hdr.tcm_info = TC_H_MAKE(1 << 16, htons(ETH_P_8021Q)); + tc_deltfilter_req_set_nlflags(req, flags); + + ret = tc_deltfilter(ys, req); + if (ret) + fprintf(stderr, "tc_deltfilter failed: %s\n", ys->err.msg); + + tc_deltfilter_req_free(req); + + return ret; +} + +static int tc_clsact_add(struct ynl_sock *ys, int ifi) +{ + struct tc_newqdisc_req *req; + __u16 flags = NLM_F_REQUEST | NLM_F_EXCL | NLM_F_CREATE; + int ret; + + req = tc_newqdisc_req_alloc(); + if (!req) { + fprintf(stderr, "tc_newqdisc_req_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_CLSACT; + req->_hdr.tcm_handle = TC_HANDLE; + tc_newqdisc_req_set_nlflags(req, flags); + tc_newqdisc_req_set_kind(req, "clsact"); + + ret = tc_newqdisc(ys, req); + if (ret) + fprintf(stderr, "tc_newqdisc failed: %s\n", ys->err.msg); + + tc_newqdisc_req_free(req); + + return ret; +} + +static int tc_clsact_del(struct ynl_sock *ys, int ifi) +{ + struct tc_delqdisc_req *req; + __u16 flags = NLM_F_REQUEST; + int ret; + + req = tc_delqdisc_req_alloc(); + if (!req) { + fprintf(stderr, "tc_delqdisc_req_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_CLSACT; + req->_hdr.tcm_handle = TC_HANDLE; + tc_delqdisc_req_set_nlflags(req, flags); + + ret = tc_delqdisc(ys, req); + if (ret) + fprintf(stderr, "tc_delqdisc failed: %s\n", ys->err.msg); + + tc_delqdisc_req_free(req); + + return ret; +} + +static int tc_filter_config(struct ynl_sock *ys, int ifi) +{ + int ret = 0; + + if (tc_filter_add(ys, ifi)) + return -1; + + ret = tc_filter_show(ys, ifi); + + if (tc_filter_del(ys, ifi)) + return -1; + + return ret; +} + +int main(int argc, char **argv) +{ + struct ynl_error yerr; + struct ynl_sock *ys; + int ifi, ret = 0; + + if (argc < 2) { + fprintf(stderr, "Usage: %s <interface_name>\n", argv[0]); + return 1; + } + ifi = if_nametoindex(argv[1]); + if (!ifi) { + perror("if_nametoindex"); + return 1; + } + + ys = ynl_sock_create(&ynl_tc_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return 1; + } + + if (tc_clsact_add(ys, ifi)) { + ret = 2; + goto err_destroy; + } + + if (tc_filter_config(ys, ifi)) + ret = 3; + + if (tc_clsact_del(ys, ifi)) + ret = 4; + +err_destroy: + ynl_sock_destroy(ys); + return ret; +} diff --git a/tools/net/ynl/tests/Makefile b/tools/net/ynl/tests/Makefile new file mode 100644 index 000000000000..c1df2e001255 --- /dev/null +++ b/tools/net/ynl/tests/Makefile @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for YNL tests + +TESTS := \ + test_ynl_cli.sh \ + test_ynl_ethtool.sh \ +# end of TESTS + +all: $(TESTS) + +run_tests: + @for test in $(TESTS); do \ + ./$$test; \ + done + +install: $(TESTS) + @mkdir -p $(DESTDIR)/usr/bin + @mkdir -p $(DESTDIR)/usr/share/kselftest + @cp ../../../testing/selftests/kselftest/ktap_helpers.sh $(DESTDIR)/usr/share/kselftest/ + @for test in $(TESTS); do \ + name=$$(basename $$test .sh); \ + sed -e 's|^ynl=.*|ynl="ynl"|' \ + -e 's|^ynl_ethtool=.*|ynl_ethtool="ynl-ethtool"|' \ + -e 's|KSELFTEST_KTAP_HELPERS=.*|KSELFTEST_KTAP_HELPERS="/usr/share/kselftest/ktap_helpers.sh"|' \ + $$test > $(DESTDIR)/usr/bin/$$name; \ + chmod +x $(DESTDIR)/usr/bin/$$name; \ + done + +clean distclean: + @# Nothing to clean + +.PHONY: all install clean run_tests diff --git a/tools/net/ynl/tests/config b/tools/net/ynl/tests/config new file mode 100644 index 000000000000..339f1309c03f --- /dev/null +++ b/tools/net/ynl/tests/config @@ -0,0 +1,6 @@ +CONFIG_DUMMY=m +CONFIG_INET_DIAG=y +CONFIG_IPV6=y +CONFIG_NET_NS=y +CONFIG_NETDEVSIM=m +CONFIG_VETH=m diff --git a/tools/net/ynl/tests/test_ynl_cli.sh b/tools/net/ynl/tests/test_ynl_cli.sh new file mode 100755 index 000000000000..7c0722a08117 --- /dev/null +++ b/tools/net/ynl/tests/test_ynl_cli.sh @@ -0,0 +1,327 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Test YNL CLI functionality + +# Load KTAP test helpers +KSELFTEST_KTAP_HELPERS="$(dirname "$(realpath "$0")")/../../../testing/selftests/kselftest/ktap_helpers.sh" +# shellcheck source=../../../testing/selftests/kselftest/ktap_helpers.sh +source "$KSELFTEST_KTAP_HELPERS" + +# Default ynl path for direct execution, can be overridden by make install +ynl="../pyynl/cli.py" + +readonly NSIM_ID="1338" +readonly NSIM_DEV_NAME="nsim${NSIM_ID}" +readonly VETH_A="veth_a" +readonly VETH_B="veth_b" + +testns="ynl-$(mktemp -u XXXXXX)" +TESTS_NO=0 + +# Test listing available families +cli_list_families() +{ + if $ynl --list-families &>/dev/null; then + ktap_test_pass "YNL CLI list families" + else + ktap_test_fail "YNL CLI list families" + fi +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test netdev family operations (dev-get, queue-get) +cli_netdev_ops() +{ + local dev_output + local ifindex + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + dev_output=$(ip netns exec "$testns" $ynl --family netdev \ + --do dev-get --json "{\"ifindex\": $ifindex}" 2>/dev/null) + + if ! echo "$dev_output" | grep -q "ifindex"; then + ktap_test_fail "YNL CLI netdev operations (netdev dev-get output missing ifindex)" + return + fi + + if ! ip netns exec "$testns" $ynl --family netdev \ + --dump queue-get --json "{\"ifindex\": $ifindex}" &>/dev/null; then + ktap_test_fail "YNL CLI netdev operations (failed to get netdev queue info)" + return + fi + + ktap_test_pass "YNL CLI netdev operations" +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test ethtool family operations (rings-get, linkinfo-get) +cli_ethtool_ops() +{ + local rings_output + local linkinfo_output + + rings_output=$(ip netns exec "$testns" $ynl --family ethtool \ + --do rings-get --json "{\"header\": {\"dev-name\": \"$NSIM_DEV_NAME\"}}" 2>/dev/null) + + if ! echo "$rings_output" | grep -q "header"; then + ktap_test_fail "YNL CLI ethtool operations (ethtool rings-get output missing header)" + return + fi + + linkinfo_output=$(ip netns exec "$testns" $ynl --family ethtool \ + --do linkinfo-get --json "{\"header\": {\"dev-name\": \"$VETH_A\"}}" 2>/dev/null) + + if ! echo "$linkinfo_output" | grep -q "header"; then + ktap_test_fail "YNL CLI ethtool operations (ethtool linkinfo-get output missing header)" + return + fi + + ktap_test_pass "YNL CLI ethtool operations" +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-route family operations +cli_rt_route_ops() +{ + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-route"; then + ktap_test_skip "YNL CLI rt-route operations (rt-route family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + # Add route: 192.0.2.0/24 dev $dev scope link + if ! ip netns exec "$testns" $ynl --family rt-route --do newroute --create \ + --json "{\"dst\": \"192.0.2.0\", \"oif\": $ifindex, \"rtm-dst-len\": 24, \"rtm-family\": 2, \"rtm-scope\": 253, \"rtm-type\": 1, \"rtm-protocol\": 3, \"rtm-table\": 254}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-route operations (failed to add route)" + return + fi + + local route_output + route_output=$(ip netns exec "$testns" $ynl --family rt-route --dump getroute 2>/dev/null) + if echo "$route_output" | grep -q "192.0.2.0"; then + ktap_test_pass "YNL CLI rt-route operations" + else + ktap_test_fail "YNL CLI rt-route operations (failed to verify route)" + fi + + ip netns exec "$testns" $ynl --family rt-route --do delroute \ + --json "{\"dst\": \"192.0.2.0\", \"oif\": $ifindex, \"rtm-dst-len\": 24, \"rtm-family\": 2, \"rtm-scope\": 253, \"rtm-type\": 1, \"rtm-protocol\": 3, \"rtm-table\": 254}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-addr family operations +cli_rt_addr_ops() +{ + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-addr"; then + ktap_test_skip "YNL CLI rt-addr operations (rt-addr family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + if ! ip netns exec "$testns" $ynl --family rt-addr --do newaddr \ + --json "{\"ifa-index\": $ifindex, \"local\": \"192.0.2.100\", \"ifa-prefixlen\": 24, \"ifa-family\": 2}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-addr operations (failed to add address)" + return + fi + + local addr_output + addr_output=$(ip netns exec "$testns" $ynl --family rt-addr --dump getaddr 2>/dev/null) + if echo "$addr_output" | grep -q "192.0.2.100"; then + ktap_test_pass "YNL CLI rt-addr operations" + else + ktap_test_fail "YNL CLI rt-addr operations (failed to verify address)" + fi + + ip netns exec "$testns" $ynl --family rt-addr --do deladdr \ + --json "{\"ifa-index\": $ifindex, \"local\": \"192.0.2.100\", \"ifa-prefixlen\": 24, \"ifa-family\": 2}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-link family operations +cli_rt_link_ops() +{ + if ! $ynl --list-families 2>/dev/null | grep -q "rt-link"; then + ktap_test_skip "YNL CLI rt-link operations (rt-link family not available)" + return + fi + + if ! ip netns exec "$testns" $ynl --family rt-link --do newlink --create \ + --json "{\"ifname\": \"dummy0\", \"linkinfo\": {\"kind\": \"dummy\"}}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-link operations (failed to add link)" + return + fi + + local link_output + link_output=$(ip netns exec "$testns" $ynl --family rt-link --dump getlink 2>/dev/null) + if echo "$link_output" | grep -q "$NSIM_DEV_NAME" && echo "$link_output" | grep -q "dummy0"; then + ktap_test_pass "YNL CLI rt-link operations" + else + ktap_test_fail "YNL CLI rt-link operations (failed to verify link)" + fi + + ip netns exec "$testns" $ynl --family rt-link --do dellink \ + --json "{\"ifname\": \"dummy0\"}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-neigh family operations +cli_rt_neigh_ops() +{ + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-neigh"; then + ktap_test_skip "YNL CLI rt-neigh operations (rt-neigh family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + # Add neighbor: 192.0.2.1 dev nsim1338 lladdr 11:22:33:44:55:66 PERMANENT + if ! ip netns exec "$testns" $ynl --family rt-neigh --do newneigh --create \ + --json "{\"ndm-ifindex\": $ifindex, \"dst\": \"192.0.2.1\", \"lladdr\": \"11:22:33:44:55:66\", \"ndm-family\": 2, \"ndm-state\": 128}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-neigh operations (failed to add neighbor)" + fi + + local neigh_output + neigh_output=$(ip netns exec "$testns" $ynl --family rt-neigh --dump getneigh 2>/dev/null) + if echo "$neigh_output" | grep -q "192.0.2.1"; then + ktap_test_pass "YNL CLI rt-neigh operations" + else + ktap_test_fail "YNL CLI rt-neigh operations (failed to verify neighbor)" + fi + + ip netns exec "$testns" $ynl --family rt-neigh --do delneigh \ + --json "{\"ndm-ifindex\": $ifindex, \"dst\": \"192.0.2.1\", \"lladdr\": \"11:22:33:44:55:66\", \"ndm-family\": 2}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-rule family operations +cli_rt_rule_ops() +{ + if ! $ynl --list-families 2>/dev/null | grep -q "rt-rule"; then + ktap_test_skip "YNL CLI rt-rule operations (rt-rule family not available)" + return + fi + + # Add rule: from 192.0.2.0/24 lookup 100 none + if ! ip netns exec "$testns" $ynl --family rt-rule --do newrule \ + --json "{\"family\": 2, \"src-len\": 24, \"src\": \"192.0.2.0\", \"table\": 100}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-rule operations (failed to add rule)" + return + fi + + local rule_output + rule_output=$(ip netns exec "$testns" $ynl --family rt-rule --dump getrule 2>/dev/null) + if echo "$rule_output" | grep -q "192.0.2.0"; then + ktap_test_pass "YNL CLI rt-rule operations" + else + ktap_test_fail "YNL CLI rt-rule operations (failed to verify rule)" + fi + + ip netns exec "$testns" $ynl --family rt-rule --do delrule \ + --json "{\"family\": 2, \"src-len\": 24, \"src\": \"192.0.2.0\", \"table\": 100}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test nlctrl family operations +cli_nlctrl_ops() +{ + local family_output + + if ! family_output=$($ynl --family nlctrl \ + --do getfamily --json "{\"family-name\": \"netdev\"}" 2>/dev/null); then + ktap_test_fail "YNL CLI nlctrl getfamily (failed to get nlctrl family info)" + return + fi + + if ! echo "$family_output" | grep -q "family-name"; then + ktap_test_fail "YNL CLI nlctrl getfamily (nlctrl getfamily output missing family-name)" + return + fi + + if ! echo "$family_output" | grep -q "family-id"; then + ktap_test_fail "YNL CLI nlctrl getfamily (nlctrl getfamily output missing family-id)" + return + fi + + ktap_test_pass "YNL CLI nlctrl getfamily" +} +TESTS_NO=$((TESTS_NO + 1)) + +setup() +{ + modprobe netdevsim &> /dev/null + if ! [ -f /sys/bus/netdevsim/new_device ]; then + ktap_skip_all "netdevsim module not available" + exit "$KSFT_SKIP" + fi + + if ! ip netns add "$testns" 2>/dev/null; then + ktap_skip_all "failed to create test namespace" + exit "$KSFT_SKIP" + fi + + echo "$NSIM_ID 1" | ip netns exec "$testns" tee /sys/bus/netdevsim/new_device >/dev/null 2>&1 || { + ktap_skip_all "failed to create netdevsim device" + exit "$KSFT_SKIP" + } + + local dev + dev=$(ip netns exec "$testns" ls /sys/bus/netdevsim/devices/netdevsim$NSIM_ID/net 2>/dev/null | head -1) + if [[ -z "$dev" ]]; then + ktap_skip_all "failed to find netdevsim device" + exit "$KSFT_SKIP" + fi + + ip -netns "$testns" link set dev "$dev" name "$NSIM_DEV_NAME" 2>/dev/null || { + ktap_skip_all "failed to rename netdevsim device" + exit "$KSFT_SKIP" + } + + ip -netns "$testns" link set dev "$NSIM_DEV_NAME" up 2>/dev/null + + if ! ip -n "$testns" link add "$VETH_A" type veth peer name "$VETH_B" 2>/dev/null; then + ktap_skip_all "failed to create veth pair" + exit "$KSFT_SKIP" + fi + + ip -n "$testns" link set "$VETH_A" up 2>/dev/null + ip -n "$testns" link set "$VETH_B" up 2>/dev/null +} + +cleanup() +{ + ip netns exec "$testns" bash -c "echo $NSIM_ID > /sys/bus/netdevsim/del_device" 2>/dev/null || true + ip netns del "$testns" 2>/dev/null || true +} + +# Check if ynl command is available +if ! command -v $ynl &>/dev/null && [[ ! -x $ynl ]]; then + ktap_skip_all "ynl command not found: $ynl" + exit "$KSFT_SKIP" +fi + +trap cleanup EXIT + +ktap_print_header +setup +ktap_set_plan "${TESTS_NO}" + +cli_list_families +cli_netdev_ops +cli_ethtool_ops +cli_rt_route_ops +cli_rt_addr_ops +cli_rt_link_ops +cli_rt_neigh_ops +cli_rt_rule_ops +cli_nlctrl_ops + +ktap_finished diff --git a/tools/net/ynl/tests/test_ynl_ethtool.sh b/tools/net/ynl/tests/test_ynl_ethtool.sh new file mode 100755 index 000000000000..b826269017f4 --- /dev/null +++ b/tools/net/ynl/tests/test_ynl_ethtool.sh @@ -0,0 +1,222 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Test YNL ethtool functionality + +# Load KTAP test helpers +KSELFTEST_KTAP_HELPERS="$(dirname "$(realpath "$0")")/../../../testing/selftests/kselftest/ktap_helpers.sh" +# shellcheck source=../../../testing/selftests/kselftest/ktap_helpers.sh +source "$KSELFTEST_KTAP_HELPERS" + +# Default ynl-ethtool path for direct execution, can be overridden by make install +ynl_ethtool="../pyynl/ethtool.py" + +readonly NSIM_ID="1337" +readonly NSIM_DEV_NAME="nsim${NSIM_ID}" +readonly VETH_A="veth_a" +readonly VETH_B="veth_b" + +testns="ynl-ethtool-$(mktemp -u XXXXXX)" +TESTS_NO=0 + +# Uses veth device as netdevsim doesn't support basic ethtool device info +ethtool_device_info() +{ + local info_output + + info_output=$(ip netns exec "$testns" $ynl_ethtool "$VETH_A" 2>/dev/null) + + if ! echo "$info_output" | grep -q "Settings for"; then + ktap_test_fail "YNL ethtool device info (device info output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool device info" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_statistics() +{ + local stats_output + + stats_output=$(ip netns exec "$testns" $ynl_ethtool --statistics "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$stats_output" | grep -q -E "(NIC statistics|packets|bytes)"; then + ktap_test_fail "YNL ethtool statistics (statistics output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool statistics" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_ring_params() +{ + local ring_output + + ring_output=$(ip netns exec "$testns" $ynl_ethtool --show-ring "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$ring_output" | grep -q -E "(Ring parameters|RX|TX)"; then + ktap_test_fail "YNL ethtool ring parameters (ring parameters output missing expected content)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-ring "$NSIM_DEV_NAME" rx 64 2>/dev/null; then + ktap_test_fail "YNL ethtool ring parameters (set-ring command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool ring parameters (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_coalesce_params() +{ + if ! ip netns exec "$testns" $ynl_ethtool --show-coalesce "$NSIM_DEV_NAME" &>/dev/null; then + ktap_test_fail "YNL ethtool coalesce parameters (failed to get coalesce parameters)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-coalesce "$NSIM_DEV_NAME" rx-usecs 50 2>/dev/null; then + ktap_test_fail "YNL ethtool coalesce parameters (set-coalesce command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool coalesce parameters (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_pause_params() +{ + if ! ip netns exec "$testns" $ynl_ethtool --show-pause "$NSIM_DEV_NAME" &>/dev/null; then + ktap_test_fail "YNL ethtool pause parameters (failed to get pause parameters)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-pause "$NSIM_DEV_NAME" tx 1 rx 1 2>/dev/null; then + ktap_test_fail "YNL ethtool pause parameters (set-pause command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool pause parameters (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_features_info() +{ + local features_output + + features_output=$(ip netns exec "$testns" $ynl_ethtool --show-features "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$features_output" | grep -q -E "(Features|offload)"; then + ktap_test_fail "YNL ethtool features info (features output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool features info (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_channels_info() +{ + local channels_output + + channels_output=$(ip netns exec "$testns" $ynl_ethtool --show-channels "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$channels_output" | grep -q -E "(Channel|Combined|RX|TX)"; then + ktap_test_fail "YNL ethtool channels info (channels output missing expected content)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-channels "$NSIM_DEV_NAME" combined-count 1 2>/dev/null; then + ktap_test_fail "YNL ethtool channels info (set-channels command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool channels info (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_time_stamping() +{ + local ts_output + + ts_output=$(ip netns exec "$testns" $ynl_ethtool --show-time-stamping "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$ts_output" | grep -q -E "(Time stamping|timestamping|SOF_TIMESTAMPING)"; then + ktap_test_fail "YNL ethtool time stamping (time stamping output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool time stamping" +} +TESTS_NO=$((TESTS_NO + 1)) + +setup() +{ + modprobe netdevsim &> /dev/null + if ! [ -f /sys/bus/netdevsim/new_device ]; then + ktap_skip_all "netdevsim module not available" + exit "$KSFT_SKIP" + fi + + if ! ip netns add "$testns" 2>/dev/null; then + ktap_skip_all "failed to create test namespace" + exit "$KSFT_SKIP" + fi + + echo "$NSIM_ID 1" | ip netns exec "$testns" tee /sys/bus/netdevsim/new_device >/dev/null 2>&1 || { + ktap_skip_all "failed to create netdevsim device" + exit "$KSFT_SKIP" + } + + local dev + dev=$(ip netns exec "$testns" ls /sys/bus/netdevsim/devices/netdevsim$NSIM_ID/net 2>/dev/null | head -1) + if [[ -z "$dev" ]]; then + ktap_skip_all "failed to find netdevsim device" + exit "$KSFT_SKIP" + fi + + ip -netns "$testns" link set dev "$dev" name "$NSIM_DEV_NAME" 2>/dev/null || { + ktap_skip_all "failed to rename netdevsim device" + exit "$KSFT_SKIP" + } + + ip -netns "$testns" link set dev "$NSIM_DEV_NAME" up 2>/dev/null + + if ! ip -n "$testns" link add "$VETH_A" type veth peer name "$VETH_B" 2>/dev/null; then + ktap_skip_all "failed to create veth pair" + exit "$KSFT_SKIP" + fi + + ip -n "$testns" link set "$VETH_A" up 2>/dev/null + ip -n "$testns" link set "$VETH_B" up 2>/dev/null +} + +cleanup() +{ + ip netns exec "$testns" bash -c "echo $NSIM_ID > /sys/bus/netdevsim/del_device" 2>/dev/null || true + ip netns del "$testns" 2>/dev/null || true +} + +# Check if ynl-ethtool command is available +if ! command -v $ynl_ethtool &>/dev/null && [[ ! -x $ynl_ethtool ]]; then + ktap_skip_all "ynl-ethtool command not found: $ynl_ethtool" + exit "$KSFT_SKIP" +fi + +trap cleanup EXIT + +ktap_print_header +setup +ktap_set_plan "${TESTS_NO}" + +ethtool_device_info +ethtool_statistics +ethtool_ring_params +ethtool_coalesce_params +ethtool_pause_params +ethtool_features_info +ethtool_channels_info +ethtool_time_stamping + +ktap_finished diff --git a/tools/net/ynl/ynltool/.gitignore b/tools/net/ynl/ynltool/.gitignore new file mode 100644 index 000000000000..690d399c921a --- /dev/null +++ b/tools/net/ynl/ynltool/.gitignore @@ -0,0 +1,2 @@ +ynltool +*.d diff --git a/tools/net/ynl/ynltool/Makefile b/tools/net/ynl/ynltool/Makefile new file mode 100644 index 000000000000..f5b1de32daa5 --- /dev/null +++ b/tools/net/ynl/ynltool/Makefile @@ -0,0 +1,55 @@ +# SPDX-License-Identifier: GPL-2.0-only + +include ../Makefile.deps + +INSTALL ?= install +prefix ?= /usr + +CC := gcc +CFLAGS := -Wall -Wextra -Werror -O2 +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif +CFLAGS += -I../lib -I../generated -I../../../include/uapi/ + +SRC_VERSION := \ + $(shell make --no-print-directory -sC ../../../.. kernelversion || \ + echo "unknown") + +CFLAGS += -DSRC_VERSION='"$(SRC_VERSION)"' + +SRCS := $(wildcard *.c) +OBJS := $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) + +YNLTOOL := $(OUTPUT)ynltool + +include $(wildcard *.d) + +all: $(YNLTOOL) + +Q = @ + +$(YNLTOOL): ../libynl.a $(OBJS) + $(Q)echo -e "\tLINK $@" + $(Q)$(CC) $(CFLAGS) -o $@ $(OBJS) ../libynl.a -lm + +%.o: %.c ../libynl.a + $(Q)echo -e "\tCC $@" + $(Q)$(COMPILE.c) -MMD -c -o $@ $< + +../libynl.a: + $(Q)$(MAKE) -C ../ + +clean: + rm -f *.o *.d *~ + +distclean: clean + rm -f $(YNLTOOL) + +bindir ?= /usr/bin + +install: $(YNLTOOL) + $(INSTALL) -m 0755 $(YNLTOOL) $(DESTDIR)$(bindir)/$(YNLTOOL) + +.PHONY: all clean distclean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/ynltool/json_writer.c b/tools/net/ynl/ynltool/json_writer.c new file mode 100644 index 000000000000..c8685e592cd3 --- /dev/null +++ b/tools/net/ynl/ynltool/json_writer.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-Clause) +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger <stephen@networkplumber.org> + */ + +#include <stdio.h> +#include <stdbool.h> +#include <stdarg.h> +#include <assert.h> +#include <malloc.h> +#include <inttypes.h> +#include <stdint.h> + +#include "json_writer.h" + +struct json_writer { + FILE *out; + unsigned depth; + bool pretty; + char sep; +}; + +static void jsonw_indent(json_writer_t *self) +{ + unsigned i; + for (i = 0; i < self->depth; ++i) + fputs(" ", self->out); +} + +static void jsonw_eol(json_writer_t *self) +{ + if (!self->pretty) + return; + + putc('\n', self->out); + jsonw_indent(self); +} + +static void jsonw_eor(json_writer_t *self) +{ + if (self->sep != '\0') + putc(self->sep, self->out); + self->sep = ','; +} + +static void jsonw_puts(json_writer_t *self, const char *str) +{ + putc('"', self->out); + for (; *str; ++str) + switch (*str) { + case '\t': + fputs("\\t", self->out); + break; + case '\n': + fputs("\\n", self->out); + break; + case '\r': + fputs("\\r", self->out); + break; + case '\f': + fputs("\\f", self->out); + break; + case '\b': + fputs("\\b", self->out); + break; + case '\\': + fputs("\\\\", self->out); + break; + case '"': + fputs("\\\"", self->out); + break; + default: + putc(*str, self->out); + } + putc('"', self->out); +} + +json_writer_t *jsonw_new(FILE *f) +{ + json_writer_t *self = malloc(sizeof(*self)); + if (self) { + self->out = f; + self->depth = 0; + self->pretty = false; + self->sep = '\0'; + } + return self; +} + +void jsonw_destroy(json_writer_t **self_p) +{ + json_writer_t *self = *self_p; + + assert(self->depth == 0); + fputs("\n", self->out); + fflush(self->out); + free(self); + *self_p = NULL; +} + +void jsonw_pretty(json_writer_t *self, bool on) +{ + self->pretty = on; +} + +void jsonw_reset(json_writer_t *self) +{ + assert(self->depth == 0); + self->sep = '\0'; +} + +static void jsonw_begin(json_writer_t *self, int c) +{ + jsonw_eor(self); + putc(c, self->out); + ++self->depth; + self->sep = '\0'; +} + +static void jsonw_end(json_writer_t *self, int c) +{ + assert(self->depth > 0); + + --self->depth; + if (self->sep != '\0') + jsonw_eol(self); + putc(c, self->out); + self->sep = ','; +} + +void jsonw_name(json_writer_t *self, const char *name) +{ + jsonw_eor(self); + jsonw_eol(self); + self->sep = '\0'; + jsonw_puts(self, name); + putc(':', self->out); + if (self->pretty) + putc(' ', self->out); +} + +void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) +{ + jsonw_eor(self); + putc('"', self->out); + vfprintf(self->out, fmt, ap); + putc('"', self->out); +} + +void jsonw_printf(json_writer_t *self, const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + jsonw_eor(self); + vfprintf(self->out, fmt, ap); + va_end(ap); +} + +void jsonw_start_object(json_writer_t *self) +{ + jsonw_begin(self, '{'); +} + +void jsonw_end_object(json_writer_t *self) +{ + jsonw_end(self, '}'); +} + +void jsonw_start_array(json_writer_t *self) +{ + jsonw_begin(self, '['); +} + +void jsonw_end_array(json_writer_t *self) +{ + jsonw_end(self, ']'); +} + +void jsonw_string(json_writer_t *self, const char *value) +{ + jsonw_eor(self); + jsonw_puts(self, value); +} + +void jsonw_bool(json_writer_t *self, bool val) +{ + jsonw_printf(self, "%s", val ? "true" : "false"); +} + +void jsonw_null(json_writer_t *self) +{ + jsonw_printf(self, "null"); +} + +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num) +{ + jsonw_printf(self, fmt, num); +} + +void jsonw_float(json_writer_t *self, double num) +{ + jsonw_printf(self, "%g", num); +} + +void jsonw_hu(json_writer_t *self, unsigned short num) +{ + jsonw_printf(self, "%hu", num); +} + +void jsonw_uint(json_writer_t *self, uint64_t num) +{ + jsonw_printf(self, "%"PRIu64, num); +} + +void jsonw_lluint(json_writer_t *self, unsigned long long int num) +{ + jsonw_printf(self, "%llu", num); +} + +void jsonw_int(json_writer_t *self, int64_t num) +{ + jsonw_printf(self, "%"PRId64, num); +} + +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val) +{ + jsonw_name(self, prop); + jsonw_string(self, val); +} + +void jsonw_bool_field(json_writer_t *self, const char *prop, bool val) +{ + jsonw_name(self, prop); + jsonw_bool(self, val); +} + +void jsonw_float_field(json_writer_t *self, const char *prop, double val) +{ + jsonw_name(self, prop); + jsonw_float(self, val); +} + +void jsonw_float_field_fmt(json_writer_t *self, + const char *prop, + const char *fmt, + double val) +{ + jsonw_name(self, prop); + jsonw_float_fmt(self, fmt, val); +} + +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num) +{ + jsonw_name(self, prop); + jsonw_uint(self, num); +} + +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num) +{ + jsonw_name(self, prop); + jsonw_hu(self, num); +} + +void jsonw_lluint_field(json_writer_t *self, + const char *prop, + unsigned long long int num) +{ + jsonw_name(self, prop); + jsonw_lluint(self, num); +} + +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num) +{ + jsonw_name(self, prop); + jsonw_int(self, num); +} + +void jsonw_null_field(json_writer_t *self, const char *prop) +{ + jsonw_name(self, prop); + jsonw_null(self); +} diff --git a/tools/net/ynl/ynltool/json_writer.h b/tools/net/ynl/ynltool/json_writer.h new file mode 100644 index 000000000000..0f1e63c88f6a --- /dev/null +++ b/tools/net/ynl/ynltool/json_writer.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger <stephen@networkplumber.org> + */ + +#ifndef _JSON_WRITER_H_ +#define _JSON_WRITER_H_ + +#include <stdbool.h> +#include <stdint.h> +#include <stdarg.h> +#include <stdio.h> + +/* Opaque class structure */ +typedef struct json_writer json_writer_t; + +/* Create a new JSON stream */ +json_writer_t *jsonw_new(FILE *f); +/* End output to JSON stream */ +void jsonw_destroy(json_writer_t **self_p); + +/* Cause output to have pretty whitespace */ +void jsonw_pretty(json_writer_t *self, bool on); + +/* Reset separator to create new JSON */ +void jsonw_reset(json_writer_t *self); + +/* Add property name */ +void jsonw_name(json_writer_t *self, const char *name); + +/* Add value */ +void __attribute__((format(printf, 2, 0))) jsonw_vprintf_enquote(json_writer_t *self, + const char *fmt, + va_list ap); +void __attribute__((format(printf, 2, 3))) jsonw_printf(json_writer_t *self, + const char *fmt, ...); +void jsonw_string(json_writer_t *self, const char *value); +void jsonw_bool(json_writer_t *self, bool value); +void jsonw_float(json_writer_t *self, double number); +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num); +void jsonw_uint(json_writer_t *self, uint64_t number); +void jsonw_hu(json_writer_t *self, unsigned short number); +void jsonw_int(json_writer_t *self, int64_t number); +void jsonw_null(json_writer_t *self); +void jsonw_lluint(json_writer_t *self, unsigned long long int num); + +/* Useful Combinations of name and value */ +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val); +void jsonw_bool_field(json_writer_t *self, const char *prop, bool value); +void jsonw_float_field(json_writer_t *self, const char *prop, double num); +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num); +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num); +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num); +void jsonw_null_field(json_writer_t *self, const char *prop); +void jsonw_lluint_field(json_writer_t *self, const char *prop, + unsigned long long int num); +void jsonw_float_field_fmt(json_writer_t *self, const char *prop, + const char *fmt, double val); + +/* Collections */ +void jsonw_start_object(json_writer_t *self); +void jsonw_end_object(json_writer_t *self); + +void jsonw_start_array(json_writer_t *self); +void jsonw_end_array(json_writer_t *self); + +/* Override default exception handling */ +typedef void (jsonw_err_handler_fn)(const char *); + +#endif /* _JSON_WRITER_H_ */ diff --git a/tools/net/ynl/ynltool/main.c b/tools/net/ynl/ynltool/main.c new file mode 100644 index 000000000000..5d0f428eed0a --- /dev/null +++ b/tools/net/ynl/ynltool/main.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +/* Copyright Meta Platforms, Inc. and affiliates */ + +#include <ctype.h> +#include <errno.h> +#include <getopt.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdarg.h> + +#include "main.h" + +const char *bin_name; +static int last_argc; +static char **last_argv; +static int (*last_do_help)(int argc, char **argv); +json_writer_t *json_wtr; +bool pretty_output; +bool json_output; + +static void __attribute__((noreturn)) clean_and_exit(int i) +{ + if (json_output) + jsonw_destroy(&json_wtr); + + exit(i); +} + +void usage(void) +{ + last_do_help(last_argc - 1, last_argv + 1); + + clean_and_exit(-1); +} + +static int do_help(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s [OPTIONS] OBJECT { COMMAND | help }\n" + " %s version\n" + "\n" + " OBJECT := { page-pool | qstats }\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, bin_name); + + return 0; +} + +static int do_version(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "version"); + jsonw_printf(json_wtr, SRC_VERSION); + jsonw_end_object(json_wtr); + } else { + printf("%s " SRC_VERSION "\n", bin_name); + } + return 0; +} + +static const struct cmd commands[] = { + { "help", do_help }, + { "page-pool", do_page_pool }, + { "qstats", do_qstats }, + { "version", do_version }, + { 0 } +}; + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)) +{ + unsigned int i; + + last_argc = argc; + last_argv = argv; + last_do_help = help; + + if (argc < 1 && cmds[0].func) + return cmds[0].func(argc, argv); + + for (i = 0; cmds[i].cmd; i++) { + if (is_prefix(*argv, cmds[i].cmd)) { + if (!cmds[i].func) { + p_err("command '%s' is not available", cmds[i].cmd); + return -1; + } + return cmds[i].func(argc - 1, argv + 1); + } + } + + help(argc - 1, argv + 1); + + return -1; +} + +bool is_prefix(const char *pfx, const char *str) +{ + if (!pfx) + return false; + if (strlen(str) < strlen(pfx)) + return false; + + return !memcmp(str, pfx, strlen(pfx)); +} + +/* Last argument MUST be NULL pointer */ +int detect_common_prefix(const char *arg, ...) +{ + unsigned int count = 0; + const char *ref; + char msg[256]; + va_list ap; + + snprintf(msg, sizeof(msg), "ambiguous prefix: '%s' could be '", arg); + va_start(ap, arg); + while ((ref = va_arg(ap, const char *))) { + if (!is_prefix(arg, ref)) + continue; + count++; + if (count > 1) + strncat(msg, "' or '", sizeof(msg) - strlen(msg) - 1); + strncat(msg, ref, sizeof(msg) - strlen(msg) - 1); + } + va_end(ap); + strncat(msg, "'", sizeof(msg) - strlen(msg) - 1); + + if (count >= 2) { + p_err("%s", msg); + return -1; + } + + return 0; +} + +void p_err(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "error"); + jsonw_vprintf_enquote(json_wtr, fmt, ap); + jsonw_end_object(json_wtr); + } else { + fprintf(stderr, "Error: "); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + } + va_end(ap); +} + +void p_info(const char *fmt, ...) +{ + va_list ap; + + if (json_output) + return; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + va_end(ap); +} + +int main(int argc, char **argv) +{ + static const struct option options[] = { + { "json", no_argument, NULL, 'j' }, + { "help", no_argument, NULL, 'h' }, + { "pretty", no_argument, NULL, 'p' }, + { "version", no_argument, NULL, 'V' }, + { 0 } + }; + bool version_requested = false; + int opt, ret; + + setlinebuf(stdout); + + last_do_help = do_help; + pretty_output = false; + json_output = false; + bin_name = "ynltool"; + + opterr = 0; + while ((opt = getopt_long(argc, argv, "Vhjp", + options, NULL)) >= 0) { + switch (opt) { + case 'V': + version_requested = true; + break; + case 'h': + return do_help(argc, argv); + case 'p': + pretty_output = true; + /* fall through */ + case 'j': + if (!json_output) { + json_wtr = jsonw_new(stdout); + if (!json_wtr) { + p_err("failed to create JSON writer"); + return -1; + } + json_output = true; + } + jsonw_pretty(json_wtr, pretty_output); + break; + default: + p_err("unrecognized option '%s'", argv[optind - 1]); + if (json_output) + clean_and_exit(-1); + else + usage(); + } + } + + argc -= optind; + argv += optind; + if (argc < 0) + usage(); + + if (version_requested) + ret = do_version(argc, argv); + else + ret = cmd_select(commands, argc, argv, do_help); + + if (json_output) + jsonw_destroy(&json_wtr); + + return ret; +} diff --git a/tools/net/ynl/ynltool/main.h b/tools/net/ynl/ynltool/main.h new file mode 100644 index 000000000000..c7039f9ac55a --- /dev/null +++ b/tools/net/ynl/ynltool/main.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +/* Copyright Meta Platforms, Inc. and affiliates */ + +#ifndef __YNLTOOL_H +#define __YNLTOOL_H + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <errno.h> +#include <string.h> + +#include "json_writer.h" + +#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) +#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) +#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; }) +#define GET_ARG() ({ argc--; *argv++; }) +#define REQ_ARGS(cnt) \ + ({ \ + int _cnt = (cnt); \ + bool _res; \ + \ + if (argc < _cnt) { \ + p_err("'%s' needs at least %d arguments, %d found", \ + argv[-1], _cnt, argc); \ + _res = false; \ + } else { \ + _res = true; \ + } \ + _res; \ + }) + +#define HELP_SPEC_OPTIONS \ + "OPTIONS := { {-j|--json} [{-p|--pretty}] }" + +extern const char *bin_name; + +extern json_writer_t *json_wtr; +extern bool json_output; +extern bool pretty_output; + +void __attribute__((format(printf, 1, 2))) p_err(const char *fmt, ...); +void __attribute__((format(printf, 1, 2))) p_info(const char *fmt, ...); + +bool is_prefix(const char *pfx, const char *str); +int detect_common_prefix(const char *arg, ...); +void usage(void) __attribute__((noreturn)); + +struct cmd { + const char *cmd; + int (*func)(int argc, char **argv); +}; + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)); + +/* subcommands */ +int do_page_pool(int argc, char **argv); +int do_qstats(int argc, char **argv); + +#endif /* __YNLTOOL_H */ diff --git a/tools/net/ynl/ynltool/page-pool.c b/tools/net/ynl/ynltool/page-pool.c new file mode 100644 index 000000000000..4b24492abab7 --- /dev/null +++ b/tools/net/ynl/ynltool/page-pool.c @@ -0,0 +1,461 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <net/if.h> + +#include <ynl.h> +#include "netdev-user.h" + +#include "main.h" + +struct pp_stat { + unsigned int ifc; + + struct { + unsigned int cnt; + size_t refs, bytes; + } live[2]; + + size_t alloc_slow, alloc_fast, recycle_ring, recycle_cache; +}; + +struct pp_stats_array { + unsigned int i, max; + struct pp_stat *s; +}; + +static struct pp_stat *find_ifc(struct pp_stats_array *a, unsigned int ifindex) +{ + unsigned int i; + + for (i = 0; i < a->i; i++) { + if (a->s[i].ifc == ifindex) + return &a->s[i]; + } + + a->i++; + if (a->i == a->max) { + a->max *= 2; + a->s = reallocarray(a->s, a->max, sizeof(*a->s)); + } + a->s[i].ifc = ifindex; + return &a->s[i]; +} + +static void count_pool(struct pp_stat *s, unsigned int l, + struct netdev_page_pool_get_rsp *pp) +{ + s->live[l].cnt++; + if (pp->_present.inflight) + s->live[l].refs += pp->inflight; + if (pp->_present.inflight_mem) + s->live[l].bytes += pp->inflight_mem; +} + +/* We don't know how many pages are sitting in cache and ring + * so we will under-count the recycling rate a bit. + */ +static void print_json_recycling_stats(struct pp_stat *s) +{ + double recycle; + + if (s->alloc_fast + s->alloc_slow) { + recycle = (double)(s->recycle_ring + s->recycle_cache) / + (s->alloc_fast + s->alloc_slow) * 100; + jsonw_float_field(json_wtr, "recycling_pct", recycle); + } + + jsonw_name(json_wtr, "alloc"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "slow", s->alloc_slow); + jsonw_uint_field(json_wtr, "fast", s->alloc_fast); + jsonw_end_object(json_wtr); + + jsonw_name(json_wtr, "recycle"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "ring", s->recycle_ring); + jsonw_uint_field(json_wtr, "cache", s->recycle_cache); + jsonw_end_object(json_wtr); +} + +static void print_plain_recycling_stats(struct pp_stat *s) +{ + double recycle; + + if (s->alloc_fast + s->alloc_slow) { + recycle = (double)(s->recycle_ring + s->recycle_cache) / + (s->alloc_fast + s->alloc_slow) * 100; + printf("recycling: %.1lf%% (alloc: %zu:%zu recycle: %zu:%zu)", + recycle, s->alloc_slow, s->alloc_fast, + s->recycle_ring, s->recycle_cache); + } +} + +static void print_json_stats(struct pp_stats_array *a) +{ + jsonw_start_array(json_wtr); + + for (unsigned int i = 0; i < a->i; i++) { + char ifname[IF_NAMESIZE]; + struct pp_stat *s = &a->s[i]; + const char *name; + + jsonw_start_object(json_wtr); + + if (!s->ifc) { + jsonw_string_field(json_wtr, "ifname", "<orphan>"); + jsonw_uint_field(json_wtr, "ifindex", 0); + } else { + name = if_indextoname(s->ifc, ifname); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", s->ifc); + } + + jsonw_uint_field(json_wtr, "page_pools", s->live[1].cnt); + jsonw_uint_field(json_wtr, "zombies", s->live[0].cnt); + + jsonw_name(json_wtr, "live"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "refs", s->live[1].refs); + jsonw_uint_field(json_wtr, "bytes", s->live[1].bytes); + jsonw_end_object(json_wtr); + + jsonw_name(json_wtr, "zombie"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "refs", s->live[0].refs); + jsonw_uint_field(json_wtr, "bytes", s->live[0].bytes); + jsonw_end_object(json_wtr); + + if (s->alloc_fast || s->alloc_slow) + print_json_recycling_stats(s); + + jsonw_end_object(json_wtr); + } + + jsonw_end_array(json_wtr); +} + +static void print_plain_stats(struct pp_stats_array *a) +{ + for (unsigned int i = 0; i < a->i; i++) { + char ifname[IF_NAMESIZE]; + struct pp_stat *s = &a->s[i]; + const char *name; + + if (!s->ifc) { + printf("<orphan>\t"); + } else { + name = if_indextoname(s->ifc, ifname); + if (name) + printf("%8s", name); + printf("[%u]\t", s->ifc); + } + + printf("page pools: %u (zombies: %u)\n", + s->live[1].cnt, s->live[0].cnt); + printf("\t\trefs: %zu bytes: %zu (refs: %zu bytes: %zu)\n", + s->live[1].refs, s->live[1].bytes, + s->live[0].refs, s->live[0].bytes); + + if (s->alloc_fast || s->alloc_slow) { + printf("\t\t"); + print_plain_recycling_stats(s); + printf("\n"); + } + } +} + +static bool +find_pool_stat_in_list(struct netdev_page_pool_stats_get_list *pp_stats, + __u64 pool_id, struct pp_stat *pstat) +{ + ynl_dump_foreach(pp_stats, pp) { + if (!pp->_present.info || !pp->info._present.id) + continue; + if (pp->info.id != pool_id) + continue; + + memset(pstat, 0, sizeof(*pstat)); + if (pp->_present.alloc_fast) + pstat->alloc_fast = pp->alloc_fast; + if (pp->_present.alloc_refill) + pstat->alloc_fast += pp->alloc_refill; + if (pp->_present.alloc_slow) + pstat->alloc_slow = pp->alloc_slow; + if (pp->_present.recycle_ring) + pstat->recycle_ring = pp->recycle_ring; + if (pp->_present.recycle_cached) + pstat->recycle_cache = pp->recycle_cached; + return true; + } + return false; +} + +static void +print_json_pool_list(struct netdev_page_pool_get_list *pools, + struct netdev_page_pool_stats_get_list *pp_stats, + bool zombies_only) +{ + jsonw_start_array(json_wtr); + + ynl_dump_foreach(pools, pp) { + char ifname[IF_NAMESIZE]; + struct pp_stat pstat; + const char *name; + + if (zombies_only && !pp->_present.detach_time) + continue; + + jsonw_start_object(json_wtr); + + jsonw_uint_field(json_wtr, "id", pp->id); + + if (pp->_present.ifindex) { + name = if_indextoname(pp->ifindex, ifname); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", pp->ifindex); + } + + if (pp->_present.napi_id) + jsonw_uint_field(json_wtr, "napi_id", pp->napi_id); + + if (pp->_present.inflight) + jsonw_uint_field(json_wtr, "refs", pp->inflight); + + if (pp->_present.inflight_mem) + jsonw_uint_field(json_wtr, "bytes", pp->inflight_mem); + + if (pp->_present.detach_time) + jsonw_uint_field(json_wtr, "detach_time", pp->detach_time); + + if (pp->_present.dmabuf) + jsonw_uint_field(json_wtr, "dmabuf", pp->dmabuf); + + if (find_pool_stat_in_list(pp_stats, pp->id, &pstat) && + (pstat.alloc_fast || pstat.alloc_slow)) + print_json_recycling_stats(&pstat); + + jsonw_end_object(json_wtr); + } + + jsonw_end_array(json_wtr); +} + +static void +print_plain_pool_list(struct netdev_page_pool_get_list *pools, + struct netdev_page_pool_stats_get_list *pp_stats, + bool zombies_only) +{ + ynl_dump_foreach(pools, pp) { + char ifname[IF_NAMESIZE]; + struct pp_stat pstat; + const char *name; + + if (zombies_only && !pp->_present.detach_time) + continue; + + printf("pool id: %llu", pp->id); + + if (pp->_present.ifindex) { + name = if_indextoname(pp->ifindex, ifname); + if (name) + printf(" dev: %s", name); + printf("[%u]", pp->ifindex); + } + + if (pp->_present.napi_id) + printf(" napi: %llu", pp->napi_id); + + printf("\n"); + + if (pp->_present.inflight || pp->_present.inflight_mem) { + printf(" inflight:"); + if (pp->_present.inflight) + printf(" %llu pages", pp->inflight); + if (pp->_present.inflight_mem) + printf(" %llu bytes", pp->inflight_mem); + printf("\n"); + } + + if (pp->_present.detach_time) + printf(" detached: %llu\n", pp->detach_time); + + if (pp->_present.dmabuf) + printf(" dmabuf: %u\n", pp->dmabuf); + + if (find_pool_stat_in_list(pp_stats, pp->id, &pstat) && + (pstat.alloc_fast || pstat.alloc_slow)) { + printf(" "); + print_plain_recycling_stats(&pstat); + printf("\n"); + } + } +} + +static void aggregate_device_stats(struct pp_stats_array *a, + struct netdev_page_pool_get_list *pools, + struct netdev_page_pool_stats_get_list *pp_stats) +{ + ynl_dump_foreach(pools, pp) { + struct pp_stat *s = find_ifc(a, pp->ifindex); + + count_pool(s, 1, pp); + if (pp->_present.detach_time) + count_pool(s, 0, pp); + } + + ynl_dump_foreach(pp_stats, pp) { + struct pp_stat *s = find_ifc(a, pp->info.ifindex); + + if (pp->_present.alloc_fast) + s->alloc_fast += pp->alloc_fast; + if (pp->_present.alloc_refill) + s->alloc_fast += pp->alloc_refill; + if (pp->_present.alloc_slow) + s->alloc_slow += pp->alloc_slow; + if (pp->_present.recycle_ring) + s->recycle_ring += pp->recycle_ring; + if (pp->_present.recycle_cached) + s->recycle_cache += pp->recycle_cached; + } +} + +static int do_stats(int argc, char **argv) +{ + struct netdev_page_pool_stats_get_list *pp_stats; + struct netdev_page_pool_get_list *pools; + enum { + GROUP_BY_DEVICE, + GROUP_BY_POOL, + } group_by = GROUP_BY_DEVICE; + bool zombies_only = false; + struct pp_stats_array a = {}; + struct ynl_error yerr; + struct ynl_sock *ys; + int ret = 0; + + /* Parse options */ + while (argc > 0) { + if (is_prefix(*argv, "group-by")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + return -1; + + if (is_prefix(*argv, "device")) { + group_by = GROUP_BY_DEVICE; + } else if (is_prefix(*argv, "pp") || + is_prefix(*argv, "page-pool") || + is_prefix(*argv, "none")) { + group_by = GROUP_BY_POOL; + } else { + p_err("invalid group-by value '%s'", *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "zombies")) { + zombies_only = true; + group_by = GROUP_BY_POOL; + NEXT_ARG(); + } else { + p_err("unknown option '%s'", *argv); + return -1; + } + } + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + p_err("YNL: %s", yerr.msg); + return -1; + } + + pools = netdev_page_pool_get_dump(ys); + if (!pools) { + p_err("failed to get page pools: %s", ys->err.msg); + ret = -1; + goto exit_close; + } + + pp_stats = netdev_page_pool_stats_get_dump(ys); + if (!pp_stats) { + p_err("failed to get page pool stats: %s", ys->err.msg); + ret = -1; + goto exit_free_pp_list; + } + + /* If grouping by pool, print individual pools */ + if (group_by == GROUP_BY_POOL) { + if (json_output) + print_json_pool_list(pools, pp_stats, zombies_only); + else + print_plain_pool_list(pools, pp_stats, zombies_only); + } else { + /* Aggregated stats mode (group-by device) */ + a.max = 64; + a.s = calloc(a.max, sizeof(*a.s)); + if (!a.s) { + p_err("failed to allocate stats array"); + ret = -1; + goto exit_free_stats_list; + } + + aggregate_device_stats(&a, pools, pp_stats); + + if (json_output) + print_json_stats(&a); + else + print_plain_stats(&a); + + free(a.s); + } + +exit_free_stats_list: + netdev_page_pool_stats_get_list_free(pp_stats); +exit_free_pp_list: + netdev_page_pool_get_list_free(pools); +exit_close: + ynl_sock_destroy(ys); + return ret; +} + +static int do_help(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s page-pool { COMMAND | help }\n" + " %s page-pool stats [ OPTIONS ]\n" + "\n" + " OPTIONS := { group-by { device | page-pool | none } | zombies }\n" + "\n" + " stats - Display page pool statistics\n" + " stats group-by device - Group statistics by network device (default)\n" + " stats group-by page-pool | pp | none\n" + " - Show individual page pool details (no grouping)\n" + " stats zombies - Show only zombie page pools (detached but with\n" + " pages in flight). Implies group-by page-pool.\n" + "", + bin_name, bin_name); + + return 0; +} + +static const struct cmd page_pool_cmds[] = { + { "help", do_help }, + { "stats", do_stats }, + { 0 } +}; + +int do_page_pool(int argc, char **argv) +{ + return cmd_select(page_pool_cmds, argc, argv, do_help); +} diff --git a/tools/net/ynl/ynltool/qstats.c b/tools/net/ynl/ynltool/qstats.c new file mode 100644 index 000000000000..31fb45709ffa --- /dev/null +++ b/tools/net/ynl/ynltool/qstats.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <net/if.h> +#include <math.h> + +#include <ynl.h> +#include "netdev-user.h" + +#include "main.h" + +static enum netdev_qstats_scope scope; /* default - device */ + +struct queue_balance { + unsigned int ifindex; + enum netdev_queue_type type; + unsigned int queue_count; + __u64 *rx_packets; + __u64 *rx_bytes; + __u64 *tx_packets; + __u64 *tx_bytes; +}; + +static void print_json_qstats(struct netdev_qstats_get_list *qstats) +{ + jsonw_start_array(json_wtr); + + ynl_dump_foreach(qstats, qs) { + char ifname[IF_NAMESIZE]; + const char *name; + + jsonw_start_object(json_wtr); + + name = if_indextoname(qs->ifindex, ifname); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", qs->ifindex); + + if (qs->_present.queue_type) + jsonw_string_field(json_wtr, "queue-type", + netdev_queue_type_str(qs->queue_type)); + if (qs->_present.queue_id) + jsonw_uint_field(json_wtr, "queue-id", qs->queue_id); + + if (qs->_present.rx_packets || qs->_present.rx_bytes || + qs->_present.rx_alloc_fail || qs->_present.rx_hw_drops || + qs->_present.rx_csum_complete || qs->_present.rx_hw_gro_packets) { + jsonw_name(json_wtr, "rx"); + jsonw_start_object(json_wtr); + if (qs->_present.rx_packets) + jsonw_uint_field(json_wtr, "packets", qs->rx_packets); + if (qs->_present.rx_bytes) + jsonw_uint_field(json_wtr, "bytes", qs->rx_bytes); + if (qs->_present.rx_alloc_fail) + jsonw_uint_field(json_wtr, "alloc-fail", qs->rx_alloc_fail); + if (qs->_present.rx_hw_drops) + jsonw_uint_field(json_wtr, "hw-drops", qs->rx_hw_drops); + if (qs->_present.rx_hw_drop_overruns) + jsonw_uint_field(json_wtr, "hw-drop-overruns", qs->rx_hw_drop_overruns); + if (qs->_present.rx_hw_drop_ratelimits) + jsonw_uint_field(json_wtr, "hw-drop-ratelimits", qs->rx_hw_drop_ratelimits); + if (qs->_present.rx_csum_complete) + jsonw_uint_field(json_wtr, "csum-complete", qs->rx_csum_complete); + if (qs->_present.rx_csum_unnecessary) + jsonw_uint_field(json_wtr, "csum-unnecessary", qs->rx_csum_unnecessary); + if (qs->_present.rx_csum_none) + jsonw_uint_field(json_wtr, "csum-none", qs->rx_csum_none); + if (qs->_present.rx_csum_bad) + jsonw_uint_field(json_wtr, "csum-bad", qs->rx_csum_bad); + if (qs->_present.rx_hw_gro_packets) + jsonw_uint_field(json_wtr, "hw-gro-packets", qs->rx_hw_gro_packets); + if (qs->_present.rx_hw_gro_bytes) + jsonw_uint_field(json_wtr, "hw-gro-bytes", qs->rx_hw_gro_bytes); + if (qs->_present.rx_hw_gro_wire_packets) + jsonw_uint_field(json_wtr, "hw-gro-wire-packets", qs->rx_hw_gro_wire_packets); + if (qs->_present.rx_hw_gro_wire_bytes) + jsonw_uint_field(json_wtr, "hw-gro-wire-bytes", qs->rx_hw_gro_wire_bytes); + jsonw_end_object(json_wtr); + } + + if (qs->_present.tx_packets || qs->_present.tx_bytes || + qs->_present.tx_hw_drops || qs->_present.tx_csum_none || + qs->_present.tx_hw_gso_packets) { + jsonw_name(json_wtr, "tx"); + jsonw_start_object(json_wtr); + if (qs->_present.tx_packets) + jsonw_uint_field(json_wtr, "packets", qs->tx_packets); + if (qs->_present.tx_bytes) + jsonw_uint_field(json_wtr, "bytes", qs->tx_bytes); + if (qs->_present.tx_hw_drops) + jsonw_uint_field(json_wtr, "hw-drops", qs->tx_hw_drops); + if (qs->_present.tx_hw_drop_errors) + jsonw_uint_field(json_wtr, "hw-drop-errors", qs->tx_hw_drop_errors); + if (qs->_present.tx_hw_drop_ratelimits) + jsonw_uint_field(json_wtr, "hw-drop-ratelimits", qs->tx_hw_drop_ratelimits); + if (qs->_present.tx_csum_none) + jsonw_uint_field(json_wtr, "csum-none", qs->tx_csum_none); + if (qs->_present.tx_needs_csum) + jsonw_uint_field(json_wtr, "needs-csum", qs->tx_needs_csum); + if (qs->_present.tx_hw_gso_packets) + jsonw_uint_field(json_wtr, "hw-gso-packets", qs->tx_hw_gso_packets); + if (qs->_present.tx_hw_gso_bytes) + jsonw_uint_field(json_wtr, "hw-gso-bytes", qs->tx_hw_gso_bytes); + if (qs->_present.tx_hw_gso_wire_packets) + jsonw_uint_field(json_wtr, "hw-gso-wire-packets", qs->tx_hw_gso_wire_packets); + if (qs->_present.tx_hw_gso_wire_bytes) + jsonw_uint_field(json_wtr, "hw-gso-wire-bytes", qs->tx_hw_gso_wire_bytes); + if (qs->_present.tx_stop) + jsonw_uint_field(json_wtr, "stop", qs->tx_stop); + if (qs->_present.tx_wake) + jsonw_uint_field(json_wtr, "wake", qs->tx_wake); + jsonw_end_object(json_wtr); + } + + jsonw_end_object(json_wtr); + } + + jsonw_end_array(json_wtr); +} + +static void print_one(bool present, const char *name, unsigned long long val, + int *line) +{ + if (!present) + return; + + if (!*line) { + printf(" "); + ++(*line); + } + + /* Don't waste space on tx- and rx- prefix, its implied by queue type */ + if (scope == NETDEV_QSTATS_SCOPE_QUEUE && + (name[0] == 'r' || name[0] == 't') && + name[1] == 'x' && name[2] == '-') + name += 3; + + printf(" %15s: %15llu", name, val); + + if (++(*line) == 3) { + printf("\n"); + *line = 0; + } +} + +static void print_plain_qstats(struct netdev_qstats_get_list *qstats) +{ + ynl_dump_foreach(qstats, qs) { + char ifname[IF_NAMESIZE]; + const char *name; + int n; + + name = if_indextoname(qs->ifindex, ifname); + if (name) + printf("%s", name); + else + printf("ifindex:%u", qs->ifindex); + + if (qs->_present.queue_type && qs->_present.queue_id) + printf("\t%s-%-3u", + netdev_queue_type_str(qs->queue_type), + qs->queue_id); + else + printf("\t "); + + n = 1; + + /* Basic counters */ + print_one(qs->_present.rx_packets, "rx-packets", qs->rx_packets, &n); + print_one(qs->_present.rx_bytes, "rx-bytes", qs->rx_bytes, &n); + print_one(qs->_present.tx_packets, "tx-packets", qs->tx_packets, &n); + print_one(qs->_present.tx_bytes, "tx-bytes", qs->tx_bytes, &n); + + /* RX error/drop counters */ + print_one(qs->_present.rx_alloc_fail, "rx-alloc-fail", + qs->rx_alloc_fail, &n); + print_one(qs->_present.rx_hw_drops, "rx-hw-drops", + qs->rx_hw_drops, &n); + print_one(qs->_present.rx_hw_drop_overruns, "rx-hw-drop-overruns", + qs->rx_hw_drop_overruns, &n); + print_one(qs->_present.rx_hw_drop_ratelimits, "rx-hw-drop-ratelimits", + qs->rx_hw_drop_ratelimits, &n); + + /* RX checksum counters */ + print_one(qs->_present.rx_csum_complete, "rx-csum-complete", + qs->rx_csum_complete, &n); + print_one(qs->_present.rx_csum_unnecessary, "rx-csum-unnecessary", + qs->rx_csum_unnecessary, &n); + print_one(qs->_present.rx_csum_none, "rx-csum-none", + qs->rx_csum_none, &n); + print_one(qs->_present.rx_csum_bad, "rx-csum-bad", + qs->rx_csum_bad, &n); + + /* RX GRO counters */ + print_one(qs->_present.rx_hw_gro_packets, "rx-hw-gro-packets", + qs->rx_hw_gro_packets, &n); + print_one(qs->_present.rx_hw_gro_bytes, "rx-hw-gro-bytes", + qs->rx_hw_gro_bytes, &n); + print_one(qs->_present.rx_hw_gro_wire_packets, "rx-hw-gro-wire-packets", + qs->rx_hw_gro_wire_packets, &n); + print_one(qs->_present.rx_hw_gro_wire_bytes, "rx-hw-gro-wire-bytes", + qs->rx_hw_gro_wire_bytes, &n); + + /* TX error/drop counters */ + print_one(qs->_present.tx_hw_drops, "tx-hw-drops", + qs->tx_hw_drops, &n); + print_one(qs->_present.tx_hw_drop_errors, "tx-hw-drop-errors", + qs->tx_hw_drop_errors, &n); + print_one(qs->_present.tx_hw_drop_ratelimits, "tx-hw-drop-ratelimits", + qs->tx_hw_drop_ratelimits, &n); + + /* TX checksum counters */ + print_one(qs->_present.tx_csum_none, "tx-csum-none", + qs->tx_csum_none, &n); + print_one(qs->_present.tx_needs_csum, "tx-needs-csum", + qs->tx_needs_csum, &n); + + /* TX GSO counters */ + print_one(qs->_present.tx_hw_gso_packets, "tx-hw-gso-packets", + qs->tx_hw_gso_packets, &n); + print_one(qs->_present.tx_hw_gso_bytes, "tx-hw-gso-bytes", + qs->tx_hw_gso_bytes, &n); + print_one(qs->_present.tx_hw_gso_wire_packets, "tx-hw-gso-wire-packets", + qs->tx_hw_gso_wire_packets, &n); + print_one(qs->_present.tx_hw_gso_wire_bytes, "tx-hw-gso-wire-bytes", + qs->tx_hw_gso_wire_bytes, &n); + + /* TX queue control */ + print_one(qs->_present.tx_stop, "tx-stop", qs->tx_stop, &n); + print_one(qs->_present.tx_wake, "tx-wake", qs->tx_wake, &n); + + if (n) + printf("\n"); + } +} + +static int do_show(int argc, char **argv) +{ + struct netdev_qstats_get_list *qstats; + struct netdev_qstats_get_req *req; + struct ynl_error yerr; + struct ynl_sock *ys; + int ret = 0; + + /* Parse options */ + while (argc > 0) { + if (is_prefix(*argv, "scope") || is_prefix(*argv, "group-by")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + return -1; + + if (is_prefix(*argv, "queue")) { + scope = NETDEV_QSTATS_SCOPE_QUEUE; + } else if (is_prefix(*argv, "device")) { + scope = 0; + } else { + p_err("invalid scope value '%s'", *argv); + return -1; + } + NEXT_ARG(); + } else { + p_err("unknown option '%s'", *argv); + return -1; + } + } + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + p_err("YNL: %s", yerr.msg); + return -1; + } + + req = netdev_qstats_get_req_alloc(); + if (!req) { + p_err("failed to allocate qstats request"); + ret = -1; + goto exit_close; + } + + if (scope) + netdev_qstats_get_req_set_scope(req, scope); + + qstats = netdev_qstats_get_dump(ys, req); + netdev_qstats_get_req_free(req); + if (!qstats) { + p_err("failed to get queue stats: %s", ys->err.msg); + ret = -1; + goto exit_close; + } + + /* Print the stats as returned by the kernel */ + if (json_output) + print_json_qstats(qstats); + else + print_plain_qstats(qstats); + + netdev_qstats_get_list_free(qstats); +exit_close: + ynl_sock_destroy(ys); + return ret; +} + +static void compute_stats(__u64 *values, unsigned int count, + double *mean, double *stddev, __u64 *min, __u64 *max) +{ + double sum = 0.0, variance = 0.0; + unsigned int i; + + *min = ~0ULL; + *max = 0; + + if (count == 0) { + *mean = 0; + *stddev = 0; + *min = 0; + return; + } + + for (i = 0; i < count; i++) { + sum += values[i]; + if (values[i] < *min) + *min = values[i]; + if (values[i] > *max) + *max = values[i]; + } + + *mean = sum / count; + + if (count > 1) { + for (i = 0; i < count; i++) { + double diff = values[i] - *mean; + + variance += diff * diff; + } + *stddev = sqrt(variance / (count - 1)); + } else { + *stddev = 0; + } +} + +static void print_balance_stats(const char *name, enum netdev_queue_type type, + __u64 *values, unsigned int count) +{ + double mean, stddev, cv, ns; + __u64 min, max; + + if ((name[0] == 'r' && type != NETDEV_QUEUE_TYPE_RX) || + (name[0] == 't' && type != NETDEV_QUEUE_TYPE_TX)) + return; + + compute_stats(values, count, &mean, &stddev, &min, &max); + + cv = mean > 0 ? (stddev / mean) * 100.0 : 0.0; + ns = min + max > 0 ? (double)2 * (max - min) / (max + min) * 100 : 0.0; + + printf(" %-12s: cv=%.1f%% ns=%.1f%% stddev=%.0f\n", + name, cv, ns, stddev); + printf(" %-12s min=%llu max=%llu mean=%.0f\n", + "", min, max, mean); +} + +static void +print_balance_stats_json(const char *name, enum netdev_queue_type type, + __u64 *values, unsigned int count) +{ + double mean, stddev, cv, ns; + __u64 min, max; + + if ((name[0] == 'r' && type != NETDEV_QUEUE_TYPE_RX) || + (name[0] == 't' && type != NETDEV_QUEUE_TYPE_TX)) + return; + + compute_stats(values, count, &mean, &stddev, &min, &max); + + cv = mean > 0 ? (stddev / mean) * 100.0 : 0.0; + ns = min + max > 0 ? (double)2 * (max - min) / (max + min) * 100 : 0.0; + + jsonw_name(json_wtr, name); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "queue-count", count); + jsonw_uint_field(json_wtr, "min", min); + jsonw_uint_field(json_wtr, "max", max); + jsonw_float_field(json_wtr, "mean", mean); + jsonw_float_field(json_wtr, "stddev", stddev); + jsonw_float_field(json_wtr, "coefficient-of-variation", cv); + jsonw_float_field(json_wtr, "normalized-spread", ns); + jsonw_end_object(json_wtr); +} + +static int cmp_ifindex_type(const void *a, const void *b) +{ + const struct netdev_qstats_get_rsp *qa = a; + const struct netdev_qstats_get_rsp *qb = b; + + if (qa->ifindex != qb->ifindex) + return qa->ifindex - qb->ifindex; + if (qa->queue_type != qb->queue_type) + return qa->queue_type - qb->queue_type; + return qa->queue_id - qb->queue_id; +} + +static int do_balance(int argc, char **argv __attribute__((unused))) +{ + struct netdev_qstats_get_list *qstats; + struct netdev_qstats_get_req *req; + struct netdev_qstats_get_rsp **sorted; + struct ynl_error yerr; + struct ynl_sock *ys; + unsigned int count = 0; + unsigned int i, j; + int ret = 0; + + if (argc > 0) { + p_err("balance command takes no arguments"); + return -1; + } + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + p_err("YNL: %s", yerr.msg); + return -1; + } + + req = netdev_qstats_get_req_alloc(); + if (!req) { + p_err("failed to allocate qstats request"); + ret = -1; + goto exit_close; + } + + /* Always use queue scope for balance analysis */ + netdev_qstats_get_req_set_scope(req, NETDEV_QSTATS_SCOPE_QUEUE); + + qstats = netdev_qstats_get_dump(ys, req); + netdev_qstats_get_req_free(req); + if (!qstats) { + p_err("failed to get queue stats: %s", ys->err.msg); + ret = -1; + goto exit_close; + } + + /* Count and sort queues */ + ynl_dump_foreach(qstats, qs) + count++; + + if (count == 0) { + if (json_output) + jsonw_start_array(json_wtr); + else + printf("No queue statistics available\n"); + goto exit_free_qstats; + } + + sorted = calloc(count, sizeof(*sorted)); + if (!sorted) { + p_err("failed to allocate sorted array"); + ret = -1; + goto exit_free_qstats; + } + + i = 0; + ynl_dump_foreach(qstats, qs) + sorted[i++] = qs; + + qsort(sorted, count, sizeof(*sorted), cmp_ifindex_type); + + if (json_output) + jsonw_start_array(json_wtr); + + /* Process each device/queue-type combination */ + i = 0; + while (i < count) { + __u64 *rx_packets, *rx_bytes, *tx_packets, *tx_bytes; + enum netdev_queue_type type = sorted[i]->queue_type; + unsigned int ifindex = sorted[i]->ifindex; + unsigned int queue_count = 0; + char ifname[IF_NAMESIZE]; + const char *name; + + /* Count queues for this device/type */ + for (j = i; j < count && sorted[j]->ifindex == ifindex && + sorted[j]->queue_type == type; j++) + queue_count++; + + /* Skip if no packets/bytes (inactive queues) */ + if (!sorted[i]->_present.rx_packets && + !sorted[i]->_present.rx_bytes && + !sorted[i]->_present.tx_packets && + !sorted[i]->_present.tx_bytes) + goto next_ifc; + + /* Allocate arrays for statistics */ + rx_packets = calloc(queue_count, sizeof(*rx_packets)); + rx_bytes = calloc(queue_count, sizeof(*rx_bytes)); + tx_packets = calloc(queue_count, sizeof(*tx_packets)); + tx_bytes = calloc(queue_count, sizeof(*tx_bytes)); + + if (!rx_packets || !rx_bytes || !tx_packets || !tx_bytes) { + p_err("failed to allocate statistics arrays"); + free(rx_packets); + free(rx_bytes); + free(tx_packets); + free(tx_bytes); + ret = -1; + goto exit_free_sorted; + } + + /* Collect statistics */ + for (j = 0; j < queue_count; j++) { + rx_packets[j] = sorted[i + j]->_present.rx_packets ? + sorted[i + j]->rx_packets : 0; + rx_bytes[j] = sorted[i + j]->_present.rx_bytes ? + sorted[i + j]->rx_bytes : 0; + tx_packets[j] = sorted[i + j]->_present.tx_packets ? + sorted[i + j]->tx_packets : 0; + tx_bytes[j] = sorted[i + j]->_present.tx_bytes ? + sorted[i + j]->tx_bytes : 0; + } + + name = if_indextoname(ifindex, ifname); + + if (json_output) { + jsonw_start_object(json_wtr); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", ifindex); + jsonw_string_field(json_wtr, "queue-type", + netdev_queue_type_str(type)); + + print_balance_stats_json("rx-packets", type, + rx_packets, queue_count); + print_balance_stats_json("rx-bytes", type, + rx_bytes, queue_count); + print_balance_stats_json("tx-packets", type, + tx_packets, queue_count); + print_balance_stats_json("tx-bytes", type, + tx_bytes, queue_count); + + jsonw_end_object(json_wtr); + } else { + if (name) + printf("%s", name); + else + printf("ifindex:%u", ifindex); + printf(" %s %d queues:\n", + netdev_queue_type_str(type), queue_count); + + print_balance_stats("rx-packets", type, + rx_packets, queue_count); + print_balance_stats("rx-bytes", type, + rx_bytes, queue_count); + print_balance_stats("tx-packets", type, + tx_packets, queue_count); + print_balance_stats("tx-bytes", type, + tx_bytes, queue_count); + printf("\n"); + } + + free(rx_packets); + free(rx_bytes); + free(tx_packets); + free(tx_bytes); + +next_ifc: + i += queue_count; + } + + if (json_output) + jsonw_end_array(json_wtr); + +exit_free_sorted: + free(sorted); +exit_free_qstats: + netdev_qstats_get_list_free(qstats); +exit_close: + ynl_sock_destroy(ys); + return ret; +} + +static int do_help(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s qstats { COMMAND | help }\n" + " %s qstats [ show ] [ OPTIONS ]\n" + " %s qstats balance\n" + "\n" + " OPTIONS := { scope queue | group-by { device | queue } }\n" + "\n" + " show - Display queue statistics (default)\n" + " Statistics are aggregated for the entire device.\n" + " show scope queue - Display per-queue statistics\n" + " show group-by device - Display device-aggregated statistics (default)\n" + " show group-by queue - Display per-queue statistics\n" + " balance - Analyze traffic distribution balance.\n" + "", + bin_name, bin_name, bin_name); + + return 0; +} + +static const struct cmd qstats_cmds[] = { + { "show", do_show }, + { "balance", do_balance }, + { "help", do_help }, + { 0 } +}; + +int do_qstats(int argc, char **argv) +{ + return cmd_select(qstats_cmds, argc, argv, do_help); +} diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 3b262487ec06..77d7c59f5d8b 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -34,10 +34,7 @@ typedef __kernel_sa_family_t sa_family_t; struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - union { - char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ - DECLARE_FLEX_ARRAY(char, sa_data); - }; + char sa_data[14]; /* 14 bytes of protocol address */ }; struct linger { diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index be1ee7ba7ce0..19c1638e312a 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -23,6 +23,7 @@ test_tcpnotify_user test_libbpf xdping test_cpp +test_progs_verification_cert *.d *.subskel.h *.skel.h @@ -32,7 +33,6 @@ test_cpp /cpuv4 /host-tools /tools -/runqslower /bench /veristat /sign-file diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f00587d4ede6..b7030a6e2e76 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -46,6 +46,7 @@ endif CFLAGS += -g $(OPT_FLAGS) -rdynamic -std=gnu11 \ -Wall -Werror -fno-omit-frame-pointer \ + -Wno-unused-but-set-variable \ $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(TOOLSARCHINCDIR) -I$(APIDIR) -I$(OUTPUT) @@ -98,14 +99,11 @@ TEST_GEN_PROGS += test_progs-cpuv4 TEST_INST_SUBDIRS += cpuv4 endif -TEST_GEN_FILES = test_tc_edt.bpf.o TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c) # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ test_lirc_mode2.sh \ - test_tc_tunnel.sh \ - test_tc_edt.sh \ test_xdping.sh \ test_bpftool_build.sh \ test_bpftool.sh \ @@ -127,7 +125,6 @@ TEST_KMOD_TARGETS = $(addprefix $(OUTPUT)/,$(TEST_KMODS)) TEST_GEN_PROGS_EXTENDED = \ bench \ flow_dissector_load \ - runqslower \ test_cpp \ test_lirc_mode2_user \ veristat \ @@ -209,8 +206,6 @@ HOST_INCLUDE_DIR := $(INCLUDE_DIR) endif HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids -RUNQSLOWER_OUTPUT := $(BUILD_DIR)/runqslower/ - VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ ../../../../vmlinux \ @@ -232,7 +227,7 @@ $(notdir $(TEST_GEN_PROGS) $(TEST_KMODS) \ MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf \ $(BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/bpftool \ $(HOST_BUILD_DIR)/resolve_btfids \ - $(RUNQSLOWER_OUTPUT) $(INCLUDE_DIR)) + $(INCLUDE_DIR)) $(MAKE_DIRS): $(call msg,MKDIR,,$@) $(Q)mkdir -p $@ @@ -304,17 +299,6 @@ TRUNNER_BPFTOOL := $(DEFAULT_BPFTOOL) USE_BOOTSTRAP := "bootstrap/" endif -$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) - $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ - OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ - BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ - BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf/ \ - BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) \ - BPF_TARGET_ENDIAN=$(BPF_TARGET_ENDIAN) \ - EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \ - EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' && \ - cp $(RUNQSLOWER_OUTPUT)runqslower $@ - TEST_GEN_PROGS_EXTENDED += $(TRUNNER_BPFTOOL) $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) @@ -453,7 +437,9 @@ BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(abspath $(OUTPUT)/../usr/include) \ -std=gnu11 \ -fno-strict-aliasing \ - -Wno-compare-distinct-pointer-types + -Wno-compare-distinct-pointer-types \ + -Wno-initializer-overrides \ + # # TODO: enable me -Wsign-compare CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) @@ -498,7 +484,8 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ LSKELS := fexit_sleep.c trace_printk.c trace_vprintk.c map_ptr_kern.c \ core_kern.c core_kern_overflow.c test_ringbuf.c \ - test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c + test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c \ + test_ringbuf_overwrite.c LSKELS_SIGNED := fentry_test.c fexit_test.c atomics.c @@ -543,6 +530,8 @@ TRUNNER_TEST_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.test.o, \ $$(notdir $$(wildcard $(TRUNNER_TESTS_DIR)/*.c))) TRUNNER_EXTRA_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ $$(filter %.c,$(TRUNNER_EXTRA_SOURCES))) +TRUNNER_LIB_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, \ + $$(filter %.c,$(TRUNNER_LIB_SOURCES))) TRUNNER_EXTRA_HDRS := $$(filter %.h,$(TRUNNER_EXTRA_SOURCES)) TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c)) @@ -686,6 +675,10 @@ $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o: \ $$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@) $(Q)$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@ +$(TRUNNER_LIB_OBJS): $(TRUNNER_OUTPUT)/%.o:$(TOOLSDIR)/lib/%.c + $$(call msg,LIB-OBJ,$(TRUNNER_BINARY),$$@) + $(Q)$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@ + # non-flavored in-srctree builds receive special treatment, in particular, we # do not need to copy extra resources (see e.g. test_btf_dump_case()) $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT) @@ -699,6 +692,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): | $(TRUNNER_BPF_OBJS) $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ) \ + $(TRUNNER_LIB_OBJS) \ $(RESOLVE_BTFIDS) \ $(TRUNNER_BPFTOOL) \ $(OUTPUT)/veristat \ @@ -721,7 +715,8 @@ $(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP) $(Q)$(VERIFY_SIG_SETUP) genkey $(BUILD_DIR) $(VERIFY_SIG_HDR): $(VERIFICATION_CERT) - $(Q)xxd -i -n test_progs_verification_cert $< > $@ + $(Q)ln -fs $< test_progs_verification_cert && \ + xxd -i test_progs_verification_cert > $@ # Define test_progs test runner. TRUNNER_TESTS_DIR := prog_tests @@ -745,6 +740,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \ $(VERIFY_SIG_HDR) \ flow_dissector_load.h \ ip_check_defrag_frags.h +TRUNNER_LIB_SOURCES := find_bit.c TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ $(OUTPUT)/liburandom_read.so \ $(OUTPUT)/xdp_synproxy \ @@ -782,6 +778,7 @@ endif TRUNNER_TESTS_DIR := map_tests TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_maps.c +TRUNNER_LIB_SOURCES := TRUNNER_EXTRA_FILES := TRUNNER_BPF_BUILD_RULE := $$(error no BPF objects should be built) TRUNNER_BPF_CFLAGS := @@ -803,7 +800,7 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT) $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Include find_bit.c to compile xskxceiver. -EXTRA_SRC := $(TOOLSDIR)/lib/find_bit.c +EXTRA_SRC := $(TOOLSDIR)/lib/find_bit.c prog_tests/test_xsk.c prog_tests/test_xsk.h $(OUTPUT)/xskxceiver: $(EXTRA_SRC) xskxceiver.c xskxceiver.h $(OUTPUT)/network_helpers.o $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT) $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ @@ -893,7 +890,8 @@ EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ $(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h \ no_alu32 cpuv4 bpf_gcc \ liburandom_read.so) \ - $(OUTPUT)/FEATURE-DUMP.selftests + $(OUTPUT)/FEATURE-DUMP.selftests \ + test_progs_verification_cert .PHONY: docs docs-clean diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index e1ee979e6acc..01bdce692799 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -19,6 +19,8 @@ static struct { int ringbuf_sz; /* per-ringbuf, in bytes */ bool ringbuf_use_output; /* use slower output API */ int perfbuf_sz; /* per-CPU size, in pages */ + bool overwrite; + bool bench_producer; } args = { .back2back = false, .batch_cnt = 500, @@ -27,6 +29,8 @@ static struct { .ringbuf_sz = 512 * 1024, .ringbuf_use_output = false, .perfbuf_sz = 128, + .overwrite = false, + .bench_producer = false, }; enum { @@ -35,6 +39,8 @@ enum { ARG_RB_BATCH_CNT = 2002, ARG_RB_SAMPLED = 2003, ARG_RB_SAMPLE_RATE = 2004, + ARG_RB_OVERWRITE = 2005, + ARG_RB_BENCH_PRODUCER = 2006, }; static const struct argp_option opts[] = { @@ -43,6 +49,8 @@ static const struct argp_option opts[] = { { "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"}, { "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"}, { "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"}, + { "rb-overwrite", ARG_RB_OVERWRITE, NULL, 0, "Overwrite mode"}, + { "rb-bench-producer", ARG_RB_BENCH_PRODUCER, NULL, 0, "Benchmark producer"}, {}, }; @@ -72,6 +80,12 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state) argp_usage(state); } break; + case ARG_RB_OVERWRITE: + args.overwrite = true; + break; + case ARG_RB_BENCH_PRODUCER: + args.bench_producer = true; + break; default: return ARGP_ERR_UNKNOWN; } @@ -95,8 +109,33 @@ static inline void bufs_trigger_batch(void) static void bufs_validate(void) { - if (env.consumer_cnt != 1) { - fprintf(stderr, "rb-libbpf benchmark needs one consumer!\n"); + if (args.bench_producer && strcmp(env.bench_name, "rb-libbpf")) { + fprintf(stderr, "--rb-bench-producer only works with rb-libbpf!\n"); + exit(1); + } + + if (args.overwrite && !args.bench_producer) { + fprintf(stderr, "overwrite mode only works with --rb-bench-producer for now!\n"); + exit(1); + } + + if (args.bench_producer && env.consumer_cnt != 0) { + fprintf(stderr, "no consumer is needed for --rb-bench-producer!\n"); + exit(1); + } + + if (args.bench_producer && args.back2back) { + fprintf(stderr, "back-to-back mode makes no sense for --rb-bench-producer!\n"); + exit(1); + } + + if (args.bench_producer && args.sampled) { + fprintf(stderr, "sampling mode makes no sense for --rb-bench-producer!\n"); + exit(1); + } + + if (!args.bench_producer && env.consumer_cnt != 1) { + fprintf(stderr, "benchmarks without --rb-bench-producer require exactly one consumer!\n"); exit(1); } @@ -128,12 +167,17 @@ static void ringbuf_libbpf_measure(struct bench_res *res) { struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx; - res->hits = atomic_swap(&buf_hits.value, 0); + if (args.bench_producer) + res->hits = atomic_swap(&ctx->skel->bss->hits, 0); + else + res->hits = atomic_swap(&buf_hits.value, 0); res->drops = atomic_swap(&ctx->skel->bss->dropped, 0); } static struct ringbuf_bench *ringbuf_setup_skeleton(void) { + __u32 flags; + struct bpf_map *ringbuf; struct ringbuf_bench *skel; setup_libbpf(); @@ -146,12 +190,19 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void) skel->rodata->batch_cnt = args.batch_cnt; skel->rodata->use_output = args.ringbuf_use_output ? 1 : 0; + skel->rodata->bench_producer = args.bench_producer; if (args.sampled) /* record data + header take 16 bytes */ skel->rodata->wakeup_data_size = args.sample_rate * 16; - bpf_map__set_max_entries(skel->maps.ringbuf, args.ringbuf_sz); + ringbuf = skel->maps.ringbuf; + if (args.overwrite) { + flags = bpf_map__map_flags(ringbuf) | BPF_F_RB_OVERWRITE; + bpf_map__set_map_flags(ringbuf, flags); + } + + bpf_map__set_max_entries(ringbuf, args.ringbuf_sz); if (ringbuf_bench__load(skel)) { fprintf(stderr, "failed to load skeleton\n"); @@ -171,10 +222,12 @@ static void ringbuf_libbpf_setup(void) { struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx; struct bpf_link *link; + int map_fd; ctx->skel = ringbuf_setup_skeleton(); - ctx->ringbuf = ring_buffer__new(bpf_map__fd(ctx->skel->maps.ringbuf), - buf_process_sample, NULL, NULL); + + map_fd = bpf_map__fd(ctx->skel->maps.ringbuf); + ctx->ringbuf = ring_buffer__new(map_fd, buf_process_sample, NULL, NULL); if (!ctx->ringbuf) { fprintf(stderr, "failed to create ringbuf\n"); exit(1); diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 1e2aff007c2a..34018fc3927f 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -180,10 +180,10 @@ static void trigger_kernel_count_setup(void) { setup_ctx(); bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false); - bpf_program__set_autoload(ctx.skel->progs.trigger_count, true); + bpf_program__set_autoload(ctx.skel->progs.trigger_kernel_count, true); load_ctx(); /* override driver program */ - ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_count); + ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_kernel_count); } static void trigger_kprobe_setup(void) diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh index 91e3567962ff..83e05e837871 100755 --- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh +++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh @@ -49,3 +49,7 @@ for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)" done +header "Ringbuf, multi-producer contention in overwrite mode, no consumer" +for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do + summarize "rb-prod nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 --rb-overwrite --rb-bench-producer rb-libbpf)" +done diff --git a/tools/testing/selftests/bpf/bpf_arena_list.h b/tools/testing/selftests/bpf/bpf_arena_list.h index 85dbc3ea4da5..e16fa7d95fcf 100644 --- a/tools/testing/selftests/bpf/bpf_arena_list.h +++ b/tools/testing/selftests/bpf/bpf_arena_list.h @@ -64,14 +64,12 @@ static inline void list_add_head(arena_list_node_t *n, arena_list_head_t *h) static inline void __list_del(arena_list_node_t *n) { - arena_list_node_t *next = n->next, *tmp; + arena_list_node_t *next = n->next; arena_list_node_t * __arena *pprev = n->pprev; cast_user(next); cast_kern(pprev); - tmp = *pprev; - cast_kern(tmp); - WRITE_ONCE(tmp, next); + WRITE_ONCE(*pprev, next); if (next) { cast_user(pprev); cast_kern(next); diff --git a/tools/testing/selftests/bpf/bpf_arena_strsearch.h b/tools/testing/selftests/bpf/bpf_arena_strsearch.h new file mode 100644 index 000000000000..c1b6eaa905bb --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_arena_strsearch.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#pragma once +#include "bpf_arena_common.h" + +__noinline int bpf_arena_strlen(const char __arena *s __arg_arena) +{ + const char __arena *sc; + + for (sc = s; *sc != '\0'; ++sc) + cond_break; + return sc - s; +} + +/** + * glob_match - Shell-style pattern matching, like !fnmatch(pat, str, 0) + * @pat: Shell-style pattern to match, e.g. "*.[ch]". + * @str: String to match. The pattern must match the entire string. + * + * Perform shell-style glob matching, returning true (1) if the match + * succeeds, or false (0) if it fails. Equivalent to !fnmatch(@pat, @str, 0). + * + * Pattern metacharacters are ?, *, [ and \. + * (And, inside character classes, !, - and ].) + * + * This is small and simple implementation intended for device blacklists + * where a string is matched against a number of patterns. Thus, it + * does not preprocess the patterns. It is non-recursive, and run-time + * is at most quadratic: strlen(@str)*strlen(@pat). + * + * An example of the worst case is glob_match("*aaaaa", "aaaaaaaaaa"); + * it takes 6 passes over the pattern before matching the string. + * + * Like !fnmatch(@pat, @str, 0) and unlike the shell, this does NOT + * treat / or leading . specially; it isn't actually used for pathnames. + * + * Note that according to glob(7) (and unlike bash), character classes + * are complemented by a leading !; this does not support the regex-style + * [^a-z] syntax. + * + * An opening bracket without a matching close is matched literally. + */ +__noinline bool glob_match(char const __arena *pat __arg_arena, char const __arena *str __arg_arena) +{ + /* + * Backtrack to previous * on mismatch and retry starting one + * character later in the string. Because * matches all characters + * (no exception for /), it can be easily proved that there's + * never a need to backtrack multiple levels. + */ + char const __arena *back_pat = NULL, *back_str; + + /* + * Loop over each token (character or class) in pat, matching + * it against the remaining unmatched tail of str. Return false + * on mismatch, or true after matching the trailing nul bytes. + */ + for (;;) { + unsigned char c = *str++; + unsigned char d = *pat++; + + switch (d) { + case '?': /* Wildcard: anything but nul */ + if (c == '\0') + return false; + break; + case '*': /* Any-length wildcard */ + if (*pat == '\0') /* Optimize trailing * case */ + return true; + back_pat = pat; + back_str = --str; /* Allow zero-length match */ + break; + case '[': { /* Character class */ + bool match = false, inverted = (*pat == '!'); + char const __arena *class = pat + inverted; + unsigned char a = *class++; + + /* + * Iterate over each span in the character class. + * A span is either a single character a, or a + * range a-b. The first span may begin with ']'. + */ + do { + unsigned char b = a; + + if (a == '\0') /* Malformed */ + goto literal; + + if (class[0] == '-' && class[1] != ']') { + b = class[1]; + + if (b == '\0') + goto literal; + + class += 2; + /* Any special action if a > b? */ + } + match |= (a <= c && c <= b); + cond_break; + } while ((a = *class++) != ']'); + + if (match == inverted) + goto backtrack; + pat = class; + } + break; + case '\\': + d = *pat++; + __attribute__((__fallthrough__)); + default: /* Literal character */ +literal: + if (c == d) { + if (d == '\0') + return true; + break; + } +backtrack: + if (c == '\0' || !back_pat) + return false; /* No point continuing */ + /* Try again from last *, one character later in str. */ + pat = back_pat; + str = ++back_str; + break; + } + cond_break; + } + return false; +} diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 794d44d19c88..e0189254bb6e 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -28,8 +28,8 @@ extern int bpf_dynptr_from_skb_meta(struct __sk_buff *skb, __u64 flags, * Either a direct pointer to the dynptr data or a pointer to the user-provided * buffer if unable to obtain a direct pointer */ -extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset, - void *buffer, __u32 buffer__szk) __ksym __weak; +extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u64 offset, + void *buffer, __u64 buffer__szk) __ksym __weak; /* Description * Obtain a read-write pointer to the dynptr's data @@ -37,13 +37,13 @@ extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u32 offset, * Either a direct pointer to the dynptr data or a pointer to the user-provided * buffer if unable to obtain a direct pointer */ -extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u32 offset, - void *buffer, __u32 buffer__szk) __ksym __weak; +extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u64 offset, void *buffer, + __u64 buffer__szk) __ksym __weak; -extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u32 start, __u32 end) __ksym __weak; +extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u64 start, __u64 end) __ksym __weak; extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym __weak; extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym __weak; -extern __u32 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym __weak; +extern __u64 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym __weak; extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym __weak; /* Description diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f2a2fd236ca8..558839e3c185 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -126,3 +126,8 @@ CONFIG_XDP_SOCKETS=y CONFIG_XFRM_INTERFACE=y CONFIG_TCP_CONG_DCTCP=y CONFIG_TCP_CONG_BBR=y +CONFIG_INFINIBAND=y +CONFIG_SMC=y +CONFIG_SMC_HS_CTRL_BPF=y +CONFIG_DIBS=y +CONFIG_DIBS_LO=y
\ No newline at end of file diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index cdf7b6641444..0a6a5561bed3 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -97,7 +97,7 @@ int settimeo(int fd, int timeout_ms) int start_server_addr(int type, const struct sockaddr_storage *addr, socklen_t addrlen, const struct network_helper_opts *opts) { - int fd; + int on = 1, fd; if (!opts) opts = &default_opts; @@ -111,6 +111,12 @@ int start_server_addr(int type, const struct sockaddr_storage *addr, socklen_t a if (settimeo(fd, opts->timeout_ms)) goto error_close; + if (type == SOCK_STREAM && + setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on))) { + log_err("Failed to enable SO_REUSEADDR"); + goto error_close; + } + if (opts->post_socket_cb && opts->post_socket_cb(fd, opts->cb_opts)) { log_err("Failed to call post_socket_cb"); @@ -766,6 +772,50 @@ int send_recv_data(int lfd, int fd, uint32_t total_bytes) return err; } +int tc_prog_attach(const char *dev, int ingress_fd, int egress_fd) +{ + int ifindex, ret; + + if (!ASSERT_TRUE(ingress_fd >= 0 || egress_fd >= 0, + "at least one program fd is valid")) + return -1; + + ifindex = if_nametoindex(dev); + if (!ASSERT_NEQ(ifindex, 0, "get ifindex")) + return -1; + + DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = ifindex, + .attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS); + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1, + .priority = 1, .prog_fd = ingress_fd); + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts2, .handle = 1, + .priority = 1, .prog_fd = egress_fd); + + ret = bpf_tc_hook_create(&hook); + if (!ASSERT_OK(ret, "create tc hook")) + return ret; + + if (ingress_fd >= 0) { + hook.attach_point = BPF_TC_INGRESS; + ret = bpf_tc_attach(&hook, &opts1); + if (!ASSERT_OK(ret, "bpf_tc_attach")) { + bpf_tc_hook_destroy(&hook); + return ret; + } + } + + if (egress_fd >= 0) { + hook.attach_point = BPF_TC_EGRESS; + ret = bpf_tc_attach(&hook, &opts2); + if (!ASSERT_OK(ret, "bpf_tc_attach")) { + bpf_tc_hook_destroy(&hook); + return ret; + } + } + + return 0; +} + #ifdef TRAFFIC_MONITOR struct tmonitor_ctx { pcap_t *pcap; diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index ef208eefd571..79a010c88e11 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -255,6 +255,22 @@ struct tmonitor_ctx; typedef int (*tm_print_fn_t)(const char *format, va_list args); +/** + * tc_prog_attach - attach BPF program(s) to an interface + * + * Takes file descriptors pointing to at least one, at most two BPF + * programs, and attach those programs to an interface ingress, egress or + * both. + * + * @dev: string containing the interface name + * @ingress_fd: file descriptor of the program to attach to interface ingress + * @egress_fd: file descriptor of the program to attach to interface egress + * + * Returns 0 on success, -1 if no valid file descriptor has been found, if + * the interface name is invalid or if an error ocurred during attach. + */ +int tc_prog_attach(const char *dev, int ingress_fd, int egress_fd); + #ifdef TRAFFIC_MONITOR struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name, const char *subtest_name); diff --git a/tools/testing/selftests/bpf/prog_tests/arena_strsearch.c b/tools/testing/selftests/bpf/prog_tests/arena_strsearch.c new file mode 100644 index 000000000000..f81a0c066505 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/arena_strsearch.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include "arena_strsearch.skel.h" + +static void test_arena_str(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + struct arena_strsearch *skel; + int ret; + + skel = arena_strsearch__open_and_load(); + if (!ASSERT_OK_PTR(skel, "arena_strsearch__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_strsearch), &opts); + ASSERT_OK(ret, "ret_add"); + ASSERT_OK(opts.retval, "retval"); + if (skel->bss->skip) { + printf("%s:SKIP:compiler doesn't support arena_cast\n", __func__); + test__skip(); + } + arena_strsearch__destroy(skel); +} + +void test_arena_strsearch(void) +{ + if (test__start_subtest("arena_strsearch")) + test_arena_str(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c b/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c new file mode 100644 index 000000000000..d138cc7b1bda --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include <linux/if_ether.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <linux/tcp.h> + +#include <sys/syscall.h> +#include <bpf/bpf.h> + +#include "bpf_gotox.skel.h" + +static void __test_run(struct bpf_program *prog, void *ctx_in, size_t ctx_size_in) +{ + LIBBPF_OPTS(bpf_test_run_opts, topts, + .ctx_in = ctx_in, + .ctx_size_in = ctx_size_in, + ); + int err, prog_fd; + + prog_fd = bpf_program__fd(prog); + err = bpf_prog_test_run_opts(prog_fd, &topts); + ASSERT_OK(err, "test_run_opts err"); +} + +static void __subtest(struct bpf_gotox *skel, void (*check)(struct bpf_gotox *)) +{ + if (skel->data->skip) + test__skip(); + else + check(skel); +} + +static void check_simple(struct bpf_gotox *skel, + struct bpf_program *prog, + __u64 ctx_in, + __u64 expected) +{ + skel->bss->ret_user = 0; + + __test_run(prog, &ctx_in, sizeof(ctx_in)); + + if (!ASSERT_EQ(skel->bss->ret_user, expected, "skel->bss->ret_user")) + return; +} + +static void check_simple_fentry(struct bpf_gotox *skel, + struct bpf_program *prog, + __u64 ctx_in, + __u64 expected) +{ + skel->bss->in_user = ctx_in; + skel->bss->ret_user = 0; + + /* trigger */ + usleep(1); + + if (!ASSERT_EQ(skel->bss->ret_user, expected, "skel->bss->ret_user")) + return; +} + +/* validate that for two loads of the same jump table libbpf generates only one map */ +static void check_one_map_two_jumps(struct bpf_gotox *skel) +{ + struct bpf_prog_info prog_info; + struct bpf_map_info map_info; + __u32 len; + __u32 map_ids[16]; + int prog_fd, map_fd; + int ret; + int i; + bool seen = false; + + memset(&prog_info, 0, sizeof(prog_info)); + prog_info.map_ids = (long)map_ids; + prog_info.nr_map_ids = ARRAY_SIZE(map_ids); + prog_fd = bpf_program__fd(skel->progs.one_map_two_jumps); + if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd(one_map_two_jumps)")) + return; + + len = sizeof(prog_info); + ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &len); + if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd(prog_fd)")) + return; + + for (i = 0; i < prog_info.nr_map_ids; i++) { + map_fd = bpf_map_get_fd_by_id(map_ids[i]); + if (!ASSERT_GE(map_fd, 0, "bpf_map_get_fd_by_id")) + return; + + len = sizeof(map_info); + memset(&map_info, 0, len); + ret = bpf_obj_get_info_by_fd(map_fd, &map_info, &len); + if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd(map_fd)")) { + close(map_fd); + return; + } + + if (map_info.type == BPF_MAP_TYPE_INSN_ARRAY) { + if (!ASSERT_EQ(seen, false, "more than one INSN_ARRAY map")) { + close(map_fd); + return; + } + seen = true; + } + close(map_fd); + } + + ASSERT_EQ(seen, true, "no INSN_ARRAY map"); +} + +static void check_one_switch(struct bpf_gotox *skel) +{ + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {2, 3, 4, 5, 7, 19, 19}; + int i; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.one_switch, in[i], out[i]); +} + +static void check_one_switch_non_zero_sec_off(struct bpf_gotox *skel) +{ + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {2, 3, 4, 5, 7, 19, 19}; + int i; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.one_switch_non_zero_sec_off, in[i], out[i]); +} + +static void check_two_switches(struct bpf_gotox *skel) +{ + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {103, 104, 107, 205, 115, 1019, 1019}; + int i; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.two_switches, in[i], out[i]); +} + +static void check_big_jump_table(struct bpf_gotox *skel) +{ + __u64 in[] = {0, 11, 27, 31, 22, 45, 99}; + __u64 out[] = {2, 3, 4, 5, 19, 19, 19}; + int i; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.big_jump_table, in[i], out[i]); +} + +static void check_one_jump_two_maps(struct bpf_gotox *skel) +{ + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {12, 15, 7 , 15, 12, 15, 15}; + int i; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.one_jump_two_maps, in[i], out[i]); +} + +static void check_static_global(struct bpf_gotox *skel) +{ + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {2, 3, 4, 5, 7, 19, 19}; + int i; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.use_static_global1, in[i], out[i]); + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.use_static_global2, in[i], out[i]); +} + +static void check_nonstatic_global(struct bpf_gotox *skel) +{ + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {2, 3, 4, 5, 7, 19, 19}; + int i; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.use_nonstatic_global1, in[i], out[i]); + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple(skel, skel->progs.use_nonstatic_global2, in[i], out[i]); +} + +static void check_other_sec(struct bpf_gotox *skel) +{ + struct bpf_link *link; + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {2, 3, 4, 5, 7, 19, 19}; + int i; + + link = bpf_program__attach(skel->progs.simple_test_other_sec); + if (!ASSERT_OK_PTR(link, "link")) + return; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple_fentry(skel, skel->progs.simple_test_other_sec, in[i], out[i]); + + bpf_link__destroy(link); +} + +static void check_static_global_other_sec(struct bpf_gotox *skel) +{ + struct bpf_link *link; + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {2, 3, 4, 5, 7, 19, 19}; + int i; + + link = bpf_program__attach(skel->progs.use_static_global_other_sec); + if (!ASSERT_OK_PTR(link, "link")) + return; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple_fentry(skel, skel->progs.use_static_global_other_sec, in[i], out[i]); + + bpf_link__destroy(link); +} + +static void check_nonstatic_global_other_sec(struct bpf_gotox *skel) +{ + struct bpf_link *link; + __u64 in[] = {0, 1, 2, 3, 4, 5, 77}; + __u64 out[] = {2, 3, 4, 5, 7, 19, 19}; + int i; + + link = bpf_program__attach(skel->progs.use_nonstatic_global_other_sec); + if (!ASSERT_OK_PTR(link, "link")) + return; + + for (i = 0; i < ARRAY_SIZE(in); i++) + check_simple_fentry(skel, skel->progs.use_nonstatic_global_other_sec, in[i], out[i]); + + bpf_link__destroy(link); +} + +void test_bpf_gotox(void) +{ + struct bpf_gotox *skel; + int ret; + + skel = bpf_gotox__open(); + if (!ASSERT_NEQ(skel, NULL, "bpf_gotox__open")) + return; + + ret = bpf_gotox__load(skel); + if (!ASSERT_OK(ret, "bpf_gotox__load")) + return; + + skel->bss->pid = getpid(); + + if (test__start_subtest("one-switch")) + __subtest(skel, check_one_switch); + + if (test__start_subtest("one-switch-non-zero-sec-offset")) + __subtest(skel, check_one_switch_non_zero_sec_off); + + if (test__start_subtest("two-switches")) + __subtest(skel, check_two_switches); + + if (test__start_subtest("big-jump-table")) + __subtest(skel, check_big_jump_table); + + if (test__start_subtest("static-global")) + __subtest(skel, check_static_global); + + if (test__start_subtest("nonstatic-global")) + __subtest(skel, check_nonstatic_global); + + if (test__start_subtest("other-sec")) + __subtest(skel, check_other_sec); + + if (test__start_subtest("static-global-other-sec")) + __subtest(skel, check_static_global_other_sec); + + if (test__start_subtest("nonstatic-global-other-sec")) + __subtest(skel, check_nonstatic_global_other_sec); + + if (test__start_subtest("one-jump-two-maps")) + __subtest(skel, check_one_jump_two_maps); + + if (test__start_subtest("one-map-two-jumps")) + __subtest(skel, check_one_map_two_jumps); + + bpf_gotox__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_insn_array.c b/tools/testing/selftests/bpf/prog_tests/bpf_insn_array.c new file mode 100644 index 000000000000..269870bec941 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_insn_array.c @@ -0,0 +1,504 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <bpf/bpf.h> +#include <test_progs.h> + +#ifdef __x86_64__ +static int map_create(__u32 map_type, __u32 max_entries) +{ + const char *map_name = "insn_array"; + __u32 key_size = 4; + __u32 value_size = sizeof(struct bpf_insn_array_value); + + return bpf_map_create(map_type, map_name, key_size, value_size, max_entries, NULL); +} + +static int prog_load(struct bpf_insn *insns, __u32 insn_cnt, int *fd_array, __u32 fd_array_cnt) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts); + + opts.fd_array = fd_array; + opts.fd_array_cnt = fd_array_cnt; + + return bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, &opts); +} + +static void __check_success(struct bpf_insn *insns, __u32 insn_cnt, __u32 *map_in, __u32 *map_out) +{ + struct bpf_insn_array_value val = {}; + int prog_fd = -1, map_fd, i; + + map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, insn_cnt); + if (!ASSERT_GE(map_fd, 0, "map_create")) + return; + + for (i = 0; i < insn_cnt; i++) { + val.orig_off = map_in[i]; + if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem")) + goto cleanup; + } + + if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) + goto cleanup; + + prog_fd = prog_load(insns, insn_cnt, &map_fd, 1); + if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)")) + goto cleanup; + + for (i = 0; i < insn_cnt; i++) { + char buf[64]; + + if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem")) + goto cleanup; + + snprintf(buf, sizeof(buf), "val.xlated_off should be equal map_out[%d]", i); + ASSERT_EQ(val.xlated_off, map_out[i], buf); + } + +cleanup: + close(prog_fd); + close(map_fd); +} + +/* + * Load a program, which will not be anyhow mangled by the verifier. Add an + * insn_array map pointing to every instruction. Check that it hasn't changed + * after the program load. + */ +static void check_one_to_one_mapping(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 4), + BPF_MOV64_IMM(BPF_REG_0, 3), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + __u32 map_in[] = {0, 1, 2, 3, 4, 5}; + __u32 map_out[] = {0, 1, 2, 3, 4, 5}; + + __check_success(insns, ARRAY_SIZE(insns), map_in, map_out); +} + +/* + * Load a program with two patches (get jiffies, for simplicity). Add an + * insn_array map pointing to every instruction. Check how it was changed + * after the program load. + */ +static void check_simple(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + __u32 map_in[] = {0, 1, 2, 3, 4, 5}; + __u32 map_out[] = {0, 1, 4, 5, 8, 9}; + + __check_success(insns, ARRAY_SIZE(insns), map_in, map_out); +} + +/* + * Verifier can delete code in two cases: nops & dead code. From insn + * array's point of view, the two cases are the same, so test using + * the simplest method: by loading some nops + */ +static void check_deletions(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + __u32 map_in[] = {0, 1, 2, 3, 4, 5}; + __u32 map_out[] = {0, -1, 1, -1, 2, 3}; + + __check_success(insns, ARRAY_SIZE(insns), map_in, map_out); +} + +/* + * Same test as check_deletions, but also add code which adds instructions + */ +static void check_deletions_with_functions(void) +{ + struct bpf_insn insns[] = { + BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */ + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }; + __u32 map_in[] = { 0, 1, 2, 3, 4, 5, /* func */ 6, 7, 8, 9, 10}; + __u32 map_out[] = {-1, 0, -1, 3, 4, 5, /* func */ -1, 6, -1, 9, 10}; + + __check_success(insns, ARRAY_SIZE(insns), map_in, map_out); +} + +/* + * Try to load a program with a map which points to outside of the program + */ +static void check_out_of_bounds_index(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 4), + BPF_MOV64_IMM(BPF_REG_0, 3), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, map_fd; + struct bpf_insn_array_value val = {}; + int key; + + map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, 1); + if (!ASSERT_GE(map_fd, 0, "map_create")) + return; + + key = 0; + val.orig_off = ARRAY_SIZE(insns); /* too big */ + if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &key, &val, 0), 0, "bpf_map_update_elem")) + goto cleanup; + + if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) + goto cleanup; + + prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1); + if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)")) { + close(prog_fd); + goto cleanup; + } + +cleanup: + close(map_fd); +} + +/* + * Try to load a program with a map which points to the middle of 16-bit insn + */ +static void check_mid_insn_index(void) +{ + struct bpf_insn insns[] = { + BPF_LD_IMM64(BPF_REG_0, 0), /* 2 x 8 */ + BPF_EXIT_INSN(), + }; + int prog_fd, map_fd; + struct bpf_insn_array_value val = {}; + int key; + + map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, 1); + if (!ASSERT_GE(map_fd, 0, "map_create")) + return; + + key = 0; + val.orig_off = 1; /* middle of 16-byte instruction */ + if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &key, &val, 0), 0, "bpf_map_update_elem")) + goto cleanup; + + if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) + goto cleanup; + + prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1); + if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)")) { + close(prog_fd); + goto cleanup; + } + +cleanup: + close(map_fd); +} + +static void check_incorrect_index(void) +{ + check_out_of_bounds_index(); + check_mid_insn_index(); +} + +static int set_bpf_jit_harden(char *level) +{ + char old_level; + int err = -1; + int fd = -1; + + fd = open("/proc/sys/net/core/bpf_jit_harden", O_RDWR | O_NONBLOCK); + if (fd < 0) { + ASSERT_FAIL("open .../bpf_jit_harden returned %d (errno=%d)", fd, errno); + return -1; + } + + err = read(fd, &old_level, 1); + if (err != 1) { + ASSERT_FAIL("read from .../bpf_jit_harden returned %d (errno=%d)", err, errno); + err = -1; + goto end; + } + + lseek(fd, 0, SEEK_SET); + + err = write(fd, level, 1); + if (err != 1) { + ASSERT_FAIL("write to .../bpf_jit_harden returned %d (errno=%d)", err, errno); + err = -1; + goto end; + } + + err = 0; + *level = old_level; +end: + if (fd >= 0) + close(fd); + return err; +} + +static void check_blindness(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 4), + BPF_MOV64_IMM(BPF_REG_0, 3), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + int prog_fd = -1, map_fd; + struct bpf_insn_array_value val = {}; + char bpf_jit_harden = '@'; /* non-exizsting value */ + int i; + + map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, ARRAY_SIZE(insns)); + if (!ASSERT_GE(map_fd, 0, "map_create")) + return; + + for (i = 0; i < ARRAY_SIZE(insns); i++) { + val.orig_off = i; + if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem")) + goto cleanup; + } + + if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) + goto cleanup; + + bpf_jit_harden = '2'; + if (set_bpf_jit_harden(&bpf_jit_harden)) { + bpf_jit_harden = '@'; /* open, read or write failed => no write was done */ + goto cleanup; + } + + prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1); + if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)")) + goto cleanup; + + for (i = 0; i < ARRAY_SIZE(insns); i++) { + char fmt[32]; + + if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem")) + goto cleanup; + + snprintf(fmt, sizeof(fmt), "val should be equal 3*%d", i); + ASSERT_EQ(val.xlated_off, i * 3, fmt); + } + +cleanup: + /* restore the old one */ + if (bpf_jit_harden != '@') + set_bpf_jit_harden(&bpf_jit_harden); + + close(prog_fd); + close(map_fd); +} + +/* Once map was initialized, it should be frozen */ +static void check_load_unfrozen_map(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd = -1, map_fd; + struct bpf_insn_array_value val = {}; + int i; + + map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, ARRAY_SIZE(insns)); + if (!ASSERT_GE(map_fd, 0, "map_create")) + return; + + for (i = 0; i < ARRAY_SIZE(insns); i++) { + val.orig_off = i; + if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem")) + goto cleanup; + } + + prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1); + if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)")) + goto cleanup; + + /* correctness: now freeze the map, the program should load fine */ + + if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) + goto cleanup; + + prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1); + if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)")) + goto cleanup; + + for (i = 0; i < ARRAY_SIZE(insns); i++) { + if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem")) + goto cleanup; + + ASSERT_EQ(val.xlated_off, i, "val should be equal i"); + } + +cleanup: + close(prog_fd); + close(map_fd); +} + +/* Map can be used only by one BPF program */ +static void check_no_map_reuse(void) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd = -1, map_fd, extra_fd = -1; + struct bpf_insn_array_value val = {}; + int i; + + map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, ARRAY_SIZE(insns)); + if (!ASSERT_GE(map_fd, 0, "map_create")) + return; + + for (i = 0; i < ARRAY_SIZE(insns); i++) { + val.orig_off = i; + if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem")) + goto cleanup; + } + + if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) + goto cleanup; + + prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1); + if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)")) + goto cleanup; + + for (i = 0; i < ARRAY_SIZE(insns); i++) { + if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem")) + goto cleanup; + + ASSERT_EQ(val.xlated_off, i, "val should be equal i"); + } + + extra_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1); + if (!ASSERT_EQ(extra_fd, -EBUSY, "program should have been rejected (extra_fd != -EBUSY)")) + goto cleanup; + + /* correctness: check that prog is still loadable without fd_array */ + extra_fd = prog_load(insns, ARRAY_SIZE(insns), NULL, 0); + if (!ASSERT_GE(extra_fd, 0, "bpf(BPF_PROG_LOAD): expected no error")) + goto cleanup; + +cleanup: + close(extra_fd); + close(prog_fd); + close(map_fd); +} + +static void check_bpf_no_lookup(void) +{ + struct bpf_insn insns[] = { + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }; + int prog_fd = -1, map_fd; + + map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, 1); + if (!ASSERT_GE(map_fd, 0, "map_create")) + return; + + insns[0].imm = map_fd; + + if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze")) + goto cleanup; + + prog_fd = prog_load(insns, ARRAY_SIZE(insns), NULL, 0); + if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)")) + goto cleanup; + + /* correctness: check that prog is still loadable with normal map */ + close(map_fd); + map_fd = map_create(BPF_MAP_TYPE_ARRAY, 1); + insns[0].imm = map_fd; + prog_fd = prog_load(insns, ARRAY_SIZE(insns), NULL, 0); + if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)")) + goto cleanup; + +cleanup: + close(prog_fd); + close(map_fd); +} + +static void check_bpf_side(void) +{ + check_bpf_no_lookup(); +} + +static void __test_bpf_insn_array(void) +{ + /* Test if offsets are adjusted properly */ + + if (test__start_subtest("one2one")) + check_one_to_one_mapping(); + + if (test__start_subtest("simple")) + check_simple(); + + if (test__start_subtest("deletions")) + check_deletions(); + + if (test__start_subtest("deletions-with-functions")) + check_deletions_with_functions(); + + if (test__start_subtest("blindness")) + check_blindness(); + + /* Check all kinds of operations and related restrictions */ + + if (test__start_subtest("incorrect-index")) + check_incorrect_index(); + + if (test__start_subtest("load-unfrozen-map")) + check_load_unfrozen_map(); + + if (test__start_subtest("no-map-reuse")) + check_no_map_reuse(); + + if (test__start_subtest("bpf-side-ops")) + check_bpf_side(); +} +#else +static void __test_bpf_insn_array(void) +{ + test__skip(); +} +#endif + +void test_bpf_insn_array(void) +{ + __test_bpf_insn_array(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 8a9ba4292109..054ecb6b1e9f 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -7496,6 +7496,71 @@ static struct btf_dedup_test dedup_tests[] = { }, }, { + .descr = "dedup: recursive typedef", + /* + * This test simulates a recursive typedef, which in GO is defined as such: + * + * type Foo func() Foo + * + * In BTF terms, this is represented as a TYPEDEF referencing + * a FUNC_PROTO that returns the same TYPEDEF. + */ + .input = { + .raw_types = { + /* + * [1] typedef Foo -> func() Foo + * [2] func_proto() -> Foo + * [3] typedef Foo -> func() Foo + * [4] func_proto() -> Foo + */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 2), /* [1] */ + BTF_FUNC_PROTO_ENC(1, 0), /* [2] */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 4), /* [3] */ + BTF_FUNC_PROTO_ENC(3, 0), /* [4] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0Foo"), + }, + .expect = { + .raw_types = { + BTF_TYPEDEF_ENC(NAME_NTH(1), 2), /* [1] */ + BTF_FUNC_PROTO_ENC(1, 0), /* [2] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0Foo"), + }, +}, +{ + .descr = "dedup: typedef", + /* + * // CU 1: + * typedef int foo; + * + * // CU 2: + * typedef int foo; + */ + .input = { + .raw_types = { + /* CU 1 */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 1), /* [2] */ + /* CU 2 */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [3] */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 3), /* [4] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0foo"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPEDEF_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0foo"), + }, +}, +{ .descr = "dedup: typedef tags", .input = { .raw_types = { diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c index 3696fb9a05ed..2d47cad50a51 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_split.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c @@ -12,11 +12,45 @@ static void btf_dump_printf(void *ctx, const char *fmt, va_list args) vfprintf(ctx, fmt, args); } +/* Write raw BTF to file, return number of bytes written or negative errno */ +static ssize_t btf_raw_write(struct btf *btf, char *file) +{ + ssize_t written = 0; + const void *data; + __u32 size = 0; + int fd, ret; + + fd = mkstemp(file); + if (!ASSERT_GE(fd, 0, "create_file")) + return -errno; + + data = btf__raw_data(btf, &size); + if (!ASSERT_OK_PTR(data, "btf__raw_data")) { + close(fd); + return -EINVAL; + } + while (written < size) { + ret = write(fd, data + written, size - written); + if (!ASSERT_GE(ret, 0, "write succeeded")) { + close(fd); + return -errno; + } + written += ret; + } + close(fd); + return written; +} + static void __test_btf_split(bool multi) { + char multisplit_btf_file[] = "/tmp/test_btf_multisplit.XXXXXX"; + char split_btf_file[] = "/tmp/test_btf_split.XXXXXX"; + char base_btf_file[] = "/tmp/test_btf_base.XXXXXX"; + ssize_t multisplit_btf_sz = 0, split_btf_sz = 0, base_btf_sz = 0; struct btf_dump *d = NULL; - const struct btf_type *t; - struct btf *btf1, *btf2, *btf3 = NULL; + const struct btf_type *t, *ot; + struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL; + struct btf *btf4 = NULL, *btf5 = NULL, *btf6 = NULL; int str_off, i, err; btf1 = btf__new_empty(); @@ -123,6 +157,45 @@ static void __test_btf_split(bool multi) " int uf2;\n" "};\n\n", "c_dump"); + /* write base, split BTFs to files and ensure parsing succeeds */ + base_btf_sz = btf_raw_write(btf1, base_btf_file); + if (base_btf_sz < 0) + goto cleanup; + split_btf_sz = btf_raw_write(btf2, split_btf_file); + if (split_btf_sz < 0) + goto cleanup; + btf4 = btf__parse(base_btf_file, NULL); + if (!ASSERT_OK_PTR(btf4, "parse_base")) + goto cleanup; + btf5 = btf__parse_split(split_btf_file, btf4); + if (!ASSERT_OK_PTR(btf5, "parse_split")) + goto cleanup; + if (multi) { + multisplit_btf_sz = btf_raw_write(btf3, multisplit_btf_file); + if (multisplit_btf_sz < 0) + goto cleanup; + btf6 = btf__parse_split(multisplit_btf_file, btf5); + if (!ASSERT_OK_PTR(btf6, "parse_multisplit")) + goto cleanup; + } else { + btf6 = btf5; + } + + if (!ASSERT_EQ(btf__type_cnt(btf3), btf__type_cnt(btf6), "cmp_type_cnt")) + goto cleanup; + + /* compare parsed to original BTF */ + for (i = 1; i < btf__type_cnt(btf6); i++) { + t = btf__type_by_id(btf6, i); + if (!ASSERT_OK_PTR(t, "type_in_parsed_btf")) + goto cleanup; + ot = btf__type_by_id(btf3, i); + if (!ASSERT_OK_PTR(ot, "type_in_orig_btf")) + goto cleanup; + if (!ASSERT_EQ(memcmp(t, ot, sizeof(*ot)), 0, "cmp_parsed_orig_btf")) + goto cleanup; + } + cleanup: if (dump_buf_file) fclose(dump_buf_file); @@ -132,6 +205,16 @@ cleanup: btf__free(btf2); if (btf2 != btf3) btf__free(btf3); + btf__free(btf4); + btf__free(btf5); + if (btf5 != btf6) + btf__free(btf6); + if (base_btf_sz > 0) + unlink(base_btf_file); + if (split_btf_sz > 0) + unlink(split_btf_file); + if (multisplit_btf_sz > 0) + unlink(multisplit_btf_file); } void test_btf_split(void) diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index 2a9a30650350..65b4512967e7 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -153,6 +153,26 @@ static void test_check_mtu_run_tc(struct test_check_mtu *skel, ASSERT_EQ(mtu_result, mtu_expect, "MTU-compare-user"); } +static void test_chk_segs_flag(struct test_check_mtu *skel, __u32 mtu) +{ + int err, prog_fd = bpf_program__fd(skel->progs.tc_chk_segs_flag); + struct __sk_buff skb = { + .gso_size = 10, + }; + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .ctx_in = &skb, + .ctx_size_in = sizeof(skb), + ); + + /* Lower the mtu to test the BPF_MTU_CHK_SEGS */ + SYS_NOFAIL("ip link set dev lo mtu 10"); + err = bpf_prog_test_run_opts(prog_fd, &topts); + SYS_NOFAIL("ip link set dev lo mtu %u", mtu); + ASSERT_OK(err, "test_run"); + ASSERT_EQ(topts.retval, BPF_OK, "retval"); +} static void test_check_mtu_tc(__u32 mtu, __u32 ifindex) { @@ -177,11 +197,12 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex) test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu); test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu); test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu); + test_chk_segs_flag(skel, mtu); cleanup: test_check_mtu__destroy(skel); } -void serial_test_check_mtu(void) +void test_ns_check_mtu(void) { int mtu_lo; diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c index 34b59f6baca1..7488a7606e6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c @@ -22,79 +22,37 @@ static int duration = 0; -struct addr_port { - in_port_t port; - union { - struct in_addr in_addr; - struct in6_addr in6_addr; - }; -}; - -struct tuple { - int family; - struct addr_port src; - struct addr_port dst; -}; - -static bool fill_addr_port(const struct sockaddr *sa, struct addr_port *ap) -{ - const struct sockaddr_in6 *in6; - const struct sockaddr_in *in; - - switch (sa->sa_family) { - case AF_INET: - in = (const struct sockaddr_in *)sa; - ap->in_addr = in->sin_addr; - ap->port = in->sin_port; - return true; - - case AF_INET6: - in6 = (const struct sockaddr_in6 *)sa; - ap->in6_addr = in6->sin6_addr; - ap->port = in6->sin6_port; - return true; - - default: - return false; - } -} -static bool set_up_conn(const struct sockaddr *addr, socklen_t len, int type, - int *server, int *conn, struct tuple *tuple) +static bool set_up_conn(const struct sockaddr_storage *addr, socklen_t len, int type, + int *server, int *conn, + struct sockaddr_storage *src, + struct sockaddr_storage *dst) { struct sockaddr_storage ss; socklen_t slen = sizeof(ss); - struct sockaddr *sa = (struct sockaddr *)&ss; - *server = start_server_addr(type, (struct sockaddr_storage *)addr, len, NULL); + *server = start_server_addr(type, addr, len, NULL); if (*server < 0) return false; - if (CHECK_FAIL(getsockname(*server, sa, &slen))) + if (CHECK_FAIL(getsockname(*server, (struct sockaddr *)&ss, &slen))) goto close_server; - *conn = connect_to_addr(type, (struct sockaddr_storage *)sa, slen, NULL); + *conn = connect_to_addr(type, &ss, slen, NULL); if (*conn < 0) goto close_server; /* We want to simulate packets arriving at conn, so we have to * swap src and dst. */ - slen = sizeof(ss); - if (CHECK_FAIL(getsockname(*conn, sa, &slen))) - goto close_conn; - - if (CHECK_FAIL(!fill_addr_port(sa, &tuple->dst))) + slen = sizeof(*dst); + if (CHECK_FAIL(getsockname(*conn, (struct sockaddr *)dst, &slen))) goto close_conn; - slen = sizeof(ss); - if (CHECK_FAIL(getpeername(*conn, sa, &slen))) + slen = sizeof(*src); + if (CHECK_FAIL(getpeername(*conn, (struct sockaddr *)src, &slen))) goto close_conn; - if (CHECK_FAIL(!fill_addr_port(sa, &tuple->src))) - goto close_conn; - - tuple->family = ss.ss_family; return true; close_conn: @@ -110,17 +68,16 @@ static socklen_t prepare_addr(struct sockaddr_storage *addr, int family) { struct sockaddr_in *addr4; struct sockaddr_in6 *addr6; + memset(addr, 0, sizeof(*addr)); switch (family) { case AF_INET: addr4 = (struct sockaddr_in *)addr; - memset(addr4, 0, sizeof(*addr4)); addr4->sin_family = family; addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); return sizeof(*addr4); case AF_INET6: addr6 = (struct sockaddr_in6 *)addr; - memset(addr6, 0, sizeof(*addr6)); addr6->sin6_family = family; addr6->sin6_addr = in6addr_loopback; return sizeof(*addr6); @@ -242,9 +199,15 @@ static void encap_init(encap_headers_t *encap, uint8_t hop_count, uint8_t proto) } static size_t build_input(const struct test_cfg *test, void *const buf, - const struct tuple *tuple) + const struct sockaddr_storage *src, + const struct sockaddr_storage *dst) { - in_port_t sport = tuple->src.port; + struct sockaddr_in6 *src_in6 = (struct sockaddr_in6 *)src; + struct sockaddr_in6 *dst_in6 = (struct sockaddr_in6 *)dst; + struct sockaddr_in *src_in = (struct sockaddr_in *)src; + struct sockaddr_in *dst_in = (struct sockaddr_in *)dst; + sa_family_t family = src->ss_family; + in_port_t sport, dport; encap_headers_t encap; struct iphdr ip; struct ipv6hdr ipv6; @@ -254,8 +217,11 @@ static size_t build_input(const struct test_cfg *test, void *const buf, uint8_t *p = buf; int proto; + sport = (family == AF_INET) ? src_in->sin_port : src_in6->sin6_port; + dport = (family == AF_INET) ? dst_in->sin_port : dst_in6->sin6_port; + proto = IPPROTO_IPIP; - if (tuple->family == AF_INET6) + if (family == AF_INET6) proto = IPPROTO_IPV6; encap_init(&encap, test->hops == ONE_HOP ? 1 : 0, proto); @@ -270,15 +236,15 @@ static size_t build_input(const struct test_cfg *test, void *const buf, if (test->type == UDP) proto = IPPROTO_UDP; - switch (tuple->family) { + switch (family) { case AF_INET: ip = (struct iphdr){ .ihl = 5, .version = 4, .ttl = IPDEFTTL, .protocol = proto, - .saddr = tuple->src.in_addr.s_addr, - .daddr = tuple->dst.in_addr.s_addr, + .saddr = src_in->sin_addr.s_addr, + .daddr = dst_in->sin_addr.s_addr, }; p = mempcpy(p, &ip, sizeof(ip)); break; @@ -287,8 +253,8 @@ static size_t build_input(const struct test_cfg *test, void *const buf, .version = 6, .hop_limit = IPDEFTTL, .nexthdr = proto, - .saddr = tuple->src.in6_addr, - .daddr = tuple->dst.in6_addr, + .saddr = src_in6->sin6_addr, + .daddr = dst_in6->sin6_addr, }; p = mempcpy(p, &ipv6, sizeof(ipv6)); break; @@ -303,18 +269,16 @@ static size_t build_input(const struct test_cfg *test, void *const buf, case TCP: tcp = (struct tcphdr){ .source = sport, - .dest = tuple->dst.port, + .dest = dport, + .syn = (test->flags == SYN), + .ack = (test->flags == ACK), }; - if (test->flags == SYN) - tcp.syn = true; - if (test->flags == ACK) - tcp.ack = true; p = mempcpy(p, &tcp, sizeof(tcp)); break; case UDP: udp = (struct udphdr){ .source = sport, - .dest = tuple->dst.port, + .dest = dport, }; p = mempcpy(p, &udp, sizeof(udp)); break; @@ -339,27 +303,26 @@ static void test_cls_redirect_common(struct bpf_program *prog) LIBBPF_OPTS(bpf_test_run_opts, tattr); int families[] = { AF_INET, AF_INET6 }; struct sockaddr_storage ss; - struct sockaddr *addr; socklen_t slen; int i, j, err, prog_fd; int servers[__NR_KIND][ARRAY_SIZE(families)] = {}; int conns[__NR_KIND][ARRAY_SIZE(families)] = {}; - struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)]; + struct sockaddr_storage srcs[__NR_KIND][ARRAY_SIZE(families)]; + struct sockaddr_storage dsts[__NR_KIND][ARRAY_SIZE(families)]; - addr = (struct sockaddr *)&ss; for (i = 0; i < ARRAY_SIZE(families); i++) { slen = prepare_addr(&ss, families[i]); if (CHECK_FAIL(!slen)) goto cleanup; - if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_DGRAM, + if (CHECK_FAIL(!set_up_conn(&ss, slen, SOCK_DGRAM, &servers[UDP][i], &conns[UDP][i], - &tuples[UDP][i]))) + &srcs[UDP][i], &dsts[UDP][i]))) goto cleanup; - if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_STREAM, + if (CHECK_FAIL(!set_up_conn(&ss, slen, SOCK_STREAM, &servers[TCP][i], &conns[TCP][i], - &tuples[TCP][i]))) + &srcs[TCP][i], &dsts[TCP][i]))) goto cleanup; } @@ -368,11 +331,12 @@ static void test_cls_redirect_common(struct bpf_program *prog) struct test_cfg *test = &tests[i]; for (j = 0; j < ARRAY_SIZE(families); j++) { - struct tuple *tuple = &tuples[test->type][j]; + struct sockaddr_storage *src = &srcs[test->type][j]; + struct sockaddr_storage *dst = &dsts[test->type][j]; char input[256]; char tmp[256]; - test_str(tmp, sizeof(tmp), test, tuple->family); + test_str(tmp, sizeof(tmp), test, families[j]); if (!test__start_subtest(tmp)) continue; @@ -380,7 +344,7 @@ static void test_cls_redirect_common(struct bpf_program *prog) tattr.data_size_out = sizeof(tmp); tattr.data_in = input; - tattr.data_size_in = build_input(test, input, tuple); + tattr.data_size_in = build_input(test, input, src, dst); if (CHECK_FAIL(!tattr.data_size_in)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/file_reader.c b/tools/testing/selftests/bpf/prog_tests/file_reader.c new file mode 100644 index 000000000000..5cde32b35da4 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/file_reader.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include <network_helpers.h> +#include "file_reader.skel.h" +#include "file_reader_fail.skel.h" +#include <dlfcn.h> +#include <sys/mman.h> + +const char *user_ptr = "hello world"; +char file_contents[256000]; + +void *get_executable_base_addr(void) +{ + Dl_info info; + + if (!dladdr((void *)&get_executable_base_addr, &info)) { + fprintf(stderr, "dladdr failed\n"); + return NULL; + } + + return info.dli_fbase; +} + +static int initialize_file_contents(void) +{ + int fd, page_sz = sysconf(_SC_PAGESIZE); + ssize_t n = 0, cur, off; + void *addr; + + fd = open("/proc/self/exe", O_RDONLY); + if (!ASSERT_OK_FD(fd, "Open /proc/self/exe\n")) + return 1; + + do { + cur = read(fd, file_contents + n, sizeof(file_contents) - n); + if (!ASSERT_GT(cur, 0, "read success")) + break; + n += cur; + } while (n < sizeof(file_contents)); + + close(fd); + + if (!ASSERT_EQ(n, sizeof(file_contents), "Read /proc/self/exe\n")) + return 1; + + addr = get_executable_base_addr(); + if (!ASSERT_NEQ(addr, NULL, "get executable address")) + return 1; + + /* page-align base file address */ + addr = (void *)((unsigned long)addr & ~(page_sz - 1)); + + /* + * Page out range 0..512K, use 0..256K for positive tests and + * 256K..512K for negative tests expecting page faults + */ + for (off = 0; off < sizeof(file_contents) * 2; off += page_sz) { + if (!ASSERT_OK(madvise(addr + off, page_sz, MADV_PAGEOUT), + "madvise pageout")) + return errno; + } + + return 0; +} + +static void run_test(const char *prog_name) +{ + struct file_reader *skel; + struct bpf_program *prog; + int err, fd; + + err = initialize_file_contents(); + if (!ASSERT_OK(err, "initialize file contents")) + return; + + skel = file_reader__open(); + if (!ASSERT_OK_PTR(skel, "file_reader__open")) + return; + + bpf_object__for_each_program(prog, skel->obj) { + bpf_program__set_autoload(prog, strcmp(bpf_program__name(prog), prog_name) == 0); + } + + memcpy(skel->bss->user_buf, file_contents, sizeof(file_contents)); + skel->bss->pid = getpid(); + + err = file_reader__load(skel); + if (!ASSERT_OK(err, "file_reader__load")) + goto cleanup; + + err = file_reader__attach(skel); + if (!ASSERT_OK(err, "file_reader__attach")) + goto cleanup; + + fd = open("/proc/self/exe", O_RDONLY); + if (fd >= 0) + close(fd); + + ASSERT_EQ(skel->bss->err, 0, "err"); + ASSERT_EQ(skel->bss->run_success, 1, "run_success"); +cleanup: + file_reader__destroy(skel); +} + +void test_file_reader(void) +{ + if (test__start_subtest("on_open_expect_fault")) + run_test("on_open_expect_fault"); + + if (test__start_subtest("on_open_validate_file_read")) + run_test("on_open_validate_file_read"); + + if (test__start_subtest("negative")) + RUN_TESTS(file_reader_fail); +} diff --git a/tools/testing/selftests/bpf/prog_tests/htab_update.c b/tools/testing/selftests/bpf/prog_tests/htab_update.c index 2bc85f4814f4..d0b405eb2966 100644 --- a/tools/testing/selftests/bpf/prog_tests/htab_update.c +++ b/tools/testing/selftests/bpf/prog_tests/htab_update.c @@ -15,17 +15,17 @@ struct htab_update_ctx { static void test_reenter_update(void) { struct htab_update *skel; - unsigned int key, value; + void *value = NULL; + unsigned int key, value_size; int err; skel = htab_update__open(); if (!ASSERT_OK_PTR(skel, "htab_update__open")) return; - /* lookup_elem_raw() may be inlined and find_kernel_btf_id() will return -ESRCH */ - bpf_program__set_autoload(skel->progs.lookup_elem_raw, true); + bpf_program__set_autoload(skel->progs.bpf_obj_free_fields, true); err = htab_update__load(skel); - if (!ASSERT_TRUE(!err || err == -ESRCH, "htab_update__load") || err) + if (!ASSERT_TRUE(!err, "htab_update__load") || err) goto out; skel->bss->pid = getpid(); @@ -33,14 +33,33 @@ static void test_reenter_update(void) if (!ASSERT_OK(err, "htab_update__attach")) goto out; - /* Will trigger the reentrancy of bpf_map_update_elem() */ + value_size = bpf_map__value_size(skel->maps.htab); + + value = calloc(1, value_size); + if (!ASSERT_OK_PTR(value, "calloc value")) + goto out; + /* + * First update: plain insert. This should NOT trigger the re-entrancy + * path, because there is no old element to free yet. + */ key = 0; - value = 0; - err = bpf_map_update_elem(bpf_map__fd(skel->maps.htab), &key, &value, 0); - if (!ASSERT_OK(err, "add element")) + err = bpf_map_update_elem(bpf_map__fd(skel->maps.htab), &key, value, BPF_ANY); + if (!ASSERT_OK(err, "first update (insert)")) + goto out; + + /* + * Second update: replace existing element with same key and trigger + * the reentrancy of bpf_map_update_elem(). + * check_and_free_fields() calls bpf_obj_free_fields() on the old + * value, which is where fentry program runs and performs a nested + * bpf_map_update_elem(), triggering -EDEADLK. + */ + memset(value, 0, value_size); + err = bpf_map_update_elem(bpf_map__fd(skel->maps.htab), &key, value, BPF_ANY); + if (!ASSERT_OK(err, "second update (replace)")) goto out; - ASSERT_EQ(skel->bss->update_err, -EBUSY, "no reentrancy"); + ASSERT_EQ(skel->bss->update_err, -EDEADLK, "no reentrancy"); out: htab_update__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c index 1de14b111931..6e35e13c2022 100644 --- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c @@ -57,7 +57,8 @@ static void subtest_kmem_cache_iter_check_slabinfo(struct kmem_cache_iter *skel) if (!ASSERT_OK(ret, "kmem_cache_lookup")) break; - ASSERT_STREQ(r.name, name, "kmem_cache_name"); + ASSERT_STRNEQ(r.name, name, sizeof(r.name) - 1, + "kmem_cache_name"); ASSERT_EQ(r.obj_size, objsize, "kmem_cache_objsize"); seen++; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index bc24f83339d6..0a7ef770c487 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -15,6 +15,10 @@ static void check_good_sample(struct test_perf_branches *skel) int pbe_size = sizeof(struct perf_branch_entry); int duration = 0; + if (CHECK(!skel->bss->run_cnt, "invalid run_cnt", + "checked sample validity before prog run")) + return; + if (CHECK(!skel->bss->valid, "output not valid", "no valid sample from prog")) return; @@ -45,6 +49,10 @@ static void check_bad_sample(struct test_perf_branches *skel) int written_stack = skel->bss->written_stack_out; int duration = 0; + if (CHECK(!skel->bss->run_cnt, "invalid run_cnt", + "checked sample validity before prog run")) + return; + if (CHECK(!skel->bss->valid, "output not valid", "no valid sample from prog")) return; @@ -83,8 +91,12 @@ static void test_perf_branches_common(int perf_fd, err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); if (CHECK(err, "set_affinity", "cpu #0, err %d\n", err)) goto out_destroy; - /* spin the loop for a while (random high number) */ - for (i = 0; i < 1000000; ++i) + + /* Spin the loop for a while by using a high iteration count, and by + * checking whether the specific run count marker has been explicitly + * incremented at least once by the backing perf_event BPF program. + */ + for (i = 0; i < 100000000 && !*(volatile int *)&skel->bss->run_cnt; ++i) ++j; test_perf_branches__detach(skel); @@ -116,11 +128,11 @@ static void test_perf_branches_hw(void) pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); /* - * Some setups don't support branch records (virtual machines, !x86), - * so skip test in this case. + * Some setups don't support LBR (virtual machines, !x86, AMD Milan Zen + * 3 which only supports BRS), so skip test in this case. */ if (pfd < 0) { - if (errno == ENOENT || errno == EOPNOTSUPP) { + if (errno == ENOENT || errno == EOPNOTSUPP || errno == EINVAL) { printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n", __func__); test__skip(); diff --git a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c index c9f855e5da24..246eb259c08a 100644 --- a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c @@ -28,6 +28,7 @@ static void test_success(void) bpf_program__set_autoload(skel->progs.two_regions, true); bpf_program__set_autoload(skel->progs.non_sleepable_1, true); bpf_program__set_autoload(skel->progs.non_sleepable_2, true); + bpf_program__set_autoload(skel->progs.nested_rcu_region, true); bpf_program__set_autoload(skel->progs.task_trusted_non_rcuptr, true); bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog, true); bpf_program__set_autoload(skel->progs.rcu_read_lock_global_subprog, true); @@ -78,7 +79,8 @@ static const char * const inproper_region_tests[] = { "non_sleepable_rcu_mismatch", "inproper_sleepable_helper", "inproper_sleepable_kfunc", - "nested_rcu_region", + "nested_rcu_region_unbalanced_1", + "nested_rcu_region_unbalanced_2", "rcu_read_lock_global_subprog_lock", "rcu_read_lock_global_subprog_unlock", "rcu_read_lock_sleepable_helper_global_subprog", diff --git a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c index d6bd5e16e637..d2c0542716a8 100644 --- a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c @@ -44,3 +44,59 @@ void test_refcounted_kptr_wrong_owner(void) ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a2 retval"); refcounted_kptr__destroy(skel); } + +void test_percpu_hash_refcounted_kptr_refcount_leak(void) +{ + struct refcounted_kptr *skel; + int cpu_nr, fd, err, key = 0; + struct bpf_map *map; + size_t values_sz; + u64 *values; + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + + cpu_nr = libbpf_num_possible_cpus(); + if (!ASSERT_GT(cpu_nr, 0, "libbpf_num_possible_cpus")) + return; + + values = calloc(cpu_nr, sizeof(u64)); + if (!ASSERT_OK_PTR(values, "calloc values")) + return; + + skel = refcounted_kptr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load")) { + free(values); + return; + } + + values_sz = cpu_nr * sizeof(u64); + memset(values, 0, values_sz); + + map = skel->maps.percpu_hash; + err = bpf_map__update_elem(map, &key, sizeof(key), values, values_sz, 0); + if (!ASSERT_OK(err, "bpf_map__update_elem")) + goto out; + + fd = bpf_program__fd(skel->progs.percpu_hash_refcount_leak); + err = bpf_prog_test_run_opts(fd, &opts); + if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) + goto out; + if (!ASSERT_EQ(opts.retval, 2, "opts.retval")) + goto out; + + err = bpf_map__update_elem(map, &key, sizeof(key), values, values_sz, 0); + if (!ASSERT_OK(err, "bpf_map__update_elem")) + goto out; + + fd = bpf_program__fd(skel->progs.check_percpu_hash_refcount); + err = bpf_prog_test_run_opts(fd, &opts); + ASSERT_OK(err, "bpf_prog_test_run_opts"); + ASSERT_EQ(opts.retval, 1, "opts.retval"); + +out: + refcounted_kptr__destroy(skel); + free(values); +} diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c index 8c6c2043a432..f0a8c828f8f1 100644 --- a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c +++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c @@ -110,8 +110,8 @@ void serial_test_res_spin_lock_stress(void) ASSERT_OK(load_module("bpf_test_rqspinlock.ko", false), "load module AA"); sleep(5); unload_module("bpf_test_rqspinlock", false); - - ASSERT_OK(load_module_params("bpf_test_rqspinlock.ko", "test_ab=1", false), "load module ABBA"); - sleep(5); - unload_module("bpf_test_rqspinlock", false); + /* + * Insert bpf_test_rqspinlock.ko manually with test_mode=[1|2] to test + * other cases (ABBA, ABBCCA). + */ } diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index d1e4cb28a72c..64520684d2cb 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -17,6 +17,7 @@ #include "test_ringbuf_n.lskel.h" #include "test_ringbuf_map_key.lskel.h" #include "test_ringbuf_write.lskel.h" +#include "test_ringbuf_overwrite.lskel.h" #define EDONE 7777 @@ -497,6 +498,68 @@ cleanup: test_ringbuf_map_key_lskel__destroy(skel_map_key); } +static void ringbuf_overwrite_mode_subtest(void) +{ + unsigned long size, len1, len2, len3, len4, len5; + unsigned long expect_avail_data, expect_prod_pos, expect_over_pos; + struct test_ringbuf_overwrite_lskel *skel; + int page_size = getpagesize(); + int err; + + skel = test_ringbuf_overwrite_lskel__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + size = page_size; + len1 = page_size / 2; + len2 = page_size / 4; + len3 = size - len1 - len2 - BPF_RINGBUF_HDR_SZ * 3; + len4 = len3 - 8; + len5 = len3; /* retry with len3 */ + + skel->maps.ringbuf.max_entries = size; + skel->rodata->LEN1 = len1; + skel->rodata->LEN2 = len2; + skel->rodata->LEN3 = len3; + skel->rodata->LEN4 = len4; + skel->rodata->LEN5 = len5; + + skel->bss->pid = getpid(); + + err = test_ringbuf_overwrite_lskel__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + err = test_ringbuf_overwrite_lskel__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto cleanup; + + syscall(__NR_getpgid); + + ASSERT_EQ(skel->bss->reserve1_fail, 0, "reserve 1"); + ASSERT_EQ(skel->bss->reserve2_fail, 0, "reserve 2"); + ASSERT_EQ(skel->bss->reserve3_fail, 1, "reserve 3"); + ASSERT_EQ(skel->bss->reserve4_fail, 0, "reserve 4"); + ASSERT_EQ(skel->bss->reserve5_fail, 0, "reserve 5"); + + ASSERT_EQ(skel->bss->ring_size, size, "check_ring_size"); + + expect_avail_data = len2 + len4 + len5 + 3 * BPF_RINGBUF_HDR_SZ; + ASSERT_EQ(skel->bss->avail_data, expect_avail_data, "check_avail_size"); + + ASSERT_EQ(skel->bss->cons_pos, 0, "check_cons_pos"); + + expect_prod_pos = len1 + len2 + len4 + len5 + 4 * BPF_RINGBUF_HDR_SZ; + ASSERT_EQ(skel->bss->prod_pos, expect_prod_pos, "check_prod_pos"); + + expect_over_pos = len1 + BPF_RINGBUF_HDR_SZ; + ASSERT_EQ(skel->bss->over_pos, expect_over_pos, "check_over_pos"); + + test_ringbuf_overwrite_lskel__detach(skel); +cleanup: + test_ringbuf_overwrite_lskel__destroy(skel); +} + void test_ringbuf(void) { if (test__start_subtest("ringbuf")) @@ -507,4 +570,6 @@ void test_ringbuf(void) ringbuf_map_key_subtest(); if (test__start_subtest("ringbuf_write")) ringbuf_write_subtest(); + if (test__start_subtest("ringbuf_overwrite_mode")) + ringbuf_overwrite_mode_subtest(); } diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 036d4760d2c1..3dbcc091f16c 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -41,11 +41,7 @@ static struct bpf_object *obj; static __u32 index_zero; static int epfd; -static union sa46 { - struct sockaddr_in6 v6; - struct sockaddr_in v4; - sa_family_t family; -} srv_sa; +static struct sockaddr_storage srv_sa; #define RET_IF(condition, tag, format...) ({ \ if (CHECK_FAIL(condition)) { \ @@ -135,24 +131,24 @@ static int prepare_bpf_obj(void) return 0; } -static void sa46_init_loopback(union sa46 *sa, sa_family_t family) +static void ss_init_loopback(struct sockaddr_storage *sa, sa_family_t family) { memset(sa, 0, sizeof(*sa)); - sa->family = family; - if (sa->family == AF_INET6) - sa->v6.sin6_addr = in6addr_loopback; + sa->ss_family = family; + if (sa->ss_family == AF_INET6) + ((struct sockaddr_in6 *)sa)->sin6_addr = in6addr_loopback; else - sa->v4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + ((struct sockaddr_in *)sa)->sin_addr.s_addr = htonl(INADDR_LOOPBACK); } -static void sa46_init_inany(union sa46 *sa, sa_family_t family) +static void ss_init_inany(struct sockaddr_storage *sa, sa_family_t family) { memset(sa, 0, sizeof(*sa)); - sa->family = family; - if (sa->family == AF_INET6) - sa->v6.sin6_addr = in6addr_any; + sa->ss_family = family; + if (sa->ss_family == AF_INET6) + ((struct sockaddr_in6 *)sa)->sin6_addr = in6addr_any; else - sa->v4.sin_addr.s_addr = INADDR_ANY; + ((struct sockaddr_in *)sa)->sin_addr.s_addr = INADDR_ANY; } static int read_int_sysctl(const char *sysctl) @@ -228,7 +224,7 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, int cli_fd) { struct data_check expected = {}, result; - union sa46 cli_sa; + struct sockaddr_storage cli_sa; socklen_t addrlen; int err; @@ -251,26 +247,32 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, } if (family == AF_INET6) { + struct sockaddr_in6 *srv_v6 = (struct sockaddr_in6 *)&srv_sa; + struct sockaddr_in6 *cli_v6 = (struct sockaddr_in6 *)&cli_sa; + expected.eth_protocol = htons(ETH_P_IPV6); - expected.bind_inany = !srv_sa.v6.sin6_addr.s6_addr32[3] && - !srv_sa.v6.sin6_addr.s6_addr32[2] && - !srv_sa.v6.sin6_addr.s6_addr32[1] && - !srv_sa.v6.sin6_addr.s6_addr32[0]; + expected.bind_inany = !srv_v6->sin6_addr.s6_addr32[3] && + !srv_v6->sin6_addr.s6_addr32[2] && + !srv_v6->sin6_addr.s6_addr32[1] && + !srv_v6->sin6_addr.s6_addr32[0]; - memcpy(&expected.skb_addrs[0], cli_sa.v6.sin6_addr.s6_addr32, - sizeof(cli_sa.v6.sin6_addr)); + memcpy(&expected.skb_addrs[0], cli_v6->sin6_addr.s6_addr32, + sizeof(cli_v6->sin6_addr)); memcpy(&expected.skb_addrs[4], &in6addr_loopback, sizeof(in6addr_loopback)); - expected.skb_ports[0] = cli_sa.v6.sin6_port; - expected.skb_ports[1] = srv_sa.v6.sin6_port; + expected.skb_ports[0] = cli_v6->sin6_port; + expected.skb_ports[1] = srv_v6->sin6_port; } else { + struct sockaddr_in *srv_v4 = (struct sockaddr_in *)&srv_sa; + struct sockaddr_in *cli_v4 = (struct sockaddr_in *)&cli_sa; + expected.eth_protocol = htons(ETH_P_IP); - expected.bind_inany = !srv_sa.v4.sin_addr.s_addr; + expected.bind_inany = !srv_v4->sin_addr.s_addr; - expected.skb_addrs[0] = cli_sa.v4.sin_addr.s_addr; + expected.skb_addrs[0] = cli_v4->sin_addr.s_addr; expected.skb_addrs[1] = htonl(INADDR_LOOPBACK); - expected.skb_ports[0] = cli_sa.v4.sin_port; - expected.skb_ports[1] = srv_sa.v4.sin_port; + expected.skb_ports[0] = cli_v4->sin_port; + expected.skb_ports[1] = srv_v4->sin_port; } if (memcmp(&result, &expected, offsetof(struct data_check, @@ -364,16 +366,15 @@ static void check_results(void) static int send_data(int type, sa_family_t family, void *data, size_t len, enum result expected) { - union sa46 cli_sa; + struct sockaddr_storage cli_sa; int fd, err; fd = socket(family, type, 0); RET_ERR(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno); - sa46_init_loopback(&cli_sa, family); + ss_init_loopback(&cli_sa, family); err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa)); RET_ERR(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno); - err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa, sizeof(srv_sa)); RET_ERR(err != len && expected >= PASS, @@ -589,9 +590,9 @@ static void prepare_sk_fds(int type, sa_family_t family, bool inany) socklen_t addrlen; if (inany) - sa46_init_inany(&srv_sa, family); + ss_init_inany(&srv_sa, family); else - sa46_init_loopback(&srv_sa, family); + ss_init_loopback(&srv_sa, family); addrlen = sizeof(srv_sa); /* diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 1702aa592c2c..7ac4d5a488aa 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -206,6 +206,11 @@ destroy_skel: skel_open_load_failure: close(pipe_c2p[0]); close(pipe_p2c[1]); + /* + * Child is either about to exit cleanly or stuck in case of errors. + * Nudge it to exit. + */ + kill(pid, SIGKILL); wait(NULL); } diff --git a/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c new file mode 100644 index 000000000000..e4940583924b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include <test_progs.h> +#include "sk_bypass_prot_mem.skel.h" +#include "network_helpers.h" + +#define NR_PAGES 32 +#define NR_SOCKETS 2 +#define BUF_TOTAL (NR_PAGES * 4096 / NR_SOCKETS) +#define BUF_SINGLE 1024 +#define NR_SEND (BUF_TOTAL / BUF_SINGLE) + +struct test_case { + char name[8]; + int family; + int type; + int (*create_sockets)(struct test_case *test_case, int sk[], int len); + long (*get_memory_allocated)(struct test_case *test_case, struct sk_bypass_prot_mem *skel); +}; + +static int tcp_create_sockets(struct test_case *test_case, int sk[], int len) +{ + int server, i, err = 0; + + server = start_server(test_case->family, test_case->type, NULL, 0, 0); + if (!ASSERT_GE(server, 0, "start_server_str")) + return server; + + /* Keep for-loop so we can change NR_SOCKETS easily. */ + for (i = 0; i < len; i += 2) { + sk[i] = connect_to_fd(server, 0); + if (sk[i] < 0) { + ASSERT_GE(sk[i], 0, "connect_to_fd"); + err = sk[i]; + break; + } + + sk[i + 1] = accept(server, NULL, NULL); + if (sk[i + 1] < 0) { + ASSERT_GE(sk[i + 1], 0, "accept"); + err = sk[i + 1]; + break; + } + } + + close(server); + + return err; +} + +static int udp_create_sockets(struct test_case *test_case, int sk[], int len) +{ + int i, j, err, rcvbuf = BUF_TOTAL; + + /* Keep for-loop so we can change NR_SOCKETS easily. */ + for (i = 0; i < len; i += 2) { + sk[i] = start_server(test_case->family, test_case->type, NULL, 0, 0); + if (sk[i] < 0) { + ASSERT_GE(sk[i], 0, "start_server"); + return sk[i]; + } + + sk[i + 1] = connect_to_fd(sk[i], 0); + if (sk[i + 1] < 0) { + ASSERT_GE(sk[i + 1], 0, "connect_to_fd"); + return sk[i + 1]; + } + + err = connect_fd_to_fd(sk[i], sk[i + 1], 0); + if (err) { + ASSERT_EQ(err, 0, "connect_fd_to_fd"); + return err; + } + + for (j = 0; j < 2; j++) { + err = setsockopt(sk[i + j], SOL_SOCKET, SO_RCVBUF, &rcvbuf, sizeof(int)); + if (err) { + ASSERT_EQ(err, 0, "setsockopt(SO_RCVBUF)"); + return err; + } + } + } + + return 0; +} + +static long get_memory_allocated(struct test_case *test_case, + bool *activated, long *memory_allocated) +{ + int sk; + + *activated = true; + + /* AF_INET and AF_INET6 share the same memory_allocated. + * tcp_init_sock() is called by AF_INET and AF_INET6, + * but udp_lib_init_sock() is inline. + */ + sk = socket(AF_INET, test_case->type, 0); + if (!ASSERT_GE(sk, 0, "get_memory_allocated")) + return -1; + + close(sk); + + return *memory_allocated; +} + +static long tcp_get_memory_allocated(struct test_case *test_case, struct sk_bypass_prot_mem *skel) +{ + return get_memory_allocated(test_case, + &skel->bss->tcp_activated, + &skel->bss->tcp_memory_allocated); +} + +static long udp_get_memory_allocated(struct test_case *test_case, struct sk_bypass_prot_mem *skel) +{ + return get_memory_allocated(test_case, + &skel->bss->udp_activated, + &skel->bss->udp_memory_allocated); +} + +static int check_bypass(struct test_case *test_case, + struct sk_bypass_prot_mem *skel, bool bypass) +{ + char buf[BUF_SINGLE] = {}; + long memory_allocated[2]; + int sk[NR_SOCKETS]; + int err, i, j; + + for (i = 0; i < ARRAY_SIZE(sk); i++) + sk[i] = -1; + + err = test_case->create_sockets(test_case, sk, ARRAY_SIZE(sk)); + if (err) + goto close; + + memory_allocated[0] = test_case->get_memory_allocated(test_case, skel); + + /* allocate pages >= NR_PAGES */ + for (i = 0; i < ARRAY_SIZE(sk); i++) { + for (j = 0; j < NR_SEND; j++) { + int bytes = send(sk[i], buf, sizeof(buf), 0); + + /* Avoid too noisy logs when something failed. */ + if (bytes != sizeof(buf)) { + ASSERT_EQ(bytes, sizeof(buf), "send"); + if (bytes < 0) { + err = bytes; + goto drain; + } + } + } + } + + memory_allocated[1] = test_case->get_memory_allocated(test_case, skel); + + if (bypass) + ASSERT_LE(memory_allocated[1], memory_allocated[0] + 10, "bypass"); + else + ASSERT_GT(memory_allocated[1], memory_allocated[0] + NR_PAGES, "no bypass"); + +drain: + if (test_case->type == SOCK_DGRAM) { + /* UDP starts purging sk->sk_receive_queue after one RCU + * grace period, then udp_memory_allocated goes down, + * so drain the queue before close(). + */ + for (i = 0; i < ARRAY_SIZE(sk); i++) { + for (j = 0; j < NR_SEND; j++) { + int bytes = recv(sk[i], buf, 1, MSG_DONTWAIT | MSG_TRUNC); + + if (bytes == sizeof(buf)) + continue; + if (bytes != -1 || errno != EAGAIN) + PRINT_FAIL("bytes: %d, errno: %s\n", bytes, strerror(errno)); + break; + } + } + } + +close: + for (i = 0; i < ARRAY_SIZE(sk); i++) { + if (sk[i] < 0) + break; + + close(sk[i]); + } + + return err; +} + +static void run_test(struct test_case *test_case) +{ + struct sk_bypass_prot_mem *skel; + struct nstoken *nstoken; + int cgroup, err; + + skel = sk_bypass_prot_mem__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + skel->bss->nr_cpus = libbpf_num_possible_cpus(); + + err = sk_bypass_prot_mem__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto destroy_skel; + + cgroup = test__join_cgroup("/sk_bypass_prot_mem"); + if (!ASSERT_GE(cgroup, 0, "join_cgroup")) + goto destroy_skel; + + err = make_netns("sk_bypass_prot_mem"); + if (!ASSERT_EQ(err, 0, "make_netns")) + goto close_cgroup; + + nstoken = open_netns("sk_bypass_prot_mem"); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto remove_netns; + + err = check_bypass(test_case, skel, false); + if (!ASSERT_EQ(err, 0, "test_bypass(false)")) + goto close_netns; + + err = write_sysctl("/proc/sys/net/core/bypass_prot_mem", "1"); + if (!ASSERT_EQ(err, 0, "write_sysctl(1)")) + goto close_netns; + + err = check_bypass(test_case, skel, true); + if (!ASSERT_EQ(err, 0, "test_bypass(true by sysctl)")) + goto close_netns; + + err = write_sysctl("/proc/sys/net/core/bypass_prot_mem", "0"); + if (!ASSERT_EQ(err, 0, "write_sysctl(0)")) + goto close_netns; + + skel->links.sock_create = bpf_program__attach_cgroup(skel->progs.sock_create, cgroup); + if (!ASSERT_OK_PTR(skel->links.sock_create, "attach_cgroup(sock_create)")) + goto close_netns; + + err = check_bypass(test_case, skel, true); + ASSERT_EQ(err, 0, "test_bypass(true by bpf)"); + +close_netns: + close_netns(nstoken); +remove_netns: + remove_netns("sk_bypass_prot_mem"); +close_cgroup: + close(cgroup); +destroy_skel: + sk_bypass_prot_mem__destroy(skel); +} + +static struct test_case test_cases[] = { + { + .name = "TCP ", + .family = AF_INET, + .type = SOCK_STREAM, + .create_sockets = tcp_create_sockets, + .get_memory_allocated = tcp_get_memory_allocated, + }, + { + .name = "UDP ", + .family = AF_INET, + .type = SOCK_DGRAM, + .create_sockets = udp_create_sockets, + .get_memory_allocated = udp_get_memory_allocated, + }, + { + .name = "TCPv6", + .family = AF_INET6, + .type = SOCK_STREAM, + .create_sockets = tcp_create_sockets, + .get_memory_allocated = tcp_get_memory_allocated, + }, + { + .name = "UDPv6", + .family = AF_INET6, + .type = SOCK_DGRAM, + .create_sockets = udp_create_sockets, + .get_memory_allocated = udp_get_memory_allocated, + }, +}; + +void serial_test_sk_bypass_prot_mem(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + if (test__start_subtest(test_cases[i].name)) + run_test(&test_cases[i]); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c index 4d66fad3c8bd..0f3bf594e7a5 100644 --- a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c +++ b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c @@ -20,7 +20,9 @@ static const char * const test_cases[] = { "strcspn_str", "strcspn_reject", "strstr", + "strcasestr", "strnstr", + "strncasestr", }; void run_too_long_tests(void) diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c new file mode 100644 index 000000000000..de22734abc4d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c @@ -0,0 +1,390 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <linux/genetlink.h> +#include "network_helpers.h" +#include "bpf_smc.skel.h" + +#ifndef IPPROTO_SMC +#define IPPROTO_SMC 256 +#endif + +#define CLIENT_IP "127.0.0.1" +#define SERVER_IP "127.0.1.0" +#define SERVER_IP_VIA_RISK_PATH "127.0.2.0" + +#define SERVICE_1 80 +#define SERVICE_2 443 +#define SERVICE_3 8443 + +#define TEST_NS "bpf_smc_netns" + +static struct netns_obj *test_netns; + +struct smc_policy_ip_key { + __u32 sip; + __u32 dip; +}; + +struct smc_policy_ip_value { + __u8 mode; +}; + +#if defined(__s390x__) +/* s390x has default seid */ +static bool setup_ueid(void) { return true; } +static void cleanup_ueid(void) {} +#else +enum { + SMC_NETLINK_ADD_UEID = 10, + SMC_NETLINK_REMOVE_UEID +}; + +enum { + SMC_NLA_EID_TABLE_UNSPEC, + SMC_NLA_EID_TABLE_ENTRY, /* string */ +}; + +struct msgtemplate { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[1024]; +}; + +#define GENLMSG_DATA(glh) ((void *)(NLMSG_DATA(glh) + GENL_HDRLEN)) +#define GENLMSG_PAYLOAD(glh) (NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN) +#define NLA_DATA(na) ((void *)((char *)(na) + NLA_HDRLEN)) +#define NLA_PAYLOAD(len) ((len) - NLA_HDRLEN) + +#define SMC_GENL_FAMILY_NAME "SMC_GEN_NETLINK" +#define SMC_BPFTEST_UEID "SMC-BPFTEST-UEID" + +static uint16_t smc_nl_family_id = -1; + +static int send_cmd(int fd, __u16 nlmsg_type, __u32 nlmsg_pid, + __u16 nlmsg_flags, __u8 genl_cmd, __u16 nla_type, + void *nla_data, int nla_len) +{ + struct nlattr *na; + struct sockaddr_nl nladdr; + int r, buflen; + char *buf; + + struct msgtemplate msg = {0}; + + msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + msg.n.nlmsg_type = nlmsg_type; + msg.n.nlmsg_flags = nlmsg_flags; + msg.n.nlmsg_seq = 0; + msg.n.nlmsg_pid = nlmsg_pid; + msg.g.cmd = genl_cmd; + msg.g.version = 1; + na = (struct nlattr *)GENLMSG_DATA(&msg); + na->nla_type = nla_type; + na->nla_len = nla_len + 1 + NLA_HDRLEN; + memcpy(NLA_DATA(na), nla_data, nla_len); + msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len); + + buf = (char *)&msg; + buflen = msg.n.nlmsg_len; + memset(&nladdr, 0, sizeof(nladdr)); + nladdr.nl_family = AF_NETLINK; + + while ((r = sendto(fd, buf, buflen, 0, (struct sockaddr *)&nladdr, + sizeof(nladdr))) < buflen) { + if (r > 0) { + buf += r; + buflen -= r; + } else if (errno != EAGAIN) { + return -1; + } + } + return 0; +} + +static bool get_smc_nl_family_id(void) +{ + struct sockaddr_nl nl_src; + struct msgtemplate msg; + struct nlattr *nl; + int fd, ret; + pid_t pid; + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + if (!ASSERT_OK_FD(fd, "nl_family socket")) + return false; + + pid = getpid(); + + memset(&nl_src, 0, sizeof(nl_src)); + nl_src.nl_family = AF_NETLINK; + nl_src.nl_pid = pid; + + ret = bind(fd, (struct sockaddr *)&nl_src, sizeof(nl_src)); + if (!ASSERT_OK(ret, "nl_family bind")) + goto fail; + + ret = send_cmd(fd, GENL_ID_CTRL, pid, + NLM_F_REQUEST, CTRL_CMD_GETFAMILY, + CTRL_ATTR_FAMILY_NAME, (void *)SMC_GENL_FAMILY_NAME, + strlen(SMC_GENL_FAMILY_NAME)); + if (!ASSERT_OK(ret, "nl_family query")) + goto fail; + + ret = recv(fd, &msg, sizeof(msg), 0); + if (!ASSERT_FALSE(msg.n.nlmsg_type == NLMSG_ERROR || ret < 0 || + !NLMSG_OK(&msg.n, ret), "nl_family response")) + goto fail; + + nl = (struct nlattr *)GENLMSG_DATA(&msg); + nl = (struct nlattr *)((char *)nl + NLA_ALIGN(nl->nla_len)); + if (!ASSERT_EQ(nl->nla_type, CTRL_ATTR_FAMILY_ID, "nl_family nla type")) + goto fail; + + smc_nl_family_id = *(uint16_t *)NLA_DATA(nl); + close(fd); + return true; +fail: + close(fd); + return false; +} + +static bool smc_ueid(int op) +{ + struct sockaddr_nl nl_src; + struct msgtemplate msg; + struct nlmsgerr *err; + char test_ueid[32]; + int fd, ret; + pid_t pid; + + /* UEID required */ + memset(test_ueid, '\x20', sizeof(test_ueid)); + memcpy(test_ueid, SMC_BPFTEST_UEID, strlen(SMC_BPFTEST_UEID)); + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + if (!ASSERT_OK_FD(fd, "ueid socket")) + return false; + + pid = getpid(); + memset(&nl_src, 0, sizeof(nl_src)); + nl_src.nl_family = AF_NETLINK; + nl_src.nl_pid = pid; + + ret = bind(fd, (struct sockaddr *)&nl_src, sizeof(nl_src)); + if (!ASSERT_OK(ret, "ueid bind")) + goto fail; + + ret = send_cmd(fd, smc_nl_family_id, pid, + NLM_F_REQUEST | NLM_F_ACK, op, SMC_NLA_EID_TABLE_ENTRY, + (void *)test_ueid, sizeof(test_ueid)); + if (!ASSERT_OK(ret, "ueid cmd")) + goto fail; + + ret = recv(fd, &msg, sizeof(msg), 0); + if (!ASSERT_FALSE(ret < 0 || + !NLMSG_OK(&msg.n, ret), "ueid response")) + goto fail; + + if (msg.n.nlmsg_type == NLMSG_ERROR) { + err = NLMSG_DATA(&msg); + switch (op) { + case SMC_NETLINK_REMOVE_UEID: + if (!ASSERT_FALSE((err->error && err->error != -ENOENT), + "ueid remove")) + goto fail; + break; + case SMC_NETLINK_ADD_UEID: + if (!ASSERT_OK(err->error, "ueid add")) + goto fail; + break; + default: + break; + } + } + close(fd); + return true; +fail: + close(fd); + return false; +} + +static bool setup_ueid(void) +{ + /* get smc nl id */ + if (!get_smc_nl_family_id()) + return false; + /* clear old ueid for bpftest */ + smc_ueid(SMC_NETLINK_REMOVE_UEID); + /* smc-loopback required ueid */ + return smc_ueid(SMC_NETLINK_ADD_UEID); +} + +static void cleanup_ueid(void) +{ + smc_ueid(SMC_NETLINK_REMOVE_UEID); +} +#endif /* __s390x__ */ + +static bool setup_netns(void) +{ + test_netns = netns_new(TEST_NS, true); + if (!ASSERT_OK_PTR(test_netns, "open net namespace")) + goto fail_netns; + + SYS(fail_ip, "ip addr add 127.0.1.0/8 dev lo"); + SYS(fail_ip, "ip addr add 127.0.2.0/8 dev lo"); + + return true; +fail_ip: + netns_free(test_netns); +fail_netns: + return false; +} + +static void cleanup_netns(void) +{ + netns_free(test_netns); +} + +static bool setup_smc(void) +{ + if (!setup_ueid()) + return false; + + if (!setup_netns()) + goto fail_netns; + + return true; +fail_netns: + cleanup_ueid(); + return false; +} + +static int set_client_addr_cb(int fd, void *opts) +{ + const char *src = (const char *)opts; + struct sockaddr_in localaddr; + + localaddr.sin_family = AF_INET; + localaddr.sin_port = htons(0); + localaddr.sin_addr.s_addr = inet_addr(src); + return !ASSERT_OK(bind(fd, &localaddr, sizeof(localaddr)), "client bind"); +} + +static void run_link(const char *src, const char *dst, int port) +{ + struct network_helper_opts opts = {0}; + int server, client; + + server = start_server_str(AF_INET, SOCK_STREAM, dst, port, NULL); + if (!ASSERT_OK_FD(server, "start service_1")) + return; + + opts.proto = IPPROTO_TCP; + opts.post_socket_cb = set_client_addr_cb; + opts.cb_opts = (void *)src; + + client = connect_to_fd_opts(server, &opts); + if (!ASSERT_OK_FD(client, "start connect")) + goto fail_client; + + close(client); +fail_client: + close(server); +} + +static void block_link(int map_fd, const char *src, const char *dst) +{ + struct smc_policy_ip_value val = { .mode = /* block */ 0 }; + struct smc_policy_ip_key key = { + .sip = inet_addr(src), + .dip = inet_addr(dst), + }; + + bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); +} + +/* + * This test describes a real-life service topology as follows: + * + * +-------------> service_1 + * link 1 | | + * +--------------------> server | link 2 + * | | V + * | +-------------> service_2 + * | link 3 + * client -------------------> server_via_unsafe_path -> service_3 + * + * Among them, + * 1. link-1 is very suitable for using SMC. + * 2. link-2 is not suitable for using SMC, because the mode of this link is + * kind of short-link services. + * 3. link-3 is also not suitable for using SMC, because the RDMA link is + * unavailable and needs to go through a long timeout before it can fallback + * to TCP. + * To achieve this goal, we use a customized SMC ip strategy via smc_hs_ctrl. + */ +static void test_topo(void) +{ + struct bpf_smc *skel; + int rc, map_fd; + + skel = bpf_smc__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_smc__open_and_load")) + return; + + rc = bpf_smc__attach(skel); + if (!ASSERT_OK(rc, "bpf_smc__attach")) + goto fail; + + map_fd = bpf_map__fd(skel->maps.smc_policy_ip); + if (!ASSERT_OK_FD(map_fd, "bpf_map__fd")) + goto fail; + + /* Mock the process of transparent replacement, since we will modify + * protocol to ipproto_smc accropding to it via + * fmod_ret/update_socket_protocol. + */ + write_sysctl("/proc/sys/net/smc/hs_ctrl", "linkcheck"); + + /* Configure ip strat */ + block_link(map_fd, CLIENT_IP, SERVER_IP_VIA_RISK_PATH); + block_link(map_fd, SERVER_IP, SERVER_IP); + + /* should go with smc */ + run_link(CLIENT_IP, SERVER_IP, SERVICE_1); + /* should go with smc fallback */ + run_link(SERVER_IP, SERVER_IP, SERVICE_2); + + ASSERT_EQ(skel->bss->smc_cnt, 2, "smc count"); + ASSERT_EQ(skel->bss->fallback_cnt, 1, "fallback count"); + + /* should go with smc */ + run_link(CLIENT_IP, SERVER_IP, SERVICE_2); + + ASSERT_EQ(skel->bss->smc_cnt, 3, "smc count"); + ASSERT_EQ(skel->bss->fallback_cnt, 1, "fallback count"); + + /* should go with smc fallback */ + run_link(CLIENT_IP, SERVER_IP_VIA_RISK_PATH, SERVICE_3); + + ASSERT_EQ(skel->bss->smc_cnt, 4, "smc count"); + ASSERT_EQ(skel->bss->fallback_cnt, 2, "fallback count"); + +fail: + bpf_smc__destroy(skel); +} + +void test_bpf_smc(void) +{ + if (!setup_smc()) { + printf("setup for smc test failed, test SKIP:\n"); + test__skip(); + return; + } + + if (test__start_subtest("topo")) + test_topo(); + + cleanup_ueid(); + cleanup_netns(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c index 2a27f3714f5c..bdc4fc06bc5a 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -139,7 +139,7 @@ static void test_lsm_tailcall(void) if (CHECK_FAIL(!err)) goto close_prog; - prog_fd = bpf_program__fd(skel->progs.lsm_file_alloc_security_prog); + prog_fd = bpf_program__fd(skel->progs.lsm_kernfs_init_security_prog); if (CHECK_FAIL(prog_fd < 0)) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_edt.c b/tools/testing/selftests/bpf/prog_tests/test_tc_edt.c new file mode 100644 index 000000000000..462512fb191f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_tc_edt.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * BPF-based flow shaping + * + * The test brings up two veth in two isolated namespaces, attach some flow + * shaping program onto it, and ensures that a manual speedtest maximum + * value matches the rate set in the BPF shapers. + */ + +#include <asm-generic/socket.h> +#include <stdio.h> +#include <unistd.h> +#include <fcntl.h> +#include <math.h> +#include <sys/time.h> +#include <sys/socket.h> +#include <bpf/libbpf.h> +#include <pthread.h> +#include "test_progs.h" +#include "network_helpers.h" +#include "test_tc_edt.skel.h" + +#define SERVER_NS "tc-edt-server-ns" +#define CLIENT_NS "tc-edt-client-ns" +#define IP4_ADDR_VETH1 "192.168.1.1" +#define IP4_ADDR_VETH2 "192.168.1.2" +#define IP4_ADDR_VETH2_HEX 0xC0A80102 + +#define TIMEOUT_MS 2000 +#define TEST_PORT 9000 +#define TARGET_RATE_MBPS 5.0 +#define TX_BYTES_COUNT (1 * 1000 * 1000) +#define RATE_ERROR_PERCENT 2.0 + +struct connection { + int server_listen_fd; + int server_conn_fd; + int client_conn_fd; +}; + +static int setup(struct test_tc_edt *skel) +{ + struct nstoken *nstoken_client, *nstoken_server; + int ret; + + if (!ASSERT_OK(make_netns(CLIENT_NS), "create client ns")) + goto fail; + if (!ASSERT_OK(make_netns(SERVER_NS), "create server ns")) + goto fail_delete_client_ns; + + nstoken_client = open_netns(CLIENT_NS); + if (!ASSERT_OK_PTR(nstoken_client, "open client ns")) + goto fail_delete_server_ns; + SYS(fail_close_client_ns, "ip link add veth1 type veth peer name %s", + "veth2 netns " SERVER_NS); + SYS(fail_close_client_ns, "ip -4 addr add " IP4_ADDR_VETH1 "/24 dev veth1"); + SYS(fail_close_client_ns, "ip link set veth1 up"); + + nstoken_server = open_netns(SERVER_NS); + if (!ASSERT_OK_PTR(nstoken_server, "enter server ns")) + goto fail_close_client_ns; + SYS(fail_close_server_ns, "ip -4 addr add " IP4_ADDR_VETH2 "/24 dev veth2"); + SYS(fail_close_server_ns, "ip link set veth2 up"); + SYS(fail_close_server_ns, "tc qdisc add dev veth2 root fq"); + ret = tc_prog_attach("veth2", -1, bpf_program__fd(skel->progs.tc_prog)); + if (!ASSERT_OK(ret, "attach bpf prog")) + goto fail_close_server_ns; + skel->bss->target_rate = TARGET_RATE_MBPS * 1000 * 1000; + close_netns(nstoken_server); + close_netns(nstoken_client); + + return 0; + +fail_close_server_ns: + close_netns(nstoken_server); +fail_close_client_ns: + close_netns(nstoken_client); +fail_delete_server_ns: + remove_netns(SERVER_NS); +fail_delete_client_ns: + remove_netns(CLIENT_NS); +fail: + return -1; +} + +static void cleanup(void) +{ + remove_netns(CLIENT_NS); + remove_netns(SERVER_NS); +} + +static void run_test(void) +{ + int server_fd, client_fd, err; + double rate_mbps, rate_error; + struct nstoken *nstoken; + __u64 ts_start, ts_end; + + nstoken = open_netns(SERVER_NS); + if (!ASSERT_OK_PTR(nstoken, "open server ns")) + return; + server_fd = start_server(AF_INET, SOCK_STREAM, IP4_ADDR_VETH2, + TEST_PORT, TIMEOUT_MS); + if (!ASSERT_OK_FD(server_fd, "start server")) + return; + + close_netns(nstoken); + nstoken = open_netns(CLIENT_NS); + if (!ASSERT_OK_PTR(nstoken, "open client ns")) + return; + client_fd = connect_to_fd(server_fd, 0); + if (!ASSERT_OK_FD(client_fd, "connect client")) + return; + + ts_start = get_time_ns(); + err = send_recv_data(server_fd, client_fd, TX_BYTES_COUNT); + ts_end = get_time_ns(); + close_netns(nstoken); + ASSERT_OK(err, "send_recv_data"); + + rate_mbps = TX_BYTES_COUNT / ((ts_end - ts_start) / 1000.0); + rate_error = + fabs((rate_mbps - TARGET_RATE_MBPS) * 100.0 / TARGET_RATE_MBPS); + + ASSERT_LE(rate_error, RATE_ERROR_PERCENT, + "rate error is lower than threshold"); +} + +void test_tc_edt(void) +{ + struct test_tc_edt *skel; + + skel = test_tc_edt__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel open and load")) + return; + + if (!ASSERT_OK(setup(skel), "global setup")) + return; + + run_test(); + + cleanup(); + test_tc_edt__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c new file mode 100644 index 000000000000..0fe0a8f62486 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c @@ -0,0 +1,714 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +/* + * End-to-end eBPF tunnel test suite + * The file tests BPF network tunnels implementation. For each tunnel + * type, the test validates that: + * - basic communication can first be established between the two veths + * - when adding a BPF-based encapsulation on client egress, it now fails + * to communicate with the server + * - when adding a kernel-based decapsulation on server ingress, client + * can now connect + * - when replacing the kernel-based decapsulation with a BPF-based one, + * the client can still connect + */ + +#include <stdio.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/socket.h> +#include <bpf/libbpf.h> + +#include "test_progs.h" +#include "network_helpers.h" +#include "test_tc_tunnel.skel.h" + +#define SERVER_NS "tc-tunnel-server-ns" +#define CLIENT_NS "tc-tunnel-client-ns" +#define MAC_ADDR_VETH1 "00:11:22:33:44:55" +#define IP4_ADDR_VETH1 "192.168.1.1" +#define IP6_ADDR_VETH1 "fd::1" +#define MAC_ADDR_VETH2 "66:77:88:99:AA:BB" +#define IP4_ADDR_VETH2 "192.168.1.2" +#define IP6_ADDR_VETH2 "fd::2" + +#define TEST_NAME_MAX_LEN 64 +#define PROG_NAME_MAX_LEN 64 +#define TUNNEL_ARGS_MAX_LEN 128 +#define BUFFER_LEN 2000 +#define DEFAULT_TEST_DATA_SIZE 100 +#define GSO_TEST_DATA_SIZE BUFFER_LEN + +#define TIMEOUT_MS 1000 +#define TEST_PORT 8000 +#define UDP_PORT 5555 +#define MPLS_UDP_PORT 6635 +#define FOU_MPLS_PROTO 137 +#define VXLAN_ID 1 +#define VXLAN_PORT 8472 +#define MPLS_TABLE_ENTRIES_COUNT 65536 + +static char tx_buffer[BUFFER_LEN], rx_buffer[BUFFER_LEN]; + +struct subtest_cfg { + char *ebpf_tun_type; + char *iproute_tun_type; + char *mac_tun_type; + int ipproto; + void (*extra_decap_mod_args_cb)(struct subtest_cfg *cfg, char *dst); + bool tunnel_need_veth_mac; + bool configure_fou_rx_port; + char *tmode; + bool expect_kern_decap_failure; + bool configure_mpls; + bool test_gso; + char *tunnel_client_addr; + char *tunnel_server_addr; + char name[TEST_NAME_MAX_LEN]; + char *server_addr; + int client_egress_prog_fd; + int server_ingress_prog_fd; + char extra_decap_mod_args[TUNNEL_ARGS_MAX_LEN]; + int server_fd; +}; + +struct connection { + int client_fd; + int server_fd; +}; + +static int build_subtest_name(struct subtest_cfg *cfg, char *dst, size_t size) +{ + int ret; + + ret = snprintf(dst, size, "%s_%s", cfg->ebpf_tun_type, + cfg->mac_tun_type); + + return ret < 0 ? ret : 0; +} + +static int set_subtest_progs(struct subtest_cfg *cfg, struct test_tc_tunnel *skel) +{ + char prog_name[PROG_NAME_MAX_LEN]; + struct bpf_program *prog; + int ret; + + ret = snprintf(prog_name, PROG_NAME_MAX_LEN, "__encap_"); + if (ret < 0) + return ret; + ret = build_subtest_name(cfg, prog_name + ret, PROG_NAME_MAX_LEN - ret); + if (ret < 0) + return ret; + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!prog) + return -1; + + cfg->client_egress_prog_fd = bpf_program__fd(prog); + cfg->server_ingress_prog_fd = bpf_program__fd(skel->progs.decap_f); + return 0; +} + +static void set_subtest_addresses(struct subtest_cfg *cfg) +{ + if (cfg->ipproto == 6) + cfg->server_addr = IP6_ADDR_VETH2; + else + cfg->server_addr = IP4_ADDR_VETH2; + + /* Some specific tunnel types need specific addressing, it then + * has been already set in the configuration table. Otherwise, + * deduce the relevant addressing from the ipproto + */ + if (cfg->tunnel_client_addr && cfg->tunnel_server_addr) + return; + + if (cfg->ipproto == 6) { + cfg->tunnel_client_addr = IP6_ADDR_VETH1; + cfg->tunnel_server_addr = IP6_ADDR_VETH2; + } else { + cfg->tunnel_client_addr = IP4_ADDR_VETH1; + cfg->tunnel_server_addr = IP4_ADDR_VETH2; + } +} + +static int run_server(struct subtest_cfg *cfg) +{ + int family = cfg->ipproto == 6 ? AF_INET6 : AF_INET; + struct nstoken *nstoken; + struct network_helper_opts opts = { + .timeout_ms = TIMEOUT_MS + }; + + nstoken = open_netns(SERVER_NS); + if (!ASSERT_OK_PTR(nstoken, "open server ns")) + return -1; + + cfg->server_fd = start_server_str(family, SOCK_STREAM, cfg->server_addr, + TEST_PORT, &opts); + close_netns(nstoken); + if (!ASSERT_OK_FD(cfg->server_fd, "start server")) + return -1; + + return 0; +} + +static int check_server_rx_data(struct subtest_cfg *cfg, + struct connection *conn, int len) +{ + int err; + + memset(rx_buffer, 0, BUFFER_LEN); + err = recv(conn->server_fd, rx_buffer, len, 0); + if (!ASSERT_EQ(err, len, "check rx data len")) + return 1; + if (!ASSERT_MEMEQ(tx_buffer, rx_buffer, len, "check received data")) + return 1; + return 0; +} + +static struct connection *connect_client_to_server(struct subtest_cfg *cfg) +{ + struct network_helper_opts opts = {.timeout_ms = 500}; + int family = cfg->ipproto == 6 ? AF_INET6 : AF_INET; + struct connection *conn = NULL; + int client_fd, server_fd; + + conn = malloc(sizeof(struct connection)); + if (!conn) + return conn; + + client_fd = connect_to_addr_str(family, SOCK_STREAM, cfg->server_addr, + TEST_PORT, &opts); + + if (client_fd < 0) { + free(conn); + return NULL; + } + + server_fd = accept(cfg->server_fd, NULL, NULL); + if (server_fd < 0) { + close(client_fd); + free(conn); + return NULL; + } + + conn->server_fd = server_fd; + conn->client_fd = client_fd; + + return conn; +} + +static void disconnect_client_from_server(struct subtest_cfg *cfg, + struct connection *conn) +{ + close(conn->server_fd); + close(conn->client_fd); + free(conn); +} + +static int send_and_test_data(struct subtest_cfg *cfg, bool must_succeed) +{ + struct connection *conn; + int err, res = -1; + + conn = connect_client_to_server(cfg); + if (!must_succeed && !ASSERT_ERR_PTR(conn, "connection that must fail")) + goto end; + else if (!must_succeed) + return 0; + + if (!ASSERT_OK_PTR(conn, "connection that must succeed")) + return -1; + + err = send(conn->client_fd, tx_buffer, DEFAULT_TEST_DATA_SIZE, 0); + if (!ASSERT_EQ(err, DEFAULT_TEST_DATA_SIZE, "send data from client")) + goto end; + if (check_server_rx_data(cfg, conn, DEFAULT_TEST_DATA_SIZE)) + goto end; + + if (!cfg->test_gso) { + res = 0; + goto end; + } + + err = send(conn->client_fd, tx_buffer, GSO_TEST_DATA_SIZE, 0); + if (!ASSERT_EQ(err, GSO_TEST_DATA_SIZE, "send (large) data from client")) + goto end; + if (check_server_rx_data(cfg, conn, DEFAULT_TEST_DATA_SIZE)) + goto end; + + res = 0; +end: + disconnect_client_from_server(cfg, conn); + return res; +} + +static void vxlan_decap_mod_args_cb(struct subtest_cfg *cfg, char *dst) +{ + snprintf(dst, TUNNEL_ARGS_MAX_LEN, "id %d dstport %d udp6zerocsumrx", + VXLAN_ID, VXLAN_PORT); +} + +static void udp_decap_mod_args_cb(struct subtest_cfg *cfg, char *dst) +{ + bool is_mpls = !strcmp(cfg->mac_tun_type, "mpls"); + + snprintf(dst, TUNNEL_ARGS_MAX_LEN, + "encap fou encap-sport auto encap-dport %d", + is_mpls ? MPLS_UDP_PORT : UDP_PORT); +} + +static int configure_fou_rx_port(struct subtest_cfg *cfg, bool add) +{ + bool is_mpls = strcmp(cfg->mac_tun_type, "mpls") == 0; + int fou_proto; + + if (is_mpls) + fou_proto = FOU_MPLS_PROTO; + else + fou_proto = cfg->ipproto == 6 ? 41 : 4; + + SYS(fail, "ip fou %s port %d ipproto %d%s", add ? "add" : "del", + is_mpls ? MPLS_UDP_PORT : UDP_PORT, fou_proto, + cfg->ipproto == 6 ? " -6" : ""); + + return 0; +fail: + return 1; +} + +static int add_fou_rx_port(struct subtest_cfg *cfg) +{ + return configure_fou_rx_port(cfg, true); +} + +static int del_fou_rx_port(struct subtest_cfg *cfg) +{ + return configure_fou_rx_port(cfg, false); +} + +static int update_tunnel_intf_addr(struct subtest_cfg *cfg) +{ + SYS(fail, "ip link set dev testtun0 address " MAC_ADDR_VETH2); + return 0; +fail: + return -1; +} + +static int configure_kernel_for_mpls(struct subtest_cfg *cfg) +{ + SYS(fail, "sysctl -qw net.mpls.platform_labels=%d", + MPLS_TABLE_ENTRIES_COUNT); + SYS(fail, "ip -f mpls route add 1000 dev lo"); + SYS(fail, "ip link set lo up"); + SYS(fail, "sysctl -qw net.mpls.conf.testtun0.input=1"); + SYS(fail, "sysctl -qw net.ipv4.conf.lo.rp_filter=0"); + return 0; +fail: + return -1; +} + +static int configure_encapsulation(struct subtest_cfg *cfg) +{ + int ret; + + ret = tc_prog_attach("veth1", -1, cfg->client_egress_prog_fd); + + return ret; +} + +static int configure_kernel_decapsulation(struct subtest_cfg *cfg) +{ + struct nstoken *nstoken = open_netns(SERVER_NS); + int ret = -1; + + if (!ASSERT_OK_PTR(nstoken, "open server ns")) + return ret; + + if (cfg->configure_fou_rx_port && + !ASSERT_OK(add_fou_rx_port(cfg), "configure FOU RX port")) + goto fail; + SYS(fail, "ip link add name testtun0 type %s %s remote %s local %s %s", + cfg->iproute_tun_type, cfg->tmode ? cfg->tmode : "", + cfg->tunnel_client_addr, cfg->tunnel_server_addr, + cfg->extra_decap_mod_args); + if (cfg->tunnel_need_veth_mac && + !ASSERT_OK(update_tunnel_intf_addr(cfg), "update testtun0 mac")) + goto fail; + if (cfg->configure_mpls && + (!ASSERT_OK(configure_kernel_for_mpls(cfg), + "configure MPLS decap"))) + goto fail; + SYS(fail, "sysctl -qw net.ipv4.conf.all.rp_filter=0"); + SYS(fail, "sysctl -qw net.ipv4.conf.testtun0.rp_filter=0"); + SYS(fail, "ip link set dev testtun0 up"); + + ret = 0; +fail: + close_netns(nstoken); + return ret; +} + +static void remove_kernel_decapsulation(struct subtest_cfg *cfg) +{ + SYS_NOFAIL("ip link del testtun0"); + if (cfg->configure_mpls) + SYS_NOFAIL("ip -f mpls route del 1000 dev lo"); + if (cfg->configure_fou_rx_port) + del_fou_rx_port(cfg); +} + +static int configure_ebpf_decapsulation(struct subtest_cfg *cfg) +{ + struct nstoken *nstoken = open_netns(SERVER_NS); + int ret = -1; + + if (!ASSERT_OK_PTR(nstoken, "open server ns")) + return ret; + + if (!cfg->expect_kern_decap_failure) + SYS(fail, "ip link del testtun0"); + + if (!ASSERT_OK(tc_prog_attach("veth2", cfg->server_ingress_prog_fd, -1), + "attach_program")) + goto fail; + + ret = 0; +fail: + close_netns(nstoken); + return ret; +} + +static void run_test(struct subtest_cfg *cfg) +{ + struct nstoken *nstoken; + + if (!ASSERT_OK(run_server(cfg), "run server")) + return; + + nstoken = open_netns(CLIENT_NS); + if (!ASSERT_OK_PTR(nstoken, "open client ns")) + goto fail; + + /* Basic communication must work */ + if (!ASSERT_OK(send_and_test_data(cfg, true), "connect without any encap")) + goto fail; + + /* Attach encapsulation program to client */ + if (!ASSERT_OK(configure_encapsulation(cfg), "configure encapsulation")) + goto fail; + + /* If supported, insert kernel decap module, connection must succeed */ + if (!cfg->expect_kern_decap_failure) { + if (!ASSERT_OK(configure_kernel_decapsulation(cfg), + "configure kernel decapsulation")) + goto fail; + if (!ASSERT_OK(send_and_test_data(cfg, true), + "connect with encap prog and kern decap")) + goto fail; + } + + /* Replace kernel decapsulation with BPF decapsulation, test must pass */ + if (!ASSERT_OK(configure_ebpf_decapsulation(cfg), "configure ebpf decapsulation")) + goto fail; + ASSERT_OK(send_and_test_data(cfg, true), "connect with encap and decap progs"); + +fail: + close_netns(nstoken); + close(cfg->server_fd); +} + +static int setup(void) +{ + struct nstoken *nstoken_client, *nstoken_server; + int fd, err; + + fd = open("/dev/urandom", O_RDONLY); + if (!ASSERT_OK_FD(fd, "open urandom")) + goto fail; + err = read(fd, tx_buffer, BUFFER_LEN); + close(fd); + + if (!ASSERT_EQ(err, BUFFER_LEN, "read random bytes")) + goto fail; + + /* Configure the testing network */ + if (!ASSERT_OK(make_netns(CLIENT_NS), "create client ns") || + !ASSERT_OK(make_netns(SERVER_NS), "create server ns")) + goto fail; + + nstoken_client = open_netns(CLIENT_NS); + if (!ASSERT_OK_PTR(nstoken_client, "open client ns")) + goto fail_delete_ns; + SYS(fail_close_ns_client, "ip link add %s type veth peer name %s", + "veth1 mtu 1500 netns " CLIENT_NS " address " MAC_ADDR_VETH1, + "veth2 mtu 1500 netns " SERVER_NS " address " MAC_ADDR_VETH2); + SYS(fail_close_ns_client, "ethtool -K veth1 tso off"); + SYS(fail_close_ns_client, "ip link set veth1 up"); + nstoken_server = open_netns(SERVER_NS); + if (!ASSERT_OK_PTR(nstoken_server, "open server ns")) + goto fail_close_ns_client; + SYS(fail_close_ns_server, "ip link set veth2 up"); + + close_netns(nstoken_server); + close_netns(nstoken_client); + return 0; + +fail_close_ns_server: + close_netns(nstoken_server); +fail_close_ns_client: + close_netns(nstoken_client); +fail_delete_ns: + SYS_NOFAIL("ip netns del " CLIENT_NS); + SYS_NOFAIL("ip netns del " SERVER_NS); +fail: + return -1; +} + +static int subtest_setup(struct test_tc_tunnel *skel, struct subtest_cfg *cfg) +{ + struct nstoken *nstoken_client, *nstoken_server; + int ret = -1; + + set_subtest_addresses(cfg); + if (!ASSERT_OK(set_subtest_progs(cfg, skel), + "find subtest progs")) + goto fail; + if (cfg->extra_decap_mod_args_cb) + cfg->extra_decap_mod_args_cb(cfg, cfg->extra_decap_mod_args); + + nstoken_client = open_netns(CLIENT_NS); + if (!ASSERT_OK_PTR(nstoken_client, "open client ns")) + goto fail; + SYS(fail_close_client_ns, + "ip -4 addr add " IP4_ADDR_VETH1 "/24 dev veth1"); + SYS(fail_close_client_ns, "ip -4 route flush table main"); + SYS(fail_close_client_ns, + "ip -4 route add " IP4_ADDR_VETH2 " mtu 1450 dev veth1"); + SYS(fail_close_client_ns, + "ip -6 addr add " IP6_ADDR_VETH1 "/64 dev veth1 nodad"); + SYS(fail_close_client_ns, "ip -6 route flush table main"); + SYS(fail_close_client_ns, + "ip -6 route add " IP6_ADDR_VETH2 " mtu 1430 dev veth1"); + nstoken_server = open_netns(SERVER_NS); + if (!ASSERT_OK_PTR(nstoken_server, "open server ns")) + goto fail_close_client_ns; + SYS(fail_close_server_ns, + "ip -4 addr add " IP4_ADDR_VETH2 "/24 dev veth2"); + SYS(fail_close_server_ns, + "ip -6 addr add " IP6_ADDR_VETH2 "/64 dev veth2 nodad"); + + ret = 0; + +fail_close_server_ns: + close_netns(nstoken_server); +fail_close_client_ns: + close_netns(nstoken_client); +fail: + return ret; +} + + +static void subtest_cleanup(struct subtest_cfg *cfg) +{ + struct nstoken *nstoken; + + nstoken = open_netns(CLIENT_NS); + if (ASSERT_OK_PTR(nstoken, "open clien ns")) { + SYS_NOFAIL("tc qdisc delete dev veth1 parent ffff:fff1"); + SYS_NOFAIL("ip a flush veth1"); + close_netns(nstoken); + } + nstoken = open_netns(SERVER_NS); + if (ASSERT_OK_PTR(nstoken, "open clien ns")) { + SYS_NOFAIL("tc qdisc delete dev veth2 parent ffff:fff1"); + SYS_NOFAIL("ip a flush veth2"); + if (!cfg->expect_kern_decap_failure) + remove_kernel_decapsulation(cfg); + close_netns(nstoken); + } +} + +static void cleanup(void) +{ + remove_netns(CLIENT_NS); + remove_netns(SERVER_NS); +} + +static struct subtest_cfg subtests_cfg[] = { + { + .ebpf_tun_type = "ipip", + .mac_tun_type = "none", + .iproute_tun_type = "ipip", + .ipproto = 4, + }, + { + .ebpf_tun_type = "ipip6", + .mac_tun_type = "none", + .iproute_tun_type = "ip6tnl", + .ipproto = 4, + .tunnel_client_addr = IP6_ADDR_VETH1, + .tunnel_server_addr = IP6_ADDR_VETH2, + }, + { + .ebpf_tun_type = "ip6tnl", + .iproute_tun_type = "ip6tnl", + .mac_tun_type = "none", + .ipproto = 6, + }, + { + .mac_tun_type = "none", + .ebpf_tun_type = "sit", + .iproute_tun_type = "sit", + .ipproto = 6, + .tunnel_client_addr = IP4_ADDR_VETH1, + .tunnel_server_addr = IP4_ADDR_VETH2, + }, + { + .ebpf_tun_type = "vxlan", + .mac_tun_type = "eth", + .iproute_tun_type = "vxlan", + .ipproto = 4, + .extra_decap_mod_args_cb = vxlan_decap_mod_args_cb, + .tunnel_need_veth_mac = true + }, + { + .ebpf_tun_type = "ip6vxlan", + .mac_tun_type = "eth", + .iproute_tun_type = "vxlan", + .ipproto = 6, + .extra_decap_mod_args_cb = vxlan_decap_mod_args_cb, + .tunnel_need_veth_mac = true + }, + { + .ebpf_tun_type = "gre", + .mac_tun_type = "none", + .iproute_tun_type = "gre", + .ipproto = 4, + .test_gso = true + }, + { + .ebpf_tun_type = "gre", + .mac_tun_type = "eth", + .iproute_tun_type = "gretap", + .ipproto = 4, + .tunnel_need_veth_mac = true, + .test_gso = true + }, + { + .ebpf_tun_type = "gre", + .mac_tun_type = "mpls", + .iproute_tun_type = "gre", + .ipproto = 4, + .configure_mpls = true, + .test_gso = true + }, + { + .ebpf_tun_type = "ip6gre", + .mac_tun_type = "none", + .iproute_tun_type = "ip6gre", + .ipproto = 6, + .test_gso = true, + }, + { + .ebpf_tun_type = "ip6gre", + .mac_tun_type = "eth", + .iproute_tun_type = "ip6gretap", + .ipproto = 6, + .tunnel_need_veth_mac = true, + .test_gso = true + }, + { + .ebpf_tun_type = "ip6gre", + .mac_tun_type = "mpls", + .iproute_tun_type = "ip6gre", + .ipproto = 6, + .configure_mpls = true, + .test_gso = true + }, + { + .ebpf_tun_type = "udp", + .mac_tun_type = "none", + .iproute_tun_type = "ipip", + .ipproto = 4, + .extra_decap_mod_args_cb = udp_decap_mod_args_cb, + .configure_fou_rx_port = true, + .test_gso = true + }, + { + .ebpf_tun_type = "udp", + .mac_tun_type = "eth", + .iproute_tun_type = "ipip", + .ipproto = 4, + .extra_decap_mod_args_cb = udp_decap_mod_args_cb, + .configure_fou_rx_port = true, + .expect_kern_decap_failure = true, + .test_gso = true + }, + { + .ebpf_tun_type = "udp", + .mac_tun_type = "mpls", + .iproute_tun_type = "ipip", + .ipproto = 4, + .extra_decap_mod_args_cb = udp_decap_mod_args_cb, + .configure_fou_rx_port = true, + .tmode = "mode any ttl 255", + .configure_mpls = true, + .test_gso = true + }, + { + .ebpf_tun_type = "ip6udp", + .mac_tun_type = "none", + .iproute_tun_type = "ip6tnl", + .ipproto = 6, + .extra_decap_mod_args_cb = udp_decap_mod_args_cb, + .configure_fou_rx_port = true, + .test_gso = true + }, + { + .ebpf_tun_type = "ip6udp", + .mac_tun_type = "eth", + .iproute_tun_type = "ip6tnl", + .ipproto = 6, + .extra_decap_mod_args_cb = udp_decap_mod_args_cb, + .configure_fou_rx_port = true, + .expect_kern_decap_failure = true, + .test_gso = true + }, + { + .ebpf_tun_type = "ip6udp", + .mac_tun_type = "mpls", + .iproute_tun_type = "ip6tnl", + .ipproto = 6, + .extra_decap_mod_args_cb = udp_decap_mod_args_cb, + .configure_fou_rx_port = true, + .tmode = "mode any ttl 255", + .expect_kern_decap_failure = true, + .test_gso = true + }, +}; + +void test_tc_tunnel(void) +{ + struct test_tc_tunnel *skel; + struct subtest_cfg *cfg; + int i, ret; + + skel = test_tc_tunnel__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel open and load")) + return; + + if (!ASSERT_OK(setup(), "global setup")) + return; + + for (i = 0; i < ARRAY_SIZE(subtests_cfg); i++) { + cfg = &subtests_cfg[i]; + ret = build_subtest_name(cfg, cfg->name, TEST_NAME_MAX_LEN); + if (ret < 0 || !test__start_subtest(cfg->name)) + continue; + if (subtest_setup(skel, cfg) == 0) + run_test(cfg); + subtest_cleanup(cfg); + } + cleanup(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c index bae0e9de277d..eb9309931272 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c +++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c @@ -534,85 +534,6 @@ static void ping6_dev1(void) close_netns(nstoken); } -static int attach_tc_prog(int ifindex, int igr_fd, int egr_fd) -{ - DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = ifindex, - .attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS); - DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1, - .priority = 1, .prog_fd = igr_fd); - DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts2, .handle = 1, - .priority = 1, .prog_fd = egr_fd); - int ret; - - ret = bpf_tc_hook_create(&hook); - if (!ASSERT_OK(ret, "create tc hook")) - return ret; - - if (igr_fd >= 0) { - hook.attach_point = BPF_TC_INGRESS; - ret = bpf_tc_attach(&hook, &opts1); - if (!ASSERT_OK(ret, "bpf_tc_attach")) { - bpf_tc_hook_destroy(&hook); - return ret; - } - } - - if (egr_fd >= 0) { - hook.attach_point = BPF_TC_EGRESS; - ret = bpf_tc_attach(&hook, &opts2); - if (!ASSERT_OK(ret, "bpf_tc_attach")) { - bpf_tc_hook_destroy(&hook); - return ret; - } - } - - return 0; -} - -static int generic_attach(const char *dev, int igr_fd, int egr_fd) -{ - int ifindex; - - if (!ASSERT_OK_FD(igr_fd, "check ingress fd")) - return -1; - if (!ASSERT_OK_FD(egr_fd, "check egress fd")) - return -1; - - ifindex = if_nametoindex(dev); - if (!ASSERT_NEQ(ifindex, 0, "get ifindex")) - return -1; - - return attach_tc_prog(ifindex, igr_fd, egr_fd); -} - -static int generic_attach_igr(const char *dev, int igr_fd) -{ - int ifindex; - - if (!ASSERT_OK_FD(igr_fd, "check ingress fd")) - return -1; - - ifindex = if_nametoindex(dev); - if (!ASSERT_NEQ(ifindex, 0, "get ifindex")) - return -1; - - return attach_tc_prog(ifindex, igr_fd, -1); -} - -static int generic_attach_egr(const char *dev, int egr_fd) -{ - int ifindex; - - if (!ASSERT_OK_FD(egr_fd, "check egress fd")) - return -1; - - ifindex = if_nametoindex(dev); - if (!ASSERT_NEQ(ifindex, 0, "get ifindex")) - return -1; - - return attach_tc_prog(ifindex, -1, egr_fd); -} - static void test_vxlan_tunnel(void) { struct test_tunnel_kern *skel = NULL; @@ -635,12 +556,12 @@ static void test_vxlan_tunnel(void) goto done; get_src_prog_fd = bpf_program__fd(skel->progs.vxlan_get_tunnel_src); set_src_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_src); - if (generic_attach(VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) + if (tc_prog_attach(VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) goto done; /* load and attach bpf prog to veth dev tc hook point */ set_dst_prog_fd = bpf_program__fd(skel->progs.veth_set_outer_dst); - if (generic_attach_igr("veth1", set_dst_prog_fd)) + if (tc_prog_attach("veth1", set_dst_prog_fd, -1)) goto done; /* load and attach prog set_md to tunnel dev tc hook point at_ns0 */ @@ -648,7 +569,7 @@ static void test_vxlan_tunnel(void) if (!ASSERT_OK_PTR(nstoken, "setns src")) goto done; set_dst_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_dst); - if (generic_attach_egr(VXLAN_TUNL_DEV0, set_dst_prog_fd)) + if (tc_prog_attach(VXLAN_TUNL_DEV0, -1, set_dst_prog_fd)) goto done; close_netns(nstoken); @@ -695,7 +616,7 @@ static void test_ip6vxlan_tunnel(void) goto done; get_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_get_tunnel_src); set_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_src); - if (generic_attach(IP6VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) + if (tc_prog_attach(IP6VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) goto done; /* load and attach prog set_md to tunnel dev tc hook point at_ns0 */ @@ -703,7 +624,7 @@ static void test_ip6vxlan_tunnel(void) if (!ASSERT_OK_PTR(nstoken, "setns src")) goto done; set_dst_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_dst); - if (generic_attach_egr(IP6VXLAN_TUNL_DEV0, set_dst_prog_fd)) + if (tc_prog_attach(IP6VXLAN_TUNL_DEV0, -1, set_dst_prog_fd)) goto done; close_netns(nstoken); @@ -764,7 +685,7 @@ static void test_ipip_tunnel(enum ipip_encap encap) skel->progs.ipip_set_tunnel); } - if (generic_attach(IPIP_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) + if (tc_prog_attach(IPIP_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd)) goto done; ping_dev0(); @@ -797,7 +718,7 @@ static void test_xfrm_tunnel(void) /* attach tc prog to tunnel dev */ tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state); - if (generic_attach_igr("veth1", tc_prog_fd)) + if (tc_prog_attach("veth1", tc_prog_fd, -1)) goto done; /* attach xdp prog to tunnel dev */ @@ -870,7 +791,7 @@ static void test_gre_tunnel(enum gre_test test) if (!ASSERT_OK(err, "add tunnel")) goto done; - if (generic_attach(GRE_TUNL_DEV1, get_fd, set_fd)) + if (tc_prog_attach(GRE_TUNL_DEV1, get_fd, set_fd)) goto done; ping_dev0(); @@ -911,7 +832,7 @@ static void test_ip6gre_tunnel(enum ip6gre_test test) set_fd = bpf_program__fd(skel->progs.ip6gretap_set_tunnel); get_fd = bpf_program__fd(skel->progs.ip6gretap_get_tunnel); - if (generic_attach(IP6GRE_TUNL_DEV1, get_fd, set_fd)) + if (tc_prog_attach(IP6GRE_TUNL_DEV1, get_fd, set_fd)) goto done; ping6_veth0(); @@ -954,7 +875,7 @@ static void test_erspan_tunnel(enum erspan_test test) set_fd = bpf_program__fd(skel->progs.erspan_set_tunnel); get_fd = bpf_program__fd(skel->progs.erspan_get_tunnel); - if (generic_attach(ERSPAN_TUNL_DEV1, get_fd, set_fd)) + if (tc_prog_attach(ERSPAN_TUNL_DEV1, get_fd, set_fd)) goto done; ping_dev0(); @@ -990,7 +911,7 @@ static void test_ip6erspan_tunnel(enum erspan_test test) set_fd = bpf_program__fd(skel->progs.ip4ip6erspan_set_tunnel); get_fd = bpf_program__fd(skel->progs.ip4ip6erspan_get_tunnel); - if (generic_attach(IP6ERSPAN_TUNL_DEV1, get_fd, set_fd)) + if (tc_prog_attach(IP6ERSPAN_TUNL_DEV1, get_fd, set_fd)) goto done; ping6_veth0(); @@ -1017,7 +938,7 @@ static void test_geneve_tunnel(void) set_fd = bpf_program__fd(skel->progs.geneve_set_tunnel); get_fd = bpf_program__fd(skel->progs.geneve_get_tunnel); - if (generic_attach(GENEVE_TUNL_DEV1, get_fd, set_fd)) + if (tc_prog_attach(GENEVE_TUNL_DEV1, get_fd, set_fd)) goto done; ping_dev0(); @@ -1044,7 +965,7 @@ static void test_ip6geneve_tunnel(void) set_fd = bpf_program__fd(skel->progs.ip6geneve_set_tunnel); get_fd = bpf_program__fd(skel->progs.ip6geneve_get_tunnel); - if (generic_attach(IP6GENEVE_TUNL_DEV1, get_fd, set_fd)) + if (tc_prog_attach(IP6GENEVE_TUNL_DEV1, get_fd, set_fd)) goto done; ping_dev0(); @@ -1083,7 +1004,7 @@ static void test_ip6tnl_tunnel(enum ip6tnl_test test) get_fd = bpf_program__fd(skel->progs.ip6ip6_get_tunnel); break; } - if (generic_attach(IP6TNL_TUNL_DEV1, get_fd, set_fd)) + if (tc_prog_attach(IP6TNL_TUNL_DEV1, get_fd, set_fd)) goto done; ping6_veth0(); diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c new file mode 100644 index 000000000000..5af28f359cfd --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c @@ -0,0 +1,2596 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <bpf/bpf.h> +#include <errno.h> +#include <linux/bitmap.h> +#include <linux/if_link.h> +#include <linux/mman.h> +#include <linux/netdev.h> +#include <poll.h> +#include <pthread.h> +#include <signal.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <unistd.h> + +#include "network_helpers.h" +#include "test_xsk.h" +#include "xsk_xdp_common.h" +#include "xsk_xdp_progs.skel.h" + +#define DEFAULT_BATCH_SIZE 64 +#define MIN_PKT_SIZE 64 +#define MAX_ETH_JUMBO_SIZE 9000 +#define MAX_INTERFACES 2 +#define MAX_TEARDOWN_ITER 10 +#define MAX_TX_BUDGET_DEFAULT 32 +#define PKT_DUMP_NB_TO_PRINT 16 +/* Just to align the data in the packet */ +#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) +#define POLL_TMOUT 1000 +#define THREAD_TMOUT 3 +#define UMEM_HEADROOM_TEST_SIZE 128 +#define XSK_DESC__INVALID_OPTION (0xffff) +#define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1) +#define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024) +#define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024) + +static const u8 g_mac[ETH_ALEN] = {0x55, 0x44, 0x33, 0x22, 0x11, 0x00}; + +bool opt_verbose; +pthread_barrier_t barr; +pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; + +int pkts_in_flight; + +/* The payload is a word consisting of a packet sequence number in the upper + * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's + * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. + */ +static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) +{ + u32 *ptr = (u32 *)dest, i; + + start /= sizeof(*ptr); + size /= sizeof(*ptr); + for (i = 0; i < size; i++) + ptr[i] = htonl(pkt_nb << 16 | (i + start)); +} + +static void gen_eth_hdr(struct xsk_socket_info *xsk, struct ethhdr *eth_hdr) +{ + memcpy(eth_hdr->h_dest, xsk->dst_mac, ETH_ALEN); + memcpy(eth_hdr->h_source, xsk->src_mac, ETH_ALEN); + eth_hdr->h_proto = htons(ETH_P_LOOPBACK); +} + +static bool is_umem_valid(struct ifobject *ifobj) +{ + return !!ifobj->umem->umem; +} + +static u32 mode_to_xdp_flags(enum test_mode mode) +{ + return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; +} + +static u64 umem_size(struct xsk_umem_info *umem) +{ + return umem->num_frames * umem->frame_size; +} + +int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, + u64 size) +{ + struct xsk_umem_config cfg = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = umem->frame_size, + .frame_headroom = umem->frame_headroom, + .flags = XSK_UMEM__DEFAULT_FLAGS + }; + int ret; + + if (umem->fill_size) + cfg.fill_size = umem->fill_size; + + if (umem->comp_size) + cfg.comp_size = umem->comp_size; + + if (umem->unaligned_mode) + cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; + + ret = xsk_umem__create(&umem->umem, buffer, size, + &umem->fq, &umem->cq, &cfg); + if (ret) + return ret; + + umem->buffer = buffer; + if (ifobj->shared_umem && ifobj->rx_on) { + umem->base_addr = umem_size(umem); + umem->next_buffer = umem_size(umem); + } + + return 0; +} + +static u64 umem_alloc_buffer(struct xsk_umem_info *umem) +{ + u64 addr; + + addr = umem->next_buffer; + umem->next_buffer += umem->frame_size; + if (umem->next_buffer >= umem->base_addr + umem_size(umem)) + umem->next_buffer = umem->base_addr; + + return addr; +} + +static void umem_reset_alloc(struct xsk_umem_info *umem) +{ + umem->next_buffer = 0; +} + +static int enable_busy_poll(struct xsk_socket_info *xsk) +{ + int sock_opt; + + sock_opt = 1; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + return -errno; + + sock_opt = 20; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + return -errno; + + sock_opt = xsk->batch_size; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + return -errno; + + return 0; +} + +int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, + struct ifobject *ifobject, bool shared) +{ + struct xsk_socket_config cfg = {}; + struct xsk_ring_cons *rxr; + struct xsk_ring_prod *txr; + + xsk->umem = umem; + cfg.rx_size = xsk->rxqsize; + cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + cfg.bind_flags = ifobject->bind_flags; + if (shared) + cfg.bind_flags |= XDP_SHARED_UMEM; + if (ifobject->mtu > MAX_ETH_PKT_SIZE) + cfg.bind_flags |= XDP_USE_SG; + if (umem->comp_size) + cfg.tx_size = umem->comp_size; + if (umem->fill_size) + cfg.rx_size = umem->fill_size; + + txr = ifobject->tx_on ? &xsk->tx : NULL; + rxr = ifobject->rx_on ? &xsk->rx : NULL; + return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg); +} + +#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags" +static unsigned int get_max_skb_frags(void) +{ + unsigned int max_skb_frags = 0; + FILE *file; + + file = fopen(MAX_SKB_FRAGS_PATH, "r"); + if (!file) { + ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH); + return 0; + } + + if (fscanf(file, "%u", &max_skb_frags) != 1) + ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH); + + fclose(file); + return max_skb_frags; +} + +static int set_ring_size(struct ifobject *ifobj) +{ + int ret; + u32 ctr = 0; + + while (ctr++ < SOCK_RECONF_CTR) { + ret = set_hw_ring_size(ifobj->ifname, &ifobj->ring); + if (!ret) + break; + + /* Retry if it fails */ + if (ctr >= SOCK_RECONF_CTR || errno != EBUSY) + return -errno; + + usleep(USLEEP_MAX); + } + + return ret; +} + +int hw_ring_size_reset(struct ifobject *ifobj) +{ + ifobj->ring.tx_pending = ifobj->set_ring.default_tx; + ifobj->ring.rx_pending = ifobj->set_ring.default_rx; + return set_ring_size(ifobj); +} + +static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx) +{ + u32 i, j; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->xsk = &ifobj->xsk_arr[0]; + ifobj->use_poll = false; + ifobj->use_fill_ring = true; + ifobj->release_rx = true; + ifobj->validation_func = NULL; + ifobj->use_metadata = false; + + if (i == 0) { + ifobj->rx_on = false; + ifobj->tx_on = true; + } else { + ifobj->rx_on = true; + ifobj->tx_on = false; + } + + memset(ifobj->umem, 0, sizeof(*ifobj->umem)); + ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; + ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + + for (j = 0; j < MAX_SOCKETS; j++) { + memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); + ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; + ifobj->xsk_arr[j].batch_size = DEFAULT_BATCH_SIZE; + if (i == 0) + ifobj->xsk_arr[j].pkt_stream = test->tx_pkt_stream_default; + else + ifobj->xsk_arr[j].pkt_stream = test->rx_pkt_stream_default; + + memcpy(ifobj->xsk_arr[j].src_mac, g_mac, ETH_ALEN); + memcpy(ifobj->xsk_arr[j].dst_mac, g_mac, ETH_ALEN); + ifobj->xsk_arr[j].src_mac[5] += ((j * 2) + 0); + ifobj->xsk_arr[j].dst_mac[5] += ((j * 2) + 1); + } + } + + if (ifobj_tx->hw_ring_size_supp) + hw_ring_size_reset(ifobj_tx); + + test->ifobj_tx = ifobj_tx; + test->ifobj_rx = ifobj_rx; + test->current_step = 0; + test->total_steps = 1; + test->nb_sockets = 1; + test->fail = false; + test->set_ring = false; + test->adjust_tail = false; + test->adjust_tail_support = false; + test->mtu = MAX_ETH_PKT_SIZE; + test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog; + test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk; + test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog; + test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk; +} + +void test_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx, enum test_mode mode, + const struct test_spec *test_to_run) +{ + struct pkt_stream *tx_pkt_stream; + struct pkt_stream *rx_pkt_stream; + u32 i; + + tx_pkt_stream = test->tx_pkt_stream_default; + rx_pkt_stream = test->rx_pkt_stream_default; + memset(test, 0, sizeof(*test)); + test->tx_pkt_stream_default = tx_pkt_stream; + test->rx_pkt_stream_default = rx_pkt_stream; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->bind_flags = XDP_USE_NEED_WAKEUP; + if (mode == TEST_MODE_ZC) + ifobj->bind_flags |= XDP_ZEROCOPY; + else + ifobj->bind_flags |= XDP_COPY; + } + + memcpy(test->name, test_to_run->name, MAX_TEST_NAME_SIZE); + test->test_func = test_to_run->test_func; + test->mode = mode; + __test_spec_init(test, ifobj_tx, ifobj_rx); +} + +static void test_spec_reset(struct test_spec *test) +{ + __test_spec_init(test, test->ifobj_tx, test->ifobj_rx); +} + +static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx, + struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx, + struct bpf_map *xskmap_tx) +{ + test->xdp_prog_rx = xdp_prog_rx; + test->xdp_prog_tx = xdp_prog_tx; + test->xskmap_rx = xskmap_rx; + test->xskmap_tx = xskmap_tx; +} + +static int test_spec_set_mtu(struct test_spec *test, int mtu) +{ + int err; + + if (test->ifobj_rx->mtu != mtu) { + err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu); + if (err) + return err; + test->ifobj_rx->mtu = mtu; + } + if (test->ifobj_tx->mtu != mtu) { + err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu); + if (err) + return err; + test->ifobj_tx->mtu = mtu; + } + + return 0; +} + +void pkt_stream_reset(struct pkt_stream *pkt_stream) +{ + if (pkt_stream) { + pkt_stream->current_pkt_nb = 0; + pkt_stream->nb_rx_pkts = 0; + } +} + +static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) +{ + if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) + return NULL; + + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; +} + +static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) +{ + while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { + (*pkts_sent)++; + if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; + pkt_stream->current_pkt_nb++; + } + return NULL; +} + +void pkt_stream_delete(struct pkt_stream *pkt_stream) +{ + free(pkt_stream->pkts); + free(pkt_stream); +} + +void pkt_stream_restore_default(struct test_spec *test) +{ + struct pkt_stream *tx_pkt_stream = test->ifobj_tx->xsk->pkt_stream; + struct pkt_stream *rx_pkt_stream = test->ifobj_rx->xsk->pkt_stream; + + if (tx_pkt_stream != test->tx_pkt_stream_default) { + pkt_stream_delete(test->ifobj_tx->xsk->pkt_stream); + test->ifobj_tx->xsk->pkt_stream = test->tx_pkt_stream_default; + } + + if (rx_pkt_stream != test->rx_pkt_stream_default) { + pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream); + test->ifobj_rx->xsk->pkt_stream = test->rx_pkt_stream_default; + } +} + +static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = calloc(1, sizeof(*pkt_stream)); + if (!pkt_stream) + return NULL; + + pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); + if (!pkt_stream->pkts) { + free(pkt_stream); + return NULL; + } + + pkt_stream->nb_pkts = nb_pkts; + return pkt_stream; +} + +static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt) +{ + u32 nb_frags = 1, next_frag; + + if (!pkt) + return 1; + + if (!pkt_stream->verbatim) { + if (!pkt->valid || !pkt->len) + return 1; + return ceil_u32(pkt->len, frame_size); + } + + /* Search for the end of the packet in verbatim mode */ + if (!pkt_continues(pkt->options)) + return nb_frags; + + next_frag = pkt_stream->current_pkt_nb; + pkt++; + while (next_frag++ < pkt_stream->nb_pkts) { + nb_frags++; + if (!pkt_continues(pkt->options) || !pkt->valid) + break; + pkt++; + } + return nb_frags; +} + +static bool set_pkt_valid(int offset, u32 len) +{ + return len <= MAX_ETH_JUMBO_SIZE; +} + +static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) +{ + pkt->offset = offset; + pkt->len = len; + pkt->valid = set_pkt_valid(offset, len); +} + +static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) +{ + bool prev_pkt_valid = pkt->valid; + + pkt_set(pkt_stream, pkt, offset, len); + pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid; +} + +static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) +{ + return ceil_u32(len, umem->frame_size) * umem->frame_size; +} + +static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb_start, u32 nb_off) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = __pkt_stream_alloc(nb_pkts); + if (!pkt_stream) + return NULL; + + pkt_stream->nb_pkts = nb_pkts; + pkt_stream->max_pkt_len = pkt_len; + for (i = 0; i < nb_pkts; i++) { + struct pkt *pkt = &pkt_stream->pkts[i]; + + pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len); + pkt->pkt_nb = nb_start + i * nb_off; + } + + return pkt_stream; +} + +struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len) +{ + return __pkt_stream_generate(nb_pkts, pkt_len, 0, 1); +} + +static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream) +{ + return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len); +} + +static int pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len) +{ + ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len); + + if (!ifobj->xsk->pkt_stream) + return -ENOMEM; + + return 0; +} + +static int pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) +{ + int ret; + + ret = pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len); + if (ret) + return ret; + + return pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len); +} + +static int __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, + int offset) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream); + if (!pkt_stream) + return -ENOMEM; + + for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2) + pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len); + + ifobj->xsk->pkt_stream = pkt_stream; + + return 0; +} + +static int pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) +{ + int ret = __pkt_stream_replace_half(test->ifobj_tx, pkt_len, offset); + + if (ret) + return ret; + + return __pkt_stream_replace_half(test->ifobj_rx, pkt_len, offset); +} + +static int pkt_stream_receive_half(struct test_spec *test) +{ + struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream; + u32 i; + + if (test->ifobj_rx->xsk->pkt_stream != test->rx_pkt_stream_default) + /* Packet stream has already been replaced so we have to release this one. + * The newly created one will be freed by the restore_default() at the + * end of the test + */ + pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream); + + test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(pkt_stream->nb_pkts, + pkt_stream->pkts[0].len); + if (!test->ifobj_rx->xsk->pkt_stream) + return -ENOMEM; + + pkt_stream = test->ifobj_rx->xsk->pkt_stream; + for (i = 1; i < pkt_stream->nb_pkts; i += 2) + pkt_stream->pkts[i].valid = false; + + pkt_stream->nb_valid_entries /= 2; + + return 0; +} + +static int pkt_stream_even_odd_sequence(struct test_spec *test) +{ + struct pkt_stream *pkt_stream; + u32 i; + + for (i = 0; i < test->nb_sockets; i++) { + pkt_stream = test->ifobj_tx->xsk_arr[i].pkt_stream; + pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, + pkt_stream->pkts[0].len, i, 2); + if (!pkt_stream) + return -ENOMEM; + test->ifobj_tx->xsk_arr[i].pkt_stream = pkt_stream; + + pkt_stream = test->ifobj_rx->xsk_arr[i].pkt_stream; + pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, + pkt_stream->pkts[0].len, i, 2); + if (!pkt_stream) + return -ENOMEM; + test->ifobj_rx->xsk_arr[i].pkt_stream = pkt_stream; + } + + return 0; +} + +static void release_even_odd_sequence(struct test_spec *test) +{ + struct pkt_stream *later_free_tx = test->ifobj_tx->xsk->pkt_stream; + struct pkt_stream *later_free_rx = test->ifobj_rx->xsk->pkt_stream; + int i; + + for (i = 0; i < test->nb_sockets; i++) { + /* later_free_{rx/tx} will be freed by restore_default() */ + if (test->ifobj_tx->xsk_arr[i].pkt_stream != later_free_tx) + pkt_stream_delete(test->ifobj_tx->xsk_arr[i].pkt_stream); + if (test->ifobj_rx->xsk_arr[i].pkt_stream != later_free_rx) + pkt_stream_delete(test->ifobj_rx->xsk_arr[i].pkt_stream); + } + +} + +static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) +{ + if (!pkt->valid) + return pkt->offset; + return pkt->offset + umem_alloc_buffer(umem); +} + +static void pkt_stream_cancel(struct pkt_stream *pkt_stream) +{ + pkt_stream->current_pkt_nb--; +} + +static void pkt_generate(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, u64 addr, u32 len, + u32 pkt_nb, u32 bytes_written) +{ + void *data = xsk_umem__get_data(umem->buffer, addr); + + if (len < MIN_PKT_SIZE) + return; + + if (!bytes_written) { + gen_eth_hdr(xsk, data); + + len -= PKT_HDR_SIZE; + data += PKT_HDR_SIZE; + } else { + bytes_written -= PKT_HDR_SIZE; + } + + write_payload(data, pkt_nb, bytes_written, len); +} + +static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames, + u32 nb_frames, bool verbatim) +{ + u32 i, len = 0, pkt_nb = 0, payload = 0; + struct pkt_stream *pkt_stream; + + pkt_stream = __pkt_stream_alloc(nb_frames); + if (!pkt_stream) + return NULL; + + for (i = 0; i < nb_frames; i++) { + struct pkt *pkt = &pkt_stream->pkts[pkt_nb]; + struct pkt *frame = &frames[i]; + + pkt->offset = frame->offset; + if (verbatim) { + *pkt = *frame; + pkt->pkt_nb = payload; + if (!frame->valid || !pkt_continues(frame->options)) + payload++; + } else { + if (frame->valid) + len += frame->len; + if (frame->valid && pkt_continues(frame->options)) + continue; + + pkt->pkt_nb = pkt_nb; + pkt->len = len; + pkt->valid = frame->valid; + pkt->options = 0; + + len = 0; + } + + print_verbose("offset: %d len: %u valid: %u options: %u pkt_nb: %u\n", + pkt->offset, pkt->len, pkt->valid, pkt->options, pkt->pkt_nb); + + if (pkt->valid && pkt->len > pkt_stream->max_pkt_len) + pkt_stream->max_pkt_len = pkt->len; + + if (pkt->valid) + pkt_stream->nb_valid_entries++; + + pkt_nb++; + } + + pkt_stream->nb_pkts = pkt_nb; + pkt_stream->verbatim = verbatim; + return pkt_stream; +} + +static int pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true); + if (!pkt_stream) + return -ENOMEM; + test->ifobj_tx->xsk->pkt_stream = pkt_stream; + + pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false); + if (!pkt_stream) + return -ENOMEM; + test->ifobj_rx->xsk->pkt_stream = pkt_stream; + + return 0; +} + +static void pkt_print_data(u32 *data, u32 cnt) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + u32 seqnum, pkt_nb; + + seqnum = ntohl(*data) & 0xffff; + pkt_nb = ntohl(*data) >> 16; + ksft_print_msg("%u:%u ", pkt_nb, seqnum); + data++; + } +} + +static void pkt_dump(void *pkt, u32 len, bool eth_header) +{ + struct ethhdr *ethhdr = pkt; + u32 i, *data; + + if (eth_header) { + /*extract L2 frame */ + ksft_print_msg("DEBUG>> L2: dst mac: "); + for (i = 0; i < ETH_ALEN; i++) + ksft_print_msg("%02X", ethhdr->h_dest[i]); + + ksft_print_msg("\nDEBUG>> L2: src mac: "); + for (i = 0; i < ETH_ALEN; i++) + ksft_print_msg("%02X", ethhdr->h_source[i]); + + data = pkt + PKT_HDR_SIZE; + } else { + data = pkt; + } + + /*extract L5 frame */ + ksft_print_msg("\nDEBUG>> L5: seqnum: "); + pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); + ksft_print_msg("...."); + if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { + ksft_print_msg("\n.... "); + pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, + PKT_DUMP_NB_TO_PRINT); + } + ksft_print_msg("\n---------------------------------------\n"); +} + +static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) +{ + u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; + u32 offset = addr % umem->frame_size, expected_offset; + int pkt_offset = pkt->valid ? pkt->offset : 0; + + if (!umem->unaligned_mode) + pkt_offset = 0; + + expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; + + if (offset == expected_offset) + return true; + + ksft_print_msg("[%s] expected [%u], got [%u]\n", __func__, expected_offset, offset); + return false; +} + +static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) +{ + void *data = xsk_umem__get_data(buffer, addr); + struct xdp_info *meta = data - sizeof(struct xdp_info); + + if (meta->count != pkt->pkt_nb) { + ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n", + __func__, pkt->pkt_nb, + (unsigned long long)meta->count); + return false; + } + + return true; +} + +static int is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx, bool *supported) +{ + struct bpf_map *data_map; + int adjust_value = 0; + int key = 0; + int ret; + + data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss"); + if (!data_map || !bpf_map__is_internal(data_map)) { + ksft_print_msg("Error: could not find bss section of XDP program\n"); + return -EINVAL; + } + + ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value); + if (ret) { + ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret); + return ret; + } + + /* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail + * helper is not supported. Skip the adjust_tail test case in this scenario. + */ + *supported = adjust_value != -EOPNOTSUPP; + + return 0; +} + +static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb, + u32 bytes_processed) +{ + u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum; + void *data = xsk_umem__get_data(umem->buffer, addr); + + addr -= umem->base_addr; + + if (addr >= umem->num_frames * umem->frame_size || + addr + len > umem->num_frames * umem->frame_size) { + ksft_print_msg("Frag invalid addr: %llx len: %u\n", + (unsigned long long)addr, len); + return false; + } + if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) { + ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", + (unsigned long long)addr, len); + return false; + } + + pkt_data = data; + if (!bytes_processed) { + pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data); + len -= PKT_HDR_SIZE; + } else { + bytes_processed -= PKT_HDR_SIZE; + } + + expected_seqnum = bytes_processed / sizeof(*pkt_data); + seqnum = ntohl(*pkt_data) & 0xffff; + pkt_nb = ntohl(*pkt_data) >> 16; + + if (expected_pkt_nb != pkt_nb) { + ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n", + __func__, expected_pkt_nb, pkt_nb); + goto error; + } + if (expected_seqnum != seqnum) { + ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n", + __func__, expected_seqnum, seqnum); + goto error; + } + + words_to_end = len / sizeof(*pkt_data) - 1; + pkt_data += words_to_end; + seqnum = ntohl(*pkt_data) & 0xffff; + expected_seqnum += words_to_end; + if (expected_seqnum != seqnum) { + ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n", + __func__, expected_seqnum, seqnum); + goto error; + } + + return true; + +error: + pkt_dump(data, len, !bytes_processed); + return false; +} + +static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) +{ + if (pkt->len != len) { + ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n", + __func__, pkt->len, len); + pkt_dump(xsk_umem__get_data(buffer, addr), len, true); + return false; + } + + return true; +} + +static u32 load_value(u32 *counter) +{ + return __atomic_load_n(counter, __ATOMIC_ACQUIRE); +} + +static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret) +{ + u32 max_budget = MAX_TX_BUDGET_DEFAULT; + u32 cons, ready_to_send; + int delta; + + cons = load_value(xsk->tx.consumer); + ready_to_send = load_value(xsk->tx.producer) - cons; + *ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + + delta = load_value(xsk->tx.consumer) - cons; + /* By default, xsk should consume exact @max_budget descs at one + * send in this case where hitting the max budget limit in while + * loop is triggered in __xsk_generic_xmit(). Please make sure that + * the number of descs to be sent is larger than @max_budget, or + * else the tx.consumer will be updated in xskq_cons_peek_desc() + * in time which hides the issue we try to verify. + */ + if (ready_to_send > max_budget && delta != max_budget) + return false; + + return true; +} + +int kick_tx(struct xsk_socket_info *xsk) +{ + int ret; + + if (xsk->check_consumer) { + if (!kick_tx_with_check(xsk, &ret)) + return TEST_FAILURE; + } else { + ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + } + if (ret >= 0) + return TEST_PASS; + if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) { + usleep(100); + return TEST_PASS; + } + return TEST_FAILURE; +} + +int kick_rx(struct xsk_socket_info *xsk) +{ + int ret; + + ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); + if (ret < 0) + return TEST_FAILURE; + + return TEST_PASS; +} + +static int complete_pkts(struct xsk_socket_info *xsk, int batch_size) +{ + unsigned int rcvd; + u32 idx; + int ret; + + if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { + ret = kick_tx(xsk); + if (ret) + return TEST_FAILURE; + } + + rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); + if (rcvd) { + if (rcvd > xsk->outstanding_tx) { + u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); + + ksft_print_msg("[%s] Too many packets completed\n", __func__); + ksft_print_msg("Last completion address: %llx\n", + (unsigned long long)addr); + return TEST_FAILURE; + } + + xsk_ring_cons__release(&xsk->umem->cq, rcvd); + xsk->outstanding_tx -= rcvd; + } + + return TEST_PASS; +} + +static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk) +{ + u32 frags_processed = 0, nb_frags = 0, pkt_len = 0; + u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0; + struct pkt_stream *pkt_stream = xsk->pkt_stream; + struct ifobject *ifobj = test->ifobj_rx; + struct xsk_umem_info *umem = xsk->umem; + struct pollfd fds = { }; + struct pkt *pkt; + u64 first_addr = 0; + int ret; + + fds.fd = xsk_socket__fd(xsk->xsk); + fds.events = POLLIN; + + ret = kick_rx(xsk); + if (ret) + return TEST_FAILURE; + + if (ifobj->use_poll) { + ret = poll(&fds, 1, POLL_TMOUT); + if (ret < 0) + return TEST_FAILURE; + + if (!ret) { + if (!is_umem_valid(test->ifobj_tx)) + return TEST_PASS; + + ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__); + return TEST_CONTINUE; + } + + if (!(fds.revents & POLLIN)) + return TEST_CONTINUE; + } + + rcvd = xsk_ring_cons__peek(&xsk->rx, xsk->batch_size, &idx_rx); + if (!rcvd) + return TEST_CONTINUE; + + if (ifobj->use_fill_ring) { + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); + while (ret != rcvd) { + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { + ret = poll(&fds, 1, POLL_TMOUT); + if (ret < 0) + return TEST_FAILURE; + } + ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); + } + } + + while (frags_processed < rcvd) { + const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); + u64 addr = desc->addr, orig; + + orig = xsk_umem__extract_addr(addr); + addr = xsk_umem__add_offset_to_addr(addr); + + if (!nb_frags) { + pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent); + if (!pkt) { + ksft_print_msg("[%s] received too many packets addr: %lx len %u\n", + __func__, addr, desc->len); + return TEST_FAILURE; + } + } + + print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n", + addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid); + + if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) || + !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && + !is_metadata_correct(pkt, umem->buffer, addr))) + return TEST_FAILURE; + + if (!nb_frags++) + first_addr = addr; + frags_processed++; + pkt_len += desc->len; + if (ifobj->use_fill_ring) + *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; + + if (pkt_continues(desc->options)) + continue; + + /* The complete packet has been received */ + if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) || + !is_offset_correct(umem, pkt, addr)) + return TEST_FAILURE; + + pkt_stream->nb_rx_pkts++; + nb_frags = 0; + pkt_len = 0; + } + + if (nb_frags) { + /* In the middle of a packet. Start over from beginning of packet. */ + idx_rx -= nb_frags; + xsk_ring_cons__cancel(&xsk->rx, nb_frags); + if (ifobj->use_fill_ring) { + idx_fq -= nb_frags; + xsk_ring_prod__cancel(&umem->fq, nb_frags); + } + frags_processed -= nb_frags; + } + + if (ifobj->use_fill_ring) + xsk_ring_prod__submit(&umem->fq, frags_processed); + if (ifobj->release_rx) + xsk_ring_cons__release(&xsk->rx, frags_processed); + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight -= pkts_sent; + pthread_mutex_unlock(&pacing_mutex); + pkts_sent = 0; + + return TEST_CONTINUE; +} + +bool all_packets_received(struct test_spec *test, struct xsk_socket_info *xsk, u32 sock_num, + unsigned long *bitmap) +{ + struct pkt_stream *pkt_stream = xsk->pkt_stream; + + if (!pkt_stream) { + __set_bit(sock_num, bitmap); + return false; + } + + if (pkt_stream->nb_rx_pkts == pkt_stream->nb_valid_entries) { + __set_bit(sock_num, bitmap); + if (bitmap_full(bitmap, test->nb_sockets)) + return true; + } + + return false; +} + +static int receive_pkts(struct test_spec *test) +{ + struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; + DECLARE_BITMAP(bitmap, test->nb_sockets); + struct xsk_socket_info *xsk; + u32 sock_num = 0; + int res, ret; + + bitmap_zero(bitmap, test->nb_sockets); + + ret = gettimeofday(&tv_now, NULL); + if (ret) + return TEST_FAILURE; + + timeradd(&tv_now, &tv_timeout, &tv_end); + + while (1) { + xsk = &test->ifobj_rx->xsk_arr[sock_num]; + + if ((all_packets_received(test, xsk, sock_num, bitmap))) + break; + + res = __receive_pkts(test, xsk); + if (!(res == TEST_PASS || res == TEST_CONTINUE)) + return res; + + ret = gettimeofday(&tv_now, NULL); + if (ret) + return TEST_FAILURE; + + if (timercmp(&tv_now, &tv_end, >)) { + ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__); + return TEST_FAILURE; + } + sock_num = (sock_num + 1) % test->nb_sockets; + } + + return TEST_PASS; +} + +static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, bool timeout) +{ + u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len; + struct pkt_stream *pkt_stream = xsk->pkt_stream; + struct xsk_umem_info *umem = ifobject->umem; + bool use_poll = ifobject->use_poll; + struct pollfd fds = { }; + int ret; + + buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len); + /* pkts_in_flight might be negative if many invalid packets are sent */ + if (pkts_in_flight >= (int)((umem_size(umem) - xsk->batch_size * buffer_len) / + buffer_len)) { + ret = kick_tx(xsk); + if (ret) + return TEST_FAILURE; + return TEST_CONTINUE; + } + + fds.fd = xsk_socket__fd(xsk->xsk); + fds.events = POLLOUT; + + while (xsk_ring_prod__reserve(&xsk->tx, xsk->batch_size, &idx) < xsk->batch_size) { + if (use_poll) { + ret = poll(&fds, 1, POLL_TMOUT); + if (timeout) { + if (ret < 0) { + ksft_print_msg("ERROR: [%s] Poll error %d\n", + __func__, errno); + return TEST_FAILURE; + } + if (ret == 0) + return TEST_PASS; + break; + } + if (ret <= 0) { + ksft_print_msg("ERROR: [%s] Poll error %d\n", + __func__, errno); + return TEST_FAILURE; + } + } + + complete_pkts(xsk, xsk->batch_size); + } + + for (i = 0; i < xsk->batch_size; i++) { + struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream); + u32 nb_frags_left, nb_frags, bytes_written = 0; + + if (!pkt) + break; + + nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt); + if (nb_frags > xsk->batch_size - i) { + pkt_stream_cancel(pkt_stream); + xsk_ring_prod__cancel(&xsk->tx, xsk->batch_size - i); + break; + } + nb_frags_left = nb_frags; + + while (nb_frags_left--) { + struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); + + tx_desc->addr = pkt_get_addr(pkt, ifobject->umem); + if (pkt_stream->verbatim) { + tx_desc->len = pkt->len; + tx_desc->options = pkt->options; + } else if (nb_frags_left) { + tx_desc->len = umem->frame_size; + tx_desc->options = XDP_PKT_CONTD; + } else { + tx_desc->len = pkt->len - bytes_written; + tx_desc->options = 0; + } + if (pkt->valid) + pkt_generate(xsk, umem, tx_desc->addr, tx_desc->len, pkt->pkt_nb, + bytes_written); + bytes_written += tx_desc->len; + + print_verbose("Tx addr: %llx len: %u options: %u pkt_nb: %u\n", + tx_desc->addr, tx_desc->len, tx_desc->options, pkt->pkt_nb); + + if (nb_frags_left) { + i++; + if (pkt_stream->verbatim) + pkt = pkt_stream_get_next_tx_pkt(pkt_stream); + } + } + + if (pkt && pkt->valid) { + valid_pkts++; + valid_frags += nb_frags; + } + } + + pthread_mutex_lock(&pacing_mutex); + pkts_in_flight += valid_pkts; + pthread_mutex_unlock(&pacing_mutex); + + xsk_ring_prod__submit(&xsk->tx, i); + xsk->outstanding_tx += valid_frags; + + if (use_poll) { + ret = poll(&fds, 1, POLL_TMOUT); + if (ret <= 0) { + if (ret == 0 && timeout) + return TEST_PASS; + + ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret); + return TEST_FAILURE; + } + } + + if (!timeout) { + if (complete_pkts(xsk, i)) + return TEST_FAILURE; + + usleep(10); + return TEST_PASS; + } + + return TEST_CONTINUE; +} + +static int wait_for_tx_completion(struct xsk_socket_info *xsk) +{ + struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; + int ret; + + ret = gettimeofday(&tv_now, NULL); + if (ret) + return TEST_FAILURE; + timeradd(&tv_now, &tv_timeout, &tv_end); + + while (xsk->outstanding_tx) { + ret = gettimeofday(&tv_now, NULL); + if (ret) + return TEST_FAILURE; + if (timercmp(&tv_now, &tv_end, >)) { + ksft_print_msg("ERROR: [%s] Transmission loop timed out\n", __func__); + return TEST_FAILURE; + } + + complete_pkts(xsk, xsk->batch_size); + } + + return TEST_PASS; +} + +bool all_packets_sent(struct test_spec *test, unsigned long *bitmap) +{ + return bitmap_full(bitmap, test->nb_sockets); +} + +static int send_pkts(struct test_spec *test, struct ifobject *ifobject) +{ + bool timeout = !is_umem_valid(test->ifobj_rx); + DECLARE_BITMAP(bitmap, test->nb_sockets); + u32 i, ret; + + bitmap_zero(bitmap, test->nb_sockets); + + while (!(all_packets_sent(test, bitmap))) { + for (i = 0; i < test->nb_sockets; i++) { + struct pkt_stream *pkt_stream; + + pkt_stream = ifobject->xsk_arr[i].pkt_stream; + if (!pkt_stream || pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) { + __set_bit(i, bitmap); + continue; + } + ret = __send_pkts(ifobject, &ifobject->xsk_arr[i], timeout); + if (ret == TEST_CONTINUE && !test->fail) + continue; + + if ((ret || test->fail) && !timeout) + return TEST_FAILURE; + + if (ret == TEST_PASS && timeout) + return ret; + + ret = wait_for_tx_completion(&ifobject->xsk_arr[i]); + if (ret) + return TEST_FAILURE; + } + } + + return TEST_PASS; +} + +static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats) +{ + int fd = xsk_socket__fd(xsk), err; + socklen_t optlen, expected_len; + + optlen = sizeof(*stats); + err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, stats, &optlen); + if (err) { + ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", + __func__, -err, strerror(-err)); + return TEST_FAILURE; + } + + expected_len = sizeof(struct xdp_statistics); + if (optlen != expected_len) { + ksft_print_msg("[%s] getsockopt optlen error. Expected: %u got: %u\n", + __func__, expected_len, optlen); + return TEST_FAILURE; + } + + return TEST_PASS; +} + +static int validate_rx_dropped(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + struct xdp_statistics stats; + int err; + + err = kick_rx(ifobject->xsk); + if (err) + return TEST_FAILURE; + + err = get_xsk_stats(xsk, &stats); + if (err) + return TEST_FAILURE; + + /* The receiver calls getsockopt after receiving the last (valid) + * packet which is not the final packet sent in this test (valid and + * invalid packets are sent in alternating fashion with the final + * packet being invalid). Since the last packet may or may not have + * been dropped already, both outcomes must be allowed. + */ + if (stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 || + stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 - 1) + return TEST_PASS; + + return TEST_FAILURE; +} + +static int validate_rx_full(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + struct xdp_statistics stats; + int err; + + usleep(1000); + err = kick_rx(ifobject->xsk); + if (err) + return TEST_FAILURE; + + err = get_xsk_stats(xsk, &stats); + if (err) + return TEST_FAILURE; + + if (stats.rx_ring_full) + return TEST_PASS; + + return TEST_FAILURE; +} + +static int validate_fill_empty(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + struct xdp_statistics stats; + int err; + + usleep(1000); + err = kick_rx(ifobject->xsk); + if (err) + return TEST_FAILURE; + + err = get_xsk_stats(xsk, &stats); + if (err) + return TEST_FAILURE; + + if (stats.rx_fill_ring_empty_descs) + return TEST_PASS; + + return TEST_FAILURE; +} + +static int validate_tx_invalid_descs(struct ifobject *ifobject) +{ + struct xsk_socket *xsk = ifobject->xsk->xsk; + int fd = xsk_socket__fd(xsk); + struct xdp_statistics stats; + socklen_t optlen; + int err; + + optlen = sizeof(stats); + err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); + if (err) { + ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", + __func__, -err, strerror(-err)); + return TEST_FAILURE; + } + + if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) { + ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n", + __func__, + (unsigned long long)stats.tx_invalid_descs, + ifobject->xsk->pkt_stream->nb_pkts); + return TEST_FAILURE; + } + + return TEST_PASS; +} + +static int xsk_configure(struct test_spec *test, struct ifobject *ifobject, + struct xsk_umem_info *umem, bool tx) +{ + int i, ret; + + for (i = 0; i < test->nb_sockets; i++) { + bool shared = (ifobject->shared_umem && tx) ? true : !!i; + u32 ctr = 0; + + while (ctr++ < SOCK_RECONF_CTR) { + ret = xsk_configure_socket(&ifobject->xsk_arr[i], umem, + ifobject, shared); + if (!ret) + break; + + /* Retry if it fails as xsk_socket__create() is asynchronous */ + if (ctr >= SOCK_RECONF_CTR) + return ret; + usleep(USLEEP_MAX); + } + if (ifobject->busy_poll) { + ret = enable_busy_poll(&ifobject->xsk_arr[i]); + if (ret) + return ret; + } + } + + return 0; +} + +static int thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobject) +{ + int ret = xsk_configure(test, ifobject, test->ifobj_rx->umem, true); + + if (ret) + return ret; + ifobject->xsk = &ifobject->xsk_arr[0]; + ifobject->xskmap = test->ifobj_rx->xskmap; + memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); + ifobject->umem->base_addr = 0; + + return 0; +} + +static int xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, + bool fill_up) +{ + u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; + u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; + int ret; + + if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + buffers_to_fill = umem->num_frames; + else + buffers_to_fill = umem->fill_size; + + ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); + if (ret != buffers_to_fill) + return -ENOSPC; + + while (filled < buffers_to_fill) { + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); + u64 addr; + u32 i; + + for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) { + if (!pkt) { + if (!fill_up) + break; + addr = filled * umem->frame_size + umem->base_addr; + } else if (pkt->offset >= 0) { + addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); + } else { + addr = pkt->offset + umem_alloc_buffer(umem); + } + + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + if (++filled >= buffers_to_fill) + break; + } + } + xsk_ring_prod__submit(&umem->fq, filled); + xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); + + pkt_stream_reset(pkt_stream); + umem_reset_alloc(umem); + + return 0; +} + +static int thread_common_ops(struct test_spec *test, struct ifobject *ifobject) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + int mmap_flags; + u64 umem_sz; + void *bufs; + int ret; + u32 i; + + umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; + mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; + + if (ifobject->umem->unaligned_mode) + mmap_flags |= MAP_HUGETLB | MAP_HUGE_2MB; + + if (ifobject->shared_umem) + umem_sz *= 2; + + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + return -errno; + + ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); + if (ret) + return ret; + + ret = xsk_configure(test, ifobject, ifobject->umem, false); + if (ret) + return ret; + + ifobject->xsk = &ifobject->xsk_arr[0]; + + if (!ifobject->rx_on) + return 0; + + ret = xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream, + ifobject->use_fill_ring); + if (ret) + return ret; + + for (i = 0; i < test->nb_sockets; i++) { + ifobject->xsk = &ifobject->xsk_arr[i]; + ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, i); + if (ret) + return ret; + } + + return 0; +} + +void *worker_testapp_validate_tx(void *arg) +{ + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_tx; + int err; + + if (test->current_step == 1) { + if (!ifobject->shared_umem) { + if (thread_common_ops(test, ifobject)) { + test->fail = true; + pthread_exit(NULL); + } + } else { + if (thread_common_ops_tx(test, ifobject)) { + test->fail = true; + pthread_exit(NULL); + } + } + } + + err = send_pkts(test, ifobject); + + if (!err && ifobject->validation_func) + err = ifobject->validation_func(ifobject); + if (err) + test->fail = true; + + pthread_exit(NULL); +} + +void *worker_testapp_validate_rx(void *arg) +{ + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_rx; + int err; + + if (test->current_step == 1) { + err = thread_common_ops(test, ifobject); + } else { + xsk_clear_xskmap(ifobject->xskmap); + err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0); + if (err) + ksft_print_msg("Error: Failed to update xskmap, error %s\n", + strerror(-err)); + } + + pthread_barrier_wait(&barr); + + /* We leave only now in case of error to avoid getting stuck in the barrier */ + if (err) { + test->fail = true; + pthread_exit(NULL); + } + + err = receive_pkts(test); + + if (!err && ifobject->validation_func) + err = ifobject->validation_func(ifobject); + + if (err) { + if (!test->adjust_tail) { + test->fail = true; + } else { + bool supported; + + if (is_adjust_tail_supported(ifobject->xdp_progs, &supported)) + test->fail = true; + else if (!supported) + test->adjust_tail_support = false; + else + test->fail = true; + } + } + + pthread_exit(NULL); +} + +static void testapp_clean_xsk_umem(struct ifobject *ifobj) +{ + u64 umem_sz = ifobj->umem->num_frames * ifobj->umem->frame_size; + + if (ifobj->shared_umem) + umem_sz *= 2; + + umem_sz = ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + xsk_umem__delete(ifobj->umem->umem); + munmap(ifobj->umem->buffer, umem_sz); +} + +static void handler(int signum) +{ + pthread_exit(NULL); +} + +static bool xdp_prog_changed_rx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_rx; + + return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; +} + +static bool xdp_prog_changed_tx(struct test_spec *test) +{ + struct ifobject *ifobj = test->ifobj_tx; + + return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; +} + +static int xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, + struct bpf_map *xskmap, enum test_mode mode) +{ + int err; + + xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode)); + err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode)); + if (err) { + ksft_print_msg("Error attaching XDP program\n"); + return err; + } + + if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC)) + if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) { + ksft_print_msg("ERROR: XDP prog not in DRV mode\n"); + return -EINVAL; + } + + ifobj->xdp_prog = xdp_prog; + ifobj->xskmap = xskmap; + ifobj->mode = mode; + + return 0; +} + +static int xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, + struct ifobject *ifobj_tx) +{ + int err = 0; + + if (xdp_prog_changed_rx(test)) { + err = xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); + if (err) + return err; + } + + if (!ifobj_tx || ifobj_tx->shared_umem) + return 0; + + if (xdp_prog_changed_tx(test)) + err = xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); + + return err; +} + +static void clean_sockets(struct test_spec *test, struct ifobject *ifobj) +{ + u32 i; + + if (!ifobj || !test) + return; + + for (i = 0; i < test->nb_sockets; i++) + xsk_socket__delete(ifobj->xsk_arr[i].xsk); +} + +static void clean_umem(struct test_spec *test, struct ifobject *ifobj1, struct ifobject *ifobj2) +{ + if (!ifobj1) + return; + + testapp_clean_xsk_umem(ifobj1); + if (ifobj2 && !ifobj2->shared_umem) + testapp_clean_xsk_umem(ifobj2); +} + +static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1, + struct ifobject *ifobj2) +{ + pthread_t t0, t1; + int err; + + if (test->mtu > MAX_ETH_PKT_SIZE) { + if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp || + (ifobj2 && !ifobj2->multi_buff_zc_supp))) { + ksft_print_msg("Multi buffer for zero-copy not supported.\n"); + return TEST_SKIP; + } + if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp || + (ifobj2 && !ifobj2->multi_buff_supp))) { + ksft_print_msg("Multi buffer not supported.\n"); + return TEST_SKIP; + } + } + err = test_spec_set_mtu(test, test->mtu); + if (err) { + ksft_print_msg("Error, could not set mtu.\n"); + return TEST_FAILURE; + } + + if (ifobj2) { + if (pthread_barrier_init(&barr, NULL, 2)) + return TEST_FAILURE; + pkt_stream_reset(ifobj2->xsk->pkt_stream); + } + + test->current_step++; + pkt_stream_reset(ifobj1->xsk->pkt_stream); + pkts_in_flight = 0; + + signal(SIGUSR1, handler); + /*Spawn RX thread */ + pthread_create(&t0, NULL, ifobj1->func_ptr, test); + + if (ifobj2) { + pthread_barrier_wait(&barr); + if (pthread_barrier_destroy(&barr)) { + pthread_kill(t0, SIGUSR1); + clean_sockets(test, ifobj1); + clean_umem(test, ifobj1, NULL); + return TEST_FAILURE; + } + + /*Spawn TX thread */ + pthread_create(&t1, NULL, ifobj2->func_ptr, test); + + pthread_join(t1, NULL); + } + + if (!ifobj2) + pthread_kill(t0, SIGUSR1); + else + pthread_join(t0, NULL); + + if (test->total_steps == test->current_step || test->fail) { + clean_sockets(test, ifobj1); + clean_sockets(test, ifobj2); + clean_umem(test, ifobj1, ifobj2); + } + + if (test->fail) + return TEST_FAILURE; + + return TEST_PASS; +} + +static int testapp_validate_traffic(struct test_spec *test) +{ + struct ifobject *ifobj_rx = test->ifobj_rx; + struct ifobject *ifobj_tx = test->ifobj_tx; + + if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || + (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { + ksft_print_msg("No huge pages present.\n"); + return TEST_SKIP; + } + + if (test->set_ring) { + if (ifobj_tx->hw_ring_size_supp) { + if (set_ring_size(ifobj_tx)) { + ksft_print_msg("Failed to change HW ring size.\n"); + return TEST_FAILURE; + } + } else { + ksft_print_msg("Changing HW ring size not supported.\n"); + return TEST_SKIP; + } + } + + if (xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx)) + return TEST_FAILURE; + return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); +} + +static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj) +{ + return __testapp_validate_traffic(test, ifobj, NULL); +} + +int testapp_teardown(struct test_spec *test) +{ + int i; + + for (i = 0; i < MAX_TEARDOWN_ITER; i++) { + if (testapp_validate_traffic(test)) + return TEST_FAILURE; + test_spec_reset(test); + } + + return TEST_PASS; +} + +static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) +{ + thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr; + struct ifobject *tmp_ifobj = (*ifobj1); + + (*ifobj1)->func_ptr = (*ifobj2)->func_ptr; + (*ifobj2)->func_ptr = tmp_func_ptr; + + *ifobj1 = *ifobj2; + *ifobj2 = tmp_ifobj; +} + +int testapp_bidirectional(struct test_spec *test) +{ + int res; + + test->ifobj_tx->rx_on = true; + test->ifobj_rx->tx_on = true; + test->total_steps = 2; + if (testapp_validate_traffic(test)) + return TEST_FAILURE; + + print_verbose("Switching Tx/Rx direction\n"); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); + res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); + + swap_directions(&test->ifobj_rx, &test->ifobj_tx); + return res; +} + +static int swap_xsk_resources(struct test_spec *test) +{ + int ret; + + test->ifobj_tx->xsk_arr[0].pkt_stream = NULL; + test->ifobj_rx->xsk_arr[0].pkt_stream = NULL; + test->ifobj_tx->xsk_arr[1].pkt_stream = test->tx_pkt_stream_default; + test->ifobj_rx->xsk_arr[1].pkt_stream = test->rx_pkt_stream_default; + test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1]; + test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1]; + + ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk, 0); + if (ret) + return TEST_FAILURE; + + return TEST_PASS; +} + +int testapp_xdp_prog_cleanup(struct test_spec *test) +{ + test->total_steps = 2; + test->nb_sockets = 2; + if (testapp_validate_traffic(test)) + return TEST_FAILURE; + + if (swap_xsk_resources(test)) { + clean_sockets(test, test->ifobj_rx); + clean_sockets(test, test->ifobj_tx); + clean_umem(test, test->ifobj_rx, test->ifobj_tx); + return TEST_FAILURE; + } + + return testapp_validate_traffic(test); +} + +int testapp_headroom(struct test_spec *test) +{ + test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; + return testapp_validate_traffic(test); +} + +int testapp_stats_rx_dropped(struct test_spec *test) +{ + if (test->mode == TEST_MODE_ZC) { + ksft_print_msg("Can not run RX_DROPPED test for ZC mode\n"); + return TEST_SKIP; + } + + if (pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0)) + return TEST_FAILURE; + test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - + XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; + if (pkt_stream_receive_half(test)) + return TEST_FAILURE; + test->ifobj_rx->validation_func = validate_rx_dropped; + return testapp_validate_traffic(test); +} + +int testapp_stats_tx_invalid_descs(struct test_spec *test) +{ + if (pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0)) + return TEST_FAILURE; + test->ifobj_tx->validation_func = validate_tx_invalid_descs; + return testapp_validate_traffic(test); +} + +int testapp_stats_rx_full(struct test_spec *test) +{ + if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE)) + return TEST_FAILURE; + test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + + test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; + test->ifobj_rx->release_rx = false; + test->ifobj_rx->validation_func = validate_rx_full; + return testapp_validate_traffic(test); +} + +int testapp_stats_fill_empty(struct test_spec *test) +{ + if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE)) + return TEST_FAILURE; + test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + + test->ifobj_rx->use_fill_ring = false; + test->ifobj_rx->validation_func = validate_fill_empty; + return testapp_validate_traffic(test); +} + +int testapp_send_receive_unaligned(struct test_spec *test) +{ + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + /* Let half of the packets straddle a 4K buffer boundary */ + if (pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2)) + return TEST_FAILURE; + + return testapp_validate_traffic(test); +} + +int testapp_send_receive_unaligned_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE)) + return TEST_FAILURE; + return testapp_validate_traffic(test); +} + +int testapp_single_pkt(struct test_spec *test) +{ + struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; + + if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts))) + return TEST_FAILURE; + return testapp_validate_traffic(test); +} + +int testapp_send_receive_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE)) + return TEST_FAILURE; + + return testapp_validate_traffic(test); +} + +int testapp_invalid_desc_mb(struct test_spec *test) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; + struct pkt pkts[] = { + /* Valid packet for synch to start with */ + {0, MIN_PKT_SIZE, 0, true, 0}, + /* Zero frame len is not legal */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, 0, 0, false, 0}, + /* Invalid address in the second frame */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + /* Invalid len in the middle */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + /* Invalid options in the middle */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION}, + /* Transmit 2 frags, receive 3 */ + {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD}, + {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0}, + /* Middle frame crosses chunk boundary with small length */ + {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, + {-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0}, + /* Valid packet for synch so that something is received */ + {0, MIN_PKT_SIZE, 0, true, 0}}; + + if (umem->unaligned_mode) { + /* Crossing a chunk boundary allowed */ + pkts[12].valid = true; + pkts[13].valid = true; + } + + test->mtu = MAX_ETH_JUMBO_SIZE; + if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts))) + return TEST_FAILURE; + return testapp_validate_traffic(test); +} + +int testapp_invalid_desc(struct test_spec *test) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + u64 umem_size = umem->num_frames * umem->frame_size; + struct pkt pkts[] = { + /* Zero packet address allowed */ + {0, MIN_PKT_SIZE, 0, true}, + /* Allowed packet */ + {0, MIN_PKT_SIZE, 0, true}, + /* Straddling the start of umem */ + {-2, MIN_PKT_SIZE, 0, false}, + /* Packet too large */ + {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + /* Up to end of umem allowed */ + {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, + /* After umem ends */ + {umem_size, MIN_PKT_SIZE, 0, false}, + /* Straddle the end of umem */ + {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 4K boundary */ + {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, + /* Straddle a 2K boundary */ + {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, + /* Valid packet for synch so that something is received */ + {0, MIN_PKT_SIZE, 0, true}}; + + if (umem->unaligned_mode) { + /* Crossing a page boundary allowed */ + pkts[7].valid = true; + } + if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundary not allowed */ + pkts[8].valid = false; + } + + if (test->ifobj_tx->shared_umem) { + pkts[4].offset += umem_size; + pkts[5].offset += umem_size; + pkts[6].offset += umem_size; + } + + if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts))) + return TEST_FAILURE; + return testapp_validate_traffic(test); +} + +int testapp_xdp_drop(struct test_spec *test) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + if (pkt_stream_receive_half(test)) + return TEST_FAILURE; + return testapp_validate_traffic(test); +} + +int testapp_xdp_metadata_copy(struct test_spec *test) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata, + skel_tx->progs.xsk_xdp_populate_metadata, + skel_rx->maps.xsk, skel_tx->maps.xsk); + test->ifobj_rx->use_metadata = true; + + skel_rx->bss->count = 0; + + return testapp_validate_traffic(test); +} + +int testapp_xdp_shared_umem(struct test_spec *test) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + int ret; + + test->total_steps = 1; + test->nb_sockets = 2; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_shared_umem, + skel_tx->progs.xsk_xdp_shared_umem, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + if (pkt_stream_even_odd_sequence(test)) + return TEST_FAILURE; + + ret = testapp_validate_traffic(test); + + release_even_odd_sequence(test); + + return ret; +} + +int testapp_poll_txq_tmout(struct test_spec *test) +{ + test->ifobj_tx->use_poll = true; + /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ + test->ifobj_tx->umem->frame_size = 2048; + if (pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048)) + return TEST_FAILURE; + return testapp_validate_traffic_single_thread(test, test->ifobj_tx); +} + +int testapp_poll_rxq_tmout(struct test_spec *test) +{ + test->ifobj_rx->use_poll = true; + return testapp_validate_traffic_single_thread(test, test->ifobj_rx); +} + +int testapp_too_many_frags(struct test_spec *test) +{ + struct pkt *pkts; + u32 max_frags, i; + int ret = TEST_FAILURE; + + if (test->mode == TEST_MODE_ZC) { + max_frags = test->ifobj_tx->xdp_zc_max_segs; + } else { + max_frags = get_max_skb_frags(); + if (!max_frags) { + ksft_print_msg("Can't get MAX_SKB_FRAGS from system, using default (17)\n"); + max_frags = 17; + } + max_frags += 1; + } + + pkts = calloc(2 * max_frags + 2, sizeof(struct pkt)); + if (!pkts) + return TEST_FAILURE; + + test->mtu = MAX_ETH_JUMBO_SIZE; + + /* Valid packet for synch */ + pkts[0].len = MIN_PKT_SIZE; + pkts[0].valid = true; + + /* One valid packet with the max amount of frags */ + for (i = 1; i < max_frags + 1; i++) { + pkts[i].len = MIN_PKT_SIZE; + pkts[i].options = XDP_PKT_CONTD; + pkts[i].valid = true; + } + pkts[max_frags].options = 0; + + /* An invalid packet with the max amount of frags but signals packet + * continues on the last frag + */ + for (i = max_frags + 1; i < 2 * max_frags + 1; i++) { + pkts[i].len = MIN_PKT_SIZE; + pkts[i].options = XDP_PKT_CONTD; + pkts[i].valid = false; + } + + /* Valid packet for synch */ + pkts[2 * max_frags + 1].len = MIN_PKT_SIZE; + pkts[2 * max_frags + 1].valid = true; + + if (pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2)) { + free(pkts); + return TEST_FAILURE; + } + + ret = testapp_validate_traffic(test); + free(pkts); + return ret; +} + +static int xsk_load_xdp_programs(struct ifobject *ifobj) +{ + ifobj->xdp_progs = xsk_xdp_progs__open_and_load(); + if (libbpf_get_error(ifobj->xdp_progs)) + return libbpf_get_error(ifobj->xdp_progs); + + return 0; +} + +/* Simple test */ +static bool hugepages_present(void) +{ + size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); + if (bufs == MAP_FAILED) + return false; + + mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; + munmap(bufs, mmap_sz); + return true; +} + +int init_iface(struct ifobject *ifobj, thread_func_t func_ptr) +{ + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); + int err; + + ifobj->func_ptr = func_ptr; + + err = xsk_load_xdp_programs(ifobj); + if (err) { + ksft_print_msg("Error loading XDP program\n"); + return err; + } + + if (hugepages_present()) + ifobj->unaligned_supp = true; + + err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts); + if (err) { + ksft_print_msg("Error querying XDP capabilities\n"); + return err; + } + if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG) + ifobj->multi_buff_supp = true; + if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) { + if (query_opts.xdp_zc_max_segs > 1) { + ifobj->multi_buff_zc_supp = true; + ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs; + } else { + ifobj->xdp_zc_max_segs = 0; + } + } + + return 0; +} + +int testapp_send_receive(struct test_spec *test) +{ + return testapp_validate_traffic(test); +} + +int testapp_send_receive_2k_frame(struct test_spec *test) +{ + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE)) + return TEST_FAILURE; + return testapp_validate_traffic(test); +} + +int testapp_poll_rx(struct test_spec *test) +{ + test->ifobj_rx->use_poll = true; + return testapp_validate_traffic(test); +} + +int testapp_poll_tx(struct test_spec *test) +{ + test->ifobj_tx->use_poll = true; + return testapp_validate_traffic(test); +} + +int testapp_aligned_inv_desc(struct test_spec *test) +{ + return testapp_invalid_desc(test); +} + +int testapp_aligned_inv_desc_2k_frame(struct test_spec *test) +{ + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + return testapp_invalid_desc(test); +} + +int testapp_unaligned_inv_desc(struct test_spec *test) +{ + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + return testapp_invalid_desc(test); +} + +int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test) +{ + u64 page_size, umem_size; + + /* Odd frame size so the UMEM doesn't end near a page boundary. */ + test->ifobj_tx->umem->frame_size = 4001; + test->ifobj_rx->umem->frame_size = 4001; + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + /* This test exists to test descriptors that staddle the end of + * the UMEM but not a page. + */ + page_size = sysconf(_SC_PAGESIZE); + umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; + assert(umem_size % page_size > MIN_PKT_SIZE); + assert(umem_size % page_size < page_size - MIN_PKT_SIZE); + + return testapp_invalid_desc(test); +} + +int testapp_aligned_inv_desc_mb(struct test_spec *test) +{ + return testapp_invalid_desc_mb(test); +} + +int testapp_unaligned_inv_desc_mb(struct test_spec *test) +{ + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + return testapp_invalid_desc_mb(test); +} + +int testapp_xdp_metadata(struct test_spec *test) +{ + return testapp_xdp_metadata_copy(test); +} + +int testapp_xdp_metadata_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + return testapp_xdp_metadata_copy(test); +} + +int testapp_hw_sw_min_ring_size(struct test_spec *test) +{ + int ret; + + test->set_ring = true; + test->total_steps = 2; + test->ifobj_tx->ring.tx_pending = DEFAULT_BATCH_SIZE; + test->ifobj_tx->ring.rx_pending = DEFAULT_BATCH_SIZE * 2; + test->ifobj_tx->xsk->batch_size = 1; + test->ifobj_rx->xsk->batch_size = 1; + ret = testapp_validate_traffic(test); + if (ret) + return ret; + + /* Set batch size to hw_ring_size - 1 */ + test->ifobj_tx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; + test->ifobj_rx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; + return testapp_validate_traffic(test); +} + +int testapp_hw_sw_max_ring_size(struct test_spec *test) +{ + u32 max_descs = XSK_RING_PROD__DEFAULT_NUM_DESCS * 4; + int ret; + + test->set_ring = true; + test->total_steps = 2; + test->ifobj_tx->ring.tx_pending = test->ifobj_tx->ring.tx_max_pending; + test->ifobj_tx->ring.rx_pending = test->ifobj_tx->ring.rx_max_pending; + test->ifobj_rx->umem->num_frames = max_descs; + test->ifobj_rx->umem->fill_size = max_descs; + test->ifobj_rx->umem->comp_size = max_descs; + test->ifobj_tx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + test->ifobj_rx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; + + ret = testapp_validate_traffic(test); + if (ret) + return ret; + + /* Set batch_size to 8152 for testing, as the ice HW ignores the 3 lowest bits when + * updating the Rx HW tail register. + */ + test->ifobj_tx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; + test->ifobj_rx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; + if (pkt_stream_replace(test, max_descs, MIN_PKT_SIZE)) { + clean_sockets(test, test->ifobj_tx); + clean_sockets(test, test->ifobj_rx); + clean_umem(test, test->ifobj_rx, test->ifobj_tx); + return TEST_FAILURE; + } + + return testapp_validate_traffic(test); +} + +static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value) +{ + struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; + struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; + + test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail, + skel_tx->progs.xsk_xdp_adjust_tail, + skel_rx->maps.xsk, skel_tx->maps.xsk); + + skel_rx->bss->adjust_value = adjust_value; + + return testapp_validate_traffic(test); +} + +static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len) +{ + int ret; + + test->adjust_tail_support = true; + test->adjust_tail = true; + test->total_steps = 1; + + ret = pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len); + if (ret) + return TEST_FAILURE; + + ret = pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value); + if (ret) + return TEST_FAILURE; + + ret = testapp_xdp_adjust_tail(test, value); + if (ret) + return ret; + + if (!test->adjust_tail_support) { + ksft_print_msg("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n", + mode_string(test), busy_poll_string(test)); + return TEST_SKIP; + } + + return 0; +} + +int testapp_adjust_tail_shrink(struct test_spec *test) +{ + /* Shrink by 4 bytes for testing purpose */ + return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2); +} + +int testapp_adjust_tail_shrink_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + /* Shrink by the frag size */ + return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2); +} + +int testapp_adjust_tail_grow(struct test_spec *test) +{ + /* Grow by 4 bytes for testing purpose */ + return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2); +} + +int testapp_adjust_tail_grow_mb(struct test_spec *test) +{ + test->mtu = MAX_ETH_JUMBO_SIZE; + /* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */ + return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1, + XSK_UMEM__LARGE_FRAME_SIZE * 2); +} + +int testapp_tx_queue_consumer(struct test_spec *test) +{ + int nr_packets; + + if (test->mode == TEST_MODE_ZC) { + ksft_print_msg("Can not run TX_QUEUE_CONSUMER test for ZC mode\n"); + return TEST_SKIP; + } + + nr_packets = MAX_TX_BUDGET_DEFAULT + 1; + if (pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE)) + return TEST_FAILURE; + test->ifobj_tx->xsk->batch_size = nr_packets; + test->ifobj_tx->xsk->check_consumer = true; + + return testapp_validate_traffic(test); +} + +struct ifobject *ifobject_create(void) +{ + struct ifobject *ifobj; + + ifobj = calloc(1, sizeof(struct ifobject)); + if (!ifobj) + return NULL; + + ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr)); + if (!ifobj->xsk_arr) + goto out_xsk_arr; + + ifobj->umem = calloc(1, sizeof(*ifobj->umem)); + if (!ifobj->umem) + goto out_umem; + + return ifobj; + +out_umem: + free(ifobj->xsk_arr); +out_xsk_arr: + free(ifobj); + return NULL; +} + +void ifobject_delete(struct ifobject *ifobj) +{ + free(ifobj->umem); + free(ifobj->xsk_arr); + free(ifobj); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.h b/tools/testing/selftests/bpf/prog_tests/test_xsk.h new file mode 100644 index 000000000000..8fc78a057de0 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.h @@ -0,0 +1,298 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef TEST_XSK_H_ +#define TEST_XSK_H_ + +#include <linux/ethtool.h> +#include <linux/if_xdp.h> + +#include "../kselftest.h" +#include "xsk.h" + +#ifndef SO_PREFER_BUSY_POLL +#define SO_PREFER_BUSY_POLL 69 +#endif + +#ifndef SO_BUSY_POLL_BUDGET +#define SO_BUSY_POLL_BUDGET 70 +#endif + +#define TEST_PASS 0 +#define TEST_FAILURE -1 +#define TEST_CONTINUE 1 +#define TEST_SKIP 2 + +#define DEFAULT_PKT_CNT (4 * 1024) +#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) +#define HUGEPAGE_SIZE (2 * 1024 * 1024) +#define MIN_PKT_SIZE 64 +#define MAX_ETH_PKT_SIZE 1518 +#define MAX_INTERFACE_NAME_CHARS 16 +#define MAX_TEST_NAME_SIZE 48 +#define SOCK_RECONF_CTR 10 +#define USLEEP_MAX 10000 + +extern bool opt_verbose; +#define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) + + +static inline u32 ceil_u32(u32 a, u32 b) +{ + return (a + b - 1) / b; +} + +static inline u64 ceil_u64(u64 a, u64 b) +{ + return (a + b - 1) / b; +} + +/* Simple test */ +enum test_mode { + TEST_MODE_SKB, + TEST_MODE_DRV, + TEST_MODE_ZC, + TEST_MODE_ALL +}; + +struct ifobject; +struct test_spec; +typedef int (*validation_func_t)(struct ifobject *ifobj); +typedef void *(*thread_func_t)(void *arg); +typedef int (*test_func_t)(struct test_spec *test); + +struct xsk_socket_info { + struct xsk_ring_cons rx; + struct xsk_ring_prod tx; + struct xsk_umem_info *umem; + struct xsk_socket *xsk; + struct pkt_stream *pkt_stream; + u32 outstanding_tx; + u32 rxqsize; + u32 batch_size; + u8 dst_mac[ETH_ALEN]; + u8 src_mac[ETH_ALEN]; + bool check_consumer; +}; + +int kick_rx(struct xsk_socket_info *xsk); +int kick_tx(struct xsk_socket_info *xsk); + +struct xsk_umem_info { + struct xsk_ring_prod fq; + struct xsk_ring_cons cq; + struct xsk_umem *umem; + u64 next_buffer; + u32 num_frames; + u32 frame_headroom; + void *buffer; + u32 frame_size; + u32 base_addr; + u32 fill_size; + u32 comp_size; + bool unaligned_mode; +}; + +struct set_hw_ring { + u32 default_tx; + u32 default_rx; +}; + +int hw_ring_size_reset(struct ifobject *ifobj); + +struct ifobject { + char ifname[MAX_INTERFACE_NAME_CHARS]; + struct xsk_socket_info *xsk; + struct xsk_socket_info *xsk_arr; + struct xsk_umem_info *umem; + thread_func_t func_ptr; + validation_func_t validation_func; + struct xsk_xdp_progs *xdp_progs; + struct bpf_map *xskmap; + struct bpf_program *xdp_prog; + struct ethtool_ringparam ring; + struct set_hw_ring set_ring; + enum test_mode mode; + int ifindex; + int mtu; + u32 bind_flags; + u32 xdp_zc_max_segs; + bool tx_on; + bool rx_on; + bool use_poll; + bool busy_poll; + bool use_fill_ring; + bool release_rx; + bool shared_umem; + bool use_metadata; + bool unaligned_supp; + bool multi_buff_supp; + bool multi_buff_zc_supp; + bool hw_ring_size_supp; +}; +struct ifobject *ifobject_create(void); +void ifobject_delete(struct ifobject *ifobj); +int init_iface(struct ifobject *ifobj, thread_func_t func_ptr); + +int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, u64 size); +int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, + struct ifobject *ifobject, bool shared); + + +struct pkt { + int offset; + u32 len; + u32 pkt_nb; + bool valid; + u16 options; +}; + +struct pkt_stream { + u32 nb_pkts; + u32 current_pkt_nb; + struct pkt *pkts; + u32 max_pkt_len; + u32 nb_rx_pkts; + u32 nb_valid_entries; + bool verbatim; +}; + +static inline bool pkt_continues(u32 options) +{ + return options & XDP_PKT_CONTD; +} + +struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len); +void pkt_stream_delete(struct pkt_stream *pkt_stream); +void pkt_stream_reset(struct pkt_stream *pkt_stream); +void pkt_stream_restore_default(struct test_spec *test); + +struct test_spec { + struct ifobject *ifobj_tx; + struct ifobject *ifobj_rx; + struct pkt_stream *tx_pkt_stream_default; + struct pkt_stream *rx_pkt_stream_default; + struct bpf_program *xdp_prog_rx; + struct bpf_program *xdp_prog_tx; + struct bpf_map *xskmap_rx; + struct bpf_map *xskmap_tx; + test_func_t test_func; + int mtu; + u16 total_steps; + u16 current_step; + u16 nb_sockets; + bool fail; + bool set_ring; + bool adjust_tail; + bool adjust_tail_support; + enum test_mode mode; + char name[MAX_TEST_NAME_SIZE]; +}; + +#define busy_poll_string(test) (test)->ifobj_tx->busy_poll ? "BUSY-POLL " : "" +static inline char *mode_string(struct test_spec *test) +{ + switch (test->mode) { + case TEST_MODE_SKB: + return "SKB"; + case TEST_MODE_DRV: + return "DRV"; + case TEST_MODE_ZC: + return "ZC"; + default: + return "BOGUS"; + } +} + +void test_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx, enum test_mode mode, + const struct test_spec *test_to_run); + +int testapp_adjust_tail_grow(struct test_spec *test); +int testapp_adjust_tail_grow_mb(struct test_spec *test); +int testapp_adjust_tail_shrink(struct test_spec *test); +int testapp_adjust_tail_shrink_mb(struct test_spec *test); +int testapp_aligned_inv_desc(struct test_spec *test); +int testapp_aligned_inv_desc_2k_frame(struct test_spec *test); +int testapp_aligned_inv_desc_mb(struct test_spec *test); +int testapp_bidirectional(struct test_spec *test); +int testapp_headroom(struct test_spec *test); +int testapp_hw_sw_max_ring_size(struct test_spec *test); +int testapp_hw_sw_min_ring_size(struct test_spec *test); +int testapp_poll_rx(struct test_spec *test); +int testapp_poll_rxq_tmout(struct test_spec *test); +int testapp_poll_tx(struct test_spec *test); +int testapp_poll_txq_tmout(struct test_spec *test); +int testapp_send_receive(struct test_spec *test); +int testapp_send_receive_2k_frame(struct test_spec *test); +int testapp_send_receive_mb(struct test_spec *test); +int testapp_send_receive_unaligned(struct test_spec *test); +int testapp_send_receive_unaligned_mb(struct test_spec *test); +int testapp_single_pkt(struct test_spec *test); +int testapp_stats_fill_empty(struct test_spec *test); +int testapp_stats_rx_dropped(struct test_spec *test); +int testapp_stats_tx_invalid_descs(struct test_spec *test); +int testapp_stats_rx_full(struct test_spec *test); +int testapp_teardown(struct test_spec *test); +int testapp_too_many_frags(struct test_spec *test); +int testapp_tx_queue_consumer(struct test_spec *test); +int testapp_unaligned_inv_desc(struct test_spec *test); +int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test); +int testapp_unaligned_inv_desc_mb(struct test_spec *test); +int testapp_xdp_drop(struct test_spec *test); +int testapp_xdp_metadata(struct test_spec *test); +int testapp_xdp_metadata_mb(struct test_spec *test); +int testapp_xdp_prog_cleanup(struct test_spec *test); +int testapp_xdp_shared_umem(struct test_spec *test); + +void *worker_testapp_validate_rx(void *arg); +void *worker_testapp_validate_tx(void *arg); + +static const struct test_spec tests[] = { + {.name = "SEND_RECEIVE", .test_func = testapp_send_receive}, + {.name = "SEND_RECEIVE_2K_FRAME", .test_func = testapp_send_receive_2k_frame}, + {.name = "SEND_RECEIVE_SINGLE_PKT", .test_func = testapp_single_pkt}, + {.name = "POLL_RX", .test_func = testapp_poll_rx}, + {.name = "POLL_TX", .test_func = testapp_poll_tx}, + {.name = "POLL_RXQ_FULL", .test_func = testapp_poll_rxq_tmout}, + {.name = "POLL_TXQ_FULL", .test_func = testapp_poll_txq_tmout}, + {.name = "ALIGNED_INV_DESC", .test_func = testapp_aligned_inv_desc}, + {.name = "ALIGNED_INV_DESC_2K_FRAME_SIZE", .test_func = testapp_aligned_inv_desc_2k_frame}, + {.name = "UMEM_HEADROOM", .test_func = testapp_headroom}, + {.name = "BIDIRECTIONAL", .test_func = testapp_bidirectional}, + {.name = "STAT_RX_DROPPED", .test_func = testapp_stats_rx_dropped}, + {.name = "STAT_TX_INVALID", .test_func = testapp_stats_tx_invalid_descs}, + {.name = "STAT_RX_FULL", .test_func = testapp_stats_rx_full}, + {.name = "STAT_FILL_EMPTY", .test_func = testapp_stats_fill_empty}, + {.name = "XDP_PROG_CLEANUP", .test_func = testapp_xdp_prog_cleanup}, + {.name = "XDP_DROP_HALF", .test_func = testapp_xdp_drop}, + {.name = "XDP_SHARED_UMEM", .test_func = testapp_xdp_shared_umem}, + {.name = "XDP_METADATA_COPY", .test_func = testapp_xdp_metadata}, + {.name = "XDP_METADATA_COPY_MULTI_BUFF", .test_func = testapp_xdp_metadata_mb}, + {.name = "ALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_aligned_inv_desc_mb}, + {.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags}, + {.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink}, + {.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer}, + }; + +static const struct test_spec ci_skip_tests[] = { + /* Flaky tests */ + {.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb}, + {.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow}, + {.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb}, + {.name = "SEND_RECEIVE_9K_PACKETS", .test_func = testapp_send_receive_mb}, + /* Tests with huge page dependency */ + {.name = "SEND_RECEIVE_UNALIGNED", .test_func = testapp_send_receive_unaligned}, + {.name = "UNALIGNED_INV_DESC", .test_func = testapp_unaligned_inv_desc}, + {.name = "UNALIGNED_INV_DESC_4001_FRAME_SIZE", + .test_func = testapp_unaligned_inv_desc_4001_frame}, + {.name = "SEND_RECEIVE_UNALIGNED_9K_PACKETS", + .test_func = testapp_send_receive_unaligned_mb}, + {.name = "UNALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_unaligned_inv_desc_mb}, + /* Test with HW ring size dependency */ + {.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size}, + {.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size}, + /* Too long test */ + {.name = "TEARDOWN", .test_func = testapp_teardown}, +}; + + +#endif /* TEST_XSK_H_ */ diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 28e81161e6fc..4b4b081b46cc 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -7,6 +7,7 @@ #include "verifier_arena.skel.h" #include "verifier_arena_large.skel.h" #include "verifier_array_access.skel.h" +#include "verifier_async_cb_context.skel.h" #include "verifier_basic_stack.skel.h" #include "verifier_bitfield_write.skel.h" #include "verifier_bounds.skel.h" @@ -34,6 +35,7 @@ #include "verifier_global_subprogs.skel.h" #include "verifier_global_ptr_args.skel.h" #include "verifier_gotol.skel.h" +#include "verifier_gotox.skel.h" #include "verifier_helper_access_var_len.skel.h" #include "verifier_helper_packet_access.skel.h" #include "verifier_helper_restricted.skel.h" @@ -172,6 +174,7 @@ void test_verifier_div_overflow(void) { RUN(verifier_div_overflow); } void test_verifier_global_subprogs(void) { RUN(verifier_global_subprogs); } void test_verifier_global_ptr_args(void) { RUN(verifier_global_ptr_args); } void test_verifier_gotol(void) { RUN(verifier_gotol); } +void test_verifier_gotox(void) { RUN(verifier_gotox); } void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); } void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); } void test_verifier_helper_restricted(void) { RUN(verifier_helper_restricted); } @@ -280,6 +283,7 @@ void test_verifier_array_access(void) verifier_array_access__elf_bytes, init_array_access_maps); } +void test_verifier_async_cb_context(void) { RUN(verifier_async_cb_context); } static int init_value_ptr_arith_maps(struct bpf_object *obj) { diff --git a/tools/testing/selftests/bpf/prog_tests/wq.c b/tools/testing/selftests/bpf/prog_tests/wq.c index 99e438fe12ac..15c67d23128b 100644 --- a/tools/testing/selftests/bpf/prog_tests/wq.c +++ b/tools/testing/selftests/bpf/prog_tests/wq.c @@ -38,3 +38,59 @@ void serial_test_failures_wq(void) { RUN_TESTS(wq_failures); } + +static void test_failure_map_no_btf(void) +{ + struct wq *skel = NULL; + char log[8192]; + const struct bpf_insn *insns; + size_t insn_cnt; + int ret, err, map_fd; + LIBBPF_OPTS(bpf_prog_load_opts, opts, .log_size = sizeof(log), .log_buf = log, + .log_level = 2); + + skel = wq__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + err = bpf_object__prepare(skel->obj); + if (!ASSERT_OK(err, "skel__prepare")) + goto out; + + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "map_no_btf", sizeof(__u32), sizeof(__u64), 100, + NULL); + if (!ASSERT_GT(map_fd, -1, "map create")) + goto out; + + err = bpf_map__reuse_fd(skel->maps.array, map_fd); + if (!ASSERT_OK(err, "map reuse fd")) { + close(map_fd); + goto out; + } + + insns = bpf_program__insns(skel->progs.test_map_no_btf); + if (!ASSERT_OK_PTR(insns, "insns ptr")) + goto out; + + insn_cnt = bpf_program__insn_cnt(skel->progs.test_map_no_btf); + if (!ASSERT_GT(insn_cnt, 0u, "insn cnt")) + goto out; + + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + if (!ASSERT_LT(ret, 0, "prog load failed")) { + if (ret > 0) + close(ret); + goto out; + } + + ASSERT_HAS_SUBSTR(log, "map 'map_no_btf' has to have BTF in order to use bpf_wq", + "log complains no map BTF"); +out: + wq__destroy(skel); +} + +void test_wq_custom(void) +{ + if (test__start_subtest("test_failure_map_no_btf")) + test_failure_map_no_btf(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index 178292d1251a..ee94c281888a 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -124,10 +124,10 @@ static int send_test_packet(int ifindex) int n, sock = -1; __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; - /* The ethernet header is not relevant for this test and doesn't need to - * be meaningful. - */ - struct ethhdr eth = { 0 }; + /* We use the Ethernet header only to identify the test packet */ + struct ethhdr eth = { + .h_source = { 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF }, + }; memcpy(packet, ð, sizeof(eth)); memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN); @@ -160,8 +160,16 @@ static int write_test_packet(int tap_fd) __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; int n; - /* The ethernet header doesn't need to be valid for this test */ - memset(packet, 0, sizeof(struct ethhdr)); + /* The Ethernet header is mostly not relevant. We use it to identify the + * test packet and some BPF helpers we exercise expect to operate on + * Ethernet frames carrying IP packets. Pretend that's the case. + */ + struct ethhdr eth = { + .h_source = { 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF }, + .h_proto = htons(ETH_P_IP), + }; + + memcpy(packet, ð, sizeof(eth)); memcpy(packet + sizeof(struct ethhdr), test_payload, TEST_PAYLOAD_LEN); n = write(tap_fd, packet, sizeof(packet)); @@ -171,31 +179,19 @@ static int write_test_packet(int tap_fd) return 0; } -static void assert_test_result(const struct bpf_map *result_map) -{ - int err; - __u32 map_key = 0; - __u8 map_value[TEST_PAYLOAD_LEN]; - - err = bpf_map__lookup_elem(result_map, &map_key, sizeof(map_key), - &map_value, TEST_PAYLOAD_LEN, BPF_ANY); - if (!ASSERT_OK(err, "lookup test_result")) - return; - - ASSERT_MEMEQ(&map_value, &test_payload, TEST_PAYLOAD_LEN, - "test_result map contains test payload"); -} - -static bool clear_test_result(struct bpf_map *result_map) +static void dump_err_stream(const struct bpf_program *prog) { - const __u8 v[sizeof(test_payload)] = {}; - const __u32 k = 0; - int err; - - err = bpf_map__update_elem(result_map, &k, sizeof(k), v, sizeof(v), BPF_ANY); - ASSERT_OK(err, "update test_result"); + char buf[512]; + int ret; - return err == 0; + ret = 0; + do { + ret = bpf_prog_stream_read(bpf_program__fd(prog), + BPF_STREAM_STDERR, buf, sizeof(buf), + NULL); + if (ret > 0) + fwrite(buf, sizeof(buf[0]), ret, stderr); + } while (ret > 0); } void test_xdp_context_veth(void) @@ -270,11 +266,14 @@ void test_xdp_context_veth(void) if (!ASSERT_GE(tx_ifindex, 0, "if_nametoindex tx")) goto close; + skel->bss->test_pass = false; + ret = send_test_packet(tx_ifindex); if (!ASSERT_OK(ret, "send_test_packet")) goto close; - assert_test_result(skel->maps.test_result); + if (!ASSERT_TRUE(skel->bss->test_pass, "test_pass")) + dump_err_stream(tc_prog); close: close_netns(nstoken); @@ -286,7 +285,7 @@ close: static void test_tuntap(struct bpf_program *xdp_prog, struct bpf_program *tc_prio_1_prog, struct bpf_program *tc_prio_2_prog, - struct bpf_map *result_map) + bool *test_pass) { LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); @@ -295,8 +294,7 @@ static void test_tuntap(struct bpf_program *xdp_prog, int tap_ifindex; int ret; - if (!clear_test_result(result_map)) - return; + *test_pass = false; ns = netns_new(TAP_NETNS, true); if (!ASSERT_OK_PTR(ns, "create and open ns")) @@ -340,7 +338,8 @@ static void test_tuntap(struct bpf_program *xdp_prog, if (!ASSERT_OK(ret, "write_test_packet")) goto close; - assert_test_result(result_map); + if (!ASSERT_TRUE(*test_pass, "test_pass")) + dump_err_stream(tc_prio_2_prog ? : tc_prio_1_prog); close: if (tap_fd >= 0) @@ -411,7 +410,8 @@ static void test_tuntap_mirred(struct bpf_program *xdp_prog, if (!ASSERT_OK(ret, "write_test_packet")) goto close; - ASSERT_TRUE(*test_pass, "test_pass"); + if (!ASSERT_TRUE(*test_pass, "test_pass")) + dump_err_stream(tc_prog); close: if (tap_fd >= 0) @@ -431,61 +431,82 @@ void test_xdp_context_tuntap(void) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls, NULL, /* tc prio 2 */ - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_read")) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls_dynptr_read, NULL, /* tc prio 2 */ - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_slice")) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls_dynptr_slice, NULL, /* tc prio 2 */ - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_write")) test_tuntap(skel->progs.ing_xdp_zalloc_meta, skel->progs.ing_cls_dynptr_write, skel->progs.ing_cls_dynptr_read, - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_slice_rdwr")) test_tuntap(skel->progs.ing_xdp_zalloc_meta, skel->progs.ing_cls_dynptr_slice_rdwr, skel->progs.ing_cls_dynptr_slice, - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_offset")) test_tuntap(skel->progs.ing_xdp_zalloc_meta, skel->progs.ing_cls_dynptr_offset_wr, skel->progs.ing_cls_dynptr_offset_rd, - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_offset_oob")) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls_dynptr_offset_oob, skel->progs.ing_cls, - skel->maps.test_result); - if (test__start_subtest("clone_data_meta_empty_on_data_write")) + &skel->bss->test_pass); + if (test__start_subtest("clone_data_meta_survives_data_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_data_meta_empty_on_data_write, + skel->progs.clone_data_meta_survives_data_write, &skel->bss->test_pass); - if (test__start_subtest("clone_data_meta_empty_on_meta_write")) + if (test__start_subtest("clone_data_meta_survives_meta_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_data_meta_empty_on_meta_write, + skel->progs.clone_data_meta_survives_meta_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_empty_on_data_slice_write")) + if (test__start_subtest("clone_meta_dynptr_survives_data_slice_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_empty_on_data_slice_write, + skel->progs.clone_meta_dynptr_survives_data_slice_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_empty_on_meta_slice_write")) + if (test__start_subtest("clone_meta_dynptr_survives_meta_slice_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_empty_on_meta_slice_write, + skel->progs.clone_meta_dynptr_survives_meta_slice_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_rdonly_before_data_dynptr_write")) + if (test__start_subtest("clone_meta_dynptr_rw_before_data_dynptr_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_rdonly_before_data_dynptr_write, + skel->progs.clone_meta_dynptr_rw_before_data_dynptr_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_rdonly_before_meta_dynptr_write")) + if (test__start_subtest("clone_meta_dynptr_rw_before_meta_dynptr_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_rdonly_before_meta_dynptr_write, + skel->progs.clone_meta_dynptr_rw_before_meta_dynptr_write, &skel->bss->test_pass); + /* Tests for BPF helpers which touch headroom */ + if (test__start_subtest("helper_skb_vlan_push_pop")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_vlan_push_pop, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); + if (test__start_subtest("helper_skb_adjust_room")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_adjust_room, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); + if (test__start_subtest("helper_skb_change_head_tail")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_change_head_tail, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); + if (test__start_subtest("helper_skb_change_proto")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_change_proto, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); test_xdp_meta__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xsk.c b/tools/testing/selftests/bpf/prog_tests/xsk.c new file mode 100644 index 000000000000..dd4c35c0e428 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xsk.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <net/if.h> +#include <stdarg.h> + +#include "network_helpers.h" +#include "test_progs.h" +#include "test_xsk.h" +#include "xsk_xdp_progs.skel.h" + +#define VETH_RX "veth0" +#define VETH_TX "veth1" +#define MTU 1500 + +int setup_veth(bool busy_poll) +{ + SYS(fail, + "ip link add %s numtxqueues 4 numrxqueues 4 type veth peer name %s numtxqueues 4 numrxqueues 4", + VETH_RX, VETH_TX); + SYS(fail, "sysctl -wq net.ipv6.conf.%s.disable_ipv6=1", VETH_RX); + SYS(fail, "sysctl -wq net.ipv6.conf.%s.disable_ipv6=1", VETH_TX); + + if (busy_poll) { + SYS(fail, "echo 2 > /sys/class/net/%s/napi_defer_hard_irqs", VETH_RX); + SYS(fail, "echo 200000 > /sys/class/net/%s/gro_flush_timeout", VETH_RX); + SYS(fail, "echo 2 > /sys/class/net/%s/napi_defer_hard_irqs", VETH_TX); + SYS(fail, "echo 200000 > /sys/class/net/%s/gro_flush_timeout", VETH_TX); + } + + SYS(fail, "ip link set %s mtu %d", VETH_RX, MTU); + SYS(fail, "ip link set %s mtu %d", VETH_TX, MTU); + SYS(fail, "ip link set %s up", VETH_RX); + SYS(fail, "ip link set %s up", VETH_TX); + + return 0; + +fail: + return -1; +} + +void delete_veth(void) +{ + SYS_NOFAIL("ip link del %s", VETH_RX); + SYS_NOFAIL("ip link del %s", VETH_TX); +} + +int configure_ifobj(struct ifobject *tx, struct ifobject *rx) +{ + rx->ifindex = if_nametoindex(VETH_RX); + if (!ASSERT_OK_FD(rx->ifindex, "get RX ifindex")) + return -1; + + tx->ifindex = if_nametoindex(VETH_TX); + if (!ASSERT_OK_FD(tx->ifindex, "get TX ifindex")) + return -1; + + tx->shared_umem = false; + rx->shared_umem = false; + + + return 0; +} + +static void test_xsk(const struct test_spec *test_to_run, enum test_mode mode) +{ + struct ifobject *ifobj_tx, *ifobj_rx; + struct test_spec test; + int ret; + + ifobj_tx = ifobject_create(); + if (!ASSERT_OK_PTR(ifobj_tx, "create ifobj_tx")) + return; + + ifobj_rx = ifobject_create(); + if (!ASSERT_OK_PTR(ifobj_rx, "create ifobj_rx")) + goto delete_tx; + + if (!ASSERT_OK(configure_ifobj(ifobj_tx, ifobj_rx), "conigure ifobj")) + goto delete_rx; + + ret = get_hw_ring_size(ifobj_tx->ifname, &ifobj_tx->ring); + if (!ret) { + ifobj_tx->hw_ring_size_supp = true; + ifobj_tx->set_ring.default_tx = ifobj_tx->ring.tx_pending; + ifobj_tx->set_ring.default_rx = ifobj_tx->ring.rx_pending; + } + + if (!ASSERT_OK(init_iface(ifobj_rx, worker_testapp_validate_rx), "init RX")) + goto delete_rx; + if (!ASSERT_OK(init_iface(ifobj_tx, worker_testapp_validate_tx), "init TX")) + goto delete_rx; + + test_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]); + + test.tx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE); + if (!ASSERT_OK_PTR(test.tx_pkt_stream_default, "TX pkt generation")) + goto delete_rx; + test.rx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE); + if (!ASSERT_OK_PTR(test.rx_pkt_stream_default, "RX pkt generation")) + goto delete_rx; + + + test_init(&test, ifobj_tx, ifobj_rx, mode, test_to_run); + ret = test.test_func(&test); + if (ret != TEST_SKIP) + ASSERT_OK(ret, "Run test"); + pkt_stream_restore_default(&test); + + if (ifobj_tx->hw_ring_size_supp) + hw_ring_size_reset(ifobj_tx); + + pkt_stream_delete(test.tx_pkt_stream_default); + pkt_stream_delete(test.rx_pkt_stream_default); + xsk_xdp_progs__destroy(ifobj_tx->xdp_progs); + xsk_xdp_progs__destroy(ifobj_rx->xdp_progs); + +delete_rx: + ifobject_delete(ifobj_rx); +delete_tx: + ifobject_delete(ifobj_tx); +} + +void test_ns_xsk_skb(void) +{ + int i; + + if (!ASSERT_OK(setup_veth(false), "setup veth")) + return; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (test__start_subtest(tests[i].name)) + test_xsk(&tests[i], TEST_MODE_SKB); + } + + delete_veth(); +} + +void test_ns_xsk_drv(void) +{ + int i; + + if (!ASSERT_OK(setup_veth(false), "setup veth")) + return; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (test__start_subtest(tests[i].name)) + test_xsk(&tests[i], TEST_MODE_DRV); + } + + delete_veth(); +} + diff --git a/tools/testing/selftests/bpf/progs/arena_strsearch.c b/tools/testing/selftests/bpf/progs/arena_strsearch.c new file mode 100644 index 000000000000..ef6b76658f7f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/arena_strsearch.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include "bpf_experimental.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARENA); + __uint(map_flags, BPF_F_MMAPABLE); + __uint(max_entries, 100); /* number of pages */ +} arena SEC(".maps"); + +#include "bpf_arena_strsearch.h" + +struct glob_test { + char const __arena *pat, *str; + bool expected; +}; + +static bool test(char const __arena *pat, char const __arena *str, bool expected) +{ + bool match = glob_match(pat, str); + bool success = match == expected; + + /* bpf_printk("glob_match %s %s res %d ok %d", pat, str, match, success); */ + return success; +} + +/* + * The tests are all jammed together in one array to make it simpler + * to place that array in the .init.rodata section. The obvious + * "array of structures containing char *" has no way to force the + * pointed-to strings to be in a particular section. + * + * Anyway, a test consists of: + * 1. Expected glob_match result: '1' or '0'. + * 2. Pattern to match: null-terminated string + * 3. String to match against: null-terminated string + * + * The list of tests is terminated with a final '\0' instead of + * a glob_match result character. + */ +static const char __arena glob_tests[] = + /* Some basic tests */ + "1" "a\0" "a\0" + "0" "a\0" "b\0" + "0" "a\0" "aa\0" + "0" "a\0" "\0" + "1" "\0" "\0" + "0" "\0" "a\0" + /* Simple character class tests */ + "1" "[a]\0" "a\0" + "0" "[a]\0" "b\0" + "0" "[!a]\0" "a\0" + "1" "[!a]\0" "b\0" + "1" "[ab]\0" "a\0" + "1" "[ab]\0" "b\0" + "0" "[ab]\0" "c\0" + "1" "[!ab]\0" "c\0" + "1" "[a-c]\0" "b\0" + "0" "[a-c]\0" "d\0" + /* Corner cases in character class parsing */ + "1" "[a-c-e-g]\0" "-\0" + "0" "[a-c-e-g]\0" "d\0" + "1" "[a-c-e-g]\0" "f\0" + "1" "[]a-ceg-ik[]\0" "a\0" + "1" "[]a-ceg-ik[]\0" "]\0" + "1" "[]a-ceg-ik[]\0" "[\0" + "1" "[]a-ceg-ik[]\0" "h\0" + "0" "[]a-ceg-ik[]\0" "f\0" + "0" "[!]a-ceg-ik[]\0" "h\0" + "0" "[!]a-ceg-ik[]\0" "]\0" + "1" "[!]a-ceg-ik[]\0" "f\0" + /* Simple wild cards */ + "1" "?\0" "a\0" + "0" "?\0" "aa\0" + "0" "??\0" "a\0" + "1" "?x?\0" "axb\0" + "0" "?x?\0" "abx\0" + "0" "?x?\0" "xab\0" + /* Asterisk wild cards (backtracking) */ + "0" "*??\0" "a\0" + "1" "*??\0" "ab\0" + "1" "*??\0" "abc\0" + "1" "*??\0" "abcd\0" + "0" "??*\0" "a\0" + "1" "??*\0" "ab\0" + "1" "??*\0" "abc\0" + "1" "??*\0" "abcd\0" + "0" "?*?\0" "a\0" + "1" "?*?\0" "ab\0" + "1" "?*?\0" "abc\0" + "1" "?*?\0" "abcd\0" + "1" "*b\0" "b\0" + "1" "*b\0" "ab\0" + "0" "*b\0" "ba\0" + "1" "*b\0" "bb\0" + "1" "*b\0" "abb\0" + "1" "*b\0" "bab\0" + "1" "*bc\0" "abbc\0" + "1" "*bc\0" "bc\0" + "1" "*bc\0" "bbc\0" + "1" "*bc\0" "bcbc\0" + /* Multiple asterisks (complex backtracking) */ + "1" "*ac*\0" "abacadaeafag\0" + "1" "*ac*ae*ag*\0" "abacadaeafag\0" + "1" "*a*b*[bc]*[ef]*g*\0" "abacadaeafag\0" + "0" "*a*b*[ef]*[cd]*g*\0" "abacadaeafag\0" + "1" "*abcd*\0" "abcabcabcabcdefg\0" + "1" "*ab*cd*\0" "abcabcabcabcdefg\0" + "1" "*abcd*abcdef*\0" "abcabcdabcdeabcdefg\0" + "0" "*abcd*\0" "abcabcabcabcefg\0" + "0" "*ab*cd*\0" "abcabcabcabcefg\0"; + +bool skip = false; + +SEC("syscall") +int arena_strsearch(void *ctx) +{ + unsigned successes = 0; + unsigned n = 0; + char const __arena *p = glob_tests; + + /* + * Tests are jammed together in a string. The first byte is '1' + * or '0' to indicate the expected outcome, or '\0' to indicate the + * end of the tests. Then come two null-terminated strings: the + * pattern and the string to match it against. + */ + while (*p) { + bool expected = *p++ & 1; + char const __arena *pat = p; + + cond_break; + p += bpf_arena_strlen(p) + 1; + successes += test(pat, p, expected); + p += bpf_arena_strlen(p) + 1; + n++; + } + + n -= successes; + /* bpf_printk("glob: %u self-tests passed, %u failed\n", successes, n); */ + + return n ? -1 : 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c index 4e51785e7606..9af19dfe4e80 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c @@ -22,10 +22,6 @@ #define TCP_PACING_CA_RATIO (120) #define TCP_REORDERING (12) -#define min(a, b) ((a) < (b) ? (a) : (b)) -#define max(a, b) ((a) > (b) ? (a) : (b)) -#define after(seq2, seq1) before(seq1, seq2) - extern void cubictcp_init(struct sock *sk) __ksym; extern void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym; extern __u32 cubictcp_recalc_ssthresh(struct sock *sk) __ksym; @@ -34,11 +30,6 @@ extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym; extern void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) __ksym; extern void cubictcp_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym; -static bool before(__u32 seq1, __u32 seq2) -{ - return (__s32)(seq1-seq2) < 0; -} - static __u64 div64_u64(__u64 dividend, __u64 divisor) { return dividend / divisor; diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index f089faa97ae6..46fb2b37d3a7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -20,13 +20,6 @@ char _license[] SEC("license") = "GPL"; #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) -#define min(a, b) ((a) < (b) ? (a) : (b)) -#define max(a, b) ((a) > (b) ? (a) : (b)) -static bool before(__u32 seq1, __u32 seq2) -{ - return (__s32)(seq1-seq2) < 0; -} -#define after(seq2, seq1) before(seq1, seq2) extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym; extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym; diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c index 32c511bcd60b..1cc83140849f 100644 --- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c +++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c @@ -13,16 +13,10 @@ #ifndef EBUSY #define EBUSY 16 #endif -#define min(a, b) ((a) < (b) ? (a) : (b)) -#define max(a, b) ((a) > (b) ? (a) : (b)) #define min_not_zero(x, y) ({ \ typeof(x) __x = (x); \ typeof(y) __y = (y); \ __x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); }) -static bool before(__u32 seq1, __u32 seq2) -{ - return (__s32)(seq1-seq2) < 0; -} char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_gotox.c b/tools/testing/selftests/bpf/progs/bpf_gotox.c new file mode 100644 index 000000000000..216c71b94c64 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_gotox.c @@ -0,0 +1,448 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +__u64 in_user; +__u64 ret_user; + +int pid; + +/* + * Skip all the tests if compiler doesn't support indirect jumps. + * + * If tests are skipped, then all functions below are compiled as + * dummy, such that the skeleton looks the same, and the userspace + * program can avoid any checks rather than if data->skip is set. + */ +#ifdef __BPF_FEATURE_GOTOX +__u64 skip SEC(".data") = 0; +#else +__u64 skip = 1; +#endif + +struct simple_ctx { + __u64 x; +}; + +#ifdef __BPF_FEATURE_GOTOX +__u64 some_var; + +/* + * This function adds code which will be replaced by a different + * number of instructions by the verifier. This adds additional + * stress on testing the insn_array maps corresponding to indirect jumps. + */ +static __always_inline void adjust_insns(__u64 x) +{ + some_var ^= x + bpf_jiffies64(); +} + +SEC("syscall") +int one_switch(struct simple_ctx *ctx) +{ + switch (ctx->x) { + case 0: + adjust_insns(ctx->x + 1); + ret_user = 2; + break; + case 1: + adjust_insns(ctx->x + 7); + ret_user = 3; + break; + case 2: + adjust_insns(ctx->x + 9); + ret_user = 4; + break; + case 3: + adjust_insns(ctx->x + 11); + ret_user = 5; + break; + case 4: + adjust_insns(ctx->x + 17); + ret_user = 7; + break; + default: + adjust_insns(ctx->x + 177); + ret_user = 19; + break; + } + + return 0; +} + +SEC("syscall") +int one_switch_non_zero_sec_off(struct simple_ctx *ctx) +{ + switch (ctx->x) { + case 0: + adjust_insns(ctx->x + 1); + ret_user = 2; + break; + case 1: + adjust_insns(ctx->x + 7); + ret_user = 3; + break; + case 2: + adjust_insns(ctx->x + 9); + ret_user = 4; + break; + case 3: + adjust_insns(ctx->x + 11); + ret_user = 5; + break; + case 4: + adjust_insns(ctx->x + 17); + ret_user = 7; + break; + default: + adjust_insns(ctx->x + 177); + ret_user = 19; + break; + } + + return 0; +} + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int simple_test_other_sec(struct pt_regs *ctx) +{ + __u64 x = in_user; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + switch (x) { + case 0: + adjust_insns(x + 1); + ret_user = 2; + break; + case 1: + adjust_insns(x + 7); + ret_user = 3; + break; + case 2: + adjust_insns(x + 9); + ret_user = 4; + break; + case 3: + adjust_insns(x + 11); + ret_user = 5; + break; + case 4: + adjust_insns(x + 17); + ret_user = 7; + break; + default: + adjust_insns(x + 177); + ret_user = 19; + break; + } + + return 0; +} + +SEC("syscall") +int two_switches(struct simple_ctx *ctx) +{ + switch (ctx->x) { + case 0: + adjust_insns(ctx->x + 1); + ret_user = 2; + break; + case 1: + adjust_insns(ctx->x + 7); + ret_user = 3; + break; + case 2: + adjust_insns(ctx->x + 9); + ret_user = 4; + break; + case 3: + adjust_insns(ctx->x + 11); + ret_user = 5; + break; + case 4: + adjust_insns(ctx->x + 17); + ret_user = 7; + break; + default: + adjust_insns(ctx->x + 177); + ret_user = 19; + break; + } + + switch (ctx->x + !!ret_user) { + case 1: + adjust_insns(ctx->x + 7); + ret_user = 103; + break; + case 2: + adjust_insns(ctx->x + 9); + ret_user = 104; + break; + case 3: + adjust_insns(ctx->x + 11); + ret_user = 107; + break; + case 4: + adjust_insns(ctx->x + 11); + ret_user = 205; + break; + case 5: + adjust_insns(ctx->x + 11); + ret_user = 115; + break; + default: + adjust_insns(ctx->x + 177); + ret_user = 1019; + break; + } + + return 0; +} + +SEC("syscall") +int big_jump_table(struct simple_ctx *ctx __attribute__((unused))) +{ + const void *const jt[256] = { + [0 ... 255] = &&default_label, + [0] = &&l0, + [11] = &&l11, + [27] = &&l27, + [31] = &&l31, + }; + + goto *jt[ctx->x & 0xff]; + +l0: + adjust_insns(ctx->x + 1); + ret_user = 2; + return 0; + +l11: + adjust_insns(ctx->x + 7); + ret_user = 3; + return 0; + +l27: + adjust_insns(ctx->x + 9); + ret_user = 4; + return 0; + +l31: + adjust_insns(ctx->x + 11); + ret_user = 5; + return 0; + +default_label: + adjust_insns(ctx->x + 177); + ret_user = 19; + return 0; +} + +SEC("syscall") +int one_jump_two_maps(struct simple_ctx *ctx __attribute__((unused))) +{ + __label__ l1, l2, l3, l4; + void *jt1[2] = { &&l1, &&l2 }; + void *jt2[2] = { &&l3, &&l4 }; + unsigned int a = ctx->x % 2; + unsigned int b = (ctx->x / 2) % 2; + volatile int ret = 0; + + if (!(a < 2 && b < 2)) + return 19; + + if (ctx->x % 2) + goto *jt1[a]; + else + goto *jt2[b]; + + l1: ret += 1; + l2: ret += 3; + l3: ret += 5; + l4: ret += 7; + + ret_user = ret; + return ret; +} + +SEC("syscall") +int one_map_two_jumps(struct simple_ctx *ctx __attribute__((unused))) +{ + __label__ l1, l2, l3; + void *jt[3] = { &&l1, &&l2, &&l3 }; + unsigned int a = (ctx->x >> 2) & 1; + unsigned int b = (ctx->x >> 3) & 1; + volatile int ret = 0; + + if (ctx->x % 2) + goto *jt[a]; + + if (ctx->x % 3) + goto *jt[a + b]; + + l1: ret += 3; + l2: ret += 5; + l3: ret += 7; + + ret_user = ret; + return ret; +} + +/* Just to introduce some non-zero offsets in .text */ +static __noinline int f0(volatile struct simple_ctx *ctx __arg_ctx) +{ + if (ctx) + return 1; + else + return 13; +} + +SEC("syscall") int f1(struct simple_ctx *ctx) +{ + ret_user = 0; + return f0(ctx); +} + +static __noinline int __static_global(__u64 x) +{ + switch (x) { + case 0: + adjust_insns(x + 1); + ret_user = 2; + break; + case 1: + adjust_insns(x + 7); + ret_user = 3; + break; + case 2: + adjust_insns(x + 9); + ret_user = 4; + break; + case 3: + adjust_insns(x + 11); + ret_user = 5; + break; + case 4: + adjust_insns(x + 17); + ret_user = 7; + break; + default: + adjust_insns(x + 177); + ret_user = 19; + break; + } + + return 0; +} + +SEC("syscall") +int use_static_global1(struct simple_ctx *ctx) +{ + ret_user = 0; + return __static_global(ctx->x); +} + +SEC("syscall") +int use_static_global2(struct simple_ctx *ctx) +{ + ret_user = 0; + adjust_insns(ctx->x + 1); + return __static_global(ctx->x); +} + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int use_static_global_other_sec(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + return __static_global(in_user); +} + +__noinline int __nonstatic_global(__u64 x) +{ + switch (x) { + case 0: + adjust_insns(x + 1); + ret_user = 2; + break; + case 1: + adjust_insns(x + 7); + ret_user = 3; + break; + case 2: + adjust_insns(x + 9); + ret_user = 4; + break; + case 3: + adjust_insns(x + 11); + ret_user = 5; + break; + case 4: + adjust_insns(x + 17); + ret_user = 7; + break; + default: + adjust_insns(x + 177); + ret_user = 19; + break; + } + + return 0; +} + +SEC("syscall") +int use_nonstatic_global1(struct simple_ctx *ctx) +{ + ret_user = 0; + return __nonstatic_global(ctx->x); +} + +SEC("syscall") +int use_nonstatic_global2(struct simple_ctx *ctx) +{ + ret_user = 0; + adjust_insns(ctx->x + 1); + return __nonstatic_global(ctx->x); +} + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int use_nonstatic_global_other_sec(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + return __nonstatic_global(in_user); +} + +#else /* __BPF_FEATURE_GOTOX */ + +#define SKIP_TEST(TEST_NAME) \ + SEC("syscall") int TEST_NAME(void *ctx) \ + { \ + return 0; \ + } + +SKIP_TEST(one_switch); +SKIP_TEST(one_switch_non_zero_sec_off); +SKIP_TEST(simple_test_other_sec); +SKIP_TEST(two_switches); +SKIP_TEST(big_jump_table); +SKIP_TEST(one_jump_two_maps); +SKIP_TEST(one_map_two_jumps); +SKIP_TEST(use_static_global1); +SKIP_TEST(use_static_global2); +SKIP_TEST(use_static_global_other_sec); +SKIP_TEST(use_nonstatic_global1); +SKIP_TEST(use_nonstatic_global2); +SKIP_TEST(use_nonstatic_global_other_sec); + +#endif /* __BPF_FEATURE_GOTOX */ + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c index 774d4dbe8189..a8aa5a71d846 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c @@ -18,23 +18,10 @@ unsigned short reuse_listen_hport = 0; unsigned short listen_hport = 0; -char cubic_cc[TCP_CA_NAME_MAX] = "bpf_cubic"; +const char cubic_cc[] = "bpf_cubic"; char dctcp_cc[TCP_CA_NAME_MAX] = "bpf_dctcp"; bool random_retry = false; -static bool tcp_cc_eq(const char *a, const char *b) -{ - int i; - - for (i = 0; i < TCP_CA_NAME_MAX; i++) { - if (a[i] != b[i]) - return false; - if (!a[i]) - break; - } - - return true; -} SEC("iter/tcp") int change_tcp_cc(struct bpf_iter__tcp *ctx) @@ -58,7 +45,7 @@ int change_tcp_cc(struct bpf_iter__tcp *ctx) cur_cc, sizeof(cur_cc))) return 0; - if (!tcp_cc_eq(cur_cc, cubic_cc)) + if (bpf_strncmp(cur_cc, TCP_CA_NAME_MAX, cubic_cc)) return 0; if (random_retry && bpf_get_prandom_u32() % 4 == 1) diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c index 164640db3a29..b1e509b231cd 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -99,13 +99,13 @@ static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp, icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk->icsk_retransmit_timer.expires; + timer_expires = sp->tcp_retransmit_timer.expires; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk->icsk_retransmit_timer.expires; - } else if (timer_pending(&sp->sk_timer)) { + timer_expires = sp->tcp_retransmit_timer.expires; + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; - timer_expires = sp->sk_timer.expires; + timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = bpf_jiffies64(); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c index 591c703f5032..dbc7166aee91 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -99,13 +99,13 @@ static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp, icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk->icsk_retransmit_timer.expires; + timer_expires = sp->tcp_retransmit_timer.expires; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk->icsk_retransmit_timer.expires; - } else if (timer_pending(&sp->sk_timer)) { + timer_expires = sp->tcp_retransmit_timer.expires; + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; - timer_expires = sp->sk_timer.expires; + timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = bpf_jiffies64(); diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index a7a1a684eed1..c9bfbe1bafc1 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -126,6 +126,9 @@ * Several __arch_* annotations could be specified at once. * When test case is not run on current arch it is marked as skipped. * __caps_unpriv Specify the capabilities that should be set when running the test. + * + * __linear_size Specify the size of the linear area of non-linear skbs, or + * 0 for linear skbs. */ #define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg))) #define __not_msg(msg) __attribute__((btf_decl_tag("comment:test_expect_not_msg=" XSTR(__COUNTER__) "=" msg))) @@ -159,6 +162,7 @@ #define __stderr_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_stderr_unpriv=" XSTR(__COUNTER__) "=" msg))) #define __stdout(msg) __attribute__((btf_decl_tag("comment:test_expect_stdout=" XSTR(__COUNTER__) "=" msg))) #define __stdout_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_stdout_unpriv=" XSTR(__COUNTER__) "=" msg))) +#define __linear_size(sz) __attribute__((btf_decl_tag("comment:test_linear_size=" XSTR(sz)))) /* Define common capabilities tested using __caps_unpriv */ #define CAP_NET_ADMIN 12 diff --git a/tools/testing/selftests/bpf/progs/bpf_smc.c b/tools/testing/selftests/bpf/progs/bpf_smc.c new file mode 100644 index 000000000000..70d8b08f5914 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_smc.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +enum { + BPF_SMC_LISTEN = 10, +}; + +struct smc_sock___local { + struct sock sk; + struct smc_sock *listen_smc; + bool use_fallback; +} __attribute__((preserve_access_index)); + +int smc_cnt = 0; +int fallback_cnt = 0; + +SEC("fentry/smc_release") +int BPF_PROG(bpf_smc_release, struct socket *sock) +{ + /* only count from one side (client) */ + if (sock->sk->__sk_common.skc_state == BPF_SMC_LISTEN) + return 0; + smc_cnt++; + return 0; +} + +SEC("fentry/smc_switch_to_fallback") +int BPF_PROG(bpf_smc_switch_to_fallback, struct smc_sock___local *smc) +{ + /* only count from one side (client) */ + if (smc && !smc->listen_smc) + fallback_cnt++; + return 0; +} + +/* go with default value if no strat was found */ +bool default_ip_strat_value = true; + +struct smc_policy_ip_key { + __u32 sip; + __u32 dip; +}; + +struct smc_policy_ip_value { + __u8 mode; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(struct smc_policy_ip_key)); + __uint(value_size, sizeof(struct smc_policy_ip_value)); + __uint(max_entries, 128); + __uint(map_flags, BPF_F_NO_PREALLOC); +} smc_policy_ip SEC(".maps"); + +static bool smc_check(__u32 src, __u32 dst) +{ + struct smc_policy_ip_value *value; + struct smc_policy_ip_key key = { + .sip = src, + .dip = dst, + }; + + value = bpf_map_lookup_elem(&smc_policy_ip, &key); + return value ? value->mode : default_ip_strat_value; +} + +SEC("fmod_ret/update_socket_protocol") +int BPF_PROG(smc_run, int family, int type, int protocol) +{ + struct task_struct *task; + + if (family != AF_INET && family != AF_INET6) + return protocol; + + if ((type & 0xf) != SOCK_STREAM) + return protocol; + + if (protocol != 0 && protocol != IPPROTO_TCP) + return protocol; + + task = bpf_get_current_task_btf(); + /* Prevent from affecting other tests */ + if (!task || !task->nsproxy->net_ns->smc.hs_ctrl) + return protocol; + + return IPPROTO_SMC; +} + +SEC("struct_ops") +int BPF_PROG(bpf_smc_set_tcp_option_cond, const struct tcp_sock *tp, + struct inet_request_sock *ireq) +{ + return smc_check(ireq->req.__req_common.skc_daddr, + ireq->req.__req_common.skc_rcv_saddr); +} + +SEC("struct_ops") +int BPF_PROG(bpf_smc_set_tcp_option, struct tcp_sock *tp) +{ + return smc_check(tp->inet_conn.icsk_inet.sk.__sk_common.skc_rcv_saddr, + tp->inet_conn.icsk_inet.sk.__sk_common.skc_daddr); +} + +SEC(".struct_ops") +struct smc_hs_ctrl linkcheck = { + .name = "linkcheck", + .syn_option = (void *)bpf_smc_set_tcp_option, + .synack_option = (void *)bpf_smc_set_tcp_option_cond, +}; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 17db400f0e0d..d8dacef37c16 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -146,6 +146,20 @@ #define tcp_jiffies32 ((__u32)bpf_jiffies64()) +#ifndef min +#define min(a, b) ((a) < (b) ? (a) : (b)) +#endif +#ifndef max +#define max(a, b) ((a) > (b) ? (a) : (b)) +#endif + +static inline bool before(__u32 seq1, __u32 seq2) +{ + return (__s32)(seq1 - seq2) < 0; +} + +#define after(seq2, seq1) before(seq1, seq2) + static inline struct inet_connection_sock *inet_csk(const struct sock *sk) { return (struct inet_connection_sock *)sk; diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 9e9ebf27b878..9d158cfad981 100644 --- a/tools/testing/selftests/bpf/progs/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c @@ -34,6 +34,9 @@ #define SOL_TCP 6 #endif +const char reno[] = "reno"; +const char cubic[] = "cubic"; + __attribute__ ((noinline)) __weak int do_bind(struct bpf_sock_addr *ctx) { @@ -50,35 +53,27 @@ int do_bind(struct bpf_sock_addr *ctx) } static __inline int verify_cc(struct bpf_sock_addr *ctx, - char expected[TCP_CA_NAME_MAX]) + const char expected[]) { char buf[TCP_CA_NAME_MAX]; - int i; if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf))) return 1; - for (i = 0; i < TCP_CA_NAME_MAX; i++) { - if (buf[i] != expected[i]) - return 1; - if (buf[i] == 0) - break; - } + if (bpf_strncmp(buf, TCP_CA_NAME_MAX, expected)) + return 1; return 0; } static __inline int set_cc(struct bpf_sock_addr *ctx) { - char reno[TCP_CA_NAME_MAX] = "reno"; - char cubic[TCP_CA_NAME_MAX] = "cubic"; - - if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno))) + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, (void *)reno, sizeof(reno))) return 1; if (verify_cc(ctx, reno)) return 1; - if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic))) + if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, (void *)cubic, sizeof(cubic))) return 1; if (verify_cc(ctx, cubic)) return 1; diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c index 127dea342e5a..e0d672d93adf 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_success.c +++ b/tools/testing/selftests/bpf/progs/dynptr_success.c @@ -914,8 +914,8 @@ void *user_ptr; char expected_str[384]; __u32 test_len[7] = {0/* placeholder */, 0, 1, 2, 255, 256, 257}; -typedef int (*bpf_read_dynptr_fn_t)(struct bpf_dynptr *dptr, u32 off, - u32 size, const void *unsafe_ptr); +typedef int (*bpf_read_dynptr_fn_t)(struct bpf_dynptr *dptr, u64 off, + u64 size, const void *unsafe_ptr); /* Returns the offset just before the end of the maximum sized xdp fragment. * Any write larger than 32 bytes will be split between 2 fragments. @@ -1106,16 +1106,16 @@ int test_copy_from_user_str_dynptr(void *ctx) return 0; } -static int bpf_copy_data_from_user_task(struct bpf_dynptr *dptr, u32 off, - u32 size, const void *unsafe_ptr) +static int bpf_copy_data_from_user_task(struct bpf_dynptr *dptr, u64 off, + u64 size, const void *unsafe_ptr) { struct task_struct *task = bpf_get_current_task_btf(); return bpf_copy_from_user_task_dynptr(dptr, off, size, unsafe_ptr, task); } -static int bpf_copy_data_from_user_task_str(struct bpf_dynptr *dptr, u32 off, - u32 size, const void *unsafe_ptr) +static int bpf_copy_data_from_user_task_str(struct bpf_dynptr *dptr, u64 off, + u64 size, const void *unsafe_ptr) { struct task_struct *task = bpf_get_current_task_btf(); diff --git a/tools/testing/selftests/bpf/progs/file_reader.c b/tools/testing/selftests/bpf/progs/file_reader.c new file mode 100644 index 000000000000..4d756b623557 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/file_reader.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <string.h> +#include <stdbool.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "errno.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct elem); +} arrmap SEC(".maps"); + +struct elem { + struct file *file; + struct bpf_task_work tw; +}; + +char user_buf[256000]; +char tmp_buf[256000]; + +int pid = 0; +int err, run_success = 0; + +static int validate_file_read(struct file *file); +static int task_work_callback(struct bpf_map *map, void *key, void *value); + +SEC("lsm/file_open") +int on_open_expect_fault(void *c) +{ + struct bpf_dynptr dynptr; + struct file *file; + int local_err = 1; + __u32 user_buf_sz = sizeof(user_buf); + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + file = bpf_get_task_exe_file(bpf_get_current_task_btf()); + if (!file) + return 0; + + if (bpf_dynptr_from_file(file, 0, &dynptr)) + goto out; + + local_err = bpf_dynptr_read(tmp_buf, user_buf_sz, &dynptr, user_buf_sz, 0); + if (local_err == -EFAULT) { /* Expect page fault */ + local_err = 0; + run_success = 1; + } +out: + bpf_dynptr_file_discard(&dynptr); + if (local_err) + err = local_err; + bpf_put_file(file); + return 0; +} + +SEC("lsm/file_open") +int on_open_validate_file_read(void *c) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct elem *work; + int key = 0; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + work = bpf_map_lookup_elem(&arrmap, &key); + if (!work) { + err = 1; + return 0; + } + bpf_task_work_schedule_signal_impl(task, &work->tw, &arrmap, task_work_callback, NULL); + return 0; +} + +/* Called in a sleepable context, read 256K bytes, cross check with user space read data */ +static int task_work_callback(struct bpf_map *map, void *key, void *value) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct file *file = bpf_get_task_exe_file(task); + + if (!file) + return 0; + + err = validate_file_read(file); + if (!err) + run_success = 1; + bpf_put_file(file); + return 0; +} + +static int verify_dynptr_read(struct bpf_dynptr *ptr, u32 off, char *user_buf, u32 len) +{ + int i; + + if (bpf_dynptr_read(tmp_buf, len, ptr, off, 0)) + return 1; + + /* Verify file contents read from BPF is the same as the one read from userspace */ + bpf_for(i, 0, len) + { + if (tmp_buf[i] != user_buf[i]) + return 1; + } + return 0; +} + +static int validate_file_read(struct file *file) +{ + struct bpf_dynptr dynptr; + int loc_err = 1, off; + __u32 user_buf_sz = sizeof(user_buf); + + if (bpf_dynptr_from_file(file, 0, &dynptr)) + goto cleanup; + + loc_err = verify_dynptr_read(&dynptr, 0, user_buf, user_buf_sz); + off = 1; + loc_err = loc_err ?: verify_dynptr_read(&dynptr, off, user_buf + off, user_buf_sz - off); + off = user_buf_sz - 1; + loc_err = loc_err ?: verify_dynptr_read(&dynptr, off, user_buf + off, user_buf_sz - off); + /* Read file with random offset and length */ + off = 4097; + loc_err = loc_err ?: verify_dynptr_read(&dynptr, off, user_buf + off, 100); + + /* Adjust dynptr, verify read */ + loc_err = loc_err ?: bpf_dynptr_adjust(&dynptr, off, off + 1); + loc_err = loc_err ?: verify_dynptr_read(&dynptr, 0, user_buf + off, 1); + /* Can't read more than 1 byte */ + loc_err = loc_err ?: verify_dynptr_read(&dynptr, 0, user_buf + off, 2) == 0; + /* Can't read with far offset */ + loc_err = loc_err ?: verify_dynptr_read(&dynptr, 1, user_buf + off, 1) == 0; + +cleanup: + bpf_dynptr_file_discard(&dynptr); + return loc_err; +} diff --git a/tools/testing/selftests/bpf/progs/file_reader_fail.c b/tools/testing/selftests/bpf/progs/file_reader_fail.c new file mode 100644 index 000000000000..32fe28ed2439 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/file_reader_fail.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <string.h> +#include <stdbool.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +int err; +void *user_ptr; + +SEC("lsm/file_open") +__failure +__msg("Unreleased reference id=") +int on_nanosleep_unreleased_ref(void *ctx) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct file *file = bpf_get_task_exe_file(task); + struct bpf_dynptr dynptr; + + if (!file) + return 0; + + err = bpf_dynptr_from_file(file, 0, &dynptr); + return err ? 1 : 0; +} + +SEC("xdp") +__failure +__msg("Expected a dynptr of type file as arg #0") +int xdp_wrong_dynptr_type(struct xdp_md *xdp) +{ + struct bpf_dynptr dynptr; + + bpf_dynptr_from_xdp(xdp, 0, &dynptr); + bpf_dynptr_file_discard(&dynptr); + return 0; +} + +SEC("xdp") +__failure +__msg("Expected an initialized dynptr as arg #0") +int xdp_no_dynptr_type(struct xdp_md *xdp) +{ + struct bpf_dynptr dynptr; + + bpf_dynptr_file_discard(&dynptr); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/htab_update.c b/tools/testing/selftests/bpf/progs/htab_update.c index 7481bb30b29b..195d3b2fba00 100644 --- a/tools/testing/selftests/bpf/progs/htab_update.c +++ b/tools/testing/selftests/bpf/progs/htab_update.c @@ -6,24 +6,31 @@ char _license[] SEC("license") = "GPL"; +/* Map value type: has BTF-managed field (bpf_timer) */ +struct val { + struct bpf_timer t; + __u64 payload; +}; + struct { __uint(type, BPF_MAP_TYPE_HASH); __uint(max_entries, 1); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(__u32)); + __type(key, __u32); + __type(value, struct val); } htab SEC(".maps"); int pid = 0; int update_err = 0; -SEC("?fentry/lookup_elem_raw") -int lookup_elem_raw(void *ctx) +SEC("?fentry/bpf_obj_free_fields") +int bpf_obj_free_fields(void *ctx) { - __u32 key = 0, value = 1; + __u32 key = 0; + struct val value = { .payload = 1 }; if ((bpf_get_current_pid_tgid() >> 32) != pid) return 0; - update_err = bpf_map_update_elem(&htab, &key, &value, 0); + update_err = bpf_map_update_elem(&htab, &key, &value, BPF_ANY); return 0; } diff --git a/tools/testing/selftests/bpf/progs/ip_check_defrag.c b/tools/testing/selftests/bpf/progs/ip_check_defrag.c index 645b2c9f7867..0e87ad1ebcfa 100644 --- a/tools/testing/selftests/bpf/progs/ip_check_defrag.c +++ b/tools/testing/selftests/bpf/progs/ip_check_defrag.c @@ -12,11 +12,6 @@ #define IP_OFFSET 0x1FFF #define NEXTHDR_FRAGMENT 44 -extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags, - struct bpf_dynptr *ptr__uninit) __ksym; -extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset, - void *buffer, uint32_t buffer__sz) __ksym; - volatile int shootdowns = 0; static bool is_frag_v4(struct iphdr *iph) diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index 0c13b7409947..7de173daf27b 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -89,14 +89,16 @@ SEC("lsm/file_mprotect") int BPF_PROG(test_int_hook, struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot, int ret) { - if (ret != 0) + struct mm_struct *mm = vma->vm_mm; + + if (ret != 0 || !mm) return ret; __s32 pid = bpf_get_current_pid_tgid() >> 32; int is_stack = 0; - is_stack = (vma->vm_start <= vma->vm_mm->start_stack && - vma->vm_end >= vma->vm_mm->start_stack); + is_stack = (vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack); if (is_stack && monitored_pid == pid) { mprotect_count++; diff --git a/tools/testing/selftests/bpf/progs/lsm_tailcall.c b/tools/testing/selftests/bpf/progs/lsm_tailcall.c index 49c075ce2d4c..6e7e58051e64 100644 --- a/tools/testing/selftests/bpf/progs/lsm_tailcall.c +++ b/tools/testing/selftests/bpf/progs/lsm_tailcall.c @@ -20,14 +20,14 @@ int lsm_file_permission_prog(void *ctx) return 0; } -SEC("lsm/file_alloc_security") -int lsm_file_alloc_security_prog(void *ctx) +SEC("lsm/kernfs_init_security") +int lsm_kernfs_init_security_prog(void *ctx) { return 0; } -SEC("lsm/file_alloc_security") -int lsm_file_alloc_security_entry(void *ctx) +SEC("lsm/kernfs_init_security") +int lsm_kernfs_init_security_entry(void *ctx) { bpf_tail_call_static(ctx, &jmp_table, 0); return 0; diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c index 3a868a199349..d70c28824bbe 100644 --- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c +++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c @@ -278,6 +278,46 @@ out: return 0; } +SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep") +int nested_rcu_region_unbalanced_1(void *ctx) +{ + struct task_struct *task, *real_parent; + + /* nested rcu read lock regions */ + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); +out: + bpf_rcu_read_unlock(); + bpf_rcu_read_unlock(); + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep") +int nested_rcu_region_unbalanced_2(void *ctx) +{ + struct task_struct *task, *real_parent; + + /* nested rcu read lock regions */ + task = bpf_get_current_task_btf(); + bpf_rcu_read_lock(); + bpf_rcu_read_lock(); + bpf_rcu_read_lock(); + real_parent = task->real_parent; + if (!real_parent) + goto out; + (void)bpf_task_storage_get(&map_a, real_parent, 0, 0); +out: + bpf_rcu_read_unlock(); + bpf_rcu_read_unlock(); + return 0; +} + SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") int task_trusted_non_rcuptr(void *ctx) { diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c index 893a4fdb4b6e..1aca85d86aeb 100644 --- a/tools/testing/selftests/bpf/progs/refcounted_kptr.c +++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c @@ -568,4 +568,64 @@ err_out: return 0; } +private(kptr_ref) u64 ref; + +static int probe_read_refcount(void) +{ + u32 refcount; + + bpf_probe_read_kernel(&refcount, sizeof(refcount), (void *) ref); + return refcount; +} + +static int __insert_in_list(struct bpf_list_head *head, struct bpf_spin_lock *lock, + struct node_data __kptr **node) +{ + struct node_data *node_new, *node_ref, *node_old; + + node_new = bpf_obj_new(typeof(*node_new)); + if (!node_new) + return -1; + + node_ref = bpf_refcount_acquire(node_new); + node_old = bpf_kptr_xchg(node, node_new); + if (node_old) { + bpf_obj_drop(node_old); + bpf_obj_drop(node_ref); + return -2; + } + + bpf_spin_lock(lock); + bpf_list_push_front(head, &node_ref->l); + ref = (u64)(void *) &node_ref->ref; + bpf_spin_unlock(lock); + return probe_read_refcount(); +} + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} percpu_hash SEC(".maps"); + +SEC("tc") +int percpu_hash_refcount_leak(void *ctx) +{ + struct map_value *v; + int key = 0; + + v = bpf_map_lookup_elem(&percpu_hash, &key); + if (!v) + return 0; + + return __insert_in_list(&head, &lock, &v->node); +} + +SEC("tc") +int check_percpu_hash_refcount(void *ctx) +{ + return probe_read_refcount(); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c index 6a468496f539..d96c7d1e8fc2 100644 --- a/tools/testing/selftests/bpf/progs/ringbuf_bench.c +++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2020 Facebook +#include <stdbool.h> #include <linux/bpf.h> #include <stdint.h> #include <bpf/bpf_helpers.h> @@ -14,9 +15,11 @@ struct { const volatile int batch_cnt = 0; const volatile long use_output = 0; +const volatile bool bench_producer = false; long sample_val = 42; long dropped __attribute__((aligned(128))) = 0; +long hits __attribute__((aligned(128))) = 0; const volatile long wakeup_data_size = 0; @@ -24,6 +27,9 @@ static __always_inline long get_flags() { long sz; + if (bench_producer) + return BPF_RB_NO_WAKEUP; + if (!wakeup_data_size) return 0; @@ -47,6 +53,8 @@ int bench_ringbuf(void *ctx) *sample = sample_val; flags = get_flags(); bpf_ringbuf_submit(sample, flags); + if (bench_producer) + __sync_add_and_fetch(&hits, 1); } } } else { @@ -55,6 +63,9 @@ int bench_ringbuf(void *ctx) if (bpf_ringbuf_output(&ringbuf, &sample_val, sizeof(sample_val), flags)) __sync_add_and_fetch(&dropped, 1); + else if (bench_producer) + __sync_add_and_fetch(&hits, 1); + } } return 0; diff --git a/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c b/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c new file mode 100644 index 000000000000..09a00d11ffcc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <errno.h> + +extern int tcp_memory_per_cpu_fw_alloc __ksym; +extern int udp_memory_per_cpu_fw_alloc __ksym; + +int nr_cpus; +bool tcp_activated, udp_activated; +long tcp_memory_allocated, udp_memory_allocated; + +struct sk_prot { + long *memory_allocated; + int *memory_per_cpu_fw_alloc; +}; + +static int drain_memory_per_cpu_fw_alloc(__u32 i, struct sk_prot *sk_prot_ctx) +{ + int *memory_per_cpu_fw_alloc; + + memory_per_cpu_fw_alloc = bpf_per_cpu_ptr(sk_prot_ctx->memory_per_cpu_fw_alloc, i); + if (memory_per_cpu_fw_alloc) + *sk_prot_ctx->memory_allocated += *memory_per_cpu_fw_alloc; + + return 0; +} + +static long get_memory_allocated(struct sock *_sk, int *memory_per_cpu_fw_alloc) +{ + struct sock *sk = bpf_core_cast(_sk, struct sock); + struct sk_prot sk_prot_ctx; + long memory_allocated; + + /* net_aligned_data.{tcp,udp}_memory_allocated was not available. */ + memory_allocated = sk->__sk_common.skc_prot->memory_allocated->counter; + + sk_prot_ctx.memory_allocated = &memory_allocated; + sk_prot_ctx.memory_per_cpu_fw_alloc = memory_per_cpu_fw_alloc; + + bpf_loop(nr_cpus, drain_memory_per_cpu_fw_alloc, &sk_prot_ctx, 0); + + return memory_allocated; +} + +static void fentry_init_sock(struct sock *sk, bool *activated, + long *memory_allocated, int *memory_per_cpu_fw_alloc) +{ + if (!*activated) + return; + + *memory_allocated = get_memory_allocated(sk, memory_per_cpu_fw_alloc); + *activated = false; +} + +SEC("fentry/tcp_init_sock") +int BPF_PROG(fentry_tcp_init_sock, struct sock *sk) +{ + fentry_init_sock(sk, &tcp_activated, + &tcp_memory_allocated, &tcp_memory_per_cpu_fw_alloc); + return 0; +} + +SEC("fentry/udp_init_sock") +int BPF_PROG(fentry_udp_init_sock, struct sock *sk) +{ + fentry_init_sock(sk, &udp_activated, + &udp_memory_allocated, &udp_memory_per_cpu_fw_alloc); + return 0; +} + +SEC("cgroup/sock_create") +int sock_create(struct bpf_sock *ctx) +{ + int err, val = 1; + + err = bpf_setsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM, + &val, sizeof(val)); + if (err) + goto err; + + val = 0; + + err = bpf_getsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM, + &val, sizeof(val)); + if (err) + goto err; + + if (val != 1) { + err = -EINVAL; + goto err; + } + + return 1; + +err: + bpf_set_retval(err); + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c index 99d72c68f76a..826e6b6aff7e 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c @@ -45,8 +45,12 @@ SEC("syscall") __retval(USER_PTR_ERR)int test_strcspn_null1(void *ctx) { return SEC("syscall") __retval(USER_PTR_ERR)int test_strcspn_null2(void *ctx) { return bpf_strcspn("hello", NULL); } SEC("syscall") __retval(USER_PTR_ERR)int test_strstr_null1(void *ctx) { return bpf_strstr(NULL, "hello"); } SEC("syscall") __retval(USER_PTR_ERR)int test_strstr_null2(void *ctx) { return bpf_strstr("hello", NULL); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strcasestr_null1(void *ctx) { return bpf_strcasestr(NULL, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strcasestr_null2(void *ctx) { return bpf_strcasestr("hello", NULL); } SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null1(void *ctx) { return bpf_strnstr(NULL, "hello", 1); } SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null2(void *ctx) { return bpf_strnstr("hello", NULL, 1); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strncasestr_null1(void *ctx) { return bpf_strncasestr(NULL, "hello", 1); } +SEC("syscall") __retval(USER_PTR_ERR)int test_strncasestr_null2(void *ctx) { return bpf_strncasestr("hello", NULL, 1); } /* Passing userspace ptr to string kfuncs */ SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr1(void *ctx) { return bpf_strcmp(user_ptr, "hello"); } @@ -65,8 +69,12 @@ SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr1(void *ctx) { re SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr2(void *ctx) { return bpf_strcspn("hello", user_ptr); } SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr1(void *ctx) { return bpf_strstr(user_ptr, "hello"); } SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr2(void *ctx) { return bpf_strstr("hello", user_ptr); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasestr_user_ptr1(void *ctx) { return bpf_strcasestr(user_ptr, "hello"); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strcasestr_user_ptr2(void *ctx) { return bpf_strcasestr("hello", user_ptr); } SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr1(void *ctx) { return bpf_strnstr(user_ptr, "hello", 1); } SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr2(void *ctx) { return bpf_strnstr("hello", user_ptr, 1); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strncasestr_user_ptr1(void *ctx) { return bpf_strncasestr(user_ptr, "hello", 1); } +SEC("syscall") __retval(USER_PTR_ERR) int test_strncasestr_user_ptr2(void *ctx) { return bpf_strncasestr("hello", user_ptr, 1); } #endif /* __TARGET_ARCH_s390 */ @@ -87,7 +95,11 @@ SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault1(void *ctx) { return SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault2(void *ctx) { return bpf_strcspn("hello", invalid_kern_ptr); } SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault1(void *ctx) { return bpf_strstr(invalid_kern_ptr, "hello"); } SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault2(void *ctx) { return bpf_strstr("hello", invalid_kern_ptr); } +SEC("syscall") __retval(-EFAULT) int test_strcasestr_pagefault1(void *ctx) { return bpf_strcasestr(invalid_kern_ptr, "hello"); } +SEC("syscall") __retval(-EFAULT) int test_strcasestr_pagefault2(void *ctx) { return bpf_strcasestr("hello", invalid_kern_ptr); } SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault1(void *ctx) { return bpf_strnstr(invalid_kern_ptr, "hello", 1); } SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault2(void *ctx) { return bpf_strnstr("hello", invalid_kern_ptr, 1); } +SEC("syscall") __retval(-EFAULT) int test_strncasestr_pagefault1(void *ctx) { return bpf_strncasestr(invalid_kern_ptr, "hello", 1); } +SEC("syscall") __retval(-EFAULT) int test_strncasestr_pagefault2(void *ctx) { return bpf_strncasestr("hello", invalid_kern_ptr, 1); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c index e41cc5601994..05e1da1f250f 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c @@ -19,6 +19,8 @@ SEC("syscall") int test_strspn_accept_too_long(void *ctx) { return bpf_strspn("b SEC("syscall") int test_strcspn_str_too_long(void *ctx) { return bpf_strcspn(long_str, "b"); } SEC("syscall") int test_strcspn_reject_too_long(void *ctx) { return bpf_strcspn("b", long_str); } SEC("syscall") int test_strstr_too_long(void *ctx) { return bpf_strstr(long_str, "hello"); } +SEC("syscall") int test_strcasestr_too_long(void *ctx) { return bpf_strcasestr(long_str, "hello"); } SEC("syscall") int test_strnstr_too_long(void *ctx) { return bpf_strnstr(long_str, "hello", sizeof(long_str)); } +SEC("syscall") int test_strncasestr_too_long(void *ctx) { return bpf_strncasestr(long_str, "hello", sizeof(long_str)); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 2e3498e37b9c..a8513964516b 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -33,8 +33,11 @@ __test(11) int test_strnlen(void *ctx) { return bpf_strnlen(str, 12); } __test(5) int test_strspn(void *ctx) { return bpf_strspn(str, "ehlo"); } __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } +__test(6) int test_strcasestr_found(void *ctx) { return bpf_strcasestr(str, "woRLD"); } __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } +__test(-ENOENT) int test_strcasestr_notfound(void *ctx) { return bpf_strcasestr(str, "hi"); } __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } +__test(0) int test_strcasestr_empty(void *ctx) { return bpf_strcasestr(str, ""); } __test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } __test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } __test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } @@ -42,5 +45,12 @@ __test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, __test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); } __test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); } __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } +__test(0) int test_strncasestr_found1(void *ctx) { return bpf_strncasestr("", "", 0); } +__test(0) int test_strncasestr_found2(void *ctx) { return bpf_strncasestr(str, "heLLO", 5); } +__test(0) int test_strncasestr_found3(void *ctx) { return bpf_strncasestr(str, "heLLO", 6); } +__test(-ENOENT) int test_strncasestr_notfound1(void *ctx) { return bpf_strncasestr(str, "hi", 10); } +__test(-ENOENT) int test_strncasestr_notfound2(void *ctx) { return bpf_strncasestr(str, "hello", 4); } +__test(-ENOENT) int test_strncasestr_notfound3(void *ctx) { return bpf_strncasestr("", "a", 0); } +__test(0) int test_strncasestr_empty(void *ctx) { return bpf_strncasestr(str, "", 1); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index a5c74d31a244..6e1918deaf26 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -330,9 +330,9 @@ static void *calc_location(struct strobe_value_loc *loc, void *tls_base) } bpf_probe_read_user(&tls_ptr, sizeof(void *), dtv); /* if pointer has (void *)-1 value, then TLS wasn't initialized yet */ - return tls_ptr && tls_ptr != (void *)-1 - ? tls_ptr + tls_index.offset - : NULL; + if (!tls_ptr || tls_ptr == (void *)-1) + return NULL; + return tls_ptr + tls_index.offset; } #ifdef SUBPROGS diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c index a58b5194fc89..022291f21dfb 100644 --- a/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c +++ b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c @@ -8,8 +8,6 @@ char _license[] SEC("license") = "GPL"; #define USEC_PER_SEC 1000000UL -#define min(a, b) ((a) < (b) ? (a) : (b)) - static unsigned int tcp_left_out(const struct tcp_sock *tp) { return tp->sacked_out + tp->lost_out; diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index 2ec1de11a3ae..7b6b2b342c1d 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -7,6 +7,7 @@ #include <stddef.h> #include <stdint.h> +#include <errno.h> char _license[] SEC("license") = "GPL"; @@ -288,3 +289,14 @@ int tc_input_len_exceed(struct __sk_buff *ctx) global_bpf_mtu_xdp = mtu_len; return retval; } + +SEC("tc") +int tc_chk_segs_flag(struct __sk_buff *ctx) +{ + __u32 mtu_len = 0; + int err; + + err = bpf_check_mtu(ctx, GLOBAL_USER_IFINDEX, &mtu_len, 0, BPF_MTU_CHK_SEGS); + + return err == -EINVAL ? BPF_OK : BPF_DROP; +} diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c index a1ccc831c882..05ac9410cd68 100644 --- a/tools/testing/selftests/bpf/progs/test_perf_branches.c +++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c @@ -8,6 +8,7 @@ #include <bpf/bpf_tracing.h> int valid = 0; +int run_cnt = 0; int required_size_out = 0; int written_stack_out = 0; int written_global_out = 0; @@ -24,6 +25,8 @@ int perf_branches(void *ctx) __u64 entries[4 * 3] = {0}; int required_size, written_stack, written_global; + ++run_cnt; + /* write to stack */ written_stack = bpf_read_branch_records(ctx, entries, sizeof(entries), 0); /* ignore spurious events */ diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c b/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c new file mode 100644 index 000000000000..ff4aa67ddacc --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_RINGBUF); + __uint(map_flags, BPF_F_RB_OVERWRITE); +} ringbuf SEC(".maps"); + +int pid; + +const volatile unsigned long LEN1; +const volatile unsigned long LEN2; +const volatile unsigned long LEN3; +const volatile unsigned long LEN4; +const volatile unsigned long LEN5; + +long reserve1_fail = 0; +long reserve2_fail = 0; +long reserve3_fail = 0; +long reserve4_fail = 0; +long reserve5_fail = 0; + +unsigned long avail_data = 0; +unsigned long ring_size = 0; +unsigned long cons_pos = 0; +unsigned long prod_pos = 0; +unsigned long over_pos = 0; + +SEC("fentry/" SYS_PREFIX "sys_getpgid") +int test_overwrite_ringbuf(void *ctx) +{ + char *rec1, *rec2, *rec3, *rec4, *rec5; + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid != pid) + return 0; + + rec1 = bpf_ringbuf_reserve(&ringbuf, LEN1, 0); + if (!rec1) { + reserve1_fail = 1; + return 0; + } + + rec2 = bpf_ringbuf_reserve(&ringbuf, LEN2, 0); + if (!rec2) { + bpf_ringbuf_discard(rec1, 0); + reserve2_fail = 1; + return 0; + } + + rec3 = bpf_ringbuf_reserve(&ringbuf, LEN3, 0); + /* expect failure */ + if (!rec3) { + reserve3_fail = 1; + } else { + bpf_ringbuf_discard(rec1, 0); + bpf_ringbuf_discard(rec2, 0); + bpf_ringbuf_discard(rec3, 0); + return 0; + } + + rec4 = bpf_ringbuf_reserve(&ringbuf, LEN4, 0); + if (!rec4) { + reserve4_fail = 1; + bpf_ringbuf_discard(rec1, 0); + bpf_ringbuf_discard(rec2, 0); + return 0; + } + + bpf_ringbuf_submit(rec1, 0); + bpf_ringbuf_submit(rec2, 0); + bpf_ringbuf_submit(rec4, 0); + + rec5 = bpf_ringbuf_reserve(&ringbuf, LEN5, 0); + if (!rec5) { + reserve5_fail = 1; + return 0; + } + + for (int i = 0; i < LEN3; i++) + rec5[i] = 0xdd; + + bpf_ringbuf_submit(rec5, 0); + + ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE); + avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA); + cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS); + prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS); + over_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_OVERWRITE_POS); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index 950a70b61e74..4f6f03122d61 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -14,7 +14,6 @@ #define TIME_HORIZON_NS (2000 * 1000 * 1000) #define NS_PER_SEC 1000000000 #define ECN_HORIZON_NS 5000000 -#define THROTTLE_RATE_BPS (5 * 1000 * 1000) /* flow_key => last_tstamp timestamp used */ struct { @@ -24,12 +23,13 @@ struct { __uint(max_entries, 1); } flow_map SEC(".maps"); +__uint64_t target_rate; + static inline int throttle_flow(struct __sk_buff *skb) { int key = 0; uint64_t *last_tstamp = bpf_map_lookup_elem(&flow_map, &key); - uint64_t delay_ns = ((uint64_t)skb->len) * NS_PER_SEC / - THROTTLE_RATE_BPS; + uint64_t delay_ns = ((uint64_t)skb->len) * NS_PER_SEC / target_rate; uint64_t now = bpf_ktime_get_ns(); uint64_t tstamp, next_tstamp = 0; @@ -70,7 +70,7 @@ static inline int handle_tcp(struct __sk_buff *skb, struct tcphdr *tcp) if ((void *)(tcp + 1) > data_end) return TC_ACT_SHOT; - if (tcp->dest == bpf_htons(9000)) + if (tcp->source == bpf_htons(9000)) return throttle_flow(skb); return TC_ACT_OK; @@ -99,7 +99,8 @@ static inline int handle_ipv4(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("cls_test") int tc_prog(struct __sk_buff *skb) +SEC("tc") +int tc_prog(struct __sk_buff *skb) { if (skb->protocol == bpf_htons(ETH_P_IP)) return handle_ipv4(skb); diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c index 404124a93892..7330c61b5730 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c @@ -2,23 +2,11 @@ /* In-place tunneling */ -#include <stdbool.h> -#include <string.h> - -#include <linux/stddef.h> -#include <linux/bpf.h> -#include <linux/if_ether.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <linux/mpls.h> -#include <linux/tcp.h> -#include <linux/udp.h> -#include <linux/pkt_cls.h> -#include <linux/types.h> +#include <vmlinux.h> -#include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include "bpf_tracing_net.h" #include "bpf_compiler.h" #pragma GCC diagnostic ignored "-Waddress-of-packed-member" @@ -27,6 +15,14 @@ static const int cfg_port = 8000; static const int cfg_udp_src = 20000; +#define ETH_P_MPLS_UC 0x8847 +#define ETH_P_TEB 0x6558 + +#define MPLS_LS_S_MASK 0x00000100 +#define BPF_F_ADJ_ROOM_ENCAP_L2(len) \ + (((__u64)len & BPF_ADJ_ROOM_ENCAP_L2_MASK) \ + << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) + #define L2_PAD_SZ (sizeof(struct vxlanhdr) + ETH_HLEN) #define UDP_PORT 5555 @@ -36,10 +32,9 @@ static const int cfg_udp_src = 20000; #define EXTPROTO_VXLAN 0x1 -#define VXLAN_N_VID (1u << 24) -#define VXLAN_VNI_MASK bpf_htonl((VXLAN_N_VID - 1) << 8) -#define VXLAN_FLAGS 0x8 -#define VXLAN_VNI 1 +#define VXLAN_FLAGS bpf_htonl(1<<27) +#define VNI_ID 1 +#define VXLAN_VNI bpf_htonl(VNI_ID << 8) #ifndef NEXTHDR_DEST #define NEXTHDR_DEST 60 @@ -48,12 +43,6 @@ static const int cfg_udp_src = 20000; /* MPLS label 1000 with S bit (last label) set and ttl of 255. */ static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 | MPLS_LS_S_MASK | 0xff); - -struct vxlanhdr { - __be32 vx_flags; - __be32 vx_vni; -} __attribute__((packed)); - struct gre_hdr { __be16 flags; __be16 protocol; @@ -94,8 +83,8 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph) static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, __u16 l2_proto, __u16 ext_proto) { + struct iphdr iph_inner = {0}; __u16 udp_dst = UDP_PORT; - struct iphdr iph_inner; struct v4hdr h_outer; struct tcphdr tcph; int olen, l2_len; @@ -122,7 +111,6 @@ static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, return TC_ACT_OK; /* Derive the IPv4 header fields from the IPv6 header */ - memset(&iph_inner, 0, sizeof(iph_inner)); iph_inner.version = 4; iph_inner.ihl = 5; iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) + @@ -210,7 +198,7 @@ static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto, struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr; vxlan_hdr->vx_flags = VXLAN_FLAGS; - vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8); + vxlan_hdr->vx_vni = VXLAN_VNI; l2_hdr += sizeof(struct vxlanhdr); } @@ -340,7 +328,7 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr; vxlan_hdr->vx_flags = VXLAN_FLAGS; - vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8); + vxlan_hdr->vx_vni = VXLAN_VNI; l2_hdr += sizeof(struct vxlanhdr); } @@ -372,8 +360,8 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, static int encap_ipv6_ipip6(struct __sk_buff *skb) { + struct v6hdr h_outer = {0}; struct iphdr iph_inner; - struct v6hdr h_outer; struct tcphdr tcph; struct ethhdr eth; __u64 flags; @@ -400,13 +388,12 @@ static int encap_ipv6_ipip6(struct __sk_buff *skb) return TC_ACT_SHOT; /* prepare new outer network header */ - memset(&h_outer.ip, 0, sizeof(h_outer.ip)); h_outer.ip.version = 6; h_outer.ip.hop_limit = iph_inner.ttl; - h_outer.ip.saddr.s6_addr[1] = 0xfd; - h_outer.ip.saddr.s6_addr[15] = 1; - h_outer.ip.daddr.s6_addr[1] = 0xfd; - h_outer.ip.daddr.s6_addr[15] = 2; + h_outer.ip.saddr.in6_u.u6_addr8[1] = 0xfd; + h_outer.ip.saddr.in6_u.u6_addr8[15] = 1; + h_outer.ip.daddr.in6_u.u6_addr8[1] = 0xfd; + h_outer.ip.daddr.in6_u.u6_addr8[15] = 2; h_outer.ip.payload_len = iph_inner.tot_len; h_outer.ip.nexthdr = IPPROTO_IPIP; @@ -431,7 +418,7 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto, return __encap_ipv6(skb, encap_proto, l2_proto, 0); } -SEC("encap_ipip_none") +SEC("tc") int __encap_ipip_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -440,7 +427,7 @@ int __encap_ipip_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_gre_none") +SEC("tc") int __encap_gre_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -449,7 +436,7 @@ int __encap_gre_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_gre_mpls") +SEC("tc") int __encap_gre_mpls(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -458,7 +445,7 @@ int __encap_gre_mpls(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_gre_eth") +SEC("tc") int __encap_gre_eth(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -467,7 +454,7 @@ int __encap_gre_eth(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_udp_none") +SEC("tc") int __encap_udp_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -476,7 +463,7 @@ int __encap_udp_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_udp_mpls") +SEC("tc") int __encap_udp_mpls(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -485,7 +472,7 @@ int __encap_udp_mpls(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_udp_eth") +SEC("tc") int __encap_udp_eth(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -494,7 +481,7 @@ int __encap_udp_eth(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_vxlan_eth") +SEC("tc") int __encap_vxlan_eth(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -505,7 +492,7 @@ int __encap_vxlan_eth(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_sit_none") +SEC("tc") int __encap_sit_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -514,7 +501,7 @@ int __encap_sit_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6tnl_none") +SEC("tc") int __encap_ip6tnl_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -523,7 +510,7 @@ int __encap_ip6tnl_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ipip6_none") +SEC("tc") int __encap_ipip6_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IP)) @@ -532,7 +519,7 @@ int __encap_ipip6_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6gre_none") +SEC("tc") int __encap_ip6gre_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -541,7 +528,7 @@ int __encap_ip6gre_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6gre_mpls") +SEC("tc") int __encap_ip6gre_mpls(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -550,7 +537,7 @@ int __encap_ip6gre_mpls(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6gre_eth") +SEC("tc") int __encap_ip6gre_eth(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -559,7 +546,7 @@ int __encap_ip6gre_eth(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6udp_none") +SEC("tc") int __encap_ip6udp_none(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -568,7 +555,7 @@ int __encap_ip6udp_none(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6udp_mpls") +SEC("tc") int __encap_ip6udp_mpls(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -577,7 +564,7 @@ int __encap_ip6udp_mpls(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6udp_eth") +SEC("tc") int __encap_ip6udp_eth(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -586,7 +573,7 @@ int __encap_ip6udp_eth(struct __sk_buff *skb) return TC_ACT_OK; } -SEC("encap_ip6vxlan_eth") +SEC("tc") int __encap_ip6vxlan_eth(struct __sk_buff *skb) { if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6)) @@ -693,7 +680,7 @@ static int decap_ipv6(struct __sk_buff *skb) iph_outer.nexthdr); } -SEC("decap") +SEC("tc") int decap_f(struct __sk_buff *skb) { switch (skb->protocol) { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index d79cb74b571e..0a0f371a2dec 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -4,6 +4,7 @@ #include <linux/if_ether.h> #include <linux/pkt_cls.h> +#include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> #include "bpf_kfuncs.h" @@ -11,37 +12,72 @@ #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem -/* Demonstrates how metadata can be passed from an XDP program to a TC program - * using bpf_xdp_adjust_meta. - * For the sake of testing the metadata support in drivers, the XDP program uses - * a fixed-size payload after the Ethernet header as metadata. The TC program - * copies the metadata it receives into a map so it can be checked from - * userspace. +/* Demonstrate passing metadata from XDP to TC using bpf_xdp_adjust_meta. + * + * The XDP program extracts a fixed-size payload following the Ethernet header + * and stores it as packet metadata to test the driver's metadata support. The + * TC program then verifies if the passed metadata is correct. */ -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); - __type(key, __u32); - __uint(value_size, META_SIZE); -} test_result SEC(".maps"); - bool test_pass; +static const __u8 smac_want[ETH_ALEN] = { + 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF, +}; + +static const __u8 meta_want[META_SIZE] = { + 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, + 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, + 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, + 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, +}; + +static bool check_smac(const struct ethhdr *eth) +{ + return !__builtin_memcmp(eth->h_source, smac_want, ETH_ALEN); +} + +static bool check_metadata(const char *file, int line, __u8 *meta_have) +{ + if (!__builtin_memcmp(meta_have, meta_want, META_SIZE)) + return true; + + bpf_stream_printk(BPF_STREAM_STDERR, + "FAIL:%s:%d: metadata mismatch\n" + " have:\n %pI6\n %pI6\n" + " want:\n %pI6\n %pI6\n", + file, line, + &meta_have[0x00], &meta_have[0x10], + &meta_want[0x00], &meta_want[0x10]); + return false; +} + +#define check_metadata(meta_have) check_metadata(__FILE__, __LINE__, meta_have) + +static bool check_skb_metadata(const char *file, int line, struct __sk_buff *skb) +{ + __u8 *data_meta = ctx_ptr(skb, data_meta); + __u8 *data = ctx_ptr(skb, data); + + return data_meta + META_SIZE <= data && (check_metadata)(file, line, data_meta); +} + +#define check_skb_metadata(skb) check_skb_metadata(__FILE__, __LINE__, skb) + SEC("tc") int ing_cls(struct __sk_buff *ctx) { - __u8 *data, *data_meta; - __u32 key = 0; - - data_meta = ctx_ptr(ctx, data_meta); - data = ctx_ptr(ctx, data); + __u8 *meta_have = ctx_ptr(ctx, data_meta); + __u8 *data = ctx_ptr(ctx, data); - if (data_meta + META_SIZE > data) - return TC_ACT_SHOT; + if (meta_have + META_SIZE > data) + goto out; - bpf_map_update_elem(&test_result, &key, data_meta, BPF_ANY); + if (!check_metadata(meta_have)) + goto out; + test_pass = true; +out: return TC_ACT_SHOT; } @@ -49,17 +85,17 @@ int ing_cls(struct __sk_buff *ctx) SEC("tc") int ing_cls_dynptr_read(struct __sk_buff *ctx) { + __u8 meta_have[META_SIZE]; struct bpf_dynptr meta; - const __u32 zero = 0; - __u8 *dst; - - dst = bpf_map_lookup_elem(&test_result, &zero); - if (!dst) - return TC_ACT_SHOT; bpf_dynptr_from_skb_meta(ctx, 0, &meta); - bpf_dynptr_read(dst, META_SIZE, &meta, 0, 0); + bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (!check_metadata(meta_have)) + goto out; + + test_pass = true; +out: return TC_ACT_SHOT; } @@ -86,20 +122,18 @@ SEC("tc") int ing_cls_dynptr_slice(struct __sk_buff *ctx) { struct bpf_dynptr meta; - const __u32 zero = 0; - __u8 *dst, *src; - - dst = bpf_map_lookup_elem(&test_result, &zero); - if (!dst) - return TC_ACT_SHOT; + __u8 *meta_have; bpf_dynptr_from_skb_meta(ctx, 0, &meta); - src = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE); - if (!src) - return TC_ACT_SHOT; + meta_have = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE); + if (!meta_have) + goto out; - __builtin_memcpy(dst, src, META_SIZE); + if (!check_metadata(meta_have)) + goto out; + test_pass = true; +out: return TC_ACT_SHOT; } @@ -129,14 +163,12 @@ int ing_cls_dynptr_slice_rdwr(struct __sk_buff *ctx) SEC("tc") int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx) { - struct bpf_dynptr meta; const __u32 chunk_len = META_SIZE / 4; - const __u32 zero = 0; + __u8 meta_have[META_SIZE]; + struct bpf_dynptr meta; __u8 *dst, *src; - dst = bpf_map_lookup_elem(&test_result, &zero); - if (!dst) - return TC_ACT_SHOT; + dst = meta_have; /* 1. Regular read */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); @@ -155,9 +187,14 @@ int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx) /* 4. Read from a slice starting at an offset */ src = bpf_dynptr_slice(&meta, 2 * chunk_len, NULL, chunk_len); if (!src) - return TC_ACT_SHOT; + goto out; __builtin_memcpy(dst, src, chunk_len); + if (!check_metadata(meta_have)) + goto out; + + test_pass = true; +out: return TC_ACT_SHOT; } @@ -254,7 +291,7 @@ int ing_xdp_zalloc_meta(struct xdp_md *ctx) /* Drop any non-test packets */ if (eth + 1 > ctx_ptr(ctx, data_end)) return XDP_DROP; - if (eth->h_proto != 0) + if (!check_smac(eth)) return XDP_DROP; ret = bpf_xdp_adjust_meta(ctx, -META_SIZE); @@ -294,9 +331,9 @@ int ing_xdp(struct xdp_md *ctx) /* The Linux networking stack may send other packets on the test * interface that interfere with the test. Just drop them. - * The test packets can be recognized by their ethertype of zero. + * The test packets can be recognized by their source MAC address. */ - if (eth->h_proto != 0) + if (!check_smac(eth)) return XDP_DROP; __builtin_memcpy(data_meta, payload, META_SIZE); @@ -304,22 +341,25 @@ int ing_xdp(struct xdp_md *ctx) } /* - * Check that skb->data_meta..skb->data is empty if prog writes to packet - * _payload_ using packet pointers. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb->data_meta..skb->data is + * kept intact if prog writes to packet _payload_ using packet pointers. */ SEC("tc") -int clone_data_meta_empty_on_data_write(struct __sk_buff *ctx) +int clone_data_meta_survives_data_write(struct __sk_buff *ctx) { + __u8 *meta_have = ctx_ptr(ctx, data_meta); struct ethhdr *eth = ctx_ptr(ctx, data); if (eth + 1 > ctx_ptr(ctx, data_end)) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) + goto out; + + if (meta_have + META_SIZE > eth) goto out; - /* Expect no metadata */ - if (ctx->data_meta != ctx->data) + if (!check_metadata(meta_have)) goto out; /* Packet write to trigger unclone in prologue */ @@ -331,40 +371,44 @@ out: } /* - * Check that skb->data_meta..skb->data is empty if prog writes to packet - * _metadata_ using packet pointers. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb->data_meta..skb->data is + * kept intact if prog writes to packet _metadata_ using packet pointers. */ SEC("tc") -int clone_data_meta_empty_on_meta_write(struct __sk_buff *ctx) +int clone_data_meta_survives_meta_write(struct __sk_buff *ctx) { + __u8 *meta_have = ctx_ptr(ctx, data_meta); struct ethhdr *eth = ctx_ptr(ctx, data); - __u8 *md = ctx_ptr(ctx, data_meta); if (eth + 1 > ctx_ptr(ctx, data_end)) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - if (md + 1 > ctx_ptr(ctx, data)) { - /* Expect no metadata */ - test_pass = true; - } else { - /* Metadata write to trigger unclone in prologue */ - *md = 42; - } + if (meta_have + META_SIZE > eth) + goto out; + + if (!check_metadata(meta_have)) + goto out; + + /* Metadata write to trigger unclone in prologue */ + *meta_have = 42; + + test_pass = true; out: return TC_ACT_SHOT; } /* - * Check that skb_meta dynptr is writable but empty if prog writes to packet - * _payload_ using a dynptr slice. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, metadata remains intact if + * prog creates a r/w slice to packet _payload_. */ SEC("tc") -int clone_dynptr_empty_on_data_slice_write(struct __sk_buff *ctx) +int clone_meta_dynptr_survives_data_slice_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; + __u8 meta_have[META_SIZE]; struct ethhdr *eth; bpf_dynptr_from_skb(ctx, 0, &data); @@ -372,51 +416,45 @@ int clone_dynptr_empty_on_data_slice_write(struct __sk_buff *ctx) if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect no metadata */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0) + bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (!check_metadata(meta_have)) goto out; - /* Packet write to trigger unclone in prologue */ - eth->h_proto = 42; - test_pass = true; out: return TC_ACT_SHOT; } /* - * Check that skb_meta dynptr is writable but empty if prog writes to packet - * _metadata_ using a dynptr slice. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, metadata remains intact if + * prog creates an r/w slice to packet _metadata_. */ SEC("tc") -int clone_dynptr_empty_on_meta_slice_write(struct __sk_buff *ctx) +int clone_meta_dynptr_survives_meta_slice_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; const struct ethhdr *eth; - __u8 *md; + __u8 *meta_have; bpf_dynptr_from_skb(ctx, 0, &data); eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect no metadata */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0) + meta_have = bpf_dynptr_slice_rdwr(&meta, 0, NULL, META_SIZE); + if (!meta_have) goto out; - /* Metadata write to trigger unclone in prologue */ - bpf_dynptr_from_skb_meta(ctx, 0, &meta); - md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); - if (md) - *md = 42; + if (!check_metadata(meta_have)) + goto out; test_pass = true; out: @@ -424,34 +462,40 @@ out: } /* - * Check that skb_meta dynptr is read-only before prog writes to packet payload - * using dynptr_write helper. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb_meta dynptr is read-write + * before prog writes to packet _payload_ using dynptr_write helper and metadata + * remains intact before and after the write. */ SEC("tc") -int clone_dynptr_rdonly_before_data_dynptr_write(struct __sk_buff *ctx) +int clone_meta_dynptr_rw_before_data_dynptr_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; + __u8 meta_have[META_SIZE]; const struct ethhdr *eth; + int err; bpf_dynptr_from_skb(ctx, 0, &data); eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect read-only metadata before unclone */ + /* Expect read-write metadata before unclone */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE) + if (bpf_dynptr_is_rdonly(&meta)) + goto out; + + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) goto out; /* Helper write to payload will unclone the packet */ bpf_dynptr_write(&data, offsetof(struct ethhdr, h_proto), "x", 1, 0); - /* Expect no metadata after unclone */ - bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != 0) + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) goto out; test_pass = true; @@ -460,31 +504,165 @@ out: } /* - * Check that skb_meta dynptr is read-only if prog writes to packet - * metadata using dynptr_write helper. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb_meta dynptr is read-write + * before prog writes to packet _metadata_ using dynptr_write helper and + * metadata remains intact before and after the write. */ SEC("tc") -int clone_dynptr_rdonly_before_meta_dynptr_write(struct __sk_buff *ctx) +int clone_meta_dynptr_rw_before_meta_dynptr_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; + __u8 meta_have[META_SIZE]; const struct ethhdr *eth; + int err; bpf_dynptr_from_skb(ctx, 0, &data); eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect read-only metadata */ + /* Expect read-write metadata before unclone */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE) + if (bpf_dynptr_is_rdonly(&meta)) goto out; - /* Metadata write. Expect failure. */ - bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_write(&meta, 0, "x", 1, 0) != -EINVAL) + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) + goto out; + + /* Helper write to metadata will unclone the packet */ + bpf_dynptr_write(&meta, 0, &meta_have[0], 1, 0); + + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_vlan_push_pop(struct __sk_buff *ctx) +{ + int err; + + /* bpf_skb_vlan_push assumes HW offload for primary VLAN tag. Only + * secondary tag push triggers an actual MAC header modification. + */ + err = bpf_skb_vlan_push(ctx, 0, 42); + if (err) + goto out; + err = bpf_skb_vlan_push(ctx, 0, 207); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + err = bpf_skb_vlan_pop(ctx); + if (err) + goto out; + err = bpf_skb_vlan_pop(ctx); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_adjust_room(struct __sk_buff *ctx) +{ + int err; + + /* Grow a 1 byte hole after the MAC header */ + err = bpf_skb_adjust_room(ctx, 1, BPF_ADJ_ROOM_MAC, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Shrink a 1 byte hole after the MAC header */ + err = bpf_skb_adjust_room(ctx, -1, BPF_ADJ_ROOM_MAC, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Grow a 256 byte hole to trigger head reallocation */ + err = bpf_skb_adjust_room(ctx, 256, BPF_ADJ_ROOM_MAC, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_change_head_tail(struct __sk_buff *ctx) +{ + int err; + + /* Reserve 1 extra in the front for packet data */ + err = bpf_skb_change_head(ctx, 1, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Reserve 256 extra bytes in the front to trigger head reallocation */ + err = bpf_skb_change_head(ctx, 256, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Reserve 4k extra bytes in the back to trigger head reallocation */ + err = bpf_skb_change_tail(ctx, ctx->len + 4096, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_change_proto(struct __sk_buff *ctx) +{ + int err; + + err = bpf_skb_change_proto(ctx, bpf_htons(ETH_P_IPV6), 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + err = bpf_skb_change_proto(ctx, bpf_htons(ETH_P_IP), 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) goto out; test_pass = true; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 3d5f30c29ae3..2898b3749d07 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -42,12 +42,14 @@ int bench_trigger_uprobe_multi(void *ctx) const volatile int batch_iters = 0; SEC("?raw_tp") -int trigger_count(void *ctx) +int trigger_kernel_count(void *ctx) { int i; - for (i = 0; i < batch_iters; i++) + for (i = 0; i < batch_iters; i++) { inc_counter(); + bpf_get_numa_node_id(); + } return 0; } diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c new file mode 100644 index 000000000000..7efa9521105e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +/* Timer tests */ + +struct timer_elem { + struct bpf_timer t; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct timer_elem); +} timer_map SEC(".maps"); + +static int timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + u32 data; + /* Timer callbacks are never sleepable, even from non-sleepable programs */ + bpf_copy_from_user(&data, sizeof(data), NULL); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +__failure __msg("helper call might sleep in a non-sleepable prog") +int timer_non_sleepable_prog(void *ctx) +{ + struct timer_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&timer_map, &key); + if (!val) + return 0; + + bpf_timer_init(&val->t, &timer_map, 0); + bpf_timer_set_callback(&val->t, timer_cb); + return 0; +} + +SEC("lsm.s/file_open") +__failure __msg("helper call might sleep in a non-sleepable prog") +int timer_sleepable_prog(void *ctx) +{ + struct timer_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&timer_map, &key); + if (!val) + return 0; + + bpf_timer_init(&val->t, &timer_map, 0); + bpf_timer_set_callback(&val->t, timer_cb); + return 0; +} + +/* Workqueue tests */ + +struct wq_elem { + struct bpf_wq w; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct wq_elem); +} wq_map SEC(".maps"); + +static int wq_cb(void *map, int *key, void *value) +{ + u32 data; + /* Workqueue callbacks are always sleepable, even from non-sleepable programs */ + bpf_copy_from_user(&data, sizeof(data), NULL); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +__success +int wq_non_sleepable_prog(void *ctx) +{ + struct wq_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&wq_map, &key); + if (!val) + return 0; + + if (bpf_wq_init(&val->w, &wq_map, 0) != 0) + return 0; + if (bpf_wq_set_callback_impl(&val->w, wq_cb, 0, NULL) != 0) + return 0; + return 0; +} + +SEC("lsm.s/file_open") +__success +int wq_sleepable_prog(void *ctx) +{ + struct wq_elem *val; + int key = 0; + + val = bpf_map_lookup_elem(&wq_map, &key); + if (!val) + return 0; + + if (bpf_wq_init(&val->w, &wq_map, 0) != 0) + return 0; + if (bpf_wq_set_callback_impl(&val->w, wq_cb, 0, NULL) != 0) + return 0; + return 0; +} + +/* Task work tests */ + +struct task_work_elem { + struct bpf_task_work tw; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct task_work_elem); +} task_work_map SEC(".maps"); + +static int task_work_cb(struct bpf_map *map, void *key, void *value) +{ + u32 data; + /* Task work callbacks are always sleepable, even from non-sleepable programs */ + bpf_copy_from_user(&data, sizeof(data), NULL); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +__success +int task_work_non_sleepable_prog(void *ctx) +{ + struct task_work_elem *val; + struct task_struct *task; + int key = 0; + + val = bpf_map_lookup_elem(&task_work_map, &key); + if (!val) + return 0; + + task = bpf_get_current_task_btf(); + if (!task) + return 0; + + bpf_task_work_schedule_resume_impl(task, &val->tw, &task_work_map, task_work_cb, NULL); + return 0; +} + +SEC("lsm.s/file_open") +__success +int task_work_sleepable_prog(void *ctx) +{ + struct task_work_elem *val; + struct task_struct *task; + int key = 0; + + val = bpf_map_lookup_elem(&task_work_map, &key); + if (!val) + return 0; + + task = bpf_get_current_task_btf(); + if (!task) + return 0; + + bpf_task_work_schedule_resume_impl(task, &val->tw, &task_work_map, task_work_cb, NULL); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 0a72e0228ea9..411a18437d7e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1709,4 +1709,158 @@ __naked void jeq_disagreeing_tnums(void *ctx) : __clobber_all); } +SEC("socket") +__description("conditional jump on same register, branch taken") +__not_msg("20: (b7) r0 = 1 {{.*}} R0=1") +__success __log_level(2) +__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS) +__naked void condition_jump_on_same_register(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + w8 = 0x80000000; \ + r0 &= r8; \ + if r0 == r0 goto +1; \ + goto l1_%=; \ + if r0 >= r0 goto +1; \ + goto l1_%=; \ + if r0 s>= r0 goto +1; \ + goto l1_%=; \ + if r0 <= r0 goto +1; \ + goto l1_%=; \ + if r0 s<= r0 goto +1; \ + goto l1_%=; \ + if r0 != r0 goto l1_%=; \ + if r0 > r0 goto l1_%=; \ + if r0 s> r0 goto l1_%=; \ + if r0 < r0 goto l1_%=; \ + if r0 s< r0 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("jset on same register, constant value branch taken") +__not_msg("7: (b7) r0 = 1 {{.*}} R0=1") +__success __log_level(2) +__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS) +__naked void jset_on_same_register_1(void *ctx) +{ + asm volatile(" \ + r0 = 0; \ + if r0 & r0 goto l1_%=; \ + r0 = 1; \ + if r0 & r0 goto +1; \ + goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("jset on same register, scalar value branch taken") +__not_msg("12: (b7) r0 = 1 {{.*}} R0=1") +__success __log_level(2) +__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS) +__naked void jset_on_same_register_2(void *ctx) +{ + asm volatile(" \ + /* range [1;2] */ \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x1; \ + r0 += 1; \ + if r0 & r0 goto +1; \ + goto l1_%=; \ + /* range [-2;-1] */ \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x1; \ + r0 -= 2; \ + if r0 & r0 goto +1; \ + goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("jset on same register, scalar value unknown branch 1") +__msg("3: (b7) r0 = 0 {{.*}} R0=0") +__msg("5: (b7) r0 = 1 {{.*}} R0=1") +__success __log_level(2) +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void jset_on_same_register_3(void *ctx) +{ + asm volatile(" \ + /* range [0;1] */ \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x1; \ + if r0 & r0 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("jset on same register, scalar value unknown branch 2") +__msg("4: (b7) r0 = 0 {{.*}} R0=0") +__msg("6: (b7) r0 = 1 {{.*}} R0=1") +__success __log_level(2) +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void jset_on_same_register_4(void *ctx) +{ + asm volatile(" \ + /* range [-1;0] */ \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x1; \ + r0 -= 1; \ + if r0 & r0 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +SEC("socket") +__description("jset on same register, scalar value unknown branch 3") +__msg("4: (b7) r0 = 0 {{.*}} R0=0") +__msg("6: (b7) r0 = 1 {{.*}} R0=1") +__success __log_level(2) +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void jset_on_same_register_5(void *ctx) +{ + asm volatile(" \ + /* range [-1;1] */ \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x2; \ + r0 -= 1; \ + if r0 & r0 goto l1_%=; \ +l0_%=: r0 = 0; \ + exit; \ +l1_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c index 28b602ac9cbe..911caa8fd1b7 100644 --- a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Converted from tools/testing/selftests/bpf/verifier/direct_packet_access.c */ +#include <linux/if_ether.h> #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" @@ -800,4 +801,62 @@ l0_%=: /* exit(0) */ \ : __clobber_all); } +#define access_test_non_linear(name, type, desc, retval, linear_sz, off) \ + SEC(type) \ + __description("direct packet access: " #name " (non-linear, " type ", " desc ")") \ + __success __retval(retval) \ + __linear_size(linear_sz) \ + __naked void access_non_linear_##name(void) \ + { \ + asm volatile (" \ + r2 = *(u32*)(r1 + %[skb_data]); \ + r3 = *(u32*)(r1 + %[skb_data_end]); \ + r0 = r2; \ + r0 += %[offset]; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r0 - 1); \ + r0 = 0; \ + exit; \ + l0_%=: r0 = 1; \ + exit; \ + " : \ + : __imm_const(skb_data, offsetof(struct __sk_buff, data)), \ + __imm_const(skb_data_end, offsetof(struct __sk_buff, data_end)), \ + __imm_const(offset, off) \ + : __clobber_all); \ + } + +access_test_non_linear(test31, "tc", "too short eth", 1, ETH_HLEN, 22); +access_test_non_linear(test32, "tc", "too short 1", 1, 1, 22); +access_test_non_linear(test33, "tc", "long enough", 0, 22, 22); +access_test_non_linear(test34, "cgroup_skb/ingress", "too short eth", 1, ETH_HLEN, 8); +access_test_non_linear(test35, "cgroup_skb/ingress", "too short 1", 1, 1, 8); +access_test_non_linear(test36, "cgroup_skb/ingress", "long enough", 0, 22, 8); + +SEC("tc") +__description("direct packet access: test37 (non-linear, linearized)") +__success __retval(0) +__linear_size(ETH_HLEN) +__naked void access_non_linear_linearized(void) +{ + asm volatile (" \ + r6 = r1; \ + r2 = 22; \ + call %[bpf_skb_pull_data]; \ + r2 = *(u32*)(r6 + %[skb_data]); \ + r3 = *(u32*)(r6 + %[skb_data_end]); \ + r0 = r2; \ + r0 += 22; \ + if r0 > r3 goto l0_%=; \ + r0 = *(u8*)(r0 - 1); \ + exit; \ +l0_%=: r0 = 1; \ + exit; \ +" : + : __imm(bpf_skb_pull_data), + __imm_const(skb_data, offsetof(struct __sk_buff, data)), + __imm_const(skb_data_end, offsetof(struct __sk_buff, data_end)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_gotox.c b/tools/testing/selftests/bpf/progs/verifier_gotox.c new file mode 100644 index 000000000000..607dad058ca1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_gotox.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Isovalent */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "../../../include/linux/filter.h" + +#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64) + +#define DEFINE_SIMPLE_JUMP_TABLE_PROG(NAME, SRC_REG, OFF, IMM, OUTCOME) \ + \ + SEC("socket") \ + OUTCOME \ + __naked void jump_table_ ## NAME(void) \ + { \ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ + jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 8; \ + r0 = *(u64 *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ + " : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, (SRC_REG), (OFF) , (IMM))) \ + : __clobber_all); \ + } + +/* + * The first program which doesn't use reserved fields + * loads and works properly. The rest fail to load. + */ +DEFINE_SIMPLE_JUMP_TABLE_PROG(ok, BPF_REG_0, 0, 0, __success __retval(1)) +DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_src_reg, BPF_REG_1, 0, 0, __failure __msg("BPF_JA|BPF_X uses reserved fields")) +DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_non_zero_off, BPF_REG_0, 1, 0, __failure __msg("BPF_JA|BPF_X uses reserved fields")) +DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_non_zero_imm, BPF_REG_0, 0, 1, __failure __msg("BPF_JA|BPF_X uses reserved fields")) + +/* + * Gotox is forbidden when there is no jump table loaded + * which points to the sub-function where the gotox is used + */ +SEC("socket") +__failure __msg("no jump tables found for subprog starting at 0") +__naked void jump_table_no_jump_table(void) +{ + asm volatile (" \ + .8byte %[gotox_r0]; \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +/* + * Incorrect type of the target register, only PTR_TO_INSN allowed + */ +SEC("socket") +__failure __msg("R1 has type scalar, expected PTR_TO_INSN") +__naked void jump_table_incorrect_dst_reg_type(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 8; \ + r0 = *(u64 *)(r0 + 0); \ + r1 = 42; \ + .8byte %[gotox_r1]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r1, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_1, 0, 0 , 0)) + : __clobber_all); +} + +#define DEFINE_INVALID_SIZE_PROG(READ_SIZE, OUTCOME) \ + \ + SEC("socket") \ + OUTCOME \ + __naked void jump_table_invalid_read_size_ ## READ_SIZE(void) \ + { \ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ + jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 8; \ + r0 = *(" #READ_SIZE " *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ + " : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) \ + : __clobber_all); \ + } + +DEFINE_INVALID_SIZE_PROG(u32, __failure __msg("Invalid read of 4 bytes from insn_array")) +DEFINE_INVALID_SIZE_PROG(u16, __failure __msg("Invalid read of 2 bytes from insn_array")) +DEFINE_INVALID_SIZE_PROG(u8, __failure __msg("Invalid read of 1 bytes from insn_array")) + +SEC("socket") +__failure __msg("misaligned value access off 0+1+0 size 8") +__naked void jump_table_misaligned_access(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 1; \ + r0 = *(u64 *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +SEC("socket") +__failure __msg("invalid access to map value, value_size=16 off=24 size=8") +__naked void jump_table_invalid_mem_acceess_pos(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 24; \ + r0 = *(u64 *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +SEC("socket") +__failure __msg("invalid access to map value, value_size=16 off=-24 size=8") +__naked void jump_table_invalid_mem_acceess_neg(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 -= 24; \ + r0 = *(u64 *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +SEC("socket") +__success __retval(1) +__naked void jump_table_add_sub_ok(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 -= 24; \ + r0 += 32; \ + r0 = *(u64 *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +SEC("socket") +__failure __msg("write into map forbidden, value_size=16 off=8 size=8") +__naked void jump_table_no_writes(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 8; \ + r1 = 0xbeef; \ + *(u64 *)(r0 + 0) = r1; \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +#define DEFINE_JUMP_TABLE_USE_REG(REG) \ + SEC("socket") \ + __success __retval(1) \ + __naked void jump_table_use_reg_r ## REG(void) \ + { \ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ + jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 16; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 8; \ + r" #REG " = *(u64 *)(r0 + 0); \ + .8byte %[gotox_rX]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ + " : \ + : __imm_insn(gotox_rX, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_ ## REG, 0, 0 , 0)) \ + : __clobber_all); \ + } + +DEFINE_JUMP_TABLE_USE_REG(0) +DEFINE_JUMP_TABLE_USE_REG(1) +DEFINE_JUMP_TABLE_USE_REG(2) +DEFINE_JUMP_TABLE_USE_REG(3) +DEFINE_JUMP_TABLE_USE_REG(4) +DEFINE_JUMP_TABLE_USE_REG(5) +DEFINE_JUMP_TABLE_USE_REG(6) +DEFINE_JUMP_TABLE_USE_REG(7) +DEFINE_JUMP_TABLE_USE_REG(8) +DEFINE_JUMP_TABLE_USE_REG(9) + +__used static int test_subprog(void) +{ + return 0; +} + +SEC("socket") +__failure __msg("jump table for insn 4 points outside of the subprog [0,10]") +__naked void jump_table_outside_subprog(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .quad ret_out_%= - socket; \ + .size jt0_%=, 24; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 8; \ + r0 = *(u64 *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + call test_subprog; \ + exit; \ + ret_out_%=: \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +SEC("socket") +__success __retval(1) +__naked void jump_table_contains_non_unique_values(void) +{ + asm volatile (" \ + .pushsection .jumptables,\"\",@progbits; \ +jt0_%=: \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .quad ret0_%= - socket; \ + .quad ret1_%= - socket; \ + .size jt0_%=, 80; \ + .global jt0_%=; \ + .popsection; \ + \ + r0 = jt0_%= ll; \ + r0 += 8; \ + r0 = *(u64 *)(r0 + 0); \ + .8byte %[gotox_r0]; \ + ret0_%=: \ + r0 = 0; \ + exit; \ + ret1_%=: \ + r0 = 1; \ + exit; \ +" : \ + : __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) + : __clobber_all); +} + +#endif /* __TARGET_ARCH_x86 || __TARGET_ARCH_arm64 */ + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_live_stack.c b/tools/testing/selftests/bpf/progs/verifier_live_stack.c index c0e808509268..2de105057bbc 100644 --- a/tools/testing/selftests/bpf/progs/verifier_live_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_live_stack.c @@ -292,3 +292,53 @@ __naked void syzbot_postorder_bug1(void) "exit;" ::: __clobber_all); } + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} map_array SEC(".maps"); + +SEC("socket") +__failure __msg("invalid read from stack R2 off=-1024 size=8") +__flag(BPF_F_TEST_STATE_FREQ) +__naked unsigned long caller_stack_write_tail_call(void) +{ + asm volatile ( + "r6 = r1;" + "*(u64 *)(r10 - 8) = -8;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto 1f;" + "goto 2f;" + "1:" + "*(u64 *)(r10 - 8) = -1024;" + "2:" + "r1 = r6;" + "r2 = r10;" + "r2 += -8;" + "call write_tail_call;" + "r1 = *(u64 *)(r10 - 8);" + "r2 = r10;" + "r2 += r1;" + "r0 = *(u64 *)(r2 + 0);" + "exit;" + :: __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +static __used __naked unsigned long write_tail_call(void) +{ + asm volatile ( + "r6 = r2;" + "r2 = %[map_array] ll;" + "r3 = 0;" + "call %[bpf_tail_call];" + "*(u64 *)(r6 + 0) = -16;" + "r0 = 0;" + "exit;" + : + : __imm(bpf_tail_call), + __imm_addr(map_array) + : __clobber_all); +} diff --git a/tools/testing/selftests/bpf/progs/verifier_lsm.c b/tools/testing/selftests/bpf/progs/verifier_lsm.c index 32e5e779cb96..6af9100a37ff 100644 --- a/tools/testing/selftests/bpf/progs/verifier_lsm.c +++ b/tools/testing/selftests/bpf/progs/verifier_lsm.c @@ -4,7 +4,7 @@ #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -SEC("lsm/file_alloc_security") +SEC("lsm/file_permission") __description("lsm bpf prog with -4095~0 retval. test 1") __success __naked int errno_zero_retval_test1(void *ctx) @@ -15,7 +15,7 @@ __naked int errno_zero_retval_test1(void *ctx) ::: __clobber_all); } -SEC("lsm/file_alloc_security") +SEC("lsm/file_permission") __description("lsm bpf prog with -4095~0 retval. test 2") __success __naked int errno_zero_retval_test2(void *ctx) diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c index ab9f9f2620ed..e2cbc5bda65e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c +++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c @@ -79,11 +79,6 @@ int with_invalid_ctx_access_test5(struct bpf_nf_ctx *ctx) return NF_ACCEPT; } -extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags, - struct bpf_dynptr *ptr__uninit) __ksym; -extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, uint32_t offset, - void *buffer, uint32_t buffer__sz) __ksym; - SEC("netfilter") __description("netfilter test prog with skb and state read access") __success __failure_unpriv diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c index 2b4610b53382..a2132c72d3b8 100644 --- a/tools/testing/selftests/bpf/progs/verifier_sock.c +++ b/tools/testing/selftests/bpf/progs/verifier_sock.c @@ -1117,10 +1117,17 @@ int tail_call(struct __sk_buff *sk) return 0; } -/* Tail calls invalidate packet pointers. */ +static __noinline +int static_tail_call(struct __sk_buff *sk) +{ + bpf_tail_call_static(sk, &jmp_table, 0); + return 0; +} + +/* Tail calls in sub-programs invalidate packet pointers. */ SEC("tc") __failure __msg("invalid mem access") -int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk) +int invalidate_pkt_pointers_by_global_tail_call(struct __sk_buff *sk) { int *p = (void *)(long)sk->data; @@ -1131,4 +1138,32 @@ int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk) return TCX_PASS; } +/* Tail calls in static sub-programs invalidate packet pointers. */ +SEC("tc") +__failure __msg("invalid mem access") +int invalidate_pkt_pointers_by_static_tail_call(struct __sk_buff *sk) +{ + int *p = (void *)(long)sk->data; + + if ((void *)(p + 1) > (void *)(long)sk->data_end) + return TCX_DROP; + static_tail_call(sk); + *p = 42; /* this is unsafe */ + return TCX_PASS; +} + +/* Direct tail calls do not invalidate packet pointers. */ +SEC("tc") +__success +int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk) +{ + int *p = (void *)(long)sk->data; + + if ((void *)(p + 1) > (void *)(long)sk->data_end) + return TCX_DROP; + bpf_tail_call_static(sk, &jmp_table, 0); + *p = 42; /* this is NOT unsafe: tail calls don't return */ + return TCX_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index ac3e418c2a96..61886ed554de 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -793,4 +793,57 @@ __naked int stack_slot_aliases_precision(void) ); } +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u32); +} map_array SEC(".maps"); + +__naked __noinline __used +static unsigned long identity_tail_call(void) +{ + /* the simplest identity function involving a tail call */ + asm volatile ( + "r6 = r2;" + "r2 = %[map_array] ll;" + "r3 = 0;" + "call %[bpf_tail_call];" + "r0 = r6;" + "exit;" + : + : __imm(bpf_tail_call), + __imm_addr(map_array) + : __clobber_all); +} + +SEC("?raw_tp") +__failure __log_level(2) +__msg("13: (85) call bpf_tail_call#12") +__msg("mark_precise: frame1: last_idx 13 first_idx 0 subseq_idx -1 ") +__msg("returning from callee:") +__msg("frame1: R0=scalar() R6=3 R10=fp0") +__msg("to caller at 4:") +__msg("R0=scalar() R6=map_value(map=.data.vals,ks=4,vs=16) R10=fp0") +__msg("6: (0f) r1 += r0") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (27) r0 *= 4") +__msg("mark_precise: frame0: parent state regs=r0 stack=: R0=Pscalar() R6=map_value(map=.data.vals,ks=4,vs=16) R10=fp0") +__msg("math between map_value pointer and register with unbounded min value is not allowed") +__naked int subprog_result_tail_call(void) +{ + asm volatile ( + "r2 = 3;" + "call identity_tail_call;" + "r0 *= 4;" + "r1 = %[vals];" + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" + "exit;" + : + : __imm_ptr(vals) + : __clobber_common + ); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/wq.c b/tools/testing/selftests/bpf/progs/wq.c index 2f1ba08c293e..25be2cd9d42c 100644 --- a/tools/testing/selftests/bpf/progs/wq.c +++ b/tools/testing/selftests/bpf/progs/wq.c @@ -187,3 +187,20 @@ long test_call_lru_sleepable(void *ctx) return test_elem_callback(&lru, &key, wq_callback); } + +SEC("tc") +long test_map_no_btf(void *ctx) +{ + struct elem *val; + struct bpf_wq *wq; + int key = 42; + + val = bpf_map_lookup_elem(&array, &key); + if (!val) + return -2; + + wq = &val->w; + if (bpf_wq_init(wq, &array, 0) != 0) + return -3; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/wq_failures.c b/tools/testing/selftests/bpf/progs/wq_failures.c index 4240211a1900..d06f6d40594a 100644 --- a/tools/testing/selftests/bpf/progs/wq_failures.c +++ b/tools/testing/selftests/bpf/progs/wq_failures.c @@ -142,3 +142,26 @@ long test_wrong_wq_pointer_offset(void *ctx) return -22; } + +SEC("tc") +__log_level(2) +__failure +__msg(": (85) call bpf_wq_init#") +__msg("R1 doesn't have constant offset. bpf_wq has to be at the constant offset") +long test_bad_wq_off(void *ctx) +{ + struct elem *val; + struct bpf_wq *wq; + int key = 42; + u64 unknown; + + val = bpf_map_lookup_elem(&array, &key); + if (!val) + return -2; + + unknown = bpf_get_prandom_u32(); + wq = &val->w + unknown; + if (bpf_wq_init(wq, &array, 0) != 0) + return -3; + return 0; +} diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh index 1453a53ed547..b03a87571592 100755 --- a/tools/testing/selftests/bpf/test_bpftool_build.sh +++ b/tools/testing/selftests/bpf/test_bpftool_build.sh @@ -90,10 +90,6 @@ echo -e "... through kbuild\n" if [ -f ".config" ] ; then make_and_clean tools/bpf - ## "make tools/bpf" sets $(OUTPUT) to ...tools/bpf/runqslower for - ## runqslower, but the default (used for the "clean" target) is .output. - ## Let's make sure we clean runqslower's directory properly. - make -C tools/bpf/runqslower OUTPUT=${KDIR_ROOT_DIR}/tools/bpf/runqslower/ clean ## $OUTPUT is overwritten in kbuild Makefile, and thus cannot be passed ## down from toplevel Makefile to bpftool's Makefile. diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c index 769206fc70e4..7b4ae5e81d32 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c @@ -5,6 +5,7 @@ #include <linux/delay.h> #include <linux/module.h> #include <linux/prandom.h> +#include <linux/ktime.h> #include <asm/rqspinlock.h> #include <linux/perf_event.h> #include <linux/kthread.h> @@ -22,48 +23,146 @@ static struct perf_event_attr hw_attr = { static rqspinlock_t lock_a; static rqspinlock_t lock_b; +static rqspinlock_t lock_c; + +#define RQSL_SLOW_THRESHOLD_MS 10 +static const unsigned int rqsl_hist_ms[] = { + 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, + 12, 14, 16, 18, 20, 25, 30, 40, 50, 75, + 100, 150, 200, 250, 1000, +}; +#define RQSL_NR_HIST_BUCKETS ARRAY_SIZE(rqsl_hist_ms) + +enum rqsl_context { + RQSL_CTX_NORMAL = 0, + RQSL_CTX_NMI, + RQSL_CTX_MAX, +}; + +struct rqsl_cpu_hist { + atomic64_t hist[RQSL_CTX_MAX][RQSL_NR_HIST_BUCKETS]; + atomic64_t success[RQSL_CTX_MAX]; + atomic64_t failure[RQSL_CTX_MAX]; +}; + +static DEFINE_PER_CPU(struct rqsl_cpu_hist, rqsl_cpu_hists); + +enum rqsl_mode { + RQSL_MODE_AA = 0, + RQSL_MODE_ABBA, + RQSL_MODE_ABBCCA, +}; + +static int test_mode = RQSL_MODE_AA; +module_param(test_mode, int, 0644); +MODULE_PARM_DESC(test_mode, + "rqspinlock test mode: 0 = AA, 1 = ABBA, 2 = ABBCCA"); + +static int normal_delay = 20; +module_param(normal_delay, int, 0644); +MODULE_PARM_DESC(normal_delay, + "rqspinlock critical section length for normal context (20ms default)"); + +static int nmi_delay = 10; +module_param(nmi_delay, int, 0644); +MODULE_PARM_DESC(nmi_delay, + "rqspinlock critical section length for NMI context (10ms default)"); static struct perf_event **rqsl_evts; static int rqsl_nevts; -static bool test_ab = false; -module_param(test_ab, bool, 0644); -MODULE_PARM_DESC(test_ab, "Test ABBA situations instead of AA situations"); - static struct task_struct **rqsl_threads; static int rqsl_nthreads; static atomic_t rqsl_ready_cpus = ATOMIC_INIT(0); static int pause = 0; -static bool nmi_locks_a(int cpu) +static const char *rqsl_mode_names[] = { + [RQSL_MODE_AA] = "AA", + [RQSL_MODE_ABBA] = "ABBA", + [RQSL_MODE_ABBCCA] = "ABBCCA", +}; + +struct rqsl_lock_pair { + rqspinlock_t *worker_lock; + rqspinlock_t *nmi_lock; +}; + +static struct rqsl_lock_pair rqsl_get_lock_pair(int cpu) { - return (cpu & 1) && test_ab; + int mode = READ_ONCE(test_mode); + + switch (mode) { + default: + case RQSL_MODE_AA: + return (struct rqsl_lock_pair){ &lock_a, &lock_a }; + case RQSL_MODE_ABBA: + if (cpu & 1) + return (struct rqsl_lock_pair){ &lock_b, &lock_a }; + return (struct rqsl_lock_pair){ &lock_a, &lock_b }; + case RQSL_MODE_ABBCCA: + switch (cpu % 3) { + case 0: + return (struct rqsl_lock_pair){ &lock_a, &lock_b }; + case 1: + return (struct rqsl_lock_pair){ &lock_b, &lock_c }; + default: + return (struct rqsl_lock_pair){ &lock_c, &lock_a }; + } + } +} + +static u32 rqsl_hist_bucket_idx(u32 delta_ms) +{ + int i; + + for (i = 0; i < RQSL_NR_HIST_BUCKETS; i++) { + if (delta_ms <= rqsl_hist_ms[i]) + return i; + } + + return RQSL_NR_HIST_BUCKETS - 1; +} + +static void rqsl_record_lock_result(u64 delta_ns, enum rqsl_context ctx, int ret) +{ + struct rqsl_cpu_hist *hist = this_cpu_ptr(&rqsl_cpu_hists); + u32 delta_ms = DIV_ROUND_UP_ULL(delta_ns, NSEC_PER_MSEC); + u32 bucket = rqsl_hist_bucket_idx(delta_ms); + atomic64_t *buckets = hist->hist[ctx]; + + atomic64_inc(&buckets[bucket]); + if (!ret) + atomic64_inc(&hist->success[ctx]); + else + atomic64_inc(&hist->failure[ctx]); } static int rqspinlock_worker_fn(void *arg) { int cpu = smp_processor_id(); unsigned long flags; + u64 start_ns; int ret; if (cpu) { atomic_inc(&rqsl_ready_cpus); while (!kthread_should_stop()) { + struct rqsl_lock_pair locks = rqsl_get_lock_pair(cpu); + rqspinlock_t *worker_lock = locks.worker_lock; + if (READ_ONCE(pause)) { msleep(1000); continue; } - if (nmi_locks_a(cpu)) - ret = raw_res_spin_lock_irqsave(&lock_b, flags); - else - ret = raw_res_spin_lock_irqsave(&lock_a, flags); - mdelay(20); - if (nmi_locks_a(cpu) && !ret) - raw_res_spin_unlock_irqrestore(&lock_b, flags); - else if (!ret) - raw_res_spin_unlock_irqrestore(&lock_a, flags); + start_ns = ktime_get_mono_fast_ns(); + ret = raw_res_spin_lock_irqsave(worker_lock, flags); + rqsl_record_lock_result(ktime_get_mono_fast_ns() - start_ns, + RQSL_CTX_NORMAL, ret); + mdelay(normal_delay); + if (!ret) + raw_res_spin_unlock_irqrestore(worker_lock, flags); cpu_relax(); } return 0; @@ -91,24 +190,25 @@ static int rqspinlock_worker_fn(void *arg) static void nmi_cb(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { + struct rqsl_lock_pair locks; int cpu = smp_processor_id(); unsigned long flags; + u64 start_ns; int ret; if (!cpu || READ_ONCE(pause)) return; - if (nmi_locks_a(cpu)) - ret = raw_res_spin_lock_irqsave(&lock_a, flags); - else - ret = raw_res_spin_lock_irqsave(test_ab ? &lock_b : &lock_a, flags); + locks = rqsl_get_lock_pair(cpu); + start_ns = ktime_get_mono_fast_ns(); + ret = raw_res_spin_lock_irqsave(locks.nmi_lock, flags); + rqsl_record_lock_result(ktime_get_mono_fast_ns() - start_ns, + RQSL_CTX_NMI, ret); - mdelay(10); + mdelay(nmi_delay); - if (nmi_locks_a(cpu) && !ret) - raw_res_spin_unlock_irqrestore(&lock_a, flags); - else if (!ret) - raw_res_spin_unlock_irqrestore(test_ab ? &lock_b : &lock_a, flags); + if (!ret) + raw_res_spin_unlock_irqrestore(locks.nmi_lock, flags); } static void free_rqsl_threads(void) @@ -142,13 +242,19 @@ static int bpf_test_rqspinlock_init(void) int i, ret; int ncpus = num_online_cpus(); - pr_err("Mode = %s\n", test_ab ? "ABBA" : "AA"); + if (test_mode < RQSL_MODE_AA || test_mode > RQSL_MODE_ABBCCA) { + pr_err("Invalid mode %d\n", test_mode); + return -EINVAL; + } + + pr_err("Mode = %s\n", rqsl_mode_names[test_mode]); - if (ncpus < 3) + if (ncpus < test_mode + 2) return -ENOTSUPP; raw_res_spin_lock_init(&lock_a); raw_res_spin_lock_init(&lock_b); + raw_res_spin_lock_init(&lock_c); rqsl_evts = kcalloc(ncpus - 1, sizeof(*rqsl_evts), GFP_KERNEL); if (!rqsl_evts) @@ -196,10 +302,88 @@ err_perf_events: module_init(bpf_test_rqspinlock_init); +static void rqsl_print_histograms(void) +{ + int cpu, i; + + pr_err("rqspinlock acquisition latency histogram (ms):\n"); + + for_each_online_cpu(cpu) { + struct rqsl_cpu_hist *hist = per_cpu_ptr(&rqsl_cpu_hists, cpu); + u64 norm_counts[RQSL_NR_HIST_BUCKETS]; + u64 nmi_counts[RQSL_NR_HIST_BUCKETS]; + u64 total_counts[RQSL_NR_HIST_BUCKETS]; + u64 norm_success, nmi_success, success_total; + u64 norm_failure, nmi_failure, failure_total; + u64 norm_total = 0, nmi_total = 0, total = 0; + bool has_slow = false; + + for (i = 0; i < RQSL_NR_HIST_BUCKETS; i++) { + norm_counts[i] = atomic64_read(&hist->hist[RQSL_CTX_NORMAL][i]); + nmi_counts[i] = atomic64_read(&hist->hist[RQSL_CTX_NMI][i]); + total_counts[i] = norm_counts[i] + nmi_counts[i]; + norm_total += norm_counts[i]; + nmi_total += nmi_counts[i]; + total += total_counts[i]; + if (rqsl_hist_ms[i] > RQSL_SLOW_THRESHOLD_MS && + total_counts[i]) + has_slow = true; + } + + norm_success = atomic64_read(&hist->success[RQSL_CTX_NORMAL]); + nmi_success = atomic64_read(&hist->success[RQSL_CTX_NMI]); + norm_failure = atomic64_read(&hist->failure[RQSL_CTX_NORMAL]); + nmi_failure = atomic64_read(&hist->failure[RQSL_CTX_NMI]); + success_total = norm_success + nmi_success; + failure_total = norm_failure + nmi_failure; + + if (!total) + continue; + + if (!has_slow) { + pr_err(" cpu%d: total %llu (normal %llu, nmi %llu) | " + "success %llu (normal %llu, nmi %llu) | " + "failure %llu (normal %llu, nmi %llu), all within 0-%ums\n", + cpu, total, norm_total, nmi_total, + success_total, norm_success, nmi_success, + failure_total, norm_failure, nmi_failure, + RQSL_SLOW_THRESHOLD_MS); + continue; + } + + pr_err(" cpu%d: total %llu (normal %llu, nmi %llu) | " + "success %llu (normal %llu, nmi %llu) | " + "failure %llu (normal %llu, nmi %llu)\n", + cpu, total, norm_total, nmi_total, + success_total, norm_success, nmi_success, + failure_total, norm_failure, nmi_failure); + for (i = 0; i < RQSL_NR_HIST_BUCKETS; i++) { + unsigned int start_ms; + + if (!total_counts[i]) + continue; + + start_ms = i == 0 ? 0 : rqsl_hist_ms[i - 1] + 1; + if (i == RQSL_NR_HIST_BUCKETS - 1) { + pr_err(" >= %ums: total %llu (normal %llu, nmi %llu)\n", + start_ms, total_counts[i], + norm_counts[i], nmi_counts[i]); + } else { + pr_err(" %u-%ums: total %llu (normal %llu, nmi %llu)\n", + start_ms, rqsl_hist_ms[i], + total_counts[i], + norm_counts[i], nmi_counts[i]); + } + } + } +} + static void bpf_test_rqspinlock_exit(void) { + WRITE_ONCE(pause, 1); free_rqsl_threads(); free_rqsl_evts(); + rqsl_print_histograms(); } module_exit(bpf_test_rqspinlock_exit); diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index ed0a4721d8fd..1669a7eeda26 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -926,7 +926,7 @@ __bpf_kfunc int bpf_kfunc_call_kernel_connect(struct addr_args *args) goto out; } - err = kernel_connect(sock, (struct sockaddr *)&args->addr, + err = kernel_connect(sock, (struct sockaddr_unsized *)&args->addr, args->addrlen, 0); out: mutex_unlock(&sock_lock); @@ -949,7 +949,7 @@ __bpf_kfunc int bpf_kfunc_call_kernel_bind(struct addr_args *args) goto out; } - err = kernel_bind(sock, (struct sockaddr *)&args->addr, args->addrlen); + err = kernel_bind(sock, (struct sockaddr_unsized *)&args->addr, args->addrlen); out: mutex_unlock(&sock_lock); diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index 74ecc281bb8c..338c035c3688 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -43,6 +43,7 @@ #define TEST_TAG_EXPECT_STDERR_PFX_UNPRIV "comment:test_expect_stderr_unpriv=" #define TEST_TAG_EXPECT_STDOUT_PFX "comment:test_expect_stdout=" #define TEST_TAG_EXPECT_STDOUT_PFX_UNPRIV "comment:test_expect_stdout_unpriv=" +#define TEST_TAG_LINEAR_SIZE "comment:test_linear_size=" /* Warning: duplicated in bpf_misc.h */ #define POINTER_VALUE 0xbadcafe @@ -89,6 +90,7 @@ struct test_spec { int mode_mask; int arch_mask; int load_mask; + int linear_sz; bool auxiliary; bool valid; }; @@ -633,6 +635,21 @@ static int parse_test_spec(struct test_loader *tester, &spec->unpriv.stdout); if (err) goto cleanup; + } else if (str_has_pfx(s, TEST_TAG_LINEAR_SIZE)) { + switch (bpf_program__type(prog)) { + case BPF_PROG_TYPE_SCHED_ACT: + case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_CGROUP_SKB: + val = s + sizeof(TEST_TAG_LINEAR_SIZE) - 1; + err = parse_int(val, &spec->linear_sz, "test linear size"); + if (err) + goto cleanup; + break; + default: + PRINT_FAIL("__linear_size for unsupported program type"); + err = -EINVAL; + goto cleanup; + } } } @@ -1007,10 +1024,11 @@ static bool is_unpriv_capable_map(struct bpf_map *map) } } -static int do_prog_test_run(int fd_prog, int *retval, bool empty_opts) +static int do_prog_test_run(int fd_prog, int *retval, bool empty_opts, int linear_sz) { __u8 tmp_out[TEST_DATA_LEN << 2] = {}; __u8 tmp_in[TEST_DATA_LEN] = {}; + struct __sk_buff ctx = {}; int err, saved_errno; LIBBPF_OPTS(bpf_test_run_opts, topts, .data_in = tmp_in, @@ -1020,6 +1038,12 @@ static int do_prog_test_run(int fd_prog, int *retval, bool empty_opts) .repeat = 1, ); + if (linear_sz) { + ctx.data_end = linear_sz; + topts.ctx_in = &ctx; + topts.ctx_size_in = sizeof(ctx); + } + if (empty_opts) { memset(&topts, 0, sizeof(struct bpf_test_run_opts)); topts.sz = sizeof(struct bpf_test_run_opts); @@ -1269,7 +1293,8 @@ void run_subtest(struct test_loader *tester, } err = do_prog_test_run(bpf_program__fd(tprog), &retval, - bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false); + bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false, + spec->linear_sz); if (!err && retval != subspec->retval && subspec->retval != POINTER_VALUE) { PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval); goto tobj_cleanup; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 3fae9ce46ca9..ccc5acd55ff9 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1399,7 +1399,8 @@ static void test_map_stress(void) static bool can_retry(int err) { return (err == EAGAIN || err == EBUSY || - (err == ENOMEM && map_opts.map_flags == BPF_F_NO_PREALLOC)); + ((err == ENOMEM || err == E2BIG) && + map_opts.map_flags == BPF_F_NO_PREALLOC)); } int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts, diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c index 5546b05a0486..f1300047c1e0 100644 --- a/tools/testing/selftests/bpf/test_tag.c +++ b/tools/testing/selftests/bpf/test_tag.c @@ -116,7 +116,7 @@ static void tag_from_alg(int insns, uint8_t *tag, uint32_t len) static const struct sockaddr_alg alg = { .salg_family = AF_ALG, .salg_type = "hash", - .salg_name = "sha1", + .salg_name = "sha256", }; int fd_base, fd_alg, ret; ssize_t size; diff --git a/tools/testing/selftests/bpf/test_tc_edt.sh b/tools/testing/selftests/bpf/test_tc_edt.sh deleted file mode 100755 index 76f0bd17061f..000000000000 --- a/tools/testing/selftests/bpf/test_tc_edt.sh +++ /dev/null @@ -1,100 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# This test installs a TC bpf program that throttles a TCP flow -# with dst port = 9000 down to 5MBps. Then it measures actual -# throughput of the flow. - -BPF_FILE="test_tc_edt.bpf.o" -if [[ $EUID -ne 0 ]]; then - echo "This script must be run as root" - echo "FAIL" - exit 1 -fi - -# check that nc, dd, and timeout are present -command -v nc >/dev/null 2>&1 || \ - { echo >&2 "nc is not available"; exit 1; } -command -v dd >/dev/null 2>&1 || \ - { echo >&2 "nc is not available"; exit 1; } -command -v timeout >/dev/null 2>&1 || \ - { echo >&2 "timeout is not available"; exit 1; } - -readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)" -readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)" - -readonly IP_SRC="172.16.1.100" -readonly IP_DST="172.16.2.100" - -cleanup() -{ - ip netns del ${NS_SRC} - ip netns del ${NS_DST} -} - -trap cleanup EXIT - -set -e # exit on error - -ip netns add "${NS_SRC}" -ip netns add "${NS_DST}" -ip link add veth_src type veth peer name veth_dst -ip link set veth_src netns ${NS_SRC} -ip link set veth_dst netns ${NS_DST} - -ip -netns ${NS_SRC} addr add ${IP_SRC}/24 dev veth_src -ip -netns ${NS_DST} addr add ${IP_DST}/24 dev veth_dst - -ip -netns ${NS_SRC} link set dev veth_src up -ip -netns ${NS_DST} link set dev veth_dst up - -ip -netns ${NS_SRC} route add ${IP_DST}/32 dev veth_src -ip -netns ${NS_DST} route add ${IP_SRC}/32 dev veth_dst - -# set up TC on TX -ip netns exec ${NS_SRC} tc qdisc add dev veth_src root fq -ip netns exec ${NS_SRC} tc qdisc add dev veth_src clsact -ip netns exec ${NS_SRC} tc filter add dev veth_src egress \ - bpf da obj ${BPF_FILE} sec cls_test - - -# start the listener -ip netns exec ${NS_DST} bash -c \ - "nc -4 -l -p 9000 >/dev/null &" -declare -i NC_PID=$! -sleep 1 - -declare -ir TIMEOUT=20 -declare -ir EXPECTED_BPS=5000000 - -# run the load, capture RX bytes on DST -declare -ir RX_BYTES_START=$( ip netns exec ${NS_DST} \ - cat /sys/class/net/veth_dst/statistics/rx_bytes ) - -set +e -ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero \ - bs=1000 count=1000000 > /dev/tcp/${IP_DST}/9000 2>/dev/null" -set -e - -declare -ir RX_BYTES_END=$( ip netns exec ${NS_DST} \ - cat /sys/class/net/veth_dst/statistics/rx_bytes ) - -declare -ir ACTUAL_BPS=$(( ($RX_BYTES_END - $RX_BYTES_START) / $TIMEOUT )) - -echo $TIMEOUT $ACTUAL_BPS $EXPECTED_BPS | \ - awk '{printf "elapsed: %d sec; bps difference: %.2f%%\n", - $1, ($2-$3)*100.0/$3}' - -# Pass the test if the actual bps is within 1% of the expected bps. -# The difference is usually about 0.1% on a 20-sec test, and ==> zero -# the longer the test runs. -declare -ir RES=$( echo $ACTUAL_BPS $EXPECTED_BPS | \ - awk 'function abs(x){return ((x < 0.0) ? -x : x)} - {if (abs(($1-$2)*100.0/$2) > 1.0) { print "1" } - else { print "0"} }' ) -if [ "${RES}" == "0" ] ; then - echo "PASS" -else - echo "FAIL" - exit 1 -fi diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh deleted file mode 100755 index cb55a908bb0d..000000000000 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ /dev/null @@ -1,320 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# In-place tunneling - -BPF_FILE="test_tc_tunnel.bpf.o" -# must match the port that the bpf program filters on -readonly port=8000 - -readonly ns_prefix="ns-$$-" -readonly ns1="${ns_prefix}1" -readonly ns2="${ns_prefix}2" - -readonly ns1_v4=192.168.1.1 -readonly ns2_v4=192.168.1.2 -readonly ns1_v6=fd::1 -readonly ns2_v6=fd::2 - -# Must match port used by bpf program -readonly udpport=5555 -# MPLSoverUDP -readonly mplsudpport=6635 -readonly mplsproto=137 - -readonly infile="$(mktemp)" -readonly outfile="$(mktemp)" - -setup() { - ip netns add "${ns1}" - ip netns add "${ns2}" - - ip link add dev veth1 mtu 1500 netns "${ns1}" type veth \ - peer name veth2 mtu 1500 netns "${ns2}" - - ip netns exec "${ns1}" ethtool -K veth1 tso off - - ip -netns "${ns1}" link set veth1 up - ip -netns "${ns2}" link set veth2 up - - ip -netns "${ns1}" -4 addr add "${ns1_v4}/24" dev veth1 - ip -netns "${ns2}" -4 addr add "${ns2_v4}/24" dev veth2 - ip -netns "${ns1}" -6 addr add "${ns1_v6}/64" dev veth1 nodad - ip -netns "${ns2}" -6 addr add "${ns2_v6}/64" dev veth2 nodad - - # clamp route to reserve room for tunnel headers - ip -netns "${ns1}" -4 route flush table main - ip -netns "${ns1}" -6 route flush table main - ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1450 dev veth1 - ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1430 dev veth1 - - sleep 1 - - dd if=/dev/urandom of="${infile}" bs="${datalen}" count=1 status=none -} - -cleanup() { - ip netns del "${ns2}" - ip netns del "${ns1}" - - if [[ -f "${outfile}" ]]; then - rm "${outfile}" - fi - if [[ -f "${infile}" ]]; then - rm "${infile}" - fi - - if [[ -n $server_pid ]]; then - kill $server_pid 2> /dev/null - fi -} - -server_listen() { - ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" & - server_pid=$! -} - -client_connect() { - ip netns exec "${ns1}" timeout 2 nc "${netcat_opt}" -w 1 "${addr2}" "${port}" < "${infile}" - echo $? -} - -verify_data() { - wait "${server_pid}" - server_pid= - # sha1sum returns two fields [sha1] [filepath] - # convert to bash array and access first elem - insum=($(sha1sum ${infile})) - outsum=($(sha1sum ${outfile})) - if [[ "${insum[0]}" != "${outsum[0]}" ]]; then - echo "data mismatch" - exit 1 - fi -} - -wait_for_port() { - for i in $(seq 20); do - if ip netns exec "${ns2}" ss ${2:--4}OHntl | grep -q "$1"; then - return 0 - fi - sleep 0.1 - done - return 1 -} - -set -e - -# no arguments: automated test, run all -if [[ "$#" -eq "0" ]]; then - echo "ipip" - $0 ipv4 ipip none 100 - - echo "ipip6" - $0 ipv4 ipip6 none 100 - - echo "ip6ip6" - $0 ipv6 ip6tnl none 100 - - echo "sit" - $0 ipv6 sit none 100 - - echo "ip4 vxlan" - $0 ipv4 vxlan eth 2000 - - echo "ip6 vxlan" - $0 ipv6 ip6vxlan eth 2000 - - for mac in none mpls eth ; do - echo "ip gre $mac" - $0 ipv4 gre $mac 100 - - echo "ip6 gre $mac" - $0 ipv6 ip6gre $mac 100 - - echo "ip gre $mac gso" - $0 ipv4 gre $mac 2000 - - echo "ip6 gre $mac gso" - $0 ipv6 ip6gre $mac 2000 - - echo "ip udp $mac" - $0 ipv4 udp $mac 100 - - echo "ip6 udp $mac" - $0 ipv6 ip6udp $mac 100 - - echo "ip udp $mac gso" - $0 ipv4 udp $mac 2000 - - echo "ip6 udp $mac gso" - $0 ipv6 ip6udp $mac 2000 - done - - echo "OK. All tests passed" - exit 0 -fi - -if [[ "$#" -ne "4" ]]; then - echo "Usage: $0" - echo " or: $0 <ipv4|ipv6> <tuntype> <none|mpls|eth> <data_len>" - exit 1 -fi - -case "$1" in -"ipv4") - readonly addr1="${ns1_v4}" - readonly addr2="${ns2_v4}" - readonly ipproto=4 - readonly netcat_opt=-${ipproto} - readonly foumod=fou - readonly foutype=ipip - readonly fouproto=4 - readonly fouproto_mpls=${mplsproto} - readonly gretaptype=gretap - ;; -"ipv6") - readonly addr1="${ns1_v6}" - readonly addr2="${ns2_v6}" - readonly ipproto=6 - readonly netcat_opt=-${ipproto} - readonly foumod=fou6 - readonly foutype=ip6tnl - readonly fouproto="41 -6" - readonly fouproto_mpls="${mplsproto} -6" - readonly gretaptype=ip6gretap - ;; -*) - echo "unknown arg: $1" - exit 1 - ;; -esac - -readonly tuntype=$2 -readonly mac=$3 -readonly datalen=$4 - -echo "encap ${addr1} to ${addr2}, type ${tuntype}, mac ${mac} len ${datalen}" - -trap cleanup EXIT - -setup - -# basic communication works -echo "test basic connectivity" -server_listen -wait_for_port ${port} ${netcat_opt} -client_connect -verify_data - -# clientside, insert bpf program to encap all TCP to port ${port} -# client can no longer connect -ip netns exec "${ns1}" tc qdisc add dev veth1 clsact -ip netns exec "${ns1}" tc filter add dev veth1 egress \ - bpf direct-action object-file ${BPF_FILE} \ - section "encap_${tuntype}_${mac}" -echo "test bpf encap without decap (expect failure)" -server_listen -wait_for_port ${port} ${netcat_opt} -! client_connect - -if [[ "$tuntype" =~ "udp" ]]; then - # Set up fou tunnel. - ttype="${foutype}" - targs="encap fou encap-sport auto encap-dport $udpport" - # fou may be a module; allow this to fail. - modprobe "${foumod}" ||true - if [[ "$mac" == "mpls" ]]; then - dport=${mplsudpport} - dproto=${fouproto_mpls} - tmode="mode any ttl 255" - else - dport=${udpport} - dproto=${fouproto} - fi - ip netns exec "${ns2}" ip fou add port $dport ipproto ${dproto} - targs="encap fou encap-sport auto encap-dport $dport" -elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then - ttype=$gretaptype -elif [[ "$tuntype" =~ "vxlan" && "$mac" == "eth" ]]; then - ttype="vxlan" - targs="id 1 dstport 8472 udp6zerocsumrx" -elif [[ "$tuntype" == "ipip6" ]]; then - ttype="ip6tnl" - targs="" -else - ttype=$tuntype - targs="" -fi - -# tunnel address family differs from inner for SIT -if [[ "${tuntype}" == "sit" ]]; then - link_addr1="${ns1_v4}" - link_addr2="${ns2_v4}" -elif [[ "${tuntype}" == "ipip6" ]]; then - link_addr1="${ns1_v6}" - link_addr2="${ns2_v6}" -else - link_addr1="${addr1}" - link_addr2="${addr2}" -fi - -# serverside, insert decap module -# server is still running -# client can connect again -ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \ - ${tmode} remote "${link_addr1}" local "${link_addr2}" $targs - -expect_tun_fail=0 - -if [[ "$tuntype" == "ip6udp" && "$mac" == "mpls" ]]; then - # No support for MPLS IPv6 fou tunnel; expect failure. - expect_tun_fail=1 -elif [[ "$tuntype" =~ "udp" && "$mac" == "eth" ]]; then - # No support for TEB fou tunnel; expect failure. - expect_tun_fail=1 -elif [[ "$tuntype" =~ (gre|vxlan) && "$mac" == "eth" ]]; then - # Share ethernet address between tunnel/veth2 so L2 decap works. - ethaddr=$(ip netns exec "${ns2}" ip link show veth2 | \ - awk '/ether/ { print $2 }') - ip netns exec "${ns2}" ip link set testtun0 address $ethaddr -elif [[ "$mac" == "mpls" ]]; then - modprobe mpls_iptunnel ||true - modprobe mpls_gso ||true - ip netns exec "${ns2}" sysctl -qw net.mpls.platform_labels=65536 - ip netns exec "${ns2}" ip -f mpls route add 1000 dev lo - ip netns exec "${ns2}" ip link set lo up - ip netns exec "${ns2}" sysctl -qw net.mpls.conf.testtun0.input=1 - ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.lo.rp_filter=0 -fi - -# Because packets are decapped by the tunnel they arrive on testtun0 from -# the IP stack perspective. Ensure reverse path filtering is disabled -# otherwise we drop the TCP SYN as arriving on testtun0 instead of the -# expected veth2 (veth2 is where 192.168.1.2 is configured). -ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0 -# rp needs to be disabled for both all and testtun0 as the rp value is -# selected as the max of the "all" and device-specific values. -ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.testtun0.rp_filter=0 -ip netns exec "${ns2}" ip link set dev testtun0 up -if [[ "$expect_tun_fail" == 1 ]]; then - # This tunnel mode is not supported, so we expect failure. - echo "test bpf encap with tunnel device decap (expect failure)" - ! client_connect -else - echo "test bpf encap with tunnel device decap" - client_connect - verify_data - server_listen - wait_for_port ${port} ${netcat_opt} -fi - -# serverside, use BPF for decap -ip netns exec "${ns2}" ip link del dev testtun0 -ip netns exec "${ns2}" tc qdisc add dev veth2 clsact -ip netns exec "${ns2}" tc filter add dev veth2 ingress \ - bpf direct-action object-file ${BPF_FILE} section decap -echo "test bpf encap with bpf decap" -client_connect -verify_data - -echo OK diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 352adc8df2d1..9234a58b0a97 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -74,31 +74,23 @@ #define _GNU_SOURCE #include <assert.h> #include <fcntl.h> -#include <errno.h> #include <getopt.h> #include <linux/if_link.h> #include <linux/if_ether.h> #include <linux/mman.h> #include <linux/netdev.h> -#include <linux/bitmap.h> #include <linux/ethtool.h> #include <arpa/inet.h> #include <net/if.h> #include <locale.h> -#include <poll.h> -#include <pthread.h> -#include <signal.h> #include <stdio.h> #include <stdlib.h> #include <libgen.h> -#include <string.h> #include <stddef.h> #include <sys/mman.h> -#include <sys/socket.h> -#include <sys/time.h> #include <sys/types.h> -#include <unistd.h> +#include "prog_tests/test_xsk.h" #include "xsk_xdp_progs.skel.h" #include "xsk.h" #include "xskxceiver.h" @@ -109,9 +101,6 @@ #include <network_helpers.h> -#define MAX_TX_BUDGET_DEFAULT 32 - -static bool opt_verbose; static bool opt_print_tests; static enum test_mode opt_mode = TEST_MODE_ALL; static u32 opt_run_test = RUN_ALL_TESTS; @@ -120,169 +109,12 @@ void test__fail(void) { /* for network_helpers.c */ } static void __exit_with_error(int error, const char *file, const char *func, int line) { - ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, - strerror(error)); + ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, + error, strerror(error)); ksft_exit_xfail(); } #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__) -#define busy_poll_string(test) (test)->ifobj_tx->busy_poll ? "BUSY-POLL " : "" -static char *mode_string(struct test_spec *test) -{ - switch (test->mode) { - case TEST_MODE_SKB: - return "SKB"; - case TEST_MODE_DRV: - return "DRV"; - case TEST_MODE_ZC: - return "ZC"; - default: - return "BOGUS"; - } -} - -static void report_failure(struct test_spec *test) -{ - if (test->fail) - return; - - ksft_test_result_fail("FAIL: %s %s%s\n", mode_string(test), busy_poll_string(test), - test->name); - test->fail = true; -} - -/* The payload is a word consisting of a packet sequence number in the upper - * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's - * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0. - */ -static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size) -{ - u32 *ptr = (u32 *)dest, i; - - start /= sizeof(*ptr); - size /= sizeof(*ptr); - for (i = 0; i < size; i++) - ptr[i] = htonl(pkt_nb << 16 | (i + start)); -} - -static void gen_eth_hdr(struct xsk_socket_info *xsk, struct ethhdr *eth_hdr) -{ - memcpy(eth_hdr->h_dest, xsk->dst_mac, ETH_ALEN); - memcpy(eth_hdr->h_source, xsk->src_mac, ETH_ALEN); - eth_hdr->h_proto = htons(ETH_P_LOOPBACK); -} - -static bool is_umem_valid(struct ifobject *ifobj) -{ - return !!ifobj->umem->umem; -} - -static u32 mode_to_xdp_flags(enum test_mode mode) -{ - return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; -} - -static u64 umem_size(struct xsk_umem_info *umem) -{ - return umem->num_frames * umem->frame_size; -} - -static int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, - u64 size) -{ - struct xsk_umem_config cfg = { - .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, - .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, - .frame_size = umem->frame_size, - .frame_headroom = umem->frame_headroom, - .flags = XSK_UMEM__DEFAULT_FLAGS - }; - int ret; - - if (umem->fill_size) - cfg.fill_size = umem->fill_size; - - if (umem->comp_size) - cfg.comp_size = umem->comp_size; - - if (umem->unaligned_mode) - cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; - - ret = xsk_umem__create(&umem->umem, buffer, size, - &umem->fq, &umem->cq, &cfg); - if (ret) - return ret; - - umem->buffer = buffer; - if (ifobj->shared_umem && ifobj->rx_on) { - umem->base_addr = umem_size(umem); - umem->next_buffer = umem_size(umem); - } - - return 0; -} - -static u64 umem_alloc_buffer(struct xsk_umem_info *umem) -{ - u64 addr; - - addr = umem->next_buffer; - umem->next_buffer += umem->frame_size; - if (umem->next_buffer >= umem->base_addr + umem_size(umem)) - umem->next_buffer = umem->base_addr; - - return addr; -} - -static void umem_reset_alloc(struct xsk_umem_info *umem) -{ - umem->next_buffer = 0; -} - -static void enable_busy_poll(struct xsk_socket_info *xsk) -{ - int sock_opt; - - sock_opt = 1; - if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL, - (void *)&sock_opt, sizeof(sock_opt)) < 0) - exit_with_error(errno); - - sock_opt = 20; - if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL, - (void *)&sock_opt, sizeof(sock_opt)) < 0) - exit_with_error(errno); - - sock_opt = xsk->batch_size; - if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET, - (void *)&sock_opt, sizeof(sock_opt)) < 0) - exit_with_error(errno); -} - -static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, - struct ifobject *ifobject, bool shared) -{ - struct xsk_socket_config cfg = {}; - struct xsk_ring_cons *rxr; - struct xsk_ring_prod *txr; - - xsk->umem = umem; - cfg.rx_size = xsk->rxqsize; - cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - cfg.bind_flags = ifobject->bind_flags; - if (shared) - cfg.bind_flags |= XDP_SHARED_UMEM; - if (ifobject->mtu > MAX_ETH_PKT_SIZE) - cfg.bind_flags |= XDP_USE_SG; - if (umem->comp_size) - cfg.tx_size = umem->comp_size; - if (umem->fill_size) - cfg.rx_size = umem->fill_size; - - txr = ifobject->tx_on ? &xsk->tx : NULL; - rxr = ifobject->rx_on ? &xsk->rx : NULL; - return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg); -} static bool ifobj_zc_avail(struct ifobject *ifobject) { @@ -314,7 +146,7 @@ static bool ifobj_zc_avail(struct ifobject *ifobject) ifobject->bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY; ifobject->rx_on = true; xsk->rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - ret = __xsk_configure_socket(xsk, umem, ifobject, false); + ret = xsk_configure_socket(xsk, umem, ifobject, false); if (!ret) zc_avail = true; @@ -327,25 +159,6 @@ out: return zc_avail; } -#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags" -static unsigned int get_max_skb_frags(void) -{ - unsigned int max_skb_frags = 0; - FILE *file; - - file = fopen(MAX_SKB_FRAGS_PATH, "r"); - if (!file) { - ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH); - return 0; - } - - if (fscanf(file, "%u", &max_skb_frags) != 1) - ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH); - - fclose(file); - return max_skb_frags; -} - static struct option long_options[] = { {"interface", required_argument, 0, 'i'}, {"busy-poll", no_argument, 0, 'b'}, @@ -446,2256 +259,36 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj } } -static int set_ring_size(struct ifobject *ifobj) -{ - int ret; - u32 ctr = 0; - - while (ctr++ < SOCK_RECONF_CTR) { - ret = set_hw_ring_size(ifobj->ifname, &ifobj->ring); - if (!ret) - break; - - /* Retry if it fails */ - if (ctr >= SOCK_RECONF_CTR || errno != EBUSY) - return -errno; - - usleep(USLEEP_MAX); - } - - return ret; -} - -static int hw_ring_size_reset(struct ifobject *ifobj) -{ - ifobj->ring.tx_pending = ifobj->set_ring.default_tx; - ifobj->ring.rx_pending = ifobj->set_ring.default_rx; - return set_ring_size(ifobj); -} - -static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, - struct ifobject *ifobj_rx) -{ - u32 i, j; - - for (i = 0; i < MAX_INTERFACES; i++) { - struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; - - ifobj->xsk = &ifobj->xsk_arr[0]; - ifobj->use_poll = false; - ifobj->use_fill_ring = true; - ifobj->release_rx = true; - ifobj->validation_func = NULL; - ifobj->use_metadata = false; - - if (i == 0) { - ifobj->rx_on = false; - ifobj->tx_on = true; - } else { - ifobj->rx_on = true; - ifobj->tx_on = false; - } - - memset(ifobj->umem, 0, sizeof(*ifobj->umem)); - ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS; - ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; - - for (j = 0; j < MAX_SOCKETS; j++) { - memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); - ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - ifobj->xsk_arr[j].batch_size = DEFAULT_BATCH_SIZE; - if (i == 0) - ifobj->xsk_arr[j].pkt_stream = test->tx_pkt_stream_default; - else - ifobj->xsk_arr[j].pkt_stream = test->rx_pkt_stream_default; - - memcpy(ifobj->xsk_arr[j].src_mac, g_mac, ETH_ALEN); - memcpy(ifobj->xsk_arr[j].dst_mac, g_mac, ETH_ALEN); - ifobj->xsk_arr[j].src_mac[5] += ((j * 2) + 0); - ifobj->xsk_arr[j].dst_mac[5] += ((j * 2) + 1); - } - } - - if (ifobj_tx->hw_ring_size_supp) - hw_ring_size_reset(ifobj_tx); - - test->ifobj_tx = ifobj_tx; - test->ifobj_rx = ifobj_rx; - test->current_step = 0; - test->total_steps = 1; - test->nb_sockets = 1; - test->fail = false; - test->set_ring = false; - test->adjust_tail = false; - test->adjust_tail_support = false; - test->mtu = MAX_ETH_PKT_SIZE; - test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog; - test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk; - test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog; - test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk; -} - -static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, - struct ifobject *ifobj_rx, enum test_mode mode, - const struct test_spec *test_to_run) -{ - struct pkt_stream *tx_pkt_stream; - struct pkt_stream *rx_pkt_stream; - u32 i; - - tx_pkt_stream = test->tx_pkt_stream_default; - rx_pkt_stream = test->rx_pkt_stream_default; - memset(test, 0, sizeof(*test)); - test->tx_pkt_stream_default = tx_pkt_stream; - test->rx_pkt_stream_default = rx_pkt_stream; - - for (i = 0; i < MAX_INTERFACES; i++) { - struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; - - ifobj->bind_flags = XDP_USE_NEED_WAKEUP; - if (mode == TEST_MODE_ZC) - ifobj->bind_flags |= XDP_ZEROCOPY; - else - ifobj->bind_flags |= XDP_COPY; - } - - strncpy(test->name, test_to_run->name, MAX_TEST_NAME_SIZE); - test->test_func = test_to_run->test_func; - test->mode = mode; - __test_spec_init(test, ifobj_tx, ifobj_rx); -} - -static void test_spec_reset(struct test_spec *test) -{ - __test_spec_init(test, test->ifobj_tx, test->ifobj_rx); -} - -static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx, - struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx, - struct bpf_map *xskmap_tx) -{ - test->xdp_prog_rx = xdp_prog_rx; - test->xdp_prog_tx = xdp_prog_tx; - test->xskmap_rx = xskmap_rx; - test->xskmap_tx = xskmap_tx; -} - -static int test_spec_set_mtu(struct test_spec *test, int mtu) -{ - int err; - - if (test->ifobj_rx->mtu != mtu) { - err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu); - if (err) - return err; - test->ifobj_rx->mtu = mtu; - } - if (test->ifobj_tx->mtu != mtu) { - err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu); - if (err) - return err; - test->ifobj_tx->mtu = mtu; - } - - return 0; -} - -static void pkt_stream_reset(struct pkt_stream *pkt_stream) -{ - if (pkt_stream) { - pkt_stream->current_pkt_nb = 0; - pkt_stream->nb_rx_pkts = 0; - } -} - -static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream) -{ - if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) - return NULL; - - return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; -} - -static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent) -{ - while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) { - (*pkts_sent)++; - if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid) - return &pkt_stream->pkts[pkt_stream->current_pkt_nb++]; - pkt_stream->current_pkt_nb++; - } - return NULL; -} - -static void pkt_stream_delete(struct pkt_stream *pkt_stream) -{ - free(pkt_stream->pkts); - free(pkt_stream); -} - -static void pkt_stream_restore_default(struct test_spec *test) -{ - struct pkt_stream *tx_pkt_stream = test->ifobj_tx->xsk->pkt_stream; - struct pkt_stream *rx_pkt_stream = test->ifobj_rx->xsk->pkt_stream; - - if (tx_pkt_stream != test->tx_pkt_stream_default) { - pkt_stream_delete(test->ifobj_tx->xsk->pkt_stream); - test->ifobj_tx->xsk->pkt_stream = test->tx_pkt_stream_default; - } - - if (rx_pkt_stream != test->rx_pkt_stream_default) { - pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream); - test->ifobj_rx->xsk->pkt_stream = test->rx_pkt_stream_default; - } -} - -static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) -{ - struct pkt_stream *pkt_stream; - - pkt_stream = calloc(1, sizeof(*pkt_stream)); - if (!pkt_stream) - return NULL; - - pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); - if (!pkt_stream->pkts) { - free(pkt_stream); - return NULL; - } - - pkt_stream->nb_pkts = nb_pkts; - return pkt_stream; -} - -static bool pkt_continues(u32 options) -{ - return options & XDP_PKT_CONTD; -} - -static u32 ceil_u32(u32 a, u32 b) -{ - return (a + b - 1) / b; -} - -static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt) -{ - u32 nb_frags = 1, next_frag; - - if (!pkt) - return 1; - - if (!pkt_stream->verbatim) { - if (!pkt->valid || !pkt->len) - return 1; - return ceil_u32(pkt->len, frame_size); - } - - /* Search for the end of the packet in verbatim mode */ - if (!pkt_continues(pkt->options)) - return nb_frags; - - next_frag = pkt_stream->current_pkt_nb; - pkt++; - while (next_frag++ < pkt_stream->nb_pkts) { - nb_frags++; - if (!pkt_continues(pkt->options) || !pkt->valid) - break; - pkt++; - } - return nb_frags; -} - -static bool set_pkt_valid(int offset, u32 len) -{ - return len <= MAX_ETH_JUMBO_SIZE; -} - -static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) -{ - pkt->offset = offset; - pkt->len = len; - pkt->valid = set_pkt_valid(offset, len); -} - -static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) -{ - bool prev_pkt_valid = pkt->valid; - - pkt_set(pkt_stream, pkt, offset, len); - pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid; -} - -static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) -{ - return ceil_u32(len, umem->frame_size) * umem->frame_size; -} - -static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb_start, u32 nb_off) -{ - struct pkt_stream *pkt_stream; - u32 i; - - pkt_stream = __pkt_stream_alloc(nb_pkts); - if (!pkt_stream) - exit_with_error(ENOMEM); - - pkt_stream->nb_pkts = nb_pkts; - pkt_stream->max_pkt_len = pkt_len; - for (i = 0; i < nb_pkts; i++) { - struct pkt *pkt = &pkt_stream->pkts[i]; - - pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len); - pkt->pkt_nb = nb_start + i * nb_off; - } - - return pkt_stream; -} - -static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len) -{ - return __pkt_stream_generate(nb_pkts, pkt_len, 0, 1); -} - -static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream) -{ - return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len); -} - -static void pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len) -{ - ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len); -} - -static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) -{ - pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len); - pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len); -} - -static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, - int offset) -{ - struct pkt_stream *pkt_stream; - u32 i; - - pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream); - for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2) - pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len); - - ifobj->xsk->pkt_stream = pkt_stream; -} - -static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) -{ - __pkt_stream_replace_half(test->ifobj_tx, pkt_len, offset); - __pkt_stream_replace_half(test->ifobj_rx, pkt_len, offset); -} - -static void pkt_stream_receive_half(struct test_spec *test) -{ - struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream; - u32 i; - - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(pkt_stream->nb_pkts, - pkt_stream->pkts[0].len); - pkt_stream = test->ifobj_rx->xsk->pkt_stream; - for (i = 1; i < pkt_stream->nb_pkts; i += 2) - pkt_stream->pkts[i].valid = false; - - pkt_stream->nb_valid_entries /= 2; -} - -static void pkt_stream_even_odd_sequence(struct test_spec *test) -{ - struct pkt_stream *pkt_stream; - u32 i; - - for (i = 0; i < test->nb_sockets; i++) { - pkt_stream = test->ifobj_tx->xsk_arr[i].pkt_stream; - pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, - pkt_stream->pkts[0].len, i, 2); - test->ifobj_tx->xsk_arr[i].pkt_stream = pkt_stream; - - pkt_stream = test->ifobj_rx->xsk_arr[i].pkt_stream; - pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2, - pkt_stream->pkts[0].len, i, 2); - test->ifobj_rx->xsk_arr[i].pkt_stream = pkt_stream; - } -} - -static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem) -{ - if (!pkt->valid) - return pkt->offset; - return pkt->offset + umem_alloc_buffer(umem); -} - -static void pkt_stream_cancel(struct pkt_stream *pkt_stream) -{ - pkt_stream->current_pkt_nb--; -} - -static void pkt_generate(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, u64 addr, u32 len, - u32 pkt_nb, u32 bytes_written) -{ - void *data = xsk_umem__get_data(umem->buffer, addr); - - if (len < MIN_PKT_SIZE) - return; - - if (!bytes_written) { - gen_eth_hdr(xsk, data); - - len -= PKT_HDR_SIZE; - data += PKT_HDR_SIZE; - } else { - bytes_written -= PKT_HDR_SIZE; - } - - write_payload(data, pkt_nb, bytes_written, len); -} - -static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames, - u32 nb_frames, bool verbatim) -{ - u32 i, len = 0, pkt_nb = 0, payload = 0; - struct pkt_stream *pkt_stream; - - pkt_stream = __pkt_stream_alloc(nb_frames); - if (!pkt_stream) - exit_with_error(ENOMEM); - - for (i = 0; i < nb_frames; i++) { - struct pkt *pkt = &pkt_stream->pkts[pkt_nb]; - struct pkt *frame = &frames[i]; - - pkt->offset = frame->offset; - if (verbatim) { - *pkt = *frame; - pkt->pkt_nb = payload; - if (!frame->valid || !pkt_continues(frame->options)) - payload++; - } else { - if (frame->valid) - len += frame->len; - if (frame->valid && pkt_continues(frame->options)) - continue; - - pkt->pkt_nb = pkt_nb; - pkt->len = len; - pkt->valid = frame->valid; - pkt->options = 0; - - len = 0; - } - - print_verbose("offset: %d len: %u valid: %u options: %u pkt_nb: %u\n", - pkt->offset, pkt->len, pkt->valid, pkt->options, pkt->pkt_nb); - - if (pkt->valid && pkt->len > pkt_stream->max_pkt_len) - pkt_stream->max_pkt_len = pkt->len; - - if (pkt->valid) - pkt_stream->nb_valid_entries++; - - pkt_nb++; - } - - pkt_stream->nb_pkts = pkt_nb; - pkt_stream->verbatim = verbatim; - return pkt_stream; -} - -static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) -{ - struct pkt_stream *pkt_stream; - - pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true); - test->ifobj_tx->xsk->pkt_stream = pkt_stream; - - pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false); - test->ifobj_rx->xsk->pkt_stream = pkt_stream; -} - -static void pkt_print_data(u32 *data, u32 cnt) -{ - u32 i; - - for (i = 0; i < cnt; i++) { - u32 seqnum, pkt_nb; - - seqnum = ntohl(*data) & 0xffff; - pkt_nb = ntohl(*data) >> 16; - ksft_print_msg("%u:%u ", pkt_nb, seqnum); - data++; - } -} - -static void pkt_dump(void *pkt, u32 len, bool eth_header) -{ - struct ethhdr *ethhdr = pkt; - u32 i, *data; - - if (eth_header) { - /*extract L2 frame */ - ksft_print_msg("DEBUG>> L2: dst mac: "); - for (i = 0; i < ETH_ALEN; i++) - ksft_print_msg("%02X", ethhdr->h_dest[i]); - - ksft_print_msg("\nDEBUG>> L2: src mac: "); - for (i = 0; i < ETH_ALEN; i++) - ksft_print_msg("%02X", ethhdr->h_source[i]); - - data = pkt + PKT_HDR_SIZE; - } else { - data = pkt; - } - - /*extract L5 frame */ - ksft_print_msg("\nDEBUG>> L5: seqnum: "); - pkt_print_data(data, PKT_DUMP_NB_TO_PRINT); - ksft_print_msg("...."); - if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) { - ksft_print_msg("\n.... "); - pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT, - PKT_DUMP_NB_TO_PRINT); - } - ksft_print_msg("\n---------------------------------------\n"); -} - -static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr) -{ - u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom; - u32 offset = addr % umem->frame_size, expected_offset; - int pkt_offset = pkt->valid ? pkt->offset : 0; - - if (!umem->unaligned_mode) - pkt_offset = 0; - - expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size; - - if (offset == expected_offset) - return true; - - ksft_print_msg("[%s] expected [%u], got [%u]\n", __func__, expected_offset, offset); - return false; -} - -static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr) -{ - void *data = xsk_umem__get_data(buffer, addr); - struct xdp_info *meta = data - sizeof(struct xdp_info); - - if (meta->count != pkt->pkt_nb) { - ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n", - __func__, pkt->pkt_nb, - (unsigned long long)meta->count); - return false; - } - - return true; -} - -static bool is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx) -{ - struct bpf_map *data_map; - int adjust_value = 0; - int key = 0; - int ret; - - data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss"); - if (!data_map || !bpf_map__is_internal(data_map)) { - ksft_print_msg("Error: could not find bss section of XDP program\n"); - exit_with_error(errno); - } - - ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value); - if (ret) { - ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret); - exit_with_error(errno); - } - - /* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail - * helper is not supported. Skip the adjust_tail test case in this scenario. - */ - return adjust_value != -EOPNOTSUPP; -} - -static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb, - u32 bytes_processed) -{ - u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum; - void *data = xsk_umem__get_data(umem->buffer, addr); - - addr -= umem->base_addr; - - if (addr >= umem->num_frames * umem->frame_size || - addr + len > umem->num_frames * umem->frame_size) { - ksft_print_msg("Frag invalid addr: %llx len: %u\n", - (unsigned long long)addr, len); - return false; - } - if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) { - ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n", - (unsigned long long)addr, len); - return false; - } - - pkt_data = data; - if (!bytes_processed) { - pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data); - len -= PKT_HDR_SIZE; - } else { - bytes_processed -= PKT_HDR_SIZE; - } - - expected_seqnum = bytes_processed / sizeof(*pkt_data); - seqnum = ntohl(*pkt_data) & 0xffff; - pkt_nb = ntohl(*pkt_data) >> 16; - - if (expected_pkt_nb != pkt_nb) { - ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n", - __func__, expected_pkt_nb, pkt_nb); - goto error; - } - if (expected_seqnum != seqnum) { - ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n", - __func__, expected_seqnum, seqnum); - goto error; - } - - words_to_end = len / sizeof(*pkt_data) - 1; - pkt_data += words_to_end; - seqnum = ntohl(*pkt_data) & 0xffff; - expected_seqnum += words_to_end; - if (expected_seqnum != seqnum) { - ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n", - __func__, expected_seqnum, seqnum); - goto error; - } - - return true; - -error: - pkt_dump(data, len, !bytes_processed); - return false; -} - -static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) -{ - if (pkt->len != len) { - ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n", - __func__, pkt->len, len); - pkt_dump(xsk_umem__get_data(buffer, addr), len, true); - return false; - } - - return true; -} - -static u32 load_value(u32 *counter) -{ - return __atomic_load_n(counter, __ATOMIC_ACQUIRE); -} - -static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret) -{ - u32 max_budget = MAX_TX_BUDGET_DEFAULT; - u32 cons, ready_to_send; - int delta; - - cons = load_value(xsk->tx.consumer); - ready_to_send = load_value(xsk->tx.producer) - cons; - *ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); - - delta = load_value(xsk->tx.consumer) - cons; - /* By default, xsk should consume exact @max_budget descs at one - * send in this case where hitting the max budget limit in while - * loop is triggered in __xsk_generic_xmit(). Please make sure that - * the number of descs to be sent is larger than @max_budget, or - * else the tx.consumer will be updated in xskq_cons_peek_desc() - * in time which hides the issue we try to verify. - */ - if (ready_to_send > max_budget && delta != max_budget) - return false; - - return true; -} - -static int kick_tx(struct xsk_socket_info *xsk) -{ - int ret; - - if (xsk->check_consumer) { - if (!kick_tx_with_check(xsk, &ret)) - return TEST_FAILURE; - } else { - ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); - } - if (ret >= 0) - return TEST_PASS; - if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) { - usleep(100); - return TEST_PASS; - } - return TEST_FAILURE; -} - -static int kick_rx(struct xsk_socket_info *xsk) -{ - int ret; - - ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); - if (ret < 0) - return TEST_FAILURE; - - return TEST_PASS; -} - -static int complete_pkts(struct xsk_socket_info *xsk, int batch_size) -{ - unsigned int rcvd; - u32 idx; - int ret; - - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { - ret = kick_tx(xsk); - if (ret) - return TEST_FAILURE; - } - - rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); - if (rcvd) { - if (rcvd > xsk->outstanding_tx) { - u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); - - ksft_print_msg("[%s] Too many packets completed\n", __func__); - ksft_print_msg("Last completion address: %llx\n", - (unsigned long long)addr); - return TEST_FAILURE; - } - - xsk_ring_cons__release(&xsk->umem->cq, rcvd); - xsk->outstanding_tx -= rcvd; - } - - return TEST_PASS; -} - -static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk) -{ - u32 frags_processed = 0, nb_frags = 0, pkt_len = 0; - u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0; - struct pkt_stream *pkt_stream = xsk->pkt_stream; - struct ifobject *ifobj = test->ifobj_rx; - struct xsk_umem_info *umem = xsk->umem; - struct pollfd fds = { }; - struct pkt *pkt; - u64 first_addr = 0; - int ret; - - fds.fd = xsk_socket__fd(xsk->xsk); - fds.events = POLLIN; - - ret = kick_rx(xsk); - if (ret) - return TEST_FAILURE; - - if (ifobj->use_poll) { - ret = poll(&fds, 1, POLL_TMOUT); - if (ret < 0) - return TEST_FAILURE; - - if (!ret) { - if (!is_umem_valid(test->ifobj_tx)) - return TEST_PASS; - - ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__); - return TEST_CONTINUE; - } - - if (!(fds.revents & POLLIN)) - return TEST_CONTINUE; - } - - rcvd = xsk_ring_cons__peek(&xsk->rx, xsk->batch_size, &idx_rx); - if (!rcvd) - return TEST_CONTINUE; - - if (ifobj->use_fill_ring) { - ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); - while (ret != rcvd) { - if (xsk_ring_prod__needs_wakeup(&umem->fq)) { - ret = poll(&fds, 1, POLL_TMOUT); - if (ret < 0) - return TEST_FAILURE; - } - ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); - } - } - - while (frags_processed < rcvd) { - const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); - u64 addr = desc->addr, orig; - - orig = xsk_umem__extract_addr(addr); - addr = xsk_umem__add_offset_to_addr(addr); - - if (!nb_frags) { - pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent); - if (!pkt) { - ksft_print_msg("[%s] received too many packets addr: %lx len %u\n", - __func__, addr, desc->len); - return TEST_FAILURE; - } - } - - print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n", - addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid); - - if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) || - !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata && - !is_metadata_correct(pkt, umem->buffer, addr))) - return TEST_FAILURE; - - if (!nb_frags++) - first_addr = addr; - frags_processed++; - pkt_len += desc->len; - if (ifobj->use_fill_ring) - *xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig; - - if (pkt_continues(desc->options)) - continue; - - /* The complete packet has been received */ - if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) || - !is_offset_correct(umem, pkt, addr)) - return TEST_FAILURE; - - pkt_stream->nb_rx_pkts++; - nb_frags = 0; - pkt_len = 0; - } - - if (nb_frags) { - /* In the middle of a packet. Start over from beginning of packet. */ - idx_rx -= nb_frags; - xsk_ring_cons__cancel(&xsk->rx, nb_frags); - if (ifobj->use_fill_ring) { - idx_fq -= nb_frags; - xsk_ring_prod__cancel(&umem->fq, nb_frags); - } - frags_processed -= nb_frags; - } - - if (ifobj->use_fill_ring) - xsk_ring_prod__submit(&umem->fq, frags_processed); - if (ifobj->release_rx) - xsk_ring_cons__release(&xsk->rx, frags_processed); - - pthread_mutex_lock(&pacing_mutex); - pkts_in_flight -= pkts_sent; - pthread_mutex_unlock(&pacing_mutex); - pkts_sent = 0; - -return TEST_CONTINUE; -} - -bool all_packets_received(struct test_spec *test, struct xsk_socket_info *xsk, u32 sock_num, - unsigned long *bitmap) -{ - struct pkt_stream *pkt_stream = xsk->pkt_stream; - - if (!pkt_stream) { - __set_bit(sock_num, bitmap); - return false; - } - - if (pkt_stream->nb_rx_pkts == pkt_stream->nb_valid_entries) { - __set_bit(sock_num, bitmap); - if (bitmap_full(bitmap, test->nb_sockets)) - return true; - } - - return false; -} - -static int receive_pkts(struct test_spec *test) -{ - struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; - DECLARE_BITMAP(bitmap, test->nb_sockets); - struct xsk_socket_info *xsk; - u32 sock_num = 0; - int res, ret; - - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - - timeradd(&tv_now, &tv_timeout, &tv_end); - - while (1) { - xsk = &test->ifobj_rx->xsk_arr[sock_num]; - - if ((all_packets_received(test, xsk, sock_num, bitmap))) - break; - - res = __receive_pkts(test, xsk); - if (!(res == TEST_PASS || res == TEST_CONTINUE)) - return res; - - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - - if (timercmp(&tv_now, &tv_end, >)) { - ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__); - return TEST_FAILURE; - } - sock_num = (sock_num + 1) % test->nb_sockets; - } - - return TEST_PASS; -} - -static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, bool timeout) -{ - u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len; - struct pkt_stream *pkt_stream = xsk->pkt_stream; - struct xsk_umem_info *umem = ifobject->umem; - bool use_poll = ifobject->use_poll; - struct pollfd fds = { }; - int ret; - - buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len); - /* pkts_in_flight might be negative if many invalid packets are sent */ - if (pkts_in_flight >= (int)((umem_size(umem) - xsk->batch_size * buffer_len) / - buffer_len)) { - ret = kick_tx(xsk); - if (ret) - return TEST_FAILURE; - return TEST_CONTINUE; - } - - fds.fd = xsk_socket__fd(xsk->xsk); - fds.events = POLLOUT; - - while (xsk_ring_prod__reserve(&xsk->tx, xsk->batch_size, &idx) < xsk->batch_size) { - if (use_poll) { - ret = poll(&fds, 1, POLL_TMOUT); - if (timeout) { - if (ret < 0) { - ksft_print_msg("ERROR: [%s] Poll error %d\n", - __func__, errno); - return TEST_FAILURE; - } - if (ret == 0) - return TEST_PASS; - break; - } - if (ret <= 0) { - ksft_print_msg("ERROR: [%s] Poll error %d\n", - __func__, errno); - return TEST_FAILURE; - } - } - - complete_pkts(xsk, xsk->batch_size); - } - - for (i = 0; i < xsk->batch_size; i++) { - struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream); - u32 nb_frags_left, nb_frags, bytes_written = 0; - - if (!pkt) - break; - - nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt); - if (nb_frags > xsk->batch_size - i) { - pkt_stream_cancel(pkt_stream); - xsk_ring_prod__cancel(&xsk->tx, xsk->batch_size - i); - break; - } - nb_frags_left = nb_frags; - - while (nb_frags_left--) { - struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - - tx_desc->addr = pkt_get_addr(pkt, ifobject->umem); - if (pkt_stream->verbatim) { - tx_desc->len = pkt->len; - tx_desc->options = pkt->options; - } else if (nb_frags_left) { - tx_desc->len = umem->frame_size; - tx_desc->options = XDP_PKT_CONTD; - } else { - tx_desc->len = pkt->len - bytes_written; - tx_desc->options = 0; - } - if (pkt->valid) - pkt_generate(xsk, umem, tx_desc->addr, tx_desc->len, pkt->pkt_nb, - bytes_written); - bytes_written += tx_desc->len; - - print_verbose("Tx addr: %llx len: %u options: %u pkt_nb: %u\n", - tx_desc->addr, tx_desc->len, tx_desc->options, pkt->pkt_nb); - - if (nb_frags_left) { - i++; - if (pkt_stream->verbatim) - pkt = pkt_stream_get_next_tx_pkt(pkt_stream); - } - } - - if (pkt && pkt->valid) { - valid_pkts++; - valid_frags += nb_frags; - } - } - - pthread_mutex_lock(&pacing_mutex); - pkts_in_flight += valid_pkts; - pthread_mutex_unlock(&pacing_mutex); - - xsk_ring_prod__submit(&xsk->tx, i); - xsk->outstanding_tx += valid_frags; - - if (use_poll) { - ret = poll(&fds, 1, POLL_TMOUT); - if (ret <= 0) { - if (ret == 0 && timeout) - return TEST_PASS; - - ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret); - return TEST_FAILURE; - } - } - - if (!timeout) { - if (complete_pkts(xsk, i)) - return TEST_FAILURE; - - usleep(10); - return TEST_PASS; - } - - return TEST_CONTINUE; -} - -static int wait_for_tx_completion(struct xsk_socket_info *xsk) -{ - struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0}; - int ret; - - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - timeradd(&tv_now, &tv_timeout, &tv_end); - - while (xsk->outstanding_tx) { - ret = gettimeofday(&tv_now, NULL); - if (ret) - exit_with_error(errno); - if (timercmp(&tv_now, &tv_end, >)) { - ksft_print_msg("ERROR: [%s] Transmission loop timed out\n", __func__); - return TEST_FAILURE; - } - - complete_pkts(xsk, xsk->batch_size); - } - - return TEST_PASS; -} - -bool all_packets_sent(struct test_spec *test, unsigned long *bitmap) -{ - return bitmap_full(bitmap, test->nb_sockets); -} - -static int send_pkts(struct test_spec *test, struct ifobject *ifobject) -{ - bool timeout = !is_umem_valid(test->ifobj_rx); - DECLARE_BITMAP(bitmap, test->nb_sockets); - u32 i, ret; - - while (!(all_packets_sent(test, bitmap))) { - for (i = 0; i < test->nb_sockets; i++) { - struct pkt_stream *pkt_stream; - - pkt_stream = ifobject->xsk_arr[i].pkt_stream; - if (!pkt_stream || pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) { - __set_bit(i, bitmap); - continue; - } - ret = __send_pkts(ifobject, &ifobject->xsk_arr[i], timeout); - if (ret == TEST_CONTINUE && !test->fail) - continue; - - if ((ret || test->fail) && !timeout) - return TEST_FAILURE; - - if (ret == TEST_PASS && timeout) - return ret; - - ret = wait_for_tx_completion(&ifobject->xsk_arr[i]); - if (ret) - return TEST_FAILURE; - } - } - - return TEST_PASS; -} - -static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats) -{ - int fd = xsk_socket__fd(xsk), err; - socklen_t optlen, expected_len; - - optlen = sizeof(*stats); - err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, stats, &optlen); - if (err) { - ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", - __func__, -err, strerror(-err)); - return TEST_FAILURE; - } - - expected_len = sizeof(struct xdp_statistics); - if (optlen != expected_len) { - ksft_print_msg("[%s] getsockopt optlen error. Expected: %u got: %u\n", - __func__, expected_len, optlen); - return TEST_FAILURE; - } - - return TEST_PASS; -} - -static int validate_rx_dropped(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - struct xdp_statistics stats; - int err; - - err = kick_rx(ifobject->xsk); - if (err) - return TEST_FAILURE; - - err = get_xsk_stats(xsk, &stats); - if (err) - return TEST_FAILURE; - - /* The receiver calls getsockopt after receiving the last (valid) - * packet which is not the final packet sent in this test (valid and - * invalid packets are sent in alternating fashion with the final - * packet being invalid). Since the last packet may or may not have - * been dropped already, both outcomes must be allowed. - */ - if (stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 || - stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 - 1) - return TEST_PASS; - - return TEST_FAILURE; -} - -static int validate_rx_full(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - struct xdp_statistics stats; - int err; - - usleep(1000); - err = kick_rx(ifobject->xsk); - if (err) - return TEST_FAILURE; - - err = get_xsk_stats(xsk, &stats); - if (err) - return TEST_FAILURE; - - if (stats.rx_ring_full) - return TEST_PASS; - - return TEST_FAILURE; -} - -static int validate_fill_empty(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - struct xdp_statistics stats; - int err; - - usleep(1000); - err = kick_rx(ifobject->xsk); - if (err) - return TEST_FAILURE; - - err = get_xsk_stats(xsk, &stats); - if (err) - return TEST_FAILURE; - - if (stats.rx_fill_ring_empty_descs) - return TEST_PASS; - - return TEST_FAILURE; -} - -static int validate_tx_invalid_descs(struct ifobject *ifobject) -{ - struct xsk_socket *xsk = ifobject->xsk->xsk; - int fd = xsk_socket__fd(xsk); - struct xdp_statistics stats; - socklen_t optlen; - int err; - - optlen = sizeof(stats); - err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); - if (err) { - ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n", - __func__, -err, strerror(-err)); - return TEST_FAILURE; - } - - if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) { - ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n", - __func__, - (unsigned long long)stats.tx_invalid_descs, - ifobject->xsk->pkt_stream->nb_pkts); - return TEST_FAILURE; - } - - return TEST_PASS; -} - -static void xsk_configure_socket(struct test_spec *test, struct ifobject *ifobject, - struct xsk_umem_info *umem, bool tx) -{ - int i, ret; - - for (i = 0; i < test->nb_sockets; i++) { - bool shared = (ifobject->shared_umem && tx) ? true : !!i; - u32 ctr = 0; - - while (ctr++ < SOCK_RECONF_CTR) { - ret = __xsk_configure_socket(&ifobject->xsk_arr[i], umem, - ifobject, shared); - if (!ret) - break; - - /* Retry if it fails as xsk_socket__create() is asynchronous */ - if (ctr >= SOCK_RECONF_CTR) - exit_with_error(-ret); - usleep(USLEEP_MAX); - } - if (ifobject->busy_poll) - enable_busy_poll(&ifobject->xsk_arr[i]); - } -} - -static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobject) -{ - xsk_configure_socket(test, ifobject, test->ifobj_rx->umem, true); - ifobject->xsk = &ifobject->xsk_arr[0]; - ifobject->xskmap = test->ifobj_rx->xskmap; - memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info)); - ifobject->umem->base_addr = 0; -} - -static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, - bool fill_up) -{ - u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM; - u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts; - int ret; - - if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) - buffers_to_fill = umem->num_frames; - else - buffers_to_fill = umem->fill_size; - - ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx); - if (ret != buffers_to_fill) - exit_with_error(ENOSPC); - - while (filled < buffers_to_fill) { - struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts); - u64 addr; - u32 i; - - for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) { - if (!pkt) { - if (!fill_up) - break; - addr = filled * umem->frame_size + umem->base_addr; - } else if (pkt->offset >= 0) { - addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem); - } else { - addr = pkt->offset + umem_alloc_buffer(umem); - } - - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; - if (++filled >= buffers_to_fill) - break; - } - } - xsk_ring_prod__submit(&umem->fq, filled); - xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled); - - pkt_stream_reset(pkt_stream); - umem_reset_alloc(umem); -} - -static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) -{ - u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; - int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; - LIBBPF_OPTS(bpf_xdp_query_opts, opts); - void *bufs; - int ret; - u32 i; - - if (ifobject->umem->unaligned_mode) - mmap_flags |= MAP_HUGETLB | MAP_HUGE_2MB; - - if (ifobject->shared_umem) - umem_sz *= 2; - - bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); - - ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz); - if (ret) - exit_with_error(-ret); - - xsk_configure_socket(test, ifobject, ifobject->umem, false); - - ifobject->xsk = &ifobject->xsk_arr[0]; - - if (!ifobject->rx_on) - return; - - xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream, ifobject->use_fill_ring); - - for (i = 0; i < test->nb_sockets; i++) { - ifobject->xsk = &ifobject->xsk_arr[i]; - ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, i); - if (ret) - exit_with_error(errno); - } -} - -static void *worker_testapp_validate_tx(void *arg) -{ - struct test_spec *test = (struct test_spec *)arg; - struct ifobject *ifobject = test->ifobj_tx; - int err; - - if (test->current_step == 1) { - if (!ifobject->shared_umem) - thread_common_ops(test, ifobject); - else - thread_common_ops_tx(test, ifobject); - } - - err = send_pkts(test, ifobject); - - if (!err && ifobject->validation_func) - err = ifobject->validation_func(ifobject); - if (err) - report_failure(test); - - pthread_exit(NULL); -} - -static void *worker_testapp_validate_rx(void *arg) -{ - struct test_spec *test = (struct test_spec *)arg; - struct ifobject *ifobject = test->ifobj_rx; - int err; - - if (test->current_step == 1) { - thread_common_ops(test, ifobject); - } else { - xsk_clear_xskmap(ifobject->xskmap); - err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0); - if (err) { - ksft_print_msg("Error: Failed to update xskmap, error %s\n", - strerror(-err)); - exit_with_error(-err); - } - } - - pthread_barrier_wait(&barr); - - err = receive_pkts(test); - - if (!err && ifobject->validation_func) - err = ifobject->validation_func(ifobject); - - if (err) { - if (test->adjust_tail && !is_adjust_tail_supported(ifobject->xdp_progs)) - test->adjust_tail_support = false; - else - report_failure(test); - } - - pthread_exit(NULL); -} - -static u64 ceil_u64(u64 a, u64 b) -{ - return (a + b - 1) / b; -} - -static void testapp_clean_xsk_umem(struct ifobject *ifobj) -{ - u64 umem_sz = ifobj->umem->num_frames * ifobj->umem->frame_size; - - if (ifobj->shared_umem) - umem_sz *= 2; - - umem_sz = ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - xsk_umem__delete(ifobj->umem->umem); - munmap(ifobj->umem->buffer, umem_sz); -} - -static void handler(int signum) -{ - pthread_exit(NULL); -} - -static bool xdp_prog_changed_rx(struct test_spec *test) -{ - struct ifobject *ifobj = test->ifobj_rx; - - return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode; -} - -static bool xdp_prog_changed_tx(struct test_spec *test) -{ - struct ifobject *ifobj = test->ifobj_tx; - - return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode; -} - -static void xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog, - struct bpf_map *xskmap, enum test_mode mode) -{ - int err; - - xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode)); - err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode)); - if (err) { - ksft_print_msg("Error attaching XDP program\n"); - exit_with_error(-err); - } - - if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC)) - if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) { - ksft_print_msg("ERROR: XDP prog not in DRV mode\n"); - exit_with_error(EINVAL); - } - - ifobj->xdp_prog = xdp_prog; - ifobj->xskmap = xskmap; - ifobj->mode = mode; -} - -static void xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx, - struct ifobject *ifobj_tx) -{ - if (xdp_prog_changed_rx(test)) - xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode); - - if (!ifobj_tx || ifobj_tx->shared_umem) - return; - - if (xdp_prog_changed_tx(test)) - xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode); -} - -static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1, - struct ifobject *ifobj2) -{ - pthread_t t0, t1; - int err; - - if (test->mtu > MAX_ETH_PKT_SIZE) { - if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp || - (ifobj2 && !ifobj2->multi_buff_zc_supp))) { - ksft_test_result_skip("Multi buffer for zero-copy not supported.\n"); - return TEST_SKIP; - } - if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp || - (ifobj2 && !ifobj2->multi_buff_supp))) { - ksft_test_result_skip("Multi buffer not supported.\n"); - return TEST_SKIP; - } - } - err = test_spec_set_mtu(test, test->mtu); - if (err) { - ksft_print_msg("Error, could not set mtu.\n"); - exit_with_error(err); - } - - if (ifobj2) { - if (pthread_barrier_init(&barr, NULL, 2)) - exit_with_error(errno); - pkt_stream_reset(ifobj2->xsk->pkt_stream); - } - - test->current_step++; - pkt_stream_reset(ifobj1->xsk->pkt_stream); - pkts_in_flight = 0; - - signal(SIGUSR1, handler); - /*Spawn RX thread */ - pthread_create(&t0, NULL, ifobj1->func_ptr, test); - - if (ifobj2) { - pthread_barrier_wait(&barr); - if (pthread_barrier_destroy(&barr)) - exit_with_error(errno); - - /*Spawn TX thread */ - pthread_create(&t1, NULL, ifobj2->func_ptr, test); - - pthread_join(t1, NULL); - } - - if (!ifobj2) - pthread_kill(t0, SIGUSR1); - else - pthread_join(t0, NULL); - - if (test->total_steps == test->current_step || test->fail) { - u32 i; - - if (ifobj2) - for (i = 0; i < test->nb_sockets; i++) - xsk_socket__delete(ifobj2->xsk_arr[i].xsk); - - for (i = 0; i < test->nb_sockets; i++) - xsk_socket__delete(ifobj1->xsk_arr[i].xsk); - - testapp_clean_xsk_umem(ifobj1); - if (ifobj2 && !ifobj2->shared_umem) - testapp_clean_xsk_umem(ifobj2); - } - - return !!test->fail; -} - -static int testapp_validate_traffic(struct test_spec *test) -{ - struct ifobject *ifobj_rx = test->ifobj_rx; - struct ifobject *ifobj_tx = test->ifobj_tx; - - if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) || - (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) { - ksft_test_result_skip("No huge pages present.\n"); - return TEST_SKIP; - } - - if (test->set_ring) { - if (ifobj_tx->hw_ring_size_supp) { - if (set_ring_size(ifobj_tx)) { - ksft_test_result_skip("Failed to change HW ring size.\n"); - return TEST_FAILURE; - } - } else { - ksft_test_result_skip("Changing HW ring size not supported.\n"); - return TEST_SKIP; - } - } - - xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx); - return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx); -} - -static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj) -{ - return __testapp_validate_traffic(test, ifobj, NULL); -} - -static int testapp_teardown(struct test_spec *test) -{ - int i; - - for (i = 0; i < MAX_TEARDOWN_ITER; i++) { - if (testapp_validate_traffic(test)) - return TEST_FAILURE; - test_spec_reset(test); - } - - return TEST_PASS; -} - -static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) -{ - thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr; - struct ifobject *tmp_ifobj = (*ifobj1); - - (*ifobj1)->func_ptr = (*ifobj2)->func_ptr; - (*ifobj2)->func_ptr = tmp_func_ptr; - - *ifobj1 = *ifobj2; - *ifobj2 = tmp_ifobj; -} - -static int testapp_bidirectional(struct test_spec *test) -{ - int res; - - test->ifobj_tx->rx_on = true; - test->ifobj_rx->tx_on = true; - test->total_steps = 2; - if (testapp_validate_traffic(test)) - return TEST_FAILURE; - - print_verbose("Switching Tx/Rx direction\n"); - swap_directions(&test->ifobj_rx, &test->ifobj_tx); - res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx); - - swap_directions(&test->ifobj_rx, &test->ifobj_tx); - return res; -} - -static int swap_xsk_resources(struct test_spec *test) -{ - int ret; - - test->ifobj_tx->xsk_arr[0].pkt_stream = NULL; - test->ifobj_rx->xsk_arr[0].pkt_stream = NULL; - test->ifobj_tx->xsk_arr[1].pkt_stream = test->tx_pkt_stream_default; - test->ifobj_rx->xsk_arr[1].pkt_stream = test->rx_pkt_stream_default; - test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1]; - test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1]; - - ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk, 0); - if (ret) - return TEST_FAILURE; - - return TEST_PASS; -} - -static int testapp_xdp_prog_cleanup(struct test_spec *test) -{ - test->total_steps = 2; - test->nb_sockets = 2; - if (testapp_validate_traffic(test)) - return TEST_FAILURE; - - if (swap_xsk_resources(test)) - return TEST_FAILURE; - return testapp_validate_traffic(test); -} - -static int testapp_headroom(struct test_spec *test) -{ - test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE; - return testapp_validate_traffic(test); -} - -static int testapp_stats_rx_dropped(struct test_spec *test) -{ - if (test->mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n"); - return TEST_SKIP; - } - - pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0); - test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3; - pkt_stream_receive_half(test); - test->ifobj_rx->validation_func = validate_rx_dropped; - return testapp_validate_traffic(test); -} - -static int testapp_stats_tx_invalid_descs(struct test_spec *test) -{ - pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0); - test->ifobj_tx->validation_func = validate_tx_invalid_descs; - return testapp_validate_traffic(test); -} - -static int testapp_stats_rx_full(struct test_spec *test) -{ - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); - - test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; - test->ifobj_rx->release_rx = false; - test->ifobj_rx->validation_func = validate_rx_full; - return testapp_validate_traffic(test); -} - -static int testapp_stats_fill_empty(struct test_spec *test) -{ - pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); - - test->ifobj_rx->use_fill_ring = false; - test->ifobj_rx->validation_func = validate_fill_empty; - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_unaligned(struct test_spec *test) -{ - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - /* Let half of the packets straddle a 4K buffer boundary */ - pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2); - - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_unaligned_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); - return testapp_validate_traffic(test); -} - -static int testapp_single_pkt(struct test_spec *test) -{ - struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}}; - - pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE); - - return testapp_validate_traffic(test); -} - -static int testapp_invalid_desc_mb(struct test_spec *test) -{ - struct xsk_umem_info *umem = test->ifobj_tx->umem; - u64 umem_size = umem->num_frames * umem->frame_size; - struct pkt pkts[] = { - /* Valid packet for synch to start with */ - {0, MIN_PKT_SIZE, 0, true, 0}, - /* Zero frame len is not legal */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, 0, 0, false, 0}, - /* Invalid address in the second frame */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - /* Invalid len in the middle */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - /* Invalid options in the middle */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION}, - /* Transmit 2 frags, receive 3 */ - {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD}, - {0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0}, - /* Middle frame crosses chunk boundary with small length */ - {0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD}, - {-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0}, - /* Valid packet for synch so that something is received */ - {0, MIN_PKT_SIZE, 0, true, 0}}; - - if (umem->unaligned_mode) { - /* Crossing a chunk boundary allowed */ - pkts[12].valid = true; - pkts[13].valid = true; - } - - test->mtu = MAX_ETH_JUMBO_SIZE; - pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - return testapp_validate_traffic(test); -} - -static int testapp_invalid_desc(struct test_spec *test) -{ - struct xsk_umem_info *umem = test->ifobj_tx->umem; - u64 umem_size = umem->num_frames * umem->frame_size; - struct pkt pkts[] = { - /* Zero packet address allowed */ - {0, MIN_PKT_SIZE, 0, true}, - /* Allowed packet */ - {0, MIN_PKT_SIZE, 0, true}, - /* Straddling the start of umem */ - {-2, MIN_PKT_SIZE, 0, false}, - /* Packet too large */ - {0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, - /* Up to end of umem allowed */ - {umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true}, - /* After umem ends */ - {umem_size, MIN_PKT_SIZE, 0, false}, - /* Straddle the end of umem */ - {umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, - /* Straddle a 4K boundary */ - {0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false}, - /* Straddle a 2K boundary */ - {0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true}, - /* Valid packet for synch so that something is received */ - {0, MIN_PKT_SIZE, 0, true}}; - - if (umem->unaligned_mode) { - /* Crossing a page boundary allowed */ - pkts[7].valid = true; - } - if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { - /* Crossing a 2K frame size boundary not allowed */ - pkts[8].valid = false; - } - - if (test->ifobj_tx->shared_umem) { - pkts[4].offset += umem_size; - pkts[5].offset += umem_size; - pkts[6].offset += umem_size; - } - - pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); - return testapp_validate_traffic(test); -} - -static int testapp_xdp_drop(struct test_spec *test) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop, - skel_rx->maps.xsk, skel_tx->maps.xsk); - - pkt_stream_receive_half(test); - return testapp_validate_traffic(test); -} - -static int testapp_xdp_metadata_copy(struct test_spec *test) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata, - skel_tx->progs.xsk_xdp_populate_metadata, - skel_rx->maps.xsk, skel_tx->maps.xsk); - test->ifobj_rx->use_metadata = true; - - skel_rx->bss->count = 0; - - return testapp_validate_traffic(test); -} - -static int testapp_xdp_shared_umem(struct test_spec *test) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test->total_steps = 1; - test->nb_sockets = 2; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_shared_umem, - skel_tx->progs.xsk_xdp_shared_umem, - skel_rx->maps.xsk, skel_tx->maps.xsk); - - pkt_stream_even_odd_sequence(test); - - return testapp_validate_traffic(test); -} - -static int testapp_poll_txq_tmout(struct test_spec *test) -{ - test->ifobj_tx->use_poll = true; - /* create invalid frame by set umem frame_size and pkt length equal to 2048 */ - test->ifobj_tx->umem->frame_size = 2048; - pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048); - return testapp_validate_traffic_single_thread(test, test->ifobj_tx); -} - -static int testapp_poll_rxq_tmout(struct test_spec *test) -{ - test->ifobj_rx->use_poll = true; - return testapp_validate_traffic_single_thread(test, test->ifobj_rx); -} - -static int testapp_too_many_frags(struct test_spec *test) -{ - struct pkt *pkts; - u32 max_frags, i; - int ret; - - if (test->mode == TEST_MODE_ZC) { - max_frags = test->ifobj_tx->xdp_zc_max_segs; - } else { - max_frags = get_max_skb_frags(); - if (!max_frags) { - ksft_print_msg("Couldn't retrieve MAX_SKB_FRAGS from system, using default (17) value\n"); - max_frags = 17; - } - max_frags += 1; - } - - pkts = calloc(2 * max_frags + 2, sizeof(struct pkt)); - if (!pkts) - return TEST_FAILURE; - - test->mtu = MAX_ETH_JUMBO_SIZE; - - /* Valid packet for synch */ - pkts[0].len = MIN_PKT_SIZE; - pkts[0].valid = true; - - /* One valid packet with the max amount of frags */ - for (i = 1; i < max_frags + 1; i++) { - pkts[i].len = MIN_PKT_SIZE; - pkts[i].options = XDP_PKT_CONTD; - pkts[i].valid = true; - } - pkts[max_frags].options = 0; - - /* An invalid packet with the max amount of frags but signals packet - * continues on the last frag - */ - for (i = max_frags + 1; i < 2 * max_frags + 1; i++) { - pkts[i].len = MIN_PKT_SIZE; - pkts[i].options = XDP_PKT_CONTD; - pkts[i].valid = false; - } - - /* Valid packet for synch */ - pkts[2 * max_frags + 1].len = MIN_PKT_SIZE; - pkts[2 * max_frags + 1].valid = true; - - pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2); - ret = testapp_validate_traffic(test); - - free(pkts); - return ret; -} - -static int xsk_load_xdp_programs(struct ifobject *ifobj) -{ - ifobj->xdp_progs = xsk_xdp_progs__open_and_load(); - if (libbpf_get_error(ifobj->xdp_progs)) - return libbpf_get_error(ifobj->xdp_progs); - - return 0; -} - static void xsk_unload_xdp_programs(struct ifobject *ifobj) { xsk_xdp_progs__destroy(ifobj->xdp_progs); } -/* Simple test */ -static bool hugepages_present(void) -{ - size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE; - void *bufs; - - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB); - if (bufs == MAP_FAILED) - return false; - - mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE; - munmap(bufs, mmap_sz); - return true; -} - -static void init_iface(struct ifobject *ifobj, thread_func_t func_ptr) -{ - LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); - int err; - - ifobj->func_ptr = func_ptr; - - err = xsk_load_xdp_programs(ifobj); - if (err) { - ksft_print_msg("Error loading XDP program\n"); - exit_with_error(err); - } - - if (hugepages_present()) - ifobj->unaligned_supp = true; - - err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts); - if (err) { - ksft_print_msg("Error querying XDP capabilities\n"); - exit_with_error(-err); - } - if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG) - ifobj->multi_buff_supp = true; - if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) { - if (query_opts.xdp_zc_max_segs > 1) { - ifobj->multi_buff_zc_supp = true; - ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs; - } else { - ifobj->xdp_zc_max_segs = 0; - } - } -} - -static int testapp_send_receive(struct test_spec *test) -{ - return testapp_validate_traffic(test); -} - -static int testapp_send_receive_2k_frame(struct test_spec *test) -{ - test->ifobj_tx->umem->frame_size = 2048; - test->ifobj_rx->umem->frame_size = 2048; - pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); - return testapp_validate_traffic(test); -} - -static int testapp_poll_rx(struct test_spec *test) -{ - test->ifobj_rx->use_poll = true; - return testapp_validate_traffic(test); -} - -static int testapp_poll_tx(struct test_spec *test) -{ - test->ifobj_tx->use_poll = true; - return testapp_validate_traffic(test); -} - -static int testapp_aligned_inv_desc(struct test_spec *test) -{ - return testapp_invalid_desc(test); -} - -static int testapp_aligned_inv_desc_2k_frame(struct test_spec *test) -{ - test->ifobj_tx->umem->frame_size = 2048; - test->ifobj_rx->umem->frame_size = 2048; - return testapp_invalid_desc(test); -} - -static int testapp_unaligned_inv_desc(struct test_spec *test) -{ - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - return testapp_invalid_desc(test); -} - -static int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test) -{ - u64 page_size, umem_size; - - /* Odd frame size so the UMEM doesn't end near a page boundary. */ - test->ifobj_tx->umem->frame_size = 4001; - test->ifobj_rx->umem->frame_size = 4001; - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - /* This test exists to test descriptors that staddle the end of - * the UMEM but not a page. - */ - page_size = sysconf(_SC_PAGESIZE); - umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size; - assert(umem_size % page_size > MIN_PKT_SIZE); - assert(umem_size % page_size < page_size - MIN_PKT_SIZE); - - return testapp_invalid_desc(test); -} - -static int testapp_aligned_inv_desc_mb(struct test_spec *test) -{ - return testapp_invalid_desc_mb(test); -} - -static int testapp_unaligned_inv_desc_mb(struct test_spec *test) -{ - test->ifobj_tx->umem->unaligned_mode = true; - test->ifobj_rx->umem->unaligned_mode = true; - return testapp_invalid_desc_mb(test); -} - -static int testapp_xdp_metadata(struct test_spec *test) -{ - return testapp_xdp_metadata_copy(test); -} - -static int testapp_xdp_metadata_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - return testapp_xdp_metadata_copy(test); -} - -static int testapp_hw_sw_min_ring_size(struct test_spec *test) -{ - int ret; - - test->set_ring = true; - test->total_steps = 2; - test->ifobj_tx->ring.tx_pending = DEFAULT_BATCH_SIZE; - test->ifobj_tx->ring.rx_pending = DEFAULT_BATCH_SIZE * 2; - test->ifobj_tx->xsk->batch_size = 1; - test->ifobj_rx->xsk->batch_size = 1; - ret = testapp_validate_traffic(test); - if (ret) - return ret; - - /* Set batch size to hw_ring_size - 1 */ - test->ifobj_tx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; - test->ifobj_rx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1; - return testapp_validate_traffic(test); -} - -static int testapp_hw_sw_max_ring_size(struct test_spec *test) -{ - u32 max_descs = XSK_RING_PROD__DEFAULT_NUM_DESCS * 4; - int ret; - - test->set_ring = true; - test->total_steps = 2; - test->ifobj_tx->ring.tx_pending = test->ifobj_tx->ring.tx_max_pending; - test->ifobj_tx->ring.rx_pending = test->ifobj_tx->ring.rx_max_pending; - test->ifobj_rx->umem->num_frames = max_descs; - test->ifobj_rx->umem->fill_size = max_descs; - test->ifobj_rx->umem->comp_size = max_descs; - test->ifobj_tx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - test->ifobj_rx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - - ret = testapp_validate_traffic(test); - if (ret) - return ret; - - /* Set batch_size to 8152 for testing, as the ice HW ignores the 3 lowest bits when - * updating the Rx HW tail register. - */ - test->ifobj_tx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; - test->ifobj_rx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8; - pkt_stream_replace(test, max_descs, MIN_PKT_SIZE); - return testapp_validate_traffic(test); -} - -static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value) -{ - struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs; - struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs; - - test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail, - skel_tx->progs.xsk_xdp_adjust_tail, - skel_rx->maps.xsk, skel_tx->maps.xsk); - - skel_rx->bss->adjust_value = adjust_value; - - return testapp_validate_traffic(test); -} - -static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len) -{ - int ret; - - test->adjust_tail_support = true; - test->adjust_tail = true; - test->total_steps = 1; - - pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len); - pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value); - - ret = testapp_xdp_adjust_tail(test, value); - if (ret) - return ret; - - if (!test->adjust_tail_support) { - ksft_test_result_skip("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n", - mode_string(test), busy_poll_string(test)); - return TEST_SKIP; - } - - return 0; -} - -static int testapp_adjust_tail_shrink(struct test_spec *test) -{ - /* Shrink by 4 bytes for testing purpose */ - return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2); -} - -static int testapp_adjust_tail_shrink_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - /* Shrink by the frag size */ - return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2); -} - -static int testapp_adjust_tail_grow(struct test_spec *test) -{ - /* Grow by 4 bytes for testing purpose */ - return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2); -} - -static int testapp_adjust_tail_grow_mb(struct test_spec *test) -{ - test->mtu = MAX_ETH_JUMBO_SIZE; - /* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */ - return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1, - XSK_UMEM__LARGE_FRAME_SIZE * 2); -} - -static int testapp_tx_queue_consumer(struct test_spec *test) -{ - int nr_packets; - - if (test->mode == TEST_MODE_ZC) { - ksft_test_result_skip("Can not run TX_QUEUE_CONSUMER test for ZC mode\n"); - return TEST_SKIP; - } - - nr_packets = MAX_TX_BUDGET_DEFAULT + 1; - pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE); - test->ifobj_tx->xsk->batch_size = nr_packets; - test->ifobj_tx->xsk->check_consumer = true; - - return testapp_validate_traffic(test); -} - static void run_pkt_test(struct test_spec *test) { int ret; ret = test->test_func(test); - if (ret == TEST_PASS) + switch (ret) { + case TEST_PASS: ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test), test->name); - pkt_stream_restore_default(test); -} - -static struct ifobject *ifobject_create(void) -{ - struct ifobject *ifobj; - - ifobj = calloc(1, sizeof(struct ifobject)); - if (!ifobj) - return NULL; - - ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr)); - if (!ifobj->xsk_arr) - goto out_xsk_arr; - - ifobj->umem = calloc(1, sizeof(*ifobj->umem)); - if (!ifobj->umem) - goto out_umem; - - return ifobj; - -out_umem: - free(ifobj->xsk_arr); -out_xsk_arr: - free(ifobj); - return NULL; -} + break; + case TEST_SKIP: + ksft_test_result_skip("SKIP: %s %s%s\n", mode_string(test), busy_poll_string(test), + test->name); + break; + case TEST_FAILURE: + ksft_test_result_fail("FAIL: %s %s%s\n", mode_string(test), busy_poll_string(test), + test->name); + break; + default: + ksft_test_result_fail("FAIL: %s %s%s -- Unexpected returned value (%d)\n", + mode_string(test), busy_poll_string(test), test->name, ret); + } -static void ifobject_delete(struct ifobject *ifobj) -{ - free(ifobj->umem); - free(ifobj->xsk_arr); - free(ifobj); + pkt_stream_restore_default(test); } static bool is_xdp_supported(int ifindex) @@ -2726,47 +319,6 @@ static bool is_xdp_supported(int ifindex) return true; } -static const struct test_spec tests[] = { - {.name = "SEND_RECEIVE", .test_func = testapp_send_receive}, - {.name = "SEND_RECEIVE_2K_FRAME", .test_func = testapp_send_receive_2k_frame}, - {.name = "SEND_RECEIVE_SINGLE_PKT", .test_func = testapp_single_pkt}, - {.name = "POLL_RX", .test_func = testapp_poll_rx}, - {.name = "POLL_TX", .test_func = testapp_poll_tx}, - {.name = "POLL_RXQ_FULL", .test_func = testapp_poll_rxq_tmout}, - {.name = "POLL_TXQ_FULL", .test_func = testapp_poll_txq_tmout}, - {.name = "SEND_RECEIVE_UNALIGNED", .test_func = testapp_send_receive_unaligned}, - {.name = "ALIGNED_INV_DESC", .test_func = testapp_aligned_inv_desc}, - {.name = "ALIGNED_INV_DESC_2K_FRAME_SIZE", .test_func = testapp_aligned_inv_desc_2k_frame}, - {.name = "UNALIGNED_INV_DESC", .test_func = testapp_unaligned_inv_desc}, - {.name = "UNALIGNED_INV_DESC_4001_FRAME_SIZE", - .test_func = testapp_unaligned_inv_desc_4001_frame}, - {.name = "UMEM_HEADROOM", .test_func = testapp_headroom}, - {.name = "TEARDOWN", .test_func = testapp_teardown}, - {.name = "BIDIRECTIONAL", .test_func = testapp_bidirectional}, - {.name = "STAT_RX_DROPPED", .test_func = testapp_stats_rx_dropped}, - {.name = "STAT_TX_INVALID", .test_func = testapp_stats_tx_invalid_descs}, - {.name = "STAT_RX_FULL", .test_func = testapp_stats_rx_full}, - {.name = "STAT_FILL_EMPTY", .test_func = testapp_stats_fill_empty}, - {.name = "XDP_PROG_CLEANUP", .test_func = testapp_xdp_prog_cleanup}, - {.name = "XDP_DROP_HALF", .test_func = testapp_xdp_drop}, - {.name = "XDP_SHARED_UMEM", .test_func = testapp_xdp_shared_umem}, - {.name = "XDP_METADATA_COPY", .test_func = testapp_xdp_metadata}, - {.name = "XDP_METADATA_COPY_MULTI_BUFF", .test_func = testapp_xdp_metadata_mb}, - {.name = "SEND_RECEIVE_9K_PACKETS", .test_func = testapp_send_receive_mb}, - {.name = "SEND_RECEIVE_UNALIGNED_9K_PACKETS", - .test_func = testapp_send_receive_unaligned_mb}, - {.name = "ALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_aligned_inv_desc_mb}, - {.name = "UNALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_unaligned_inv_desc_mb}, - {.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags}, - {.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size}, - {.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size}, - {.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink}, - {.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb}, - {.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow}, - {.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb}, - {.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer}, - }; - static void print_tests(void) { u32 i; @@ -2774,10 +326,13 @@ static void print_tests(void) printf("Tests:\n"); for (i = 0; i < ARRAY_SIZE(tests); i++) printf("%u: %s\n", i, tests[i].name); + for (i = ARRAY_SIZE(tests); i < ARRAY_SIZE(tests) + ARRAY_SIZE(ci_skip_tests); i++) + printf("%u: %s\n", i, ci_skip_tests[i - ARRAY_SIZE(tests)].name); } int main(int argc, char **argv) { + const size_t total_tests = ARRAY_SIZE(tests) + ARRAY_SIZE(ci_skip_tests); struct pkt_stream *rx_pkt_stream_default; struct pkt_stream *tx_pkt_stream_default; struct ifobject *ifobj_tx, *ifobj_rx; @@ -2805,7 +360,7 @@ int main(int argc, char **argv) print_tests(); ksft_exit_xpass(); } - if (opt_run_test != RUN_ALL_TESTS && opt_run_test >= ARRAY_SIZE(tests)) { + if (opt_run_test != RUN_ALL_TESTS && opt_run_test >= total_tests) { ksft_print_msg("Error: test %u does not exist.\n", opt_run_test); ksft_exit_xfail(); } @@ -2830,10 +385,13 @@ int main(int argc, char **argv) ifobj_tx->set_ring.default_rx = ifobj_tx->ring.rx_pending; } - init_iface(ifobj_rx, worker_testapp_validate_rx); - init_iface(ifobj_tx, worker_testapp_validate_tx); + if (init_iface(ifobj_rx, worker_testapp_validate_rx) || + init_iface(ifobj_tx, worker_testapp_validate_tx)) { + ksft_print_msg("Error : can't initialize interfaces\n"); + ksft_exit_xfail(); + } - test_spec_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]); + test_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]); tx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE); rx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE); if (!tx_pkt_stream_default || !rx_pkt_stream_default) @@ -2842,7 +400,7 @@ int main(int argc, char **argv) test.rx_pkt_stream_default = rx_pkt_stream_default; if (opt_run_test == RUN_ALL_TESTS) - nb_tests = ARRAY_SIZE(tests); + nb_tests = total_tests; else nb_tests = 1; if (opt_mode == TEST_MODE_ALL) { @@ -2864,11 +422,15 @@ int main(int argc, char **argv) if (opt_mode != TEST_MODE_ALL && i != opt_mode) continue; - for (j = 0; j < ARRAY_SIZE(tests); j++) { + for (j = 0; j < total_tests; j++) { if (opt_run_test != RUN_ALL_TESTS && j != opt_run_test) continue; - test_spec_init(&test, ifobj_tx, ifobj_rx, i, &tests[j]); + if (j < ARRAY_SIZE(tests)) + test_init(&test, ifobj_tx, ifobj_rx, i, &tests[j]); + else + test_init(&test, ifobj_tx, ifobj_rx, i, + &ci_skip_tests[j - ARRAY_SIZE(tests)]); run_pkt_test(&test); usleep(USLEEP_MAX); diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h index 4df3a5d329ac..3ca518df23ad 100644 --- a/tools/testing/selftests/bpf/xskxceiver.h +++ b/tools/testing/selftests/bpf/xskxceiver.h @@ -22,169 +22,13 @@ #define PF_XDP AF_XDP #endif -#ifndef SO_BUSY_POLL_BUDGET -#define SO_BUSY_POLL_BUDGET 70 -#endif - -#ifndef SO_PREFER_BUSY_POLL -#define SO_PREFER_BUSY_POLL 69 -#endif - -#define TEST_PASS 0 -#define TEST_FAILURE -1 -#define TEST_CONTINUE 1 -#define TEST_SKIP 2 -#define MAX_INTERFACES 2 -#define MAX_INTERFACE_NAME_CHARS 16 -#define MAX_TEST_NAME_SIZE 48 #define MAX_TEARDOWN_ITER 10 -#define PKT_HDR_SIZE (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */ -#define MIN_PKT_SIZE 64 -#define MAX_ETH_PKT_SIZE 1518 #define MAX_ETH_JUMBO_SIZE 9000 -#define USLEEP_MAX 10000 #define SOCK_RECONF_CTR 10 -#define DEFAULT_BATCH_SIZE 64 -#define POLL_TMOUT 1000 -#define THREAD_TMOUT 3 -#define DEFAULT_PKT_CNT (4 * 1024) -#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) #define RX_FULL_RXQSIZE 32 #define UMEM_HEADROOM_TEST_SIZE 128 #define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1) -#define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024) -#define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024) -#define XSK_DESC__INVALID_OPTION (0xffff) -#define HUGEPAGE_SIZE (2 * 1024 * 1024) -#define PKT_DUMP_NB_TO_PRINT 16 #define RUN_ALL_TESTS UINT_MAX #define NUM_MAC_ADDRESSES 4 -#define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) - -enum test_mode { - TEST_MODE_SKB, - TEST_MODE_DRV, - TEST_MODE_ZC, - TEST_MODE_ALL -}; - -struct xsk_umem_info { - struct xsk_ring_prod fq; - struct xsk_ring_cons cq; - struct xsk_umem *umem; - u64 next_buffer; - u32 num_frames; - u32 frame_headroom; - void *buffer; - u32 frame_size; - u32 base_addr; - u32 fill_size; - u32 comp_size; - bool unaligned_mode; -}; - -struct xsk_socket_info { - struct xsk_ring_cons rx; - struct xsk_ring_prod tx; - struct xsk_umem_info *umem; - struct xsk_socket *xsk; - struct pkt_stream *pkt_stream; - u32 outstanding_tx; - u32 rxqsize; - u32 batch_size; - u8 dst_mac[ETH_ALEN]; - u8 src_mac[ETH_ALEN]; - bool check_consumer; -}; - -struct pkt { - int offset; - u32 len; - u32 pkt_nb; - bool valid; - u16 options; -}; - -struct pkt_stream { - u32 nb_pkts; - u32 current_pkt_nb; - struct pkt *pkts; - u32 max_pkt_len; - u32 nb_rx_pkts; - u32 nb_valid_entries; - bool verbatim; -}; - -struct set_hw_ring { - u32 default_tx; - u32 default_rx; -}; - -struct ifobject; -struct test_spec; -typedef int (*validation_func_t)(struct ifobject *ifobj); -typedef void *(*thread_func_t)(void *arg); -typedef int (*test_func_t)(struct test_spec *test); - -struct ifobject { - char ifname[MAX_INTERFACE_NAME_CHARS]; - struct xsk_socket_info *xsk; - struct xsk_socket_info *xsk_arr; - struct xsk_umem_info *umem; - thread_func_t func_ptr; - validation_func_t validation_func; - struct xsk_xdp_progs *xdp_progs; - struct bpf_map *xskmap; - struct bpf_program *xdp_prog; - struct ethtool_ringparam ring; - struct set_hw_ring set_ring; - enum test_mode mode; - int ifindex; - int mtu; - u32 bind_flags; - u32 xdp_zc_max_segs; - bool tx_on; - bool rx_on; - bool use_poll; - bool busy_poll; - bool use_fill_ring; - bool release_rx; - bool shared_umem; - bool use_metadata; - bool unaligned_supp; - bool multi_buff_supp; - bool multi_buff_zc_supp; - bool hw_ring_size_supp; -}; - -struct test_spec { - struct ifobject *ifobj_tx; - struct ifobject *ifobj_rx; - struct pkt_stream *tx_pkt_stream_default; - struct pkt_stream *rx_pkt_stream_default; - struct bpf_program *xdp_prog_rx; - struct bpf_program *xdp_prog_tx; - struct bpf_map *xskmap_rx; - struct bpf_map *xskmap_tx; - test_func_t test_func; - int mtu; - u16 total_steps; - u16 current_step; - u16 nb_sockets; - bool fail; - bool set_ring; - bool adjust_tail; - bool adjust_tail_support; - enum test_mode mode; - char name[MAX_TEST_NAME_SIZE]; -}; - -pthread_barrier_t barr; -pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER; - -int pkts_in_flight; - -static const u8 g_mac[ETH_ALEN] = {0x55, 0x44, 0x33, 0x22, 0x11, 0x00}; - #endif /* XSKXCEIVER_H_ */ diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore index 585ecb4d5dc4..3633c7a3ed65 100644 --- a/tools/testing/selftests/drivers/net/.gitignore +++ b/tools/testing/selftests/drivers/net/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only +gro napi_id_helper psp_responder diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 71ee69e524d7..f5c71d993750 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -6,10 +6,12 @@ TEST_INCLUDES := $(wildcard lib/py/*.py) \ ../../net/lib.sh \ TEST_GEN_FILES := \ + gro \ napi_id_helper \ # end of TEST_GEN_FILES TEST_PROGS := \ + gro.py \ hds.py \ napi_id.py \ napi_threaded.py \ @@ -23,6 +25,7 @@ TEST_PROGS := \ ping.py \ psp.py \ queues.py \ + ring_reconfig.py \ shaper.py \ stats.py \ xdp.py \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh index c4711272fe45..559f300f965a 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh @@ -30,6 +30,7 @@ check_connection() local message=${3} RET=0 + sleep 0.25 ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null check_err $? "ping failed" log_test "${bond_mode}/${xvlan_type}_${xvlan_mode}: ${message}" diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/drivers/net/gro.c index cfc39f70635d..995b492f5bcb 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/drivers/net/gro.c @@ -57,7 +57,8 @@ #include <string.h> #include <unistd.h> -#include "../kselftest.h" +#include "../../kselftest.h" +#include "../../net/lib/ksft.h" #define DPORT 8000 #define SPORT 1500 @@ -1127,6 +1128,8 @@ static void gro_receiver(void) set_timeout(rxfd); bind_packetsocket(rxfd); + ksft_ready(); + memset(correct_payload, 0, sizeof(correct_payload)); if (strcmp(testname, "data") == 0) { diff --git a/tools/testing/selftests/drivers/net/gro.py b/tools/testing/selftests/drivers/net/gro.py new file mode 100755 index 000000000000..ba83713bf7b5 --- /dev/null +++ b/tools/testing/selftests/drivers/net/gro.py @@ -0,0 +1,164 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +GRO (Generic Receive Offload) conformance tests. + +Validates that GRO coalescing works correctly by running the gro +binary in different configurations and checking for correct packet +coalescing behavior. + +Test cases: + - data: Data packets with same size/headers and correct seq numbers coalesce + - ack: Pure ACK packets do not coalesce + - flags: Packets with PSH, SYN, URG, RST flags do not coalesce + - tcp: Packets with incorrect checksum, non-consecutive seqno don't coalesce + - ip: Packets with different ECN, TTL, TOS, or IP options don't coalesce + - large: Packets larger than GRO_MAX_SIZE don't coalesce +""" + +import os +from lib.py import ksft_run, ksft_exit, ksft_pr +from lib.py import NetDrvEpEnv, KsftXfailEx +from lib.py import cmd, defer, bkg, ip +from lib.py import ksft_variants + + +def _resolve_dmac(cfg, ipver): + """ + Find the destination MAC address remote host should use to send packets + towards the local host. It may be a router / gateway address. + """ + + attr = "dmac" + ipver + # Cache the response across test cases + if hasattr(cfg, attr): + return getattr(cfg, attr) + + route = ip(f"-{ipver} route get {cfg.addr_v[ipver]}", + json=True, host=cfg.remote)[0] + gw = route.get("gateway") + # Local L2 segment, address directly + if not gw: + setattr(cfg, attr, cfg.dev['address']) + return getattr(cfg, attr) + + # ping to make sure neighbor is resolved, + # bind to an interface, for v6 the GW is likely link local + cmd(f"ping -c1 -W0 -I{cfg.remote_ifname} {gw}", host=cfg.remote) + + neigh = ip(f"neigh get {gw} dev {cfg.remote_ifname}", + json=True, host=cfg.remote)[0] + setattr(cfg, attr, neigh['lladdr']) + return getattr(cfg, attr) + + +def _write_defer_restore(cfg, path, val, defer_undo=False): + with open(path, "r", encoding="utf-8") as fp: + orig_val = fp.read().strip() + if str(val) == orig_val: + return + with open(path, "w", encoding="utf-8") as fp: + fp.write(val) + if defer_undo: + defer(_write_defer_restore, cfg, path, orig_val) + + +def _set_mtu_restore(dev, mtu, host): + if dev['mtu'] < mtu: + ip(f"link set dev {dev['ifname']} mtu {mtu}", host=host) + defer(ip, f"link set dev {dev['ifname']} mtu {dev['mtu']}", host=host) + + +def _setup(cfg, test_name): + """ Setup hardware loopback mode for GRO testing. """ + + if not hasattr(cfg, "bin_remote"): + cfg.bin_local = cfg.test_dir / "gro" + cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) + + # "large" test needs at least 4k MTU + if test_name == "large": + _set_mtu_restore(cfg.dev, 4096, None) + _set_mtu_restore(cfg.remote_dev, 4096, cfg.remote) + + flush_path = f"/sys/class/net/{cfg.ifname}/gro_flush_timeout" + irq_path = f"/sys/class/net/{cfg.ifname}/napi_defer_hard_irqs" + + _write_defer_restore(cfg, flush_path, "200000", defer_undo=True) + _write_defer_restore(cfg, irq_path, "10", defer_undo=True) + + try: + # Disable TSO for local tests + cfg.require_nsim() # will raise KsftXfailEx if not running on nsim + + cmd(f"ethtool -K {cfg.ifname} gro on tso off") + cmd(f"ethtool -K {cfg.remote_ifname} gro on tso off", host=cfg.remote) + except KsftXfailEx: + pass + +def _gro_variants(): + """Generator that yields all combinations of protocol and test types.""" + + for protocol in ["ipv4", "ipv6", "ipip"]: + for test_name in ["data", "ack", "flags", "tcp", "ip", "large"]: + yield protocol, test_name + + +@ksft_variants(_gro_variants()) +def test(cfg, protocol, test_name): + """Run a single GRO test with retries.""" + + ipver = "6" if protocol[-1] == "6" else "4" + cfg.require_ipver(ipver) + + _setup(cfg, test_name) + + base_cmd_args = [ + f"--{protocol}", + f"--dmac {_resolve_dmac(cfg, ipver)}", + f"--smac {cfg.remote_dev['address']}", + f"--daddr {cfg.addr_v[ipver]}", + f"--saddr {cfg.remote_addr_v[ipver]}", + f"--test {test_name}", + "--verbose" + ] + base_args = " ".join(base_cmd_args) + + # Each test is run 6 times to deflake, because given the receive timing, + # not all packets that should coalesce will be considered in the same flow + # on every try. + max_retries = 6 + for attempt in range(max_retries): + rx_cmd = f"{cfg.bin_local} {base_args} --rx --iface {cfg.ifname}" + tx_cmd = f"{cfg.bin_remote} {base_args} --iface {cfg.remote_ifname}" + + fail_now = attempt >= max_retries - 1 + + with bkg(rx_cmd, ksft_ready=True, exit_wait=True, + fail=fail_now) as rx_proc: + cmd(tx_cmd, host=cfg.remote) + + if rx_proc.ret == 0: + return + + ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# ')) + ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# ')) + + if test_name == "large" and os.environ.get("KSFT_MACHINE_SLOW"): + ksft_pr(f"Ignoring {protocol}/{test_name} failure due to slow environment") + return + + ksft_pr(f"Attempt {attempt + 1}/{max_retries} failed, retrying...") + + +def main() -> None: + """ Ksft boiler plate main """ + + with NetDrvEpEnv(__file__) as cfg: + ksft_run(cases=[test], args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/.gitignore b/tools/testing/selftests/drivers/net/hw/.gitignore index 6942bf575497..46540468a775 100644 --- a/tools/testing/selftests/drivers/net/hw/.gitignore +++ b/tools/testing/selftests/drivers/net/hw/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only iou-zcrx ncdevmem +toeplitz diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 8133d1a0051c..9c163ba6feee 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -1,10 +1,26 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT -TEST_GEN_FILES = iou-zcrx +# Check if io_uring supports zero-copy receive +HAS_IOURING_ZCRX := $(shell \ + echo -e '#include <liburing.h>\n' \ + 'void *func = (void *)io_uring_register_ifq;\n' \ + 'int main() {return 0;}' | \ + $(CC) -luring -x c - -o /dev/null 2>&1 && echo y) + +ifeq ($(HAS_IOURING_ZCRX),y) +COND_GEN_FILES += iou-zcrx +else +$(warning excluding iouring tests, liburing not installed or too old) +endif + +TEST_GEN_FILES := \ + $(COND_GEN_FILES) \ +# end of TEST_GEN_FILES TEST_PROGS = \ csum.py \ devlink_port_split.py \ + devlink_rate_tc_bw.py \ devmem.py \ ethtool.sh \ ethtool_extended_state.sh \ @@ -21,6 +37,7 @@ TEST_PROGS = \ rss_ctx.py \ rss_flow_label.py \ rss_input_xfrm.py \ + toeplitz.py \ tso.py \ xsk_reconfig.py \ # @@ -38,7 +55,10 @@ TEST_INCLUDES := \ # # YNL files, must be before "include ..lib.mk" -YNL_GEN_FILES := ncdevmem +YNL_GEN_FILES := \ + ncdevmem \ + toeplitz \ +# end of YNL_GEN_FILES TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) @@ -54,4 +74,6 @@ include ../../../net/ynl.mk include ../../../net/bpf.mk +ifeq ($(HAS_IOURING_ZCRX),y) $(OUTPUT)/iou-zcrx: LDLIBS += -luring +endif diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py index ead6784d1910..4e4faa9275bb 100755 --- a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py +++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py @@ -21,21 +21,21 @@ Test Cases: ---------- 1. test_no_tc_mapping_bandwidth: - Verifies that without TC mapping, bandwidth is NOT distributed according to - the configured 80/20 split between TC4 and TC3 - - This test should fail if bandwidth matches the 80/20 split without TC + the configured 20/80 split between TC3 and TC4 + - This test should fail if bandwidth matches the 20/80 split without TC mapping - - Expected: Bandwidth should NOT be distributed as 80/20 + - Expected: Bandwidth should NOT be distributed as 20/80 2. test_tc_mapping_bandwidth: - Configures TC mapping using mqprio qdisc - Verifies that with TC mapping, bandwidth IS distributed according to the - configured 80/20 split between TC3 and TC4 - - Expected: Bandwidth should be distributed as 80/20 + configured 20/80 split between TC3 and TC4 + - Expected: Bandwidth should be distributed as 20/80 Bandwidth Distribution: ---------------------- -- TC3 (VLAN 101): Configured for 80% of total bandwidth -- TC4 (VLAN 102): Configured for 20% of total bandwidth +- TC3 (VLAN 101): Configured for 20% of total bandwidth +- TC4 (VLAN 102): Configured for 80% of total bandwidth - Total bandwidth: 1Gbps - Tolerance: +-12% @@ -64,43 +64,40 @@ from lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from lib.py import NetDrvEpEnv, DevlinkFamily from lib.py import NlError from lib.py import cmd, defer, ethtool, ip +from lib.py import Iperf3Runner class BandwidthValidator: """ - Validates bandwidth totals and per-TC shares against expected values - with a tolerance. + Validates total bandwidth and individual shares with tolerance + relative to the overall total. """ - def __init__(self): + def __init__(self, shares): self.tolerance_percent = 12 - self.expected_total_gbps = 1.0 - self.total_min_expected = self.min_expected(self.expected_total_gbps) - self.total_max_expected = self.max_expected(self.expected_total_gbps) - self.tc_expected_percent = { - 3: 20.0, - 4: 80.0, - } + self.expected_total = sum(shares.values()) + self.bounds = {} + + for name, exp in shares.items(): + self.bounds[name] = (self.min_expected(exp), self.max_expected(exp)) def min_expected(self, value): """Calculates the minimum acceptable value based on tolerance.""" - return value - (value * self.tolerance_percent / 100) + return value - (self.expected_total * self.tolerance_percent / 100) def max_expected(self, value): """Calculates the maximum acceptable value based on tolerance.""" - return value + (value * self.tolerance_percent / 100) - - def bound(self, expected, value): - """Returns True if value is within expected tolerance.""" - return self.min_expected(expected) <= value <= self.max_expected(expected) + return value + (self.expected_total * self.tolerance_percent / 100) - def tc_bandwidth_bound(self, value, tc_ix): + def bound(self, values): """ - Returns True if the given bandwidth value is within tolerance - for the TC's expected bandwidth. + Return True if all given values fall within tolerance. """ - expected = self.tc_expected_percent[tc_ix] - return self.bound(expected, value) + for name, value in values.items(): + low, high = self.bounds[name] + if not low <= value <= high: + return False + return True def setup_vf(cfg, set_tc_mapping=True): @@ -116,8 +113,8 @@ def setup_vf(cfg, set_tc_mapping=True): except Exception as exc: raise KsftSkipEx(f"Failed to enable switchdev mode on {cfg.pci}") from exc try: - cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") - defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs") + cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True) + defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True) except Exception as exc: raise KsftSkipEx(f"Failed to enable SR-IOV on {cfg.ifname}") from exc @@ -139,8 +136,8 @@ def setup_vlans_on_vf(vf_ifc): Sets up two VLAN interfaces on the given VF, each mapped to a different TC. """ vlan_configs = [ - {"vlan_id": 101, "tc": 3, "ip": "198.51.100.2"}, - {"vlan_id": 102, "tc": 4, "ip": "198.51.100.10"}, + {"vlan_id": 101, "tc": 3, "ip": "198.51.100.1"}, + {"vlan_id": 102, "tc": 4, "ip": "198.51.100.9"}, ] for config in vlan_configs: @@ -224,13 +221,13 @@ def setup_devlink_rate(cfg): raise KsftFailEx(f"rate_set failed on VF port {port_index}") from exc -def setup_remote_server(cfg): +def setup_remote_vlans(cfg): """ - Sets up VLAN interfaces and starts iperf3 servers on the remote side. + Sets up VLAN interfaces on the remote side. """ remote_dev = cfg.remote_ifname vlan_ids = [101, 102] - remote_ips = ["198.51.100.1", "198.51.100.9"] + remote_ips = ["198.51.100.2", "198.51.100.10"] for vlan_id, ip_addr in zip(vlan_ids, remote_ips): vlan_dev = f"{remote_dev}.{vlan_id}" @@ -238,14 +235,13 @@ def setup_remote_server(cfg): f"type vlan id {vlan_id}", host=cfg.remote) cmd(f"ip addr add {ip_addr}/29 dev {vlan_dev}", host=cfg.remote) cmd(f"ip link set dev {vlan_dev} up", host=cfg.remote) - cmd(f"iperf3 -s -1 -B {ip_addr}",background=True, host=cfg.remote) defer(cmd, f"ip link del {vlan_dev}", host=cfg.remote) def setup_test_environment(cfg, set_tc_mapping=True): """ Sets up the complete test environment including VF creation, VLANs, - bridge configuration, devlink rate setup, and the remote server. + bridge configuration and devlink rate setup. """ vf_ifc = setup_vf(cfg, set_tc_mapping) ksft_pr(f"Created VF interface: {vf_ifc}") @@ -256,51 +252,39 @@ def setup_test_environment(cfg, set_tc_mapping=True): setup_bridge(cfg) setup_devlink_rate(cfg) - setup_remote_server(cfg) - time.sleep(2) + setup_remote_vlans(cfg) -def run_iperf_client(server_ip, local_ip, barrier, min_expected_gbps=0.1): +def measure_bandwidth(cfg, server_ip, client_ip, barrier): """ - Runs a single iperf3 client instance, binding to the given local IP. - Waits on a barrier to synchronize with other threads. + Synchronizes with peers and runs an iperf3-based bandwidth measurement + between the given endpoints. Returns average Gbps. """ + runner = Iperf3Runner(cfg, server_ip=server_ip, client_ip=client_ip) try: barrier.wait(timeout=10) except Exception as exc: raise KsftFailEx("iperf3 barrier wait timed") from exc - iperf_cmd = ["iperf3", "-c", server_ip, "-B", local_ip, "-J"] - result = subprocess.run(iperf_cmd, capture_output=True, text=True, - check=True) - try: - output = json.loads(result.stdout) - bits_per_second = output["end"]["sum_received"]["bits_per_second"] - gbps = bits_per_second / 1e9 - if gbps < min_expected_gbps: - ksft_pr( - f"iperf3 bandwidth too low: {gbps:.2f} Gbps " - f"(expected ≥ {min_expected_gbps} Gbps)" - ) - return None - return gbps - except json.JSONDecodeError as exc: - ksft_pr(f"Failed to parse iperf3 JSON output: {exc}") - return None + bw_gbps = runner.measure_bandwidth(reverse=True) + except Exception as exc: + raise KsftFailEx("iperf3 bandwidth measurement failed") from exc + + return bw_gbps -def run_bandwidth_test(): +def run_bandwidth_test(cfg): """ - Launches iperf3 client threads for each VLAN/TC pair and collects results. + Runs parallel bandwidth measurements for each VLAN/TC pair and collects results. """ - def _run_iperf_client_thread(server_ip, local_ip, results, barrier, tc_ix): - results[tc_ix] = run_iperf_client(server_ip, local_ip, barrier) + def _run_measure_bandwidth_thread(local_ip, remote_ip, results, barrier, tc_ix): + results[tc_ix] = measure_bandwidth(cfg, local_ip, remote_ip, barrier) vf_vlan_data = [ # (local_ip, remote_ip, TC) - ("198.51.100.2", "198.51.100.1", 3), - ("198.51.100.10", "198.51.100.9", 4), + ("198.51.100.1", "198.51.100.2", 3), + ("198.51.100.9", "198.51.100.10", 4), ] results = {} @@ -309,8 +293,8 @@ def run_bandwidth_test(): for local_ip, remote_ip, tc_ix in vf_vlan_data: thread = threading.Thread( - target=_run_iperf_client_thread, - args=(remote_ip, local_ip, results, start_barrier, tc_ix) + target=_run_measure_bandwidth_thread, + args=(local_ip, remote_ip, results, start_barrier, tc_ix) ) thread.start() threads.append(thread) @@ -320,10 +304,11 @@ def run_bandwidth_test(): for tc_ix, tc_bw in results.items(): if tc_bw is None: - raise KsftFailEx("iperf3 client failed; cannot evaluate bandwidth") + raise KsftFailEx("iperf3 failed; cannot evaluate bandwidth") return results + def calculate_bandwidth_percentages(results): """ Calculates the percentage of total bandwidth received by TC3 and TC4. @@ -364,59 +349,48 @@ def verify_total_bandwidth(bw_data, validator): """ total = bw_data['total_bw'] - if validator.bound(validator.expected_total_gbps, total): + if validator.bound({"total": total}): return - if total < validator.total_min_expected: + low, high = validator.bounds["total"] + + if total < low: raise KsftSkipEx( f"Total bandwidth {total:.2f} Gbps < minimum " - f"{validator.total_min_expected:.2f} Gbps; " - f"parent tx_max ({validator.expected_total_gbps:.1f} G) " + f"{low:.2f} Gbps; " + f"parent tx_max ({validator.expected_total:.1f} G) " f"not reached, cannot validate share" ) raise KsftFailEx( f"Total bandwidth {total:.2f} Gbps exceeds allowed ceiling " - f"{validator.total_max_expected:.2f} Gbps " - f"(VF tx_max set to {validator.expected_total_gbps:.1f} G)" + f"{high:.2f} Gbps " + f"(VF tx_max set to {validator.expected_total:.1f} G)" ) -def check_bandwidth_distribution(bw_data, validator): - """ - Checks whether the measured TC3 and TC4 bandwidth percentages - fall within their expected tolerance ranges. - - Returns: - bool: True if both TC3 and TC4 percentages are within bounds. - """ - tc3_valid = validator.tc_bandwidth_bound(bw_data['tc3_percentage'], 3) - tc4_valid = validator.tc_bandwidth_bound(bw_data['tc4_percentage'], 4) - - return tc3_valid and tc4_valid - - def run_bandwidth_distribution_test(cfg, set_tc_mapping): """ - Runs parallel iperf3 tests for both TCs and collects results. + Runs parallel bandwidth measurements for both TCs and collects results. """ setup_test_environment(cfg, set_tc_mapping) - bandwidths = run_bandwidth_test() + bandwidths = run_bandwidth_test(cfg) bw_data = calculate_bandwidth_percentages(bandwidths) test_name = "with TC mapping" if set_tc_mapping else "without TC mapping" print_bandwidth_results(bw_data, test_name) - verify_total_bandwidth(bw_data, cfg.bw_validator) + verify_total_bandwidth(bw_data, cfg.traffic_bw_validator) - return check_bandwidth_distribution(bw_data, cfg.bw_validator) + return cfg.tc_bw_validator.bound({"tc3": bw_data['tc3_percentage'], + "tc4": bw_data['tc4_percentage']}) def test_no_tc_mapping_bandwidth(cfg): """ - Verifies that bandwidth is not split 80/20 without traffic class mapping. + Verifies that bandwidth is not split 20/80 without traffic class mapping. """ - pass_bw_msg = "Bandwidth is NOT distributed as 80/20 without TC mapping" - fail_bw_msg = "Bandwidth matched 80/20 split without TC mapping" + pass_bw_msg = "Bandwidth is NOT distributed as 20/80 without TC mapping" + fail_bw_msg = "Bandwidth matched 20/80 split without TC mapping" is_mlx5 = "driver: mlx5" in ethtool(f"-i {cfg.ifname}").stdout if run_bandwidth_distribution_test(cfg, set_tc_mapping=False): @@ -430,13 +404,13 @@ def test_no_tc_mapping_bandwidth(cfg): def test_tc_mapping_bandwidth(cfg): """ - Verifies that bandwidth is correctly split 80/20 between TC3 and TC4 + Verifies that bandwidth is correctly split 20/80 between TC3 and TC4 when traffic class mapping is set. """ if run_bandwidth_distribution_test(cfg, set_tc_mapping=True): - ksft_pr("Bandwidth is distributed as 80/20 with TC mapping") + ksft_pr("Bandwidth is distributed as 20/80 with TC mapping") else: - raise KsftFailEx("Bandwidth did not match 80/20 split with TC mapping") + raise KsftFailEx("Bandwidth did not match 20/80 split with TC mapping") def main() -> None: @@ -451,9 +425,9 @@ def main() -> None: ) if not cfg.pci: raise KsftSkipEx("Could not get PCI address of the interface") - cfg.require_cmd("iperf3", local=True, remote=True) - cfg.bw_validator = BandwidthValidator() + cfg.traffic_bw_validator = BandwidthValidator({"total": 1}) + cfg.tc_bw_validator = BandwidthValidator({"tc3": 20, "tc4": 80}) cases = [test_no_tc_mapping_bandwidth, test_tc_mapping_bandwidth] diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index fb010a48a5a1..766bfc4ad842 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -25,10 +25,10 @@ try: fd_read_timeout, ip, rand_port, wait_port_listen, wait_file from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ - ksft_setup + ksft_setup, ksft_variants, KsftNamedVariant from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none - from drivers.net.lib.py import GenerateTraffic, Remote + from drivers.net.lib.py import GenerateTraffic, Remote, Iperf3Runner from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev", @@ -40,11 +40,12 @@ try: "wait_port_listen", "wait_file", "KsftSkipEx", "KsftFailEx", "KsftXfailEx", "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run", - "ksft_setup", + "ksft_setup", "ksft_variants", "KsftNamedVariant", "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt", "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt", "ksft_not_none", "ksft_not_none", - "NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote"] + "NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote", + "Iperf3Runner"] except ModuleNotFoundError as e: print("Failed importing `net` library from kernel sources") print(str(e)) diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c index 9ba03164d73a..a4d04438c313 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c @@ -52,7 +52,11 @@ #include <sys/types.h> #include <unistd.h> -#include "../kselftest.h" +#include <ynl.h> +#include "ethtool-user.h" + +#include "../../../kselftest.h" +#include "../../../net/lib/ksft.h" #define TOEPLITZ_KEY_MIN_LEN 40 #define TOEPLITZ_KEY_MAX_LEN 60 @@ -64,6 +68,7 @@ #define FOUR_TUPLE_MAX_LEN ((sizeof(struct in6_addr) * 2) + (sizeof(uint16_t) * 2)) #define RSS_MAX_CPUS (1 << 16) /* real constraint is PACKET_FANOUT_MAX */ +#define RSS_MAX_INDIR (1 << 16) #define RPS_MAX_CPUS 16UL /* must be a power of 2 */ @@ -101,6 +106,8 @@ struct ring_state { static unsigned int rx_irq_cpus[RSS_MAX_CPUS]; /* map from rxq to cpu */ static int rps_silo_to_cpu[RPS_MAX_CPUS]; static unsigned char toeplitz_key[TOEPLITZ_KEY_MAX_LEN]; +static unsigned int rss_indir_tbl[RSS_MAX_INDIR]; +static unsigned int rss_indir_tbl_size; static struct ring_state rings[RSS_MAX_CPUS]; static inline uint32_t toeplitz(const unsigned char *four_tuple, @@ -129,7 +136,12 @@ static inline uint32_t toeplitz(const unsigned char *four_tuple, /* Compare computed cpu with arrival cpu from packet_fanout_cpu */ static void verify_rss(uint32_t rx_hash, int cpu) { - int queue = rx_hash % cfg_num_queues; + int queue; + + if (rss_indir_tbl_size) + queue = rss_indir_tbl[rx_hash % rss_indir_tbl_size]; + else + queue = rx_hash % cfg_num_queues; log_verbose(" rxq %d (cpu %d)", queue, rx_irq_cpus[queue]); if (rx_irq_cpus[queue] != cpu) { @@ -482,6 +494,56 @@ static void parse_rps_bitmap(const char *arg) rps_silo_to_cpu[cfg_num_rps_cpus++] = i; } +static void read_rss_dev_info_ynl(void) +{ + struct ethtool_rss_get_req *req; + struct ethtool_rss_get_rsp *rsp; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_ethtool_family, NULL); + if (!ys) + error(1, errno, "ynl_sock_create failed"); + + req = ethtool_rss_get_req_alloc(); + if (!req) + error(1, errno, "ethtool_rss_get_req_alloc failed"); + + ethtool_rss_get_req_set_header_dev_name(req, cfg_ifname); + + rsp = ethtool_rss_get(ys, req); + if (!rsp) + error(1, ys->err.code, "YNL: %s", ys->err.msg); + + if (!rsp->_len.hkey) + error(1, 0, "RSS key not available for %s", cfg_ifname); + + if (rsp->_len.hkey < TOEPLITZ_KEY_MIN_LEN || + rsp->_len.hkey > TOEPLITZ_KEY_MAX_LEN) + error(1, 0, "RSS key length %u out of bounds [%u, %u]", + rsp->_len.hkey, TOEPLITZ_KEY_MIN_LEN, + TOEPLITZ_KEY_MAX_LEN); + + memcpy(toeplitz_key, rsp->hkey, rsp->_len.hkey); + + if (rsp->_count.indir > RSS_MAX_INDIR) + error(1, 0, "RSS indirection table too large (%u > %u)", + rsp->_count.indir, RSS_MAX_INDIR); + + /* If indir table not available we'll fallback to simple modulo math */ + if (rsp->_count.indir) { + memcpy(rss_indir_tbl, rsp->indir, + rsp->_count.indir * sizeof(rss_indir_tbl[0])); + rss_indir_tbl_size = rsp->_count.indir; + + log_verbose("RSS indirection table size: %u\n", + rss_indir_tbl_size); + } + + ethtool_rss_get_rsp_free(rsp); + ethtool_rss_get_req_free(req); + ynl_sock_destroy(ys); +} + static void parse_opts(int argc, char **argv) { static struct option long_options[] = { @@ -550,7 +612,7 @@ static void parse_opts(int argc, char **argv) } if (!have_toeplitz) - error(1, 0, "Must supply rss key ('-k')"); + read_rss_dev_info_ynl(); num_cpus = get_nprocs(); if (num_cpus > RSS_MAX_CPUS) @@ -576,6 +638,10 @@ int main(int argc, char **argv) fd_sink = setup_sink(); setup_rings(); + + /* Signal to test framework that we're ready to receive */ + ksft_ready(); + process_rings(); cleanup_rings(); diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py new file mode 100755 index 000000000000..d2db5ee9e358 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -0,0 +1,211 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Toeplitz Rx hashing test: + - rxhash (the hash value calculation itself); + - RSS mapping from rxhash to rx queue; + - RPS mapping from rxhash to cpu. +""" + +import glob +import os +import socket +from lib.py import ksft_run, ksft_exit, ksft_pr +from lib.py import NetDrvEpEnv, EthtoolFamily, NetdevFamily +from lib.py import cmd, bkg, rand_port, defer +from lib.py import ksft_in +from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx + +# "define" for the ID of the Toeplitz hash function +ETH_RSS_HASH_TOP = 1 + + +def _check_rps_and_rfs_not_configured(cfg): + """Verify that RPS is not already configured.""" + + for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"): + with open(rps_file, "r", encoding="utf-8") as fp: + val = fp.read().strip() + if set(val) - {"0", ","}: + raise KsftSkipEx(f"RPS already configured on {rps_file}: {val}") + + rfs_file = "/proc/sys/net/core/rps_sock_flow_entries" + with open(rfs_file, "r", encoding="utf-8") as fp: + val = fp.read().strip() + if val != "0": + raise KsftSkipEx(f"RFS already configured {rfs_file}: {val}") + + +def _get_cpu_for_irq(irq): + with open(f"/proc/irq/{irq}/smp_affinity_list", "r", + encoding="utf-8") as fp: + data = fp.read().strip() + if "," in data or "-" in data: + raise KsftFailEx(f"IRQ{irq} is not mapped to a single core: {data}") + return int(data) + + +def _get_irq_cpus(cfg): + """ + Read the list of IRQs for the device Rx queues. + """ + queues = cfg.netnl.queue_get({"ifindex": cfg.ifindex}, dump=True) + napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True) + + # Remap into ID-based dicts + napis = {n["id"]: n for n in napis} + queues = {f"{q['type']}{q['id']}": q for q in queues} + + cpus = [] + for rx in range(9999): + name = f"rx{rx}" + if name not in queues: + break + cpus.append(_get_cpu_for_irq(napis[queues[name]["napi-id"]]["irq"])) + + return cpus + + +def _get_unused_cpus(cfg, count=2): + """ + Get CPUs that are not used by Rx queues. + Returns a list of at least 'count' CPU numbers. + """ + + # Get CPUs used by Rx queues + rx_cpus = set(_get_irq_cpus(cfg)) + + # Get total number of CPUs + num_cpus = os.cpu_count() + + # Find unused CPUs + unused_cpus = [cpu for cpu in range(num_cpus) if cpu not in rx_cpus] + + if len(unused_cpus) < count: + raise KsftSkipEx(f"Need at {count} CPUs not used by Rx queues, found {len(unused_cpus)}") + + return unused_cpus[:count] + + +def _configure_rps(cfg, rps_cpus): + """Configure RPS for all Rx queues.""" + + mask = 0 + for cpu in rps_cpus: + mask |= (1 << cpu) + mask = hex(mask)[2:] + + # Set RPS bitmap for all rx queues + for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"): + with open(rps_file, "w", encoding="utf-8") as fp: + fp.write(mask) + + return mask + + +def _send_traffic(cfg, proto_flag, ipver, port): + """Send 20 packets of requested type.""" + + # Determine protocol and IP version for socat + if proto_flag == "-u": + proto = "UDP" + else: + proto = "TCP" + + baddr = f"[{cfg.addr_v['6']}]" if ipver == "6" else cfg.addr_v["4"] + + # Run socat in a loop to send traffic periodically + # Use sh -c with a loop similar to toeplitz_client.sh + socat_cmd = f""" + for i in `seq 20`; do + echo "msg $i" | socat -{ipver} -t 0.1 - {proto}:{baddr}:{port}; + sleep 0.001; + done + """ + + cmd(socat_cmd, shell=True, host=cfg.remote) + + +def _test_variants(): + for grp in ["", "rss", "rps"]: + for l4 in ["tcp", "udp"]: + for l3 in ["4", "6"]: + name = f"{l4}_ipv{l3}" + if grp: + name = f"{grp}_{name}" + yield KsftNamedVariant(name, "-" + l4[0], l3, grp) + + +@ksft_variants(_test_variants()) +def test(cfg, proto_flag, ipver, grp): + """Run a single toeplitz test.""" + + cfg.require_ipver(ipver) + + # Check that rxhash is enabled + ksft_in("receive-hashing: on", cmd(f"ethtool -k {cfg.ifname}").stdout) + + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # Make sure NIC is configured to use Toeplitz hash, and no key xfrm. + if rss.get('hfunc') != ETH_RSS_HASH_TOP or rss.get('input-xfrm'): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hfunc": ETH_RSS_HASH_TOP, + "input-xfrm": {}}) + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex}, + "hfunc": rss.get('hfunc'), + "input-xfrm": rss.get('input-xfrm', {}) + }) + + port = rand_port(socket.SOCK_DGRAM) + + toeplitz_path = cfg.test_dir / "toeplitz" + rx_cmd = [ + str(toeplitz_path), + "-" + ipver, + proto_flag, + "-d", str(port), + "-i", cfg.ifname, + "-T", "4000", + "-s", + "-v" + ] + + if grp: + _check_rps_and_rfs_not_configured(cfg) + if grp == "rss": + irq_cpus = ",".join([str(x) for x in _get_irq_cpus(cfg)]) + rx_cmd += ["-C", irq_cpus] + ksft_pr(f"RSS using CPUs: {irq_cpus}") + elif grp == "rps": + # Get CPUs not used by Rx queues and configure them for RPS + rps_cpus = _get_unused_cpus(cfg, count=2) + rps_mask = _configure_rps(cfg, rps_cpus) + defer(_configure_rps, cfg, []) + rx_cmd += ["-r", rps_mask] + ksft_pr(f"RPS using CPUs: {rps_cpus}, mask: {rps_mask}") + + # Run rx in background, it will exit once it has seen enough packets + with bkg(" ".join(rx_cmd), ksft_ready=True, exit_wait=True) as rx_proc: + while rx_proc.proc.poll() is None: + _send_traffic(cfg, proto_flag, ipver, port) + + # Check rx result + ksft_pr("Receiver output:") + ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# ')) + if rx_proc.stderr: + ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# ')) + + +def main() -> None: + """Ksft boilerplate main.""" + + with NetDrvEpEnv(__file__) as cfg: + cfg.ethnl = EthtoolFamily() + cfg.netnl = NetdevFamily() + ksft_run(cases=[test], args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index b0c6300150fb..8b75faa9af6d 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -25,7 +25,7 @@ try: fd_read_timeout, ip, rand_port, wait_port_listen, wait_file from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ - ksft_setup + ksft_setup, ksft_variants, KsftNamedVariant from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none @@ -38,16 +38,17 @@ try: "wait_port_listen", "wait_file", "KsftSkipEx", "KsftFailEx", "KsftXfailEx", "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run", - "ksft_setup", + "ksft_setup", "ksft_variants", "KsftNamedVariant", "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt", "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt", "ksft_not_none", "ksft_not_none"] from .env import NetDrvEnv, NetDrvEpEnv - from .load import GenerateTraffic + from .load import GenerateTraffic, Iperf3Runner from .remote import Remote - __all__ += ["NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote"] + __all__ += ["NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote", + "Iperf3Runner"] except ModuleNotFoundError as e: print("Failed importing `net` library from kernel sources") print(str(e)) diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 01be3d9b9720..8b644fd84ff2 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -168,6 +168,8 @@ class NetDrvEpEnv(NetDrvEnvBase): # resolve remote interface name self.remote_ifname = self.resolve_remote_ifc() + self.remote_dev = ip("-d link show dev " + self.remote_ifname, + host=self.remote, json=True)[0] self._required_cmd = {} diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index c4e808407cc4..f181fa2d38fc 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -2,21 +2,89 @@ import re import time +import json from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen -class GenerateTraffic: - def __init__(self, env, port=None): - env.require_cmd("iperf3", local=True, remote=True) +class Iperf3Runner: + """ + Sets up and runs iperf3 traffic. + """ + def __init__(self, env, port=None, server_ip=None, client_ip=None): + env.require_cmd("iperf3", local=True, remote=True) self.env = env - self.port = rand_port() if port is None else port - self._iperf_server = cmd(f"iperf3 -s -1 -p {self.port}", background=True) + self.server_ip = server_ip + self.client_ip = client_ip + + def _build_server(self): + cmdline = f"iperf3 -s -1 -p {self.port}" + if self.server_ip: + cmdline += f" -B {self.server_ip}" + return cmdline + + def _build_client(self, streams, duration, reverse): + host = self.env.addr if self.server_ip is None else self.server_ip + cmdline = f"iperf3 -c {host} -p {self.port} -P {streams} -t {duration} -J" + if self.client_ip: + cmdline += f" -B {self.client_ip}" + if reverse: + cmdline += " --reverse" + return cmdline + + def start_server(self): + """ + Starts an iperf3 server with optional bind IP. + """ + cmdline = self._build_server() + proc = cmd(cmdline, background=True) wait_port_listen(self.port) time.sleep(0.1) - self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {self.port} -t 86400", - background=True, host=env.remote) + return proc + + def start_client(self, background=False, streams=1, duration=10, reverse=False): + """ + Starts the iperf3 client with the configured options. + """ + cmdline = self._build_client(streams, duration, reverse) + return cmd(cmdline, background=background, host=self.env.remote) + + def measure_bandwidth(self, reverse=False): + """ + Runs an iperf3 measurement and returns the average bandwidth (Gbps). + Discards the first and last few reporting intervals and uses only the + middle part of the run where throughput is typically stable. + """ + self.start_server() + result = self.start_client(duration=10, reverse=reverse) + + if result.ret != 0: + raise RuntimeError("iperf3 failed to run successfully") + try: + out = json.loads(result.stdout) + except json.JSONDecodeError as exc: + raise ValueError("Failed to parse iperf3 JSON output") from exc + + intervals = out.get("intervals", []) + samples = [i["sum"]["bits_per_second"] / 1e9 for i in intervals] + if len(samples) < 10: + raise ValueError(f"iperf3 returned too few intervals: {len(samples)}") + # Discard potentially unstable first and last 3 seconds. + stable = samples[3:-3] + + avg = sum(stable) / len(stable) + + return avg + + +class GenerateTraffic: + def __init__(self, env, port=None): + self.env = env + self.runner = Iperf3Runner(env, port) + + self._iperf_server = self.runner.start_server() + self._iperf_client = self.runner.start_client(background=True, streams=16, duration=86400) # Wait for traffic to ramp up if not self._wait_pkts(pps=1000): @@ -61,7 +129,7 @@ class GenerateTraffic: def _wait_client_stopped(self, sleep=0.005, timeout=5): end = time.monotonic() + timeout - live_port_pattern = re.compile(fr":{self.port:04X} 0[^6] ") + live_port_pattern = re.compile(fr":{self.runner.port:04X} 0[^6] ") while time.monotonic() < end: data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 87f89fd92f8c..ae8abff4be40 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -249,7 +249,7 @@ function listen_port_and_save_to() { # Just wait for 2 seconds timeout 2 ip netns exec "${NAMESPACE}" \ - socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" + socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" 2> /dev/null } # Only validate that the message arrived properly diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index a3446b569976..2022f3061738 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -28,8 +28,6 @@ OUTPUT_FILE="/tmp/${TARGET}" # Check for basic system dependency and exit if not found check_for_dependencies -# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) -echo "6 5" > /proc/sys/kernel/printk # Remove the namespace, interfaces and netconsole target on exit trap cleanup EXIT @@ -39,6 +37,9 @@ do for IP_VERSION in "ipv6" "ipv4" do echo "Running with target mode: ${FORMAT} (${IP_VERSION})" + # Set current loglevel to KERN_INFO(6), and default to + # KERN_NOTICE(5) + echo "6 5" > /proc/sys/kernel/printk # Create one namespace and two interfaces set_network "${IP_VERSION}" # Create a dynamic target for netconsole diff --git a/tools/testing/selftests/drivers/net/netcons_overflow.sh b/tools/testing/selftests/drivers/net/netcons_overflow.sh index 29bad56448a2..06089643b771 100755 --- a/tools/testing/selftests/drivers/net/netcons_overflow.sh +++ b/tools/testing/selftests/drivers/net/netcons_overflow.sh @@ -15,7 +15,7 @@ SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh # This is coming from netconsole code. Check for it in drivers/net/netconsole.c -MAX_USERDATA_ITEMS=16 +MAX_USERDATA_ITEMS=256 # Function to create userdata entries function create_userdata_max_entries() { diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile index df10c7243511..1a228c5430f5 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/Makefile +++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile @@ -8,7 +8,6 @@ TEST_PROGS := \ ethtool-features.sh \ ethtool-fec.sh \ ethtool-pause.sh \ - ethtool-ring.sh \ fib.sh \ fib_notifications.sh \ hw_stats_l3.sh \ diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 030762b203d7..1b529ccaf050 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -3,7 +3,8 @@ lib_dir=$(dirname $0)/../../../net/forwarding -ALL_TESTS="fw_flash_test params_test regions_test reload_test \ +ALL_TESTS="fw_flash_test params_test \ + params_default_test regions_test reload_test \ netns_reload_test resource_test dev_info_test \ empty_reporter_test dummy_reporter_test rate_test" NUM_NETIFS=0 @@ -78,17 +79,28 @@ fw_flash_test() param_get() { local name=$1 + local attr=${2:-value} + local cmode=${3:-driverinit} cmd_jq "devlink dev param show $DL_HANDLE name $name -j" \ - '.[][][].values[] | select(.cmode == "driverinit").value' + '.[][][].values[] | select(.cmode == "'"$cmode"'").'"$attr" } param_set() { local name=$1 local value=$2 + local cmode=${3:-driverinit} - devlink dev param set $DL_HANDLE name $name cmode driverinit value $value + devlink dev param set $DL_HANDLE name $name cmode $cmode value $value +} + +param_set_default() +{ + local name=$1 + local cmode=${2:-driverinit} + + devlink dev param set $DL_HANDLE name $name default cmode $cmode } check_value() @@ -97,12 +109,18 @@ check_value() local phase_name=$2 local expected_param_value=$3 local expected_debugfs_value=$4 + local cmode=${5:-driverinit} local value + local attr="value" - value=$(param_get $name) - check_err $? "Failed to get $name param value" + if [[ "$phase_name" == *"default"* ]]; then + attr="default" + fi + + value=$(param_get $name $attr $cmode) + check_err $? "Failed to get $name param $attr" [ "$value" == "$expected_param_value" ] - check_err $? "Unexpected $phase_name $name param value" + check_err $? "Unexpected $phase_name $name param $attr" value=$(<$DEBUGFS_DIR/$name) check_err $? "Failed to get $name debugfs value" [ "$value" == "$expected_debugfs_value" ] @@ -135,6 +153,92 @@ params_test() log_test "params test" } +value_to_debugfs() +{ + local value=$1 + + case "$value" in + true) + echo "Y" + ;; + false) + echo "N" + ;; + *) + echo "$value" + ;; + esac +} + +test_default() +{ + local param_name=$1 + local new_value=$2 + local expected_default=$3 + local cmode=${4:-driverinit} + local default_debugfs + local new_debugfs + local expected_debugfs + + default_debugfs=$(value_to_debugfs $expected_default) + new_debugfs=$(value_to_debugfs $new_value) + + expected_debugfs=$default_debugfs + check_value $param_name initial-default $expected_default $expected_debugfs $cmode + + param_set $param_name $new_value $cmode + check_err $? "Failed to set $param_name to $new_value" + + expected_debugfs=$([ "$cmode" == "runtime" ] && echo "$new_debugfs" || echo "$default_debugfs") + check_value $param_name post-set $new_value $expected_debugfs $cmode + + devlink dev reload $DL_HANDLE + check_err $? "Failed to reload device" + + expected_debugfs=$new_debugfs + check_value $param_name post-reload-new-value $new_value $expected_debugfs $cmode + + param_set_default $param_name $cmode + check_err $? "Failed to set $param_name to default" + + expected_debugfs=$([ "$cmode" == "runtime" ] && echo "$default_debugfs" || echo "$new_debugfs") + check_value $param_name post-set-default $expected_default $expected_debugfs $cmode + + devlink dev reload $DL_HANDLE + check_err $? "Failed to reload device" + + expected_debugfs=$default_debugfs + check_value $param_name post-reload-default $expected_default $expected_debugfs $cmode +} + +params_default_test() +{ + RET=0 + + if ! devlink dev param help 2>&1 | grep -q "value VALUE | default"; then + echo "SKIP: devlink cli missing default feature" + return + fi + + # Remove side effects of previous tests. Use plain param_set, because + # param_set_default is a feature under test here. + param_set max_macs 32 driverinit + check_err $? "Failed to reset max_macs to default value" + param_set test1 true driverinit + check_err $? "Failed to reset test1 to default value" + param_set test2 1234 runtime + check_err $? "Failed to reset test2 to default value" + + devlink dev reload $DL_HANDLE + check_err $? "Failed to reload device for clean state" + + test_default max_macs 16 32 driverinit + test_default test1 false true driverinit + test_default test2 100 1234 runtime + + log_test "params default test" +} + check_region_size() { local name=$1 diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh deleted file mode 100755 index c969559ffa7a..000000000000 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh +++ /dev/null @@ -1,85 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0-only - -source ethtool-common.sh - -function get_value { - local query="${SETTINGS_MAP[$1]}" - - echo $(ethtool -g $NSIM_NETDEV | \ - tail -n +$CURR_SETT_LINE | \ - awk -F':' -v pattern="$query:" '$0 ~ pattern {gsub(/[\t ]/, "", $2); print $2}') -} - -function update_current_settings { - for key in ${!SETTINGS_MAP[@]}; do - CURRENT_SETTINGS[$key]=$(get_value $key) - done - echo ${CURRENT_SETTINGS[@]} -} - -if ! ethtool -h | grep -q set-ring >/dev/null; then - echo "SKIP: No --set-ring support in ethtool" - exit 4 -fi - -NSIM_NETDEV=$(make_netdev) - -set -o pipefail - -declare -A SETTINGS_MAP=( - ["rx"]="RX" - ["rx-mini"]="RX Mini" - ["rx-jumbo"]="RX Jumbo" - ["tx"]="TX" -) - -declare -A EXPECTED_SETTINGS=( - ["rx"]="" - ["rx-mini"]="" - ["rx-jumbo"]="" - ["tx"]="" -) - -declare -A CURRENT_SETTINGS=( - ["rx"]="" - ["rx-mini"]="" - ["rx-jumbo"]="" - ["tx"]="" -) - -MAX_VALUE=$((RANDOM % $((2**32-1)))) -RING_MAX_LIST=$(ls $NSIM_DEV_DFS/ethtool/ring/) - -for ring_max_entry in $RING_MAX_LIST; do - echo $MAX_VALUE > $NSIM_DEV_DFS/ethtool/ring/$ring_max_entry -done - -CURR_SETT_LINE=$(ethtool -g $NSIM_NETDEV | grep -i -m1 -n 'Current hardware settings' | cut -f1 -d:) - -# populate the expected settings map -for key in ${!SETTINGS_MAP[@]}; do - EXPECTED_SETTINGS[$key]=$(get_value $key) -done - -# test -for key in ${!SETTINGS_MAP[@]}; do - value=$((RANDOM % $MAX_VALUE)) - - ethtool -G $NSIM_NETDEV "$key" "$value" - - EXPECTED_SETTINGS[$key]="$value" - expected=${EXPECTED_SETTINGS[@]} - current=$(update_current_settings) - - check $? "$current" "$expected" - set +x -done - -if [ $num_errors -eq 0 ]; then - echo "PASSED all $((num_passes)) checks" - exit 0 -else - echo "FAILED $num_errors/$((num_errors+num_passes)) checks" - exit 1 -fi diff --git a/tools/testing/selftests/drivers/net/psp.py b/tools/testing/selftests/drivers/net/psp.py index 4ae7a785ff10..06559ef49b9a 100755 --- a/tools/testing/selftests/drivers/net/psp.py +++ b/tools/testing/selftests/drivers/net/psp.py @@ -109,6 +109,10 @@ def _check_data_outq(s, exp_len, force_wait=False): time.sleep(0.01) ksft_eq(outq, exp_len) + +def _get_stat(cfg, key): + return cfg.pspnl.get_stats({'dev-id': cfg.psp_dev_id})[key] + # # Test case boiler plate # @@ -171,11 +175,16 @@ def dev_rotate(cfg): """ Test key rotation """ _init_psp_dev(cfg) + prev_rotations = _get_stat(cfg, 'key-rotations') + rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) ksft_eq(rot['id'], cfg.psp_dev_id) rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) ksft_eq(rot['id'], cfg.psp_dev_id) + cur_rotations = _get_stat(cfg, 'key-rotations') + ksft_eq(cur_rotations, prev_rotations + 2) + def dev_rotate_spi(cfg): """ Test key rotation and SPI check """ @@ -475,6 +484,7 @@ def data_stale_key(cfg): """ Test send on a double-rotated key """ _init_psp_dev(cfg) + prev_stale = _get_stat(cfg, 'stale-events') s = _make_psp_conn(cfg) try: rx_assoc = cfg.pspnl.rx_assoc({"version": 0, @@ -495,6 +505,9 @@ def data_stale_key(cfg): cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) + cur_stale = _get_stat(cfg, 'stale-events') + ksft_gt(cur_stale, prev_stale) + s.send(b'0123456789' * 200) _check_data_outq(s, 2000, force_wait=True) finally: diff --git a/tools/testing/selftests/drivers/net/ring_reconfig.py b/tools/testing/selftests/drivers/net/ring_reconfig.py new file mode 100755 index 000000000000..f9530a8b0856 --- /dev/null +++ b/tools/testing/selftests/drivers/net/ring_reconfig.py @@ -0,0 +1,167 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Test channel and ring size configuration via ethtool (-L / -G). +""" + +from lib.py import ksft_run, ksft_exit, ksft_pr +from lib.py import ksft_eq +from lib.py import NetDrvEpEnv, EthtoolFamily, GenerateTraffic +from lib.py import defer, NlError + + +def channels(cfg) -> None: + """ + Twiddle channel counts in various combinations of parameters. + We're only looking for driver adhering to the requested config + if the config is accepted and crashes. + """ + ehdr = {'header':{'dev-index': cfg.ifindex}} + chans = cfg.eth.channels_get(ehdr) + + all_keys = ["rx", "tx", "combined"] + mixes = [{"combined"}, {"rx", "tx"}, {"rx", "combined"}, {"tx", "combined"}, + {"rx", "tx", "combined"},] + + # Get the set of keys that device actually supports + restore = {} + supported = set() + for key in all_keys: + if key + "-max" in chans: + supported.add(key) + restore |= {key + "-count": chans[key + "-count"]} + + defer(cfg.eth.channels_set, ehdr | restore) + + def test_config(config): + try: + cfg.eth.channels_set(ehdr | config) + get = cfg.eth.channels_get(ehdr) + for k, v in config.items(): + ksft_eq(get.get(k, 0), v) + except NlError as e: + failed.append(mix) + ksft_pr("Can't set", config, e) + else: + ksft_pr("Okay", config) + + failed = [] + for mix in mixes: + if not mix.issubset(supported): + continue + + # Set all the values in the mix to 1, other supported to 0 + config = {} + for key in all_keys: + config[key + "-count"] = 1 if key in mix else 0 + test_config(config) + + for mix in mixes: + if not mix.issubset(supported): + continue + if mix in failed: + continue + + # Set all the values in the mix to max, other supported to 0 + config = {} + for key in all_keys: + config[key + "-count"] = chans[key + '-max'] if key in mix else 0 + test_config(config) + + +def _configure_min_ring_cnt(cfg) -> None: + """ Try to configure a single Rx/Tx ring. """ + ehdr = {'header':{'dev-index': cfg.ifindex}} + chans = cfg.eth.channels_get(ehdr) + + all_keys = ["rx-count", "tx-count", "combined-count"] + restore = {} + config = {} + for key in all_keys: + if key in chans: + restore[key] = chans[key] + config[key] = 0 + + if chans.get('combined-count', 0) > 1: + config['combined-count'] = 1 + elif chans.get('rx-count', 0) > 1 and chans.get('tx-count', 0) > 1: + config['tx-count'] = 1 + config['rx-count'] = 1 + else: + # looks like we're already on 1 channel + return + + cfg.eth.channels_set(ehdr | config) + defer(cfg.eth.channels_set, ehdr | restore) + + +def ringparam(cfg) -> None: + """ + Tweak the ringparam configuration. Try to run some traffic over min + ring size to make sure it actually functions. + """ + ehdr = {'header':{'dev-index': cfg.ifindex}} + rings = cfg.eth.rings_get(ehdr) + + restore = {} + maxes = {} + params = set() + for key in rings.keys(): + if 'max' in key: + param = key[:-4] + maxes[param] = rings[key] + params.add(param) + restore[param] = rings[param] + + defer(cfg.eth.rings_set, ehdr | restore) + + # Speed up the reconfig by configuring just one ring + _configure_min_ring_cnt(cfg) + + # Try to reach min on all settings + for param in params: + val = rings[param] + while True: + try: + cfg.eth.rings_set({'header':{'dev-index': cfg.ifindex}, + param: val // 2}) + if val == 0: + break + val //= 2 + except NlError: + break + + get = cfg.eth.rings_get(ehdr) + ksft_eq(get[param], val) + + ksft_pr(f"Reached min for '{param}' at {val} (max {rings[param]})") + + GenerateTraffic(cfg).wait_pkts_and_stop(10000) + + # Try max across all params, if the driver supports large rings + # this may OOM so we ignore errors + try: + ksft_pr("Applying max settings") + config = {p: maxes[p] for p in params} + cfg.eth.rings_set(ehdr | config) + except NlError as e: + ksft_pr("Can't set max params", config, e) + else: + GenerateTraffic(cfg).wait_pkts_and_stop(10000) + + +def main() -> None: + """ Ksft boiler plate main """ + + with NetDrvEpEnv(__file__) as cfg: + cfg.eth = EthtoolFamily() + + ksft_run([channels, + ringparam], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 04d0a2a13e73..b08e4d48b15c 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -263,14 +263,15 @@ def procfs_downup_hammer(cfg) -> None: Reading stats via procfs only holds the RCU lock, drivers often try to sleep when reading the stats, or don't protect against races. """ - # Max out the queues, we'll flip between max and 1 + # Set a large number of queues, + # we'll flip between min(max_queues, 64) and 1 channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) if channels['combined-count'] == 0: rx_type = 'rx' else: rx_type = 'combined' cur_queue_cnt = channels[f'{rx_type}-count'] - max_queue_cnt = channels[f'{rx_type}-max'] + max_queue_cnt = min(channels[f'{rx_type}-max'], 64) cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py index a148004e1c36..e54df158dfe9 100755 --- a/tools/testing/selftests/drivers/net/xdp.py +++ b/tools/testing/selftests/drivers/net/xdp.py @@ -12,6 +12,7 @@ from dataclasses import dataclass from enum import Enum from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_ne, ksft_pr +from lib.py import KsftNamedVariant, ksft_variants from lib.py import KsftFailEx, NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import bkg, cmd, rand_port, wait_port_listen @@ -672,7 +673,18 @@ def test_xdp_native_adjst_head_shrnk_data(cfg): _validate_res(res, offset_lst, pkt_sz_lst) -def _test_xdp_native_ifc_stats(cfg, act): +@ksft_variants([ + KsftNamedVariant("pass", XDPAction.PASS), + KsftNamedVariant("drop", XDPAction.DROP), + KsftNamedVariant("tx", XDPAction.TX), +]) +def test_xdp_native_qstats(cfg, act): + """ + Send 1000 messages. Expect XDP action specified in @act. + Make sure the packets were counted to interface level qstats + (Rx, and Tx if act is TX). + """ + cfg.require_cmd("socat") bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) @@ -687,9 +699,12 @@ def _test_xdp_native_ifc_stats(cfg, act): "/dev/null" # Listener runs on "remote" in case of XDP_TX rx_host = cfg.remote if act == XDPAction.TX else None - # We want to spew 2000 packets quickly, bash seems to do a good enough job - tx_udp = f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \ - "for i in `seq 2000`; do echo a >&5; done; exec 5>&-" + # We want to spew 1000 packets quickly, bash seems to do a good enough job + # Each reopening of the socket gives us a differenot local port (for RSS) + tx_udp = "for _ in `seq 20`; do " \ + f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \ + "for i in `seq 50`; do echo a >&5; done; " \ + "exec 5>&-; done" cfg.wait_hw_stats_settle() # Qstats have more clearly defined semantics than rtnetlink. @@ -704,11 +719,11 @@ def _test_xdp_native_ifc_stats(cfg, act): cfg.wait_hw_stats_settle() after = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] - ksft_ge(after['rx-packets'] - before['rx-packets'], 2000) + expected_pkts = 1000 + ksft_ge(after['rx-packets'] - before['rx-packets'], expected_pkts) if act == XDPAction.TX: - ksft_ge(after['tx-packets'] - before['tx-packets'], 2000) + ksft_ge(after['tx-packets'] - before['tx-packets'], expected_pkts) - expected_pkts = 2000 stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) ksft_eq(stats[XDPStats.RX.value], expected_pkts, "XDP RX stats mismatch") if act == XDPAction.TX: @@ -730,30 +745,6 @@ def _test_xdp_native_ifc_stats(cfg, act): ksft_ge(after['tx-packets'], before['tx-packets']) -def test_xdp_native_qstats_pass(cfg): - """ - Send 2000 messages, expect XDP_PASS, make sure the packets were counted - to interface level qstats (Rx). - """ - _test_xdp_native_ifc_stats(cfg, XDPAction.PASS) - - -def test_xdp_native_qstats_drop(cfg): - """ - Send 2000 messages, expect XDP_DROP, make sure the packets were counted - to interface level qstats (Rx). - """ - _test_xdp_native_ifc_stats(cfg, XDPAction.DROP) - - -def test_xdp_native_qstats_tx(cfg): - """ - Send 2000 messages, expect XDP_TX, make sure the packets were counted - to interface level qstats (Rx and Tx) - """ - _test_xdp_native_ifc_stats(cfg, XDPAction.TX) - - def main(): """ Main function to execute the XDP tests. @@ -778,9 +769,7 @@ def main(): test_xdp_native_adjst_tail_shrnk_data, test_xdp_native_adjst_head_grow_data, test_xdp_native_adjst_head_shrnk_data, - test_xdp_native_qstats_pass, - test_xdp_native_qstats_drop, - test_xdp_native_qstats_tx, + test_xdp_native_qstats, ], args=(cfg,)) ksft_exit() diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 8f9850a71f54..6930fe926c58 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -4,10 +4,8 @@ bind_timewait bind_wildcard busy_poller cmsg_sender -diag_uid epoll_busy_poll fin_ack_lat -gro hwtstamp_config io_uring_zerocopy_tx ioam6_parser @@ -18,7 +16,6 @@ ipv6_flowlabel ipv6_flowlabel_mgr ipv6_fragmentation log.txt -msg_oob msg_zerocopy netlink-dumps nettest @@ -35,9 +32,6 @@ reuseport_bpf_numa reuseport_dualstack rxtimestamp sctp_hello -scm_inq -scm_pidfd -scm_rights sk_bind_sendto_listen sk_connect_zero_addr sk_so_peek_off @@ -45,7 +39,6 @@ skf_net_off socket so_incoming_cpu so_netns_cookie -so_peek_off so_txtime so_rcv_listener stress_reuseport_listen @@ -57,7 +50,6 @@ tcp_port_share tfo timestamping tls -toeplitz tools tun txring_overwrite @@ -65,4 +57,3 @@ txtimestamp udpgso udpgso_bench_rx udpgso_bench_tx -unix_connect diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b5127e968108..b66ba04f19d9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -38,7 +38,6 @@ TEST_PROGS := \ fq_band_pktlimit.sh \ gre_gso.sh \ gre_ipv6_lladdr.sh \ - gro.sh \ icmp.sh \ icmp_redirect.sh \ io_uring_zerocopy_tx.sh \ @@ -121,8 +120,6 @@ TEST_PROGS := \ # end of TEST_PROGS TEST_PROGS_EXTENDED := \ - toeplitz.sh \ - toeplitz_client.sh \ xfrm_policy_add_speed.sh \ # end of TEST_PROGS_EXTENDED @@ -130,7 +127,6 @@ TEST_GEN_FILES := \ bind_bhash \ cmsg_sender \ fin_ack_lat \ - gro \ hwtstamp_config \ io_uring_zerocopy_tx \ ioam6_parser \ @@ -159,7 +155,6 @@ TEST_GEN_FILES := \ tcp_mmap \ tfo \ timestamping \ - toeplitz \ txring_overwrite \ txtimestamp \ udpgso \ @@ -193,8 +188,6 @@ TEST_FILES := \ in_netns.sh \ lib.sh \ settings \ - setup_loopback.sh \ - setup_veth.sh \ # end of TEST_FILES # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/af_unix/.gitignore b/tools/testing/selftests/net/af_unix/.gitignore new file mode 100644 index 000000000000..240b26740c9e --- /dev/null +++ b/tools/testing/selftests/net/af_unix/.gitignore @@ -0,0 +1,8 @@ +diag_uid +msg_oob +scm_inq +scm_pidfd +scm_rights +so_peek_off +unix_connect +unix_connreset diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 528d14c598bb..3cd677b72072 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -8,6 +8,7 @@ TEST_GEN_PROGS := \ scm_rights \ so_peek_off \ unix_connect \ + unix_connreset \ # end of TEST_GEN_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/so_peek_off.c b/tools/testing/selftests/net/af_unix/so_peek_off.c index 1a77728128e5..86e7b0fb522d 100644 --- a/tools/testing/selftests/net/af_unix/so_peek_off.c +++ b/tools/testing/selftests/net/af_unix/so_peek_off.c @@ -36,8 +36,8 @@ FIXTURE_VARIANT_ADD(so_peek_off, seqpacket) FIXTURE_SETUP(so_peek_off) { struct timeval timeout = { - .tv_sec = 0, - .tv_usec = 3000, + .tv_sec = 5, + .tv_usec = 0, }; int ret; diff --git a/tools/testing/selftests/net/af_unix/unix_connreset.c b/tools/testing/selftests/net/af_unix/unix_connreset.c new file mode 100644 index 000000000000..08c1de8f5a98 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/unix_connreset.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Selftest for AF_UNIX socket close and ECONNRESET behaviour. + * + * This test verifies: + * 1. SOCK_STREAM returns EOF when the peer closes normally. + * 2. SOCK_STREAM returns ECONNRESET if peer closes with unread data. + * 3. SOCK_SEQPACKET returns EOF when the peer closes normally. + * 4. SOCK_SEQPACKET returns ECONNRESET if the peer closes with unread data. + * 5. SOCK_DGRAM does not return ECONNRESET when the peer closes. + * + * These tests document the intended Linux behaviour. + * + */ + +#define _GNU_SOURCE +#include <string.h> +#include <fcntl.h> +#include <unistd.h> +#include <errno.h> +#include <sys/socket.h> +#include <sys/un.h> +#include "../../kselftest_harness.h" + +#define SOCK_PATH "/tmp/af_unix_connreset.sock" + +static void remove_socket_file(void) +{ + unlink(SOCK_PATH); +} + +FIXTURE(unix_sock) +{ + int server; + int client; + int child; +}; + +FIXTURE_VARIANT(unix_sock) +{ + int socket_type; + const char *name; +}; + +FIXTURE_VARIANT_ADD(unix_sock, stream) { + .socket_type = SOCK_STREAM, + .name = "SOCK_STREAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, dgram) { + .socket_type = SOCK_DGRAM, + .name = "SOCK_DGRAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, seqpacket) { + .socket_type = SOCK_SEQPACKET, + .name = "SOCK_SEQPACKET", +}; + +FIXTURE_SETUP(unix_sock) +{ + struct sockaddr_un addr = {}; + int err; + + addr.sun_family = AF_UNIX; + strcpy(addr.sun_path, SOCK_PATH); + remove_socket_file(); + + self->server = socket(AF_UNIX, variant->socket_type, 0); + ASSERT_LT(-1, self->server); + + err = bind(self->server, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + self->client = socket(AF_UNIX, variant->socket_type | SOCK_NONBLOCK, 0); + ASSERT_LT(-1, self->client); + + err = connect(self->client, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(unix_sock) +{ + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) + close(self->child); + + close(self->client); + close(self->server); + remove_socket_file(); +} + +/* Test 1: peer closes normally */ +TEST_F(unix_sock, eof) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + close(self->child); + } else { + close(self->server); + } + + n = recv(self->client, buf, sizeof(buf), 0); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(0, n); + } else { + ASSERT_EQ(-1, n); + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 2: peer closes with unread data */ +TEST_F(unix_sock, reset_unread_behavior) +{ + char buf[16] = {}; + ssize_t n; + + /* Send data that will remain unread */ + send(self->client, "hello", 5, 0); + + if (variant->socket_type == SOCK_DGRAM) { + /* No real connection, just close the server */ + close(self->server); + } else { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + /* Peer closes before client reads */ + close(self->child); + } + + n = recv(self->client, buf, sizeof(buf), 0); + ASSERT_EQ(-1, n); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(ECONNRESET, errno); + } else { + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 3: closing unaccepted (embryo) server socket should reset client. */ +TEST_F(unix_sock, reset_closed_embryo) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_DGRAM) { + snprintf(_metadata->results->reason, + sizeof(_metadata->results->reason), + "Test only applies to SOCK_STREAM and SOCK_SEQPACKET"); + exit(KSFT_XFAIL); + } + + /* Close server without accept()ing */ + close(self->server); + + n = recv(self->client, buf, sizeof(buf), 0); + + ASSERT_EQ(-1, n); + ASSERT_EQ(ECONNRESET, errno); +} + +TEST_HARNESS_MAIN + diff --git a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh index 92eb880c52f2..00758f00efbf 100755 --- a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh +++ b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh @@ -75,7 +75,7 @@ setup_v4() { ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1 if [ $? -ne 0 ]; then cleanup_v4 - echo "failed" + echo "failed; is the system using MACAddressPolicy=persistent ?" exit 1 fi diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh index 7d2d40812074..5ec1c85c1623 100755 --- a/tools/testing/selftests/net/busy_poll_test.sh +++ b/tools/testing/selftests/net/busy_poll_test.sh @@ -27,6 +27,8 @@ NAPI_DEFER_HARD_IRQS=100 GRO_FLUSH_TIMEOUT=50000 SUSPEND_TIMEOUT=20000000 +NAPI_THREADED_MODE_BUSY_POLL=2 + setup_ns() { set -e @@ -62,6 +64,9 @@ cleanup_ns() test_busypoll() { suspend_value=${1:-0} + napi_threaded_value=${2:-0} + prefer_busy_poll_value=${3:-$PREFER_BUSY_POLL} + tmp_file=$(mktemp) out_file=$(mktemp) @@ -73,10 +78,11 @@ test_busypoll() -b${SERVER_IP} \ -m${MAX_EVENTS} \ -u${BUSY_POLL_USECS} \ - -P${PREFER_BUSY_POLL} \ + -P${prefer_busy_poll_value} \ -g${BUSY_POLL_BUDGET} \ -i${NSIM_SV_IFIDX} \ -s${suspend_value} \ + -t${napi_threaded_value} \ -o${out_file}& wait_local_port_listen nssv ${SERVER_PORT} tcp @@ -109,6 +115,15 @@ test_busypoll_with_suspend() return $? } +test_busypoll_with_napi_threaded() +{ + # Only enable napi threaded poll. Set suspend timeout and prefer busy + # poll to 0. + test_busypoll 0 ${NAPI_THREADED_MODE_BUSY_POLL} 0 + + return $? +} + ### ### Code start ### @@ -154,6 +169,13 @@ if [ $? -ne 0 ]; then exit 1 fi +test_busypoll_with_napi_threaded +if [ $? -ne 0 ]; then + echo "test_busypoll_with_napi_threaded failed" + cleanup_ns + exit 1 +fi + echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c index 04c7ff577bb8..3a81f9c94795 100644 --- a/tools/testing/selftests/net/busy_poller.c +++ b/tools/testing/selftests/net/busy_poller.c @@ -65,15 +65,16 @@ static uint32_t cfg_busy_poll_usecs; static uint16_t cfg_busy_poll_budget; static uint8_t cfg_prefer_busy_poll; -/* IRQ params */ +/* NAPI params */ static uint32_t cfg_defer_hard_irqs; static uint64_t cfg_gro_flush_timeout; static uint64_t cfg_irq_suspend_timeout; +static enum netdev_napi_threaded cfg_napi_threaded_poll = NETDEV_NAPI_THREADED_DISABLED; static void usage(const char *filepath) { error(1, 0, - "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -i<ifindex>", + "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -t<napi_threaded_poll> -i<ifindex>", filepath); } @@ -86,7 +87,7 @@ static void parse_opts(int argc, char **argv) if (argc <= 1) usage(argv[0]); - while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) { + while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:t:")) != -1) { /* most options take integer values, except o and b, so reduce * code duplication a bit for the common case by calling * strtoull here and leave bounds checking and casting per @@ -168,6 +169,12 @@ static void parse_opts(int argc, char **argv) cfg_ifindex = (int)tmp; break; + case 't': + if (tmp > 2) + error(1, ERANGE, "napi threaded poll value must be 0-2"); + + cfg_napi_threaded_poll = (enum netdev_napi_threaded)tmp; + break; } } @@ -247,6 +254,9 @@ static void setup_queue(void) netdev_napi_set_req_set_irq_suspend_timeout(set_req, cfg_irq_suspend_timeout); + if (cfg_napi_threaded_poll) + netdev_napi_set_req_set_threaded(set_req, cfg_napi_threaded_poll); + if (netdev_napi_set(ys, set_req)) error(1, 0, "can't set NAPI params: %s\n", yerr.msg); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a94b73a53f72..a88f797c549a 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -11,7 +11,8 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \ ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \ - ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance" + ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance \ + fib6_ra_to_static" VERBOSE=0 PAUSE_ON_FAIL=no @@ -1476,6 +1477,68 @@ ipv6_route_metrics_test() route_cleanup } +fib6_ra_to_static() +{ + setup + + echo + echo "Fib6 route promotion from RA-learned to static test" + set -e + + # ra6 is required for the test. (ipv6toolkit) + if [ ! -x "$(command -v ra6)" ]; then + echo "SKIP: ra6 not found." + set +e + cleanup &> /dev/null + return + fi + + # Create a pair of veth devices to send a RA message from one + # device to another. + $IP link add veth1 type veth peer name veth2 + $IP link set dev veth1 up + $IP link set dev veth2 up + $IP -6 address add 2001:10::1/64 dev veth1 nodad + $IP -6 address add 2001:10::2/64 dev veth2 nodad + + # Make veth1 ready to receive RA messages. + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_ra=2 + + # Send a RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + + # Wait for the RA message. + sleep 1 + + # systemd may mess up the test. Make sure that + # systemd-networkd.service and systemd-networkd.socket are stopped. + check_rt_num_clean 2 $($IP -6 route list|grep expires|wc -l) || return + + # Configure static address on the same prefix + $IP -6 address add 2001:12::dead/64 dev veth1 nodad + + # On-link route won't expire anymore, default route still owned by RA + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + # Send a second RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + sleep 1 + + # Expire is not back, on-link route is still static + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + $IP -6 address del 2001:12::dead/64 dev veth1 nodad + + # Expire is back, on-link route is now owned by RA again + check_rt_num 2 $($IP -6 route list |grep expires|wc -l) + + log_test $ret 0 "ipv6 promote RA route to static" + + set +e + + cleanup &> /dev/null +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route() @@ -2798,6 +2861,7 @@ do ipv6_mpath_list) ipv6_mpath_list_test;; ipv4_mpath_balance) ipv4_mpath_balance_test;; ipv6_mpath_balance) ipv6_mpath_balance_test;; + fib6_ra_to_static) fib6_ra_to_static;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 8c1597ebc2d3..e86d77946585 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -28,6 +28,7 @@ ALL_TESTS=" cfg_test fwd_test ctrl_test + disable_test " NUM_NETIFS=4 @@ -64,7 +65,10 @@ h2_destroy() switch_create() { - ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + local vlan_filtering=$1; shift + + ip link add name br0 type bridge \ + vlan_filtering "$vlan_filtering" vlan_default_pvid 0 \ mcast_snooping 1 mcast_igmp_version 3 mcast_mld_version 2 bridge vlan add vid 10 dev br0 self bridge vlan add vid 20 dev br0 self @@ -118,7 +122,7 @@ setup_prepare() h1_create h2_create - switch_create + switch_create 1 } cleanup() @@ -1357,6 +1361,98 @@ ctrl_test() ctrl_mldv2_is_in_test } +check_group() +{ + local group=$1; shift + local vid=$1; shift + local should_fail=$1; shift + local when=$1; shift + local -a vidkws + + if ((vid)); then + vidkws=(vid "$vid") + fi + + bridge mdb get dev br0 grp "$group" "${vidkws[@]}" 2>/dev/null | + grep -q "port $swp1" + check_err_fail "$should_fail" $? "$group seen $when snooping disable:" +} + +__disable_test() +{ + local vid=$1; shift + local what=$1; shift + local -a vidkws + + if ((vid)); then + vidkws=(vid "$vid") + fi + + RET=0 + + bridge mdb add dev br0 port "$swp1" grp ff0e::1 permanent \ + "${vidkws[@]}" filter_mode include source_list 2001:db8:1::1 + bridge mdb add dev br0 port "$swp1" grp ff0e::2 permanent \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp ff0e::3 \ + "${vidkws[@]}" filter_mode include source_list 2001:db8:1::2 + bridge mdb add dev br0 port "$swp1" grp ff0e::4 \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp 239.1.1.1 permanent \ + "${vidkws[@]}" filter_mode include source_list 192.0.2.1 + bridge mdb add dev br0 port "$swp1" grp 239.1.1.2 permanent \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp 239.1.1.3 \ + "${vidkws[@]}" filter_mode include source_list 192.0.2.2 + bridge mdb add dev br0 port "$swp1" grp 239.1.1.4 \ + "${vidkws[@]}" filter_mode exclude + + check_group ff0e::1 "$vid" 0 "before" + check_group ff0e::2 "$vid" 0 "before" + check_group ff0e::3 "$vid" 0 "before" + check_group ff0e::4 "$vid" 0 "before" + + check_group 239.1.1.1 "$vid" 0 "before" + check_group 239.1.1.2 "$vid" 0 "before" + check_group 239.1.1.3 "$vid" 0 "before" + check_group 239.1.1.4 "$vid" 0 "before" + + ip link set dev br0 type bridge mcast_snooping 0 + + check_group ff0e::1 "$vid" 0 "after" + check_group ff0e::2 "$vid" 0 "after" + check_group ff0e::3 "$vid" 1 "after" + check_group ff0e::4 "$vid" 1 "after" + + check_group 239.1.1.1 "$vid" 0 "after" + check_group 239.1.1.2 "$vid" 0 "after" + check_group 239.1.1.3 "$vid" 1 "after" + check_group 239.1.1.4 "$vid" 1 "after" + + log_test "$what: Flush after disable" + + ip link set dev br0 type bridge mcast_snooping 1 + sleep 10 +} + +disable_test() +{ + __disable_test 10 802.1q + + switch_destroy + switch_create 0 + setup_wait + + __disable_test 0 802.1d + + switch_destroy + switch_create 1 + setup_wait +} + if ! bridge mdb help 2>&1 | grep -q "flush"; then echo "SKIP: iproute2 too old, missing bridge mdb flush support" exit $ksft_skip diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh deleted file mode 100755 index 4c5144c6f652..000000000000 --- a/tools/testing/selftests/net/gro.sh +++ /dev/null @@ -1,105 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly SERVER_MAC="aa:00:00:00:00:02" -readonly CLIENT_MAC="aa:00:00:00:00:01" -readonly TESTS=("data" "ack" "flags" "tcp" "ip" "large") -readonly PROTOS=("ipv4" "ipv6" "ipip") -dev="" -test="all" -proto="ipv4" - -run_test() { - local server_pid=0 - local exit_code=0 - local protocol=$1 - local test=$2 - local ARGS=( "--${protocol}" "--dmac" "${SERVER_MAC}" \ - "--smac" "${CLIENT_MAC}" "--test" "${test}" "--verbose" ) - - setup_ns - # Each test is run 6 times to deflake, because given the receive timing, - # not all packets that should coalesce will be considered in the same flow - # on every try. - for tries in {1..6}; do - # Actual test starts here - ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \ - 1>>log.txt & - server_pid=$! - sleep 0.5 # to allow for socket init - ip netns exec $client_ns ./gro "${ARGS[@]}" "--iface" "client" \ - 1>>log.txt - wait "${server_pid}" - exit_code=$? - if [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \ - ${exit_code} -ne 0 ]]; then - echo "Ignoring errors due to slow environment" 1>&2 - exit_code=0 - fi - if [[ "${exit_code}" -eq 0 ]]; then - break; - fi - done - cleanup_ns - echo ${exit_code} -} - -run_all_tests() { - local failed_tests=() - for proto in "${PROTOS[@]}"; do - for test in "${TESTS[@]}"; do - echo "running test ${proto} ${test}" >&2 - exit_code=$(run_test $proto $test) - if [[ "${exit_code}" -ne 0 ]]; then - failed_tests+=("${proto}_${test}") - fi; - done; - done - if [[ ${#failed_tests[@]} -ne 0 ]]; then - echo "failed tests: ${failed_tests[*]}. \ - Please see log.txt for more logs" - exit 1 - else - echo "All Tests Succeeded!" - fi; -} - -usage() { - echo "Usage: $0 \ - [-i <DEV>] \ - [-t data|ack|flags|tcp|ip|large] \ - [-p <ipv4|ipv6>]" 1>&2; - exit 1; -} - -while getopts "i:t:p:" opt; do - case "${opt}" in - i) - dev="${OPTARG}" - ;; - t) - test="${OPTARG}" - ;; - p) - proto="${OPTARG}" - ;; - *) - usage - ;; - esac -done - -if [ -n "$dev" ]; then - source setup_loopback.sh -else - source setup_veth.sh -fi - -setup -trap cleanup EXIT -if [[ "${test}" == "all" ]]; then - run_all_tests -else - exit_code=$(run_test "${proto}" "${test}") - exit $exit_code -fi; diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c index 76e604e4810e..7bfeeb133705 100644 --- a/tools/testing/selftests/net/io_uring_zerocopy_tx.c +++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c @@ -106,14 +106,14 @@ static void do_tx(int domain, int type, int protocol) ret = io_uring_queue_init(512, &ring, 0); if (ret) - error(1, ret, "io_uring: queue init"); + error(1, -ret, "io_uring: queue init"); iov.iov_base = payload; iov.iov_len = cfg_payload_len; ret = io_uring_register_buffers(&ring, &iov, 1); if (ret) - error(1, ret, "io_uring: buffer registration"); + error(1, -ret, "io_uring: buffer registration"); tstop = gettimeofday_ms() + cfg_runtime_ms; do { @@ -149,24 +149,24 @@ static void do_tx(int domain, int type, int protocol) ret = io_uring_submit(&ring); if (ret != cfg_nr_reqs) - error(1, ret, "submit"); + error(1, -ret, "submit"); if (cfg_cork) do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); for (i = 0; i < cfg_nr_reqs; i++) { ret = io_uring_wait_cqe(&ring, &cqe); if (ret) - error(1, ret, "wait cqe"); + error(1, -ret, "wait cqe"); if (cqe->user_data != NONZC_TAG && cqe->user_data != ZC_TAG) - error(1, -EINVAL, "invalid cqe->user_data"); + error(1, EINVAL, "invalid cqe->user_data"); if (cqe->flags & IORING_CQE_F_NOTIF) { if (cqe->flags & IORING_CQE_F_MORE) - error(1, -EINVAL, "invalid notif flags"); + error(1, EINVAL, "invalid notif flags"); if (compl_cqes <= 0) - error(1, -EINVAL, "notification mismatch"); + error(1, EINVAL, "notification mismatch"); compl_cqes--; i--; io_uring_cqe_seen(&ring); @@ -174,14 +174,14 @@ static void do_tx(int domain, int type, int protocol) } if (cqe->flags & IORING_CQE_F_MORE) { if (cqe->user_data != ZC_TAG) - error(1, cqe->res, "unexpected F_MORE"); + error(1, -cqe->res, "unexpected F_MORE"); compl_cqes++; } if (cqe->res >= 0) { packets++; bytes += cqe->res; } else if (cqe->res != -EAGAIN) { - error(1, cqe->res, "send failed"); + error(1, -cqe->res, "send failed"); } io_uring_cqe_seen(&ring); } @@ -190,11 +190,11 @@ static void do_tx(int domain, int type, int protocol) while (compl_cqes) { ret = io_uring_wait_cqe(&ring, &cqe); if (ret) - error(1, ret, "wait cqe"); + error(1, -ret, "wait cqe"); if (cqe->flags & IORING_CQE_F_MORE) - error(1, -EINVAL, "invalid notif flags"); + error(1, EINVAL, "invalid notif flags"); if (!(cqe->flags & IORING_CQE_F_NOTIF)) - error(1, -EINVAL, "missing notif flag"); + error(1, EINVAL, "missing notif flag"); io_uring_cqe_seen(&ring); compl_cqes--; diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index ce795bc0a1af..5339f56329e1 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -8,6 +8,7 @@ CFLAGS += -I../../ TEST_FILES := \ ../../../../net/ynl \ ../../../../../Documentation/netlink/specs \ + ksft_setup_loopback.sh \ # end of TEST_FILES TEST_GEN_FILES := \ diff --git a/tools/testing/selftests/net/lib/ksft_setup_loopback.sh b/tools/testing/selftests/net/lib/ksft_setup_loopback.sh new file mode 100755 index 000000000000..3defbb1919c5 --- /dev/null +++ b/tools/testing/selftests/net/lib/ksft_setup_loopback.sh @@ -0,0 +1,111 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Setup script for running ksft tests over a real interface in loopback mode. +# This scripts replaces the historical setup_loopback.sh. It puts +# a (presumably) real hardware interface into loopback mode, creates macvlan +# interfaces on top and places them in a network namespace for isolation. +# +# NETIF env variable must be exported to indicate the real target device. +# Note that the test will override NETIF with one of the macvlans, the +# actual ksft test will only see the macvlans. +# +# Example use: +# export NETIF=eth0 +# ./net/lib/ksft_setup_loopback.sh ./drivers/net/gro.py + +if [ -z "$NETIF" ]; then + echo "Error: NETIF variable not set" + exit 1 +fi +if ! [ -d "/sys/class/net/$NETIF" ]; then + echo "Error: Can't find $NETIF, invalid netdevice" + exit 1 +fi + +# Save original settings for cleanup +readonly FLUSH_PATH="/sys/class/net/${NETIF}/gro_flush_timeout" +readonly IRQ_PATH="/sys/class/net/${NETIF}/napi_defer_hard_irqs" +FLUSH_TIMEOUT="$(< "${FLUSH_PATH}")" +readonly FLUSH_TIMEOUT +HARD_IRQS="$(< "${IRQ_PATH}")" +readonly HARD_IRQS + +SERVER_NS=$(mktemp -u server-XXXXXXXX) +readonly SERVER_NS +CLIENT_NS=$(mktemp -u client-XXXXXXXX) +readonly CLIENT_NS +readonly SERVER_MAC="aa:00:00:00:00:02" +readonly CLIENT_MAC="aa:00:00:00:00:01" + +# ksft expects addresses to communicate with remote +export LOCAL_V6=2001:db8:1::1 +export REMOTE_V6=2001:db8:1::2 + +cleanup() { + local exit_code=$? + + echo "Cleaning up..." + + # Remove macvlan interfaces and namespaces + ip -netns "${SERVER_NS}" link del dev server 2>/dev/null || true + ip netns del "${SERVER_NS}" 2>/dev/null || true + ip -netns "${CLIENT_NS}" link del dev client 2>/dev/null || true + ip netns del "${CLIENT_NS}" 2>/dev/null || true + + # Disable loopback + ethtool -K "${NETIF}" loopback off 2>/dev/null || true + sleep 1 + + echo "${FLUSH_TIMEOUT}" >"${FLUSH_PATH}" + echo "${HARD_IRQS}" >"${IRQ_PATH}" + + exit $exit_code +} + +trap cleanup EXIT INT TERM + +# Enable loopback mode +echo "Enabling loopback on ${NETIF}..." +ethtool -K "${NETIF}" loopback on || { + echo "Failed to enable loopback mode" + exit 1 +} +# The interface may need time to get carrier back, but selftests +# will wait for carrier, so no need to wait / sleep here. + +# Use timer on host to trigger the network stack +# Also disable device interrupt to not depend on NIC interrupt +# Reduce test flakiness caused by unexpected interrupts +echo 100000 >"${FLUSH_PATH}" +echo 50 >"${IRQ_PATH}" + +# Create server namespace with macvlan +ip netns add "${SERVER_NS}" +ip link add link "${NETIF}" dev server address "${SERVER_MAC}" type macvlan +ip link set dev server netns "${SERVER_NS}" +ip -netns "${SERVER_NS}" link set dev server up +ip -netns "${SERVER_NS}" addr add $LOCAL_V6/64 dev server +ip -netns "${SERVER_NS}" link set dev lo up + +# Create client namespace with macvlan +ip netns add "${CLIENT_NS}" +ip link add link "${NETIF}" dev client address "${CLIENT_MAC}" type macvlan +ip link set dev client netns "${CLIENT_NS}" +ip -netns "${CLIENT_NS}" link set dev client up +ip -netns "${CLIENT_NS}" addr add $REMOTE_V6/64 dev client +ip -netns "${CLIENT_NS}" link set dev lo up + +echo "Setup complete!" +echo " Device: ${NETIF}" +echo " Server NS: ${SERVER_NS}" +echo " Client NS: ${CLIENT_NS}" +echo "" + +# Setup environment variables for tests +export NETIF=server +export REMOTE_TYPE=netns +export REMOTE_ARGS="${CLIENT_NS}" + +# Run the command +ip netns exec "${SERVER_NS}" "$@" diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 97b7cf2b20eb..40f9ce307dd1 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -8,7 +8,8 @@ from .consts import KSRC from .ksft import KsftFailEx, KsftSkipEx, KsftXfailEx, ksft_pr, ksft_eq, \ ksft_ne, ksft_true, ksft_not_none, ksft_in, ksft_not_in, ksft_is, \ ksft_ge, ksft_gt, ksft_lt, ksft_raises, ksft_busy_wait, \ - ktap_result, ksft_disruptive, ksft_setup, ksft_run, ksft_exit + ktap_result, ksft_disruptive, ksft_setup, ksft_run, ksft_exit, \ + ksft_variants, KsftNamedVariant from .netns import NetNS, NetNSEnter from .nsim import NetdevSim, NetdevSimDev from .utils import CmdExitFailure, fd_read_timeout, cmd, bkg, defer, \ @@ -21,7 +22,7 @@ __all__ = ["KSRC", "ksft_ne", "ksft_true", "ksft_not_none", "ksft_in", "ksft_not_in", "ksft_is", "ksft_ge", "ksft_gt", "ksft_lt", "ksft_raises", "ksft_busy_wait", "ktap_result", "ksft_disruptive", "ksft_setup", - "ksft_run", "ksft_exit", + "ksft_run", "ksft_exit", "ksft_variants", "KsftNamedVariant", "NetNS", "NetNSEnter", "CmdExitFailure", "fd_read_timeout", "cmd", "bkg", "defer", "bpftool", "ip", "ethtool", "bpftrace", "rand_port", diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 83b1574f7719..531e7fa1b3ea 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -1,12 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 -import builtins import functools import inspect import signal import sys import time import traceback +from collections import namedtuple from .consts import KSFT_MAIN_NAME from .utils import global_defer_queue @@ -136,7 +136,7 @@ def ksft_busy_wait(cond, sleep=0.005, deadline=1, comment=""): time.sleep(sleep) -def ktap_result(ok, cnt=1, case="", comment=""): +def ktap_result(ok, cnt=1, case_name="", comment=""): global KSFT_RESULT_ALL KSFT_RESULT_ALL = KSFT_RESULT_ALL and ok @@ -146,8 +146,8 @@ def ktap_result(ok, cnt=1, case="", comment=""): res += "ok " res += str(cnt) + " " res += KSFT_MAIN_NAME - if case: - res += "." + str(case.__name__) + if case_name: + res += "." + case_name if comment: res += " # " + comment print(res, flush=True) @@ -163,7 +163,7 @@ def ksft_flush_defer(): entry = global_defer_queue.pop() try: entry.exec_only() - except: + except Exception: ksft_pr(f"Exception while handling defer / cleanup (callback {i} of {qlen_start})!") tb = traceback.format_exc() for line in tb.strip().split('\n'): @@ -171,6 +171,10 @@ def ksft_flush_defer(): KSFT_RESULT = False +KsftCaseFunction = namedtuple("KsftCaseFunction", + ['name', 'original_func', 'variants']) + + def ksft_disruptive(func): """ Decorator that marks the test as disruptive (e.g. the test @@ -181,11 +185,47 @@ def ksft_disruptive(func): @functools.wraps(func) def wrapper(*args, **kwargs): if not KSFT_DISRUPTIVE: - raise KsftSkipEx(f"marked as disruptive") + raise KsftSkipEx("marked as disruptive") return func(*args, **kwargs) return wrapper +class KsftNamedVariant: + """ Named string name + argument list tuple for @ksft_variants """ + + def __init__(self, name, *params): + self.params = params + self.name = name or "_".join([str(x) for x in self.params]) + + +def ksft_variants(params): + """ + Decorator defining the sets of inputs for a test. + The parameters will be included in the name of the resulting sub-case. + Parameters can be either single object, tuple or a KsftNamedVariant. + The argument can be a list or a generator. + + Example: + + @ksft_variants([ + (1, "a"), + (2, "b"), + KsftNamedVariant("three", 3, "c"), + ]) + def my_case(cfg, a, b): + pass # ... + + ksft_run(cases=[my_case], args=(cfg, )) + + Will generate cases: + my_case.1_a + my_case.2_b + my_case.three + """ + + return lambda func: KsftCaseFunction(func.__name__, func, params) + + def ksft_setup(env): """ Setup test framework global state from the environment. @@ -199,7 +239,7 @@ def ksft_setup(env): return False try: return bool(int(value)) - except: + except Exception: raise Exception(f"failed to parse {name}") if "DISRUPTIVE" in env: @@ -220,9 +260,13 @@ def _ksft_intr(signum, frame): ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...") -def ksft_run(cases=None, globs=None, case_pfx=None, args=()): +def _ksft_generate_test_cases(cases, globs, case_pfx, args): + """Generate a flat list of (func, args, name) tuples""" + cases = cases or [] + test_cases = [] + # If using the globs method find all relevant functions if globs and case_pfx: for key, value in globs.items(): if not callable(value): @@ -232,6 +276,27 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): cases.append(value) break + for func in cases: + if isinstance(func, KsftCaseFunction): + # Parametrized test - create case for each param + for param in func.variants: + if not isinstance(param, KsftNamedVariant): + if not isinstance(param, tuple): + param = (param, ) + param = KsftNamedVariant(None, *param) + + test_cases.append((func.original_func, + (*args, *param.params), + func.name + "." + param.name)) + else: + test_cases.append((func, args, func.__name__)) + + return test_cases + + +def ksft_run(cases=None, globs=None, case_pfx=None, args=()): + test_cases = _ksft_generate_test_cases(cases, globs, case_pfx, args) + global term_cnt term_cnt = 0 prev_sigterm = signal.signal(signal.SIGTERM, _ksft_intr) @@ -239,19 +304,19 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} print("TAP version 13", flush=True) - print("1.." + str(len(cases)), flush=True) + print("1.." + str(len(test_cases)), flush=True) global KSFT_RESULT cnt = 0 stop = False - for case in cases: + for func, args, name in test_cases: KSFT_RESULT = True cnt += 1 comment = "" cnt_key = "" try: - case(*args) + func(*args) except KsftSkipEx as e: comment = "SKIP " + str(e) cnt_key = 'skip' @@ -268,12 +333,26 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): KSFT_RESULT = False cnt_key = 'fail' - ksft_flush_defer() + try: + ksft_flush_defer() + except BaseException as e: + tb = traceback.format_exc() + for line in tb.strip().split('\n'): + ksft_pr("Exception|", line) + if isinstance(e, KeyboardInterrupt): + ksft_pr() + ksft_pr("WARN: defer() interrupted, cleanup may be incomplete.") + ksft_pr(" Attempting to finish cleanup before exiting.") + ksft_pr(" Interrupt again to exit immediately.") + ksft_pr() + stop = True + # Flush was interrupted, try to finish the job best we can + ksft_flush_defer() if not cnt_key: cnt_key = 'pass' if KSFT_RESULT else 'fail' - ktap_result(KSFT_RESULT, cnt, case, comment=comment) + ktap_result(KSFT_RESULT, cnt, name, comment=comment) totals[cnt_key] += 1 if stop: diff --git a/tools/testing/selftests/net/lib/py/nsim.py b/tools/testing/selftests/net/lib/py/nsim.py index 1a8cbe9acc48..7c640ed64c0b 100644 --- a/tools/testing/selftests/net/lib/py/nsim.py +++ b/tools/testing/selftests/net/lib/py/nsim.py @@ -27,7 +27,7 @@ class NetdevSim: self.port_index = port_index self.ns = ns self.dfs_dir = "%s/ports/%u/" % (nsimdev.dfs_dir, port_index) - ret = ip("-j link show dev %s" % ifname, ns=ns) + ret = ip("-d -j link show dev %s" % ifname, ns=ns) self.dev = json.loads(ret.stdout)[0] self.ifindex = self.dev["ifindex"] diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index cb40ecef9456..106ee1f2df86 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -32,7 +32,7 @@ class cmd: Use bkg() instead to run a command in the background. """ def __init__(self, comm, shell=None, fail=True, ns=None, background=False, - host=None, timeout=5, ksft_wait=None): + host=None, timeout=5, ksft_ready=None, ksft_wait=None): if ns: comm = f'ip netns exec {ns} ' + comm @@ -52,21 +52,25 @@ class cmd: # ksft_wait lets us wait for the background process to fully start, # we pass an FD to the child process, and wait for it to write back. # Similarly term_fd tells child it's time to exit. - pass_fds = () + pass_fds = [] env = os.environ.copy() if ksft_wait is not None: - rfd, ready_fd = os.pipe() wait_fd, self.ksft_term_fd = os.pipe() - pass_fds = (ready_fd, wait_fd, ) - env["KSFT_READY_FD"] = str(ready_fd) + pass_fds.append(wait_fd) env["KSFT_WAIT_FD"] = str(wait_fd) + ksft_ready = True # ksft_wait implies ready + if ksft_ready is not None: + rfd, ready_fd = os.pipe() + pass_fds.append(ready_fd) + env["KSFT_READY_FD"] = str(ready_fd) self.proc = subprocess.Popen(comm, shell=shell, stdout=subprocess.PIPE, stderr=subprocess.PIPE, pass_fds=pass_fds, env=env) if ksft_wait is not None: - os.close(ready_fd) os.close(wait_fd) + if ksft_ready is not None: + os.close(ready_fd) msg = fd_read_timeout(rfd, ksft_wait) os.close(rfd) if not msg: @@ -116,10 +120,10 @@ class bkg(cmd): with bkg("my_binary", ksft_wait=5): """ def __init__(self, comm, shell=None, fail=None, ns=None, host=None, - exit_wait=False, ksft_wait=None): + exit_wait=False, ksft_ready=None, ksft_wait=None): super().__init__(comm, background=True, shell=shell, fail=fail, ns=ns, host=host, - ksft_wait=ksft_wait) + ksft_ready=ksft_ready, ksft_wait=ksft_wait) self.terminate = not exit_wait and not ksft_wait self._exit_wait = exit_wait self.check_fail = fail diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c index c368fc045f4b..64f05229ab24 100644 --- a/tools/testing/selftests/net/lib/xdp_native.bpf.c +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -332,7 +332,7 @@ static __u16 csum_fold_helper(__u32 csum) } static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, - __u32 hdr_len) + unsigned long hdr_len) { char tmp_buff[MAX_ADJST_OFFSET]; __u32 buff_pos, udp_csum = 0; @@ -422,8 +422,9 @@ static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) { struct udphdr *udph = NULL; __s32 *adjust_offset, *val; - __u32 key, hdr_len; + unsigned long hdr_len; void *offset_ptr; + __u32 key; __u8 tag; int ret; diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index fc7e22b503d3..404a77bf366a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1072,6 +1072,8 @@ static void check_getpeername_connect(int fd) socklen_t salen = sizeof(ss); char a[INET6_ADDRSTRLEN]; char b[INET6_ADDRSTRLEN]; + const char *iface; + size_t len; if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) { perror("getpeername"); @@ -1081,7 +1083,13 @@ static void check_getpeername_connect(int fd) xgetnameinfo((struct sockaddr *)&ss, salen, a, sizeof(a), b, sizeof(b)); - if (strcmp(cfg_host, a) || strcmp(cfg_port, b)) + iface = strchr(cfg_host, '%'); + if (iface) + len = iface - cfg_host; + else + len = strlen(cfg_host) + 1; + + if (strncmp(cfg_host, a, len) || strcmp(cfg_port, b)) fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__, cfg_host, a, cfg_port, b); } diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 9b7b93f8eb0c..a6447f7a31fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -375,81 +375,75 @@ do_transfer() local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}" local capopt="-i any -s 65535 -B 32768 ${capuser}" - ip netns exec ${listener_ns} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + ip netns exec ${listener_ns} tcpdump ${capopt} \ + -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & local cappid_listener=$! - ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & - local cappid_connector=$! + if [ ${listener_ns} != ${connector_ns} ]; then + ip netns exec ${connector_ns} tcpdump ${capopt} \ + -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! + fi sleep 1 fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - fi - - local stat_synrx_last_l - local stat_ackrx_last_l - local stat_cookietx_last - local stat_cookierx_last - local stat_csum_err_s - local stat_csum_err_c - local stat_tcpfb_last_l - stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_args $local_addr < "$sin" > "$sout" & + mptcp_lib_nstat_init "${connector_ns}" + fi + + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args $local_addr < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" local start start=$(date +%s%3N) - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + local stop stop=$(date +%s%3N) if $capture; then sleep 1 kill ${cappid_listener} - kill ${cappid_connector} + if [ ${listener_ns} != ${connector_ns} ]; then + kill ${cappid_connector} + fi fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out + mptcp_lib_nstat_get "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${connector_ns}" fi local duration duration=$((stop-start)) printf "(duration %05sms) " "${duration}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" echo cat "$capout" @@ -463,38 +457,38 @@ do_transfer() rets=$? local extra="" - local stat_synrx_now_l - local stat_ackrx_now_l - local stat_cookietx_now - local stat_cookierx_now - local stat_ooo_now - local stat_tcpfb_now_l - stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") - stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - expect_synrx=$((stat_synrx_last_l)) - expect_ackrx=$((stat_ackrx_last_l)) + local stat_synrx + local stat_ackrx + local stat_cookietx + local stat_cookierx + local stat_ooo + local stat_tcpfb + stat_synrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_ooo=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + stat_tcpfb=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") + + expect_synrx=0 + expect_ackrx=0 cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) cookies=${cookies##*=} if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then - expect_synrx=$((stat_synrx_last_l+connect_per_transfer)) - expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer)) + expect_synrx=${connect_per_transfer} + expect_ackrx=${connect_per_transfer} fi - if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then - mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx_now_l})" \ + if [ ${stat_synrx} -lt ${expect_synrx} ]; then + mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx})" \ "than expected (${expect_synrx})" retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then - if [ ${stat_ooo_now} -eq 0 ]; then - mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx_now_l})" \ + if [ ${stat_ackrx} -lt ${expect_ackrx} ]; then + if [ ${stat_ooo} -eq 0 ]; then + mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx})" \ "than expected (${expect_ackrx})" rets=1 else @@ -508,47 +502,45 @@ do_transfer() csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) - if [ $csum_err_s_nr -gt 0 ]; then - mptcp_lib_pr_fail "server got ${csum_err_s_nr} data checksum error[s]" + if [ $csum_err_s -gt 0 ]; then + mptcp_lib_pr_fail "server got ${csum_err_s} data checksum error[s]" rets=1 fi - local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) - if [ $csum_err_c_nr -gt 0 ]; then - mptcp_lib_pr_fail "client got ${csum_err_c_nr} data checksum error[s]" + if [ $csum_err_c -gt 0 ]; then + mptcp_lib_pr_fail "client got ${csum_err_c} data checksum error[s]" retc=1 fi fi - if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + if [ ${stat_ooo} -eq 0 ] && [ ${stat_tcpfb} -gt 0 ]; then mptcp_lib_pr_fail "unexpected fallback to TCP" rets=1 fi if [ $cookies -eq 2 ];then - if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + if [ $stat_cookietx -eq 0 ] ;then extra+=" WARN: CookieSent: did not advance" fi - if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + if [ $stat_cookierx -eq 0 ] ;then extra+=" WARN: CookieRecv: did not advance" fi else - if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + if [ $stat_cookietx -gt 0 ] ;then extra+=" WARN: CookieSent: changed" fi - if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + if [ $stat_cookierx -gt 0 ] ;then extra+=" WARN: CookieRecv: changed" fi fi - if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then + if [ ${stat_synrx} -gt ${expect_synrx} ]; then extra+=" WARN: SYNRX: expect ${expect_synrx}," - extra+=" got ${stat_synrx_now_l} (probably retransmissions)" + extra+=" got ${stat_synrx} (probably retransmissions)" fi - if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then + if [ ${stat_ackrx} -gt ${expect_ackrx} ]; then extra+=" WARN: ACKRX: expect ${expect_ackrx}," - extra+=" got ${stat_ackrx_now_l} (probably retransmissions)" + extra+=" got ${stat_ackrx} (probably retransmissions)" fi if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 43f31f8d587f..b2e6e548f796 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -62,6 +62,7 @@ unset sflags unset fastclose unset fullmesh unset speed +unset bind_addr unset join_syn_rej unset join_csum_ns1 unset join_csum_ns2 @@ -645,6 +646,27 @@ wait_mpj() done } +wait_ll_ready() +{ + local ns="${1}" + + local i + for i in $(seq 50); do + ip -n "${ns}" -6 addr show scope link | grep "inet6 fe80" | + grep -qw "tentative" || break + sleep 0.1 + done +} + +get_ll_addr() +{ + local ns="${1}" + local iface="${2}" + + ip -n "${ns}" -6 addr show dev "${iface}" scope link | + grep "inet6 fe80" | sed 's#.*\(fe80::.*\)/.*#\1#' +} + kill_events_pids() { mptcp_lib_kill_wait $evts_ns1_pid @@ -951,6 +973,9 @@ do_transfer() local FAILING_LINKS=${FAILING_LINKS:-""} local fastclose=${fastclose:-""} local speed=${speed:-"fast"} + local bind_addr=${bind_addr:-"::"} + local listener_in="${sin}" + local connector_in="${cin}" port=$(get_port) :> "$cout" @@ -958,10 +983,8 @@ do_transfer() cond_start_capture ${listener_ns} - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" local extra_args if [ $speed = "fast" ]; then @@ -999,42 +1022,40 @@ do_transfer() extra_srv_args="$extra_args $extra_srv_args" if [ "$test_linkfail" -gt 1 ];then - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sinfail" > "$sout" & - else - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sin" > "$sout" & + listener_in="${sinfail}" fi + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p ${port} -s ${srv_proto} \ + ${extra_srv_args} "${bind_addr}" < "${listener_in}" > "${sout}" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" extra_cl_args="$extra_args $extra_cl_args" if [ "$test_linkfail" -eq 0 ];then - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr < "$cin" > "$cout" & elif [ "$test_linkfail" -eq 1 ] || [ "$test_linkfail" -eq 2 ];then + connector_in="${cinsent}" ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ tee "$cinsent" | \ - timeout ${timeout_test} \ ip netns exec ${connector_ns} \ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_cl_args $connect_addr > "$cout" & else + connector_in="${cinsent}" tee "$cinsent" < "$cinfail" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & fi local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr check_cestab $listener_ns $connector_ns @@ -1043,31 +1064,26 @@ do_transfer() wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + cond_stop_capture - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then fail_test "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" return 1 fi - if [ "$test_linkfail" -gt 1 ];then - check_transfer $sinfail $cout "file received by client" $trunc_size - else - check_transfer $sin $cout "file received by client" $trunc_size - fi + check_transfer $listener_in $cout "file received by client" $trunc_size retc=$? - if [ "$test_linkfail" -eq 0 ];then - check_transfer $cin $sout "file received by server" $trunc_size - else - check_transfer $cinsent $sout "file received by server" $trunc_size - fi + check_transfer $connector_in $sout "file received by server" $trunc_size rets=$? [ $retc -eq 0 ] && [ $rets -eq 0 ] @@ -1136,12 +1152,20 @@ run_tests() do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} } +_dump_stats() +{ + local ns="${1}" + local side="${2}" + + mptcp_lib_print_err "${side} ns stats (${ns2})" + mptcp_lib_pr_nstat "${ns}" + echo +} + dump_stats() { - echo Server ns stats - ip netns exec $ns1 nstat -as | grep Tcp - echo Client ns stats - ip netns exec $ns2 nstat -as | grep Tcp + _dump_stats "${ns1}" "Server" + _dump_stats "${ns2}" "Client" } chk_csum_nr() @@ -2952,7 +2976,11 @@ mixed_tests() pm_nl_add_endpoint $ns1 10.0.1.1 flags signal speed=slow \ run_tests $ns1 $ns2 dead:beef:2::1 - chk_join_nr 1 1 1 + if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_fullmesh_max$"; then + chk_join_nr 0 0 0 + else + chk_join_nr 1 1 1 + fi fi # fullmesh still tries to create all the possibly subflows with @@ -3233,6 +3261,133 @@ add_addr_ports_tests() fi } +bind_tests() +{ + # bind to one address should not allow extra subflows to other addresses + if reset "bind main address v4, no join v4"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + bind_addr="10.0.1.1" \ + run_tests $ns1 $ns2 10.0.1.1 + join_syn_tx=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # bind to one address should not allow extra subflows to other addresses + if reset "bind main address v6, no join v6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + bind_addr="dead:beef:1::1" \ + run_tests $ns1 $ns2 dead:beef:1::1 + join_syn_tx=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # multiple binds to allow extra subflows to other addresses + if reset "multiple bind to allow joins v4"; then + local extra_bind + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + + # Launching another app listening on a different address + # Note: it could be a totally different app, e.g. nc, socat, ... + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP 10.0.2.1 & + extra_bind=$! + + bind_addr="10.0.1.1" \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to other addresses + if reset "multiple bind to allow joins v6"; then + local extra_bind + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + + # Launching another app listening on a different address + # Note: it could be a totally different app, e.g. nc, socat, ... + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP dead:beef:2::1 & + extra_bind=$! + + bind_addr="dead:beef:1::1" \ + run_tests $ns1 $ns2 dead:beef:1::1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to other addresses: v6 LL case + if reset "multiple bind to allow joins v6 link-local routing"; then + local extra_bind ns1ll1 ns1ll2 + + ns1ll1="$(get_ll_addr $ns1 ns1eth1)" + ns1ll2="$(get_ll_addr $ns1 ns1eth2)" + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 "${ns1ll2}" flags signal + + wait_ll_ready $ns1 # to be able to bind + wait_ll_ready $ns2 # also needed to bind on the client side + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP "${ns1ll2}%ns1eth2" & + extra_bind=$! + + bind_addr="${ns1ll1}%ns1eth1" \ + run_tests $ns1 $ns2 "${ns1ll1}%ns2eth1" + # it is not possible to connect to the announced LL addr without + # specifying the outgoing interface. + join_connect_err=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to v6 LL addresses: laminar + if reset "multiple bind to allow joins v6 link-local laminar" && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + local extra_bind ns1ll1 ns1ll2 ns2ll2 + + ns1ll1="$(get_ll_addr $ns1 ns1eth1)" + ns1ll2="$(get_ll_addr $ns1 ns1eth2)" + ns2ll2="$(get_ll_addr $ns2 ns2eth2)" + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 "${ns1ll2}" flags signal + pm_nl_add_endpoint $ns2 "${ns2ll2}" flags laminar dev ns2eth2 + + wait_ll_ready $ns1 # to be able to bind + wait_ll_ready $ns2 # also needed to bind on the client side + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP "${ns1ll2}%ns1eth2" & + extra_bind=$! + + bind_addr="${ns1ll1}%ns1eth1" \ + run_tests $ns1 $ns2 "${ns1ll1}%ns2eth1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi +} + syncookies_tests() { # single subflow, syncookies @@ -4192,6 +4347,7 @@ all_tests_sorted=( M@mixed_tests b@backup_tests p@add_addr_ports_tests + B@bind_tests k@syncookies_tests S@checksum_tests d@deny_join_id0_tests diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index f4388900016a..5fea7e7df628 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -106,23 +106,32 @@ mptcp_lib_pr_info() { mptcp_lib_print_info "INFO: ${*}" } -# $1-2: listener/connector ns ; $3 port ; $4-5 listener/connector stat file +mptcp_lib_pr_nstat() { + local ns="${1}" + local hist="/tmp/${ns}.out" + + if [ -f "${hist}" ]; then + awk '$2 != 0 { print " "$0 }' "${hist}" + else + ip netns exec "${ns}" nstat -as | grep Tcp + fi +} + +# $1-2: listener/connector ns ; $3 port mptcp_lib_pr_err_stats() { local lns="${1}" local cns="${2}" local port="${3}" - local lstat="${4}" - local cstat="${5}" echo -en "${MPTCP_LIB_COLOR_RED}" { printf "\nnetns %s (listener) socket stat for %d:\n" "${lns}" "${port}" ip netns exec "${lns}" ss -Menitam -o "sport = :${port}" - cat "${lstat}" + mptcp_lib_pr_nstat "${lns}" printf "\nnetns %s (connector) socket stat for %d:\n" "${cns}" "${port}" ip netns exec "${cns}" ss -Menitam -o "dport = :${port}" - [ "${lstat}" != "${cstat}" ] && cat "${cstat}" + [ "${lns}" != "${cns}" ] && mptcp_lib_pr_nstat "${cns}" } 1>&2 echo -en "${MPTCP_LIB_COLOR_RESET}" } @@ -341,6 +350,19 @@ mptcp_lib_evts_get_info() { mptcp_lib_get_info_value "${1}" "^type:${3:-1}," } +mptcp_lib_wait_timeout() { + local timeout_test="${1}" + local listener_ns="${2}" + local connector_ns="${3}" + local port="${4}" + shift 4 # rest are PIDs + + sleep "${timeout_test}" + mptcp_lib_print_err "timeout" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" + kill "${@}" 2>/dev/null +} + # $1: PID mptcp_lib_kill_wait() { [ "${1}" -eq 0 ] && return 0 @@ -376,14 +398,36 @@ mptcp_lib_is_v6() { [ -z "${1##*:*}" ] } +mptcp_lib_nstat_init() { + local ns="${1}" + + rm -f "/tmp/${ns}."{nstat,out} + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -n +} + +mptcp_lib_nstat_get() { + local ns="${1}" + + # filter out non-*TCP stats, and the rate (last column) + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -sz | + grep -o ".*Tcp\S\+\s\+[0-9]\+" > "/tmp/${ns}.out" +} + # $1: ns, $2: MIB counter +# Get the counter from the history (mptcp_lib_nstat_{init,get}()) if available. +# If not, get the counter from nstat ignoring any history. mptcp_lib_get_counter() { local ns="${1}" local counter="${2}" + local hist="/tmp/${ns}.out" local count - count=$(ip netns exec "${ns}" nstat -asz "${counter}" | - awk 'NR==1 {next} {print $2}') + if [[ -s "${hist}" && "${counter}" == *"Tcp"* ]]; then + count=$(awk "/^${counter} / {print \$2; exit}" "${hist}") + else + count=$(ip netns exec "${ns}" nstat -asz "${counter}" | + awk 'NR==1 {next} {print $2}') + fi if [ -z "${count}" ]; then mptcp_lib_fail_if_expected_feature "${counter} counter" return 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index f01989be6e9b..ab8bce06b262 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -169,41 +169,44 @@ do_transfer() cmsg+=",TCPINQ" fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ - ${local_addr} < "$sin" > "$sout" & + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" + + ip netns exec ${listener_ns} \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ + ${local_addr} < "$sin" > "$sout" & local spid=$! - sleep 1 + mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ - $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ + $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" print_title "Transfer ${ip:2}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" mptcp_lib_result_fail "transfer ${ip}" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 1903e8e84a31..806aaa7d2d61 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -155,48 +155,53 @@ do_transfer() sleep 1 fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat -n - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${ns3} \ - ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ - 0.0.0.0 < "$sin" > "$sout" & + mptcp_lib_nstat_init "${ns3}" + mptcp_lib_nstat_init "${ns1}" + + ip netns exec ${ns3} \ + ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ + 0.0.0.0 < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${ns3}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${ns1} \ - ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ - 10.0.3.3 < "$cin" > "$cout" & + ip netns exec ${ns1} \ + ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ + 10.0.3.3 < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${ns3}" "${ns1}" "${port}" \ + "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + if $capture; then sleep 1 kill ${cappid_listener} kill ${cappid_connector} fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat | grep Tcp > /tmp/${ns3}.out - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat | grep Tcp > /tmp/${ns1}.out + mptcp_lib_nstat_get "${ns3}" + mptcp_lib_nstat_get "${ns1}" cmp $sin $cout > /dev/null 2>&1 local cmps=$? cmp $cin $sout > /dev/null 2>&1 local cmpc=$? - if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ - [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then + if [ $retc -eq 0 ] && [ $rets -eq 0 ] && + [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && + [ $timeout_pid -eq 0 ]; then printf "%-16s" " max $max_time " mptcp_lib_pr_ok cat "$capout" @@ -204,8 +209,7 @@ do_transfer() fi mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" \ - "/tmp/${ns3}.out" "/tmp/${ns1}.out" + mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" ls -l $sin $cout ls -l $cin $sout diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 87323942cb8a..e9ae1806ab07 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -211,7 +211,8 @@ make_connection() ip netns exec "$ns1" \ ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 & local server_pid=$! - sleep 0.5 + + mptcp_lib_wait_local_port_listen "${ns1}" "${port}" # Run the client, transfer $file and stay connected to the server # to conduct tests diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index 45832df98295..a68bc882fa4e 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -127,6 +127,8 @@ ip -net "$nsr1" addr add fee1:2::1/64 dev veth1 nodad ip -net "$nsr2" addr add 192.168.10.2/24 dev veth0 ip -net "$nsr2" addr add fee1:2::2/64 dev veth0 nodad +ip netns exec "$nsr1" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null +ip netns exec "$nsr2" sysctl net.ipv6.conf.all.forwarding=1 > /dev/null for i in 0 1; do ip netns exec "$nsr1" sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null ip netns exec "$nsr2" sysctl net.ipv4.conf.veth$i.forwarding=1 > /dev/null @@ -153,7 +155,9 @@ ip -net "$ns1" route add default via dead:1::1 ip -net "$ns2" route add default via dead:2::1 ip -net "$nsr1" route add default via 192.168.10.2 +ip -6 -net "$nsr1" route add default via fee1:2::2 ip -net "$nsr2" route add default via 192.168.10.1 +ip -6 -net "$nsr2" route add default via fee1:2::1 ip netns exec "$nsr1" nft -f - <<EOF table inet filter { @@ -352,8 +356,9 @@ test_tcp_forwarding_ip() local nsa=$1 local nsb=$2 local pmtu=$3 - local dstip=$4 - local dstport=$5 + local proto=$4 + local dstip=$5 + local dstport=$6 local lret=0 local socatc local socatl @@ -363,12 +368,14 @@ test_tcp_forwarding_ip() infile="$nsin_small" fi - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" & + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -${proto} \ + TCP"${proto}"-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" & lpid=$! busywait 1000 listener_ready - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out" + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -${proto} \ + TCP"${proto}":"$dstip":"$dstport" STDIO < "$infile" > "$ns1out" socatc=$? wait $lpid @@ -394,8 +401,11 @@ test_tcp_forwarding_ip() test_tcp_forwarding() { local pmtu="$3" + local proto="$4" + local dstip="$5" + local dstport="$6" - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" return $? } @@ -403,6 +413,9 @@ test_tcp_forwarding() test_tcp_forwarding_set_dscp() { local pmtu="$3" + local proto="$4" + local dstip="$5" + local dstport="$6" ip netns exec "$nsr1" nft -f - <<EOF table netdev dscpmangle { @@ -413,7 +426,7 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" check_dscp "dscp_ingress" "$pmtu" ip netns exec "$nsr1" nft delete table netdev dscpmangle @@ -430,7 +443,7 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" check_dscp "dscp_egress" "$pmtu" ip netns exec "$nsr1" nft delete table netdev dscpmangle @@ -441,7 +454,7 @@ fi # partial. If flowtable really works, then both dscp-is-0 and dscp-is-cs3 # counters should have seen packets (before and after ft offload kicks in). ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3 - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" "$proto" "$dstip" "$dstport" check_dscp "dscp_fwd" "$pmtu" } @@ -455,7 +468,7 @@ test_tcp_forwarding_nat() [ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)" - test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345 + test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 4 10.0.2.99 12345 lret=$? if [ "$lret" -eq 0 ] ; then @@ -465,7 +478,7 @@ test_tcp_forwarding_nat() echo "PASS: flow offload for ns1/ns2 with masquerade $what" fi - test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 4 10.6.6.6 1666 lret=$? if [ "$pmtu" -eq 1 ] ;then check_counters "flow offload for ns1/ns2 with dnat $what" @@ -487,7 +500,7 @@ make_file "$nsin_small" "$filesize_small" # Due to MTU mismatch in both directions, all packets (except small packets like pure # acks) have to be handled by normal forwarding path. Therefore, packet counters # are not checked. -if test_tcp_forwarding "$ns1" "$ns2" 0; then +if test_tcp_forwarding "$ns1" "$ns2" 0 4 10.0.2.99 12345; then echo "PASS: flow offloaded for ns1/ns2" else echo "FAIL: flow offload for ns1/ns2:" 1>&2 @@ -495,6 +508,14 @@ else ret=1 fi +if test_tcp_forwarding "$ns1" "$ns2" 0 6 "[dead:2::99]" 12345; then + echo "PASS: IPv6 flow offloaded for ns1/ns2" +else + echo "FAIL: IPv6 flow offload for ns1/ns2:" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 +fi + # delete default route, i.e. ns2 won't be able to reach ns1 and # will depend on ns1 being masqueraded in nsr1. # expect ns1 has nsr1 address. @@ -520,7 +541,7 @@ table ip nat { EOF check_dscp "dscp_none" "0" -if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then +if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 4 10.0.2.99 12345; then echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2 exit 0 fi @@ -546,7 +567,7 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null ip netns exec "$ns2" nft reset counters table inet filter >/dev/null -if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then +if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 4 10.0.2.99 12345; then echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2 exit 0 fi @@ -558,6 +579,73 @@ if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then ip netns exec "$nsr1" nft list ruleset fi +# IPIP tunnel test: +# Add IPIP tunnel interfaces and check flowtable acceleration. +test_ipip() { +if ! ip -net "$nsr1" link add name tun0 type ipip \ + local 192.168.10.1 remote 192.168.10.2 >/dev/null;then + echo "SKIP: could not add ipip tunnel" + [ "$ret" -eq 0 ] && ret=$ksft_skip + return +fi +ip -net "$nsr1" link set tun0 up +ip -net "$nsr1" addr add 192.168.100.1/24 dev tun0 +ip netns exec "$nsr1" sysctl net.ipv4.conf.tun0.forwarding=1 > /dev/null + +ip -net "$nsr2" link add name tun0 type ipip local 192.168.10.2 remote 192.168.10.1 +ip -net "$nsr2" link set tun0 up +ip -net "$nsr2" addr add 192.168.100.2/24 dev tun0 +ip netns exec "$nsr2" sysctl net.ipv4.conf.tun0.forwarding=1 > /dev/null + +ip -net "$nsr1" route change default via 192.168.100.2 +ip -net "$nsr2" route change default via 192.168.100.1 +ip -net "$ns2" route add default via 10.0.2.1 + +ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun0 accept' +ip netns exec "$nsr1" nft -a insert rule inet filter forward \ + 'meta oif "veth0" tcp sport 12345 ct mark set 1 flow add @f1 counter name routed_repl accept' + +if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel"; then + echo "FAIL: flow offload for ns1/ns2 with IPIP tunnel" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 +fi + +# Create vlan tagged devices for IPIP traffic. +ip -net "$nsr1" link add link veth1 name veth1.10 type vlan id 10 +ip -net "$nsr1" link set veth1.10 up +ip -net "$nsr1" addr add 192.168.20.1/24 dev veth1.10 +ip netns exec "$nsr1" sysctl net.ipv4.conf.veth1/10.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif veth1.10 accept' +ip -net "$nsr1" link add name tun1 type ipip local 192.168.20.1 remote 192.168.20.2 +ip -net "$nsr1" link set tun1 up +ip -net "$nsr1" addr add 192.168.200.1/24 dev tun1 +ip -net "$nsr1" route change default via 192.168.200.2 +ip netns exec "$nsr1" sysctl net.ipv4.conf.tun1.forwarding=1 > /dev/null +ip netns exec "$nsr1" nft -a insert rule inet filter forward 'meta oif tun1 accept' + +ip -net "$nsr2" link add link veth0 name veth0.10 type vlan id 10 +ip -net "$nsr2" link set veth0.10 up +ip -net "$nsr2" addr add 192.168.20.2/24 dev veth0.10 +ip netns exec "$nsr2" sysctl net.ipv4.conf.veth0/10.forwarding=1 > /dev/null +ip -net "$nsr2" link add name tun1 type ipip local 192.168.20.2 remote 192.168.20.1 +ip -net "$nsr2" link set tun1 up +ip -net "$nsr2" addr add 192.168.200.2/24 dev tun1 +ip -net "$nsr2" route change default via 192.168.200.1 +ip netns exec "$nsr2" sysctl net.ipv4.conf.tun1.forwarding=1 > /dev/null + +if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 "IPIP tunnel over vlan"; then + echo "FAIL: flow offload for ns1/ns2 with IPIP tunnel over vlan" 1>&2 + ip netns exec "$nsr1" nft list ruleset + ret=1 +fi + +# Restore the previous configuration +ip -net "$nsr1" route change default via 192.168.10.2 +ip -net "$nsr2" route change default via 192.168.10.1 +ip -net "$ns2" route del default via 10.0.2.1 +} + # Another test: # Add bridge interface br0 to Router1, with NAT enabled. test_bridge() { @@ -643,6 +731,8 @@ ip -net "$nsr1" addr add dead:1::1/64 dev veth0 nodad ip -net "$nsr1" link set up dev veth0 } +test_ipip + test_bridge KEY_SHA="0x"$(ps -af | sha1sum | cut -d " " -f 1) @@ -683,7 +773,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1 ip -net "$ns2" route add default via 10.0.2.1 ip -net "$ns2" route add default via dead:2::1 -if test_tcp_forwarding "$ns1" "$ns2" 1; then +if test_tcp_forwarding "$ns1" "$ns2" 1 4 10.0.2.99 12345; then check_counters "ipsec tunnel mode for ns1/ns2" else echo "FAIL: ipsec tunnel mode for ns1/ns2" @@ -691,6 +781,14 @@ else ip netns exec "$nsr1" cat /proc/net/xfrm_stat 1>&2 fi +if test_tcp_forwarding "$ns1" "$ns2" 1 6 "[dead:2::99]" 12345; then + check_counters "IPv6 ipsec tunnel mode for ns1/ns2" +else + echo "FAIL: IPv6 ipsec tunnel mode for ns1/ns2" + ip netns exec "$nsr1" nft list ruleset 1>&2 + ip netns exec "$nsr1" cat /proc/net/xfrm_stat 1>&2 +fi + if [ "$1" = "" ]; then low=1280 mtu=$((65536 - low)) diff --git a/tools/testing/selftests/net/netfilter/sctp_collision.c b/tools/testing/selftests/net/netfilter/sctp_collision.c index 21bb1cfd8a85..b282d1785c9b 100644 --- a/tools/testing/selftests/net/netfilter/sctp_collision.c +++ b/tools/testing/selftests/net/netfilter/sctp_collision.c @@ -9,9 +9,10 @@ int main(int argc, char *argv[]) { struct sockaddr_in saddr = {}, daddr = {}; - int sd, ret, len = sizeof(daddr); + socklen_t len = sizeof(daddr); struct timeval tv = {25, 0}; char buf[] = "hello"; + int sd, ret; if (argc != 6 || (strcmp(argv[1], "server") && strcmp(argv[1], "client"))) { printf("%s <server|client> <LOCAL_IP> <LOCAL_PORT> <REMOTE_IP> <REMOTE_PORT>\n", diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 7618ebe528a4..679b6c77ace7 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -143,6 +143,7 @@ TEST(dump_extack) EXPECT_EQ(n, -1); EXPECT_EQ(errno, ENOBUFS); + ret = NO_CTRL; for (i = 0; i < cnt; i++) { struct ext_ack ea = {}; diff --git a/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt b/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt new file mode 100644 index 000000000000..47550df124ce --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Test SYN+ACK RTX with 1s RTO. +// +`./defaults.sh + ./set_sysctls.py /proc/sys/net/ipv4/tcp_rto_max_ms=1000` + +// +// Test 1: TFO SYN+ACK +// + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0 + + +0 < S 0:10(10) win 1000 <mss 1460,sackOK,nop,nop,FO TFO_COOKIE,nop,nop> + +0 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + +// RTO must be capped to 1s + +1 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 11 <mss 1460,nop,nop,sackOK> + + +0 < . 11:11(0) ack 1 win 1000 <mss 1460,nop,nop,sackOK> + +0 accept(3, ..., ...) = 4 + +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }% + + +0 close(4) = 0 + +0 close(3) = 0 + + +// +// Test 2: non-TFO SYN+ACK +// + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 1000 <mss 1460,sackOK,nop,nop> + +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +// RTO must be capped to 1s + +1 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + +1 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK> + + +0 < . 1:1(0) ack 1 win 1000 <mss 1460,nop,nop,sackOK> + +0 accept(3, ..., ...) = 4 + +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }% + + +0 close(4) = 0 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt index b2b2cdf27e20..454441e7ecff 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt @@ -1,6 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 // Test that we correctly skip zero-length IOVs. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt index 183051ba0cae..6882b8240a8a 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt @@ -23,14 +23,16 @@ // install a qdisc dropping all packets +0 `tc qdisc delete dev tun0 root 2>/dev/null ; tc qdisc add dev tun0 root pfifo limit 0` + +0 write(4, ..., 24) = 24 // When qdisc is congested we retry every 500ms // (TCP_RESOURCE_PROBE_INTERVAL) and therefore // we retry 6 times before hitting 3s timeout. // First verify that the connection is alive: -+3.250 write(4, ..., 24) = 24 ++3 write(4, ..., 24) = 24 + // Now verify that shortly after that the socket is dead: - +.100 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) ++1 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) +0 %{ assert tcpi_probes == 6, tcpi_probes; \ assert tcpi_backoff == 0, tcpi_backoff }% diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt index a82c8899d36b..0a0700afdaa3 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt @@ -4,6 +4,8 @@ // send a packet with MSG_ZEROCOPY and receive the notification ID // repeat and verify IDs are consecutive +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt index c01915e7f4a1..df91675d2991 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt @@ -3,6 +3,8 @@ // // send multiple packets, then read one range of all notifications. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt index 6509882932e9..2963cfcb14df 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Minimal client-side zerocopy test +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt index 2cd78755cb2a..ea0c2fa73c2d 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt @@ -7,6 +7,8 @@ // First send on a closed socket and wait for (absent) notification. // Then connect and send and verify that notification nr. is zero. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt index 7671c20e01cf..4df978a9b82e 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt @@ -7,6 +7,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt index fadc480fdb7f..36b6edc4858c 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt @@ -8,6 +8,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt index 5bfa0d1d2f4a..1bea6f3b4558 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt @@ -8,6 +8,9 @@ // is correctly fired only once, when EPOLLONESHOT is set. send another packet // with MSG_ZEROCOPY. confirm that EPOLLERR is not fired. Rearm the FD and // confirm that EPOLLERR is correctly set. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt index 4a73bbf46961..e27c21ff5d18 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt @@ -8,6 +8,8 @@ // one will have no data in the initial send. On return 0 the // zerocopy notification counter is not incremented. Verify this too. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` // Send a FastOpen request, no cookie yet so no data in SYN diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt index 36086c5877ce..b1fa77c77dfa 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt @@ -4,6 +4,8 @@ // send data with MSG_FASTOPEN | MSG_ZEROCOPY and verify that the // kernel returns the notification ID. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x207` diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt index 672f817faca0..2f5317d0a9fa 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt @@ -7,6 +7,8 @@ // because each iovec element becomes a frag // 3) the PSH bit is set on an skb when it runs out of fragments +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt index a9a1ac0aea4f..9d5272c6b207 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt @@ -4,6 +4,8 @@ // verify that SO_EE_CODE_ZEROCOPY_COPIED is set on zerocopy // packets of all sizes, including the smallest payload, 1B. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 163a084d525d..248c2b91fe42 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -8,6 +8,7 @@ ALL_TESTS=" kci_test_polrouting kci_test_route_get kci_test_addrlft + kci_test_addrlft_route_cleanup kci_test_promote_secondaries kci_test_tc kci_test_gre @@ -323,6 +324,25 @@ kci_test_addrlft() end_test "PASS: preferred_lft addresses have expired" } +kci_test_addrlft_route_cleanup() +{ + local ret=0 + local test_addr="2001:db8:99::1/64" + local test_prefix="2001:db8:99::/64" + + run_cmd ip -6 addr add $test_addr dev "$devdummy" valid_lft 300 preferred_lft 300 + run_cmd_grep "$test_prefix proto kernel" ip -6 route show dev "$devdummy" + run_cmd ip -6 addr del $test_addr dev "$devdummy" + run_cmd_grep_fail "$test_prefix" ip -6 route show dev "$devdummy" + + if [ $ret -ne 0 ]; then + end_test "FAIL: route not cleaned up when address with valid_lft deleted" + return 1 + fi + + end_test "PASS: route cleaned up when address with valid_lft deleted" +} + kci_test_promote_secondaries() { run_cmd ifconfig "$devdummy" diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh deleted file mode 100644 index 2070b57849de..000000000000 --- a/tools/testing/selftests/net/setup_loopback.sh +++ /dev/null @@ -1,120 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly FLUSH_PATH="/sys/class/net/${dev}/gro_flush_timeout" -readonly IRQ_PATH="/sys/class/net/${dev}/napi_defer_hard_irqs" -readonly FLUSH_TIMEOUT="$(< ${FLUSH_PATH})" -readonly HARD_IRQS="$(< ${IRQ_PATH})" -readonly server_ns=$(mktemp -u server-XXXXXXXX) -readonly client_ns=$(mktemp -u client-XXXXXXXX) - -netdev_check_for_carrier() { - local -r dev="$1" - - for i in {1..5}; do - carrier="$(cat /sys/class/net/${dev}/carrier)" - if [[ "${carrier}" -ne 1 ]] ; then - echo "carrier not ready yet..." >&2 - sleep 1 - else - echo "carrier ready" >&2 - break - fi - done - echo "${carrier}" -} - -# Assumes that there is no existing ipvlan device on the physical device -setup_loopback_environment() { - local dev="$1" - - # Fail hard if cannot turn on loopback mode for current NIC - ethtool -K "${dev}" loopback on || exit 1 - sleep 1 - - # Check for the carrier - carrier=$(netdev_check_for_carrier ${dev}) - if [[ "${carrier}" -ne 1 ]] ; then - echo "setup_loopback_environment failed" - exit 1 - fi -} - -setup_macvlan_ns(){ - local -r link_dev="$1" - local -r ns_name="$2" - local -r ns_dev="$3" - local -r ns_mac="$4" - local -r addr="$5" - - ip link add link "${link_dev}" dev "${ns_dev}" \ - address "${ns_mac}" type macvlan - exit_code=$? - if [[ "${exit_code}" -ne 0 ]]; then - echo "setup_macvlan_ns failed" - exit $exit_code - fi - - [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - ip link set dev "${ns_dev}" netns "${ns_name}" - ip -netns "${ns_name}" link set dev "${ns_dev}" up - if [[ -n "${addr}" ]]; then - ip -netns "${ns_name}" addr add dev "${ns_dev}" "${addr}" - fi - - sleep 1 -} - -cleanup_macvlan_ns(){ - while (( $# >= 2 )); do - ns_name="$1" - ns_dev="$2" - ip -netns "${ns_name}" link del dev "${ns_dev}" - ip netns del "${ns_name}" - shift 2 - done -} - -cleanup_loopback(){ - local -r dev="$1" - - ethtool -K "${dev}" loopback off - sleep 1 - - # Check for the carrier - carrier=$(netdev_check_for_carrier ${dev}) - if [[ "${carrier}" -ne 1 ]] ; then - echo "setup_loopback_environment failed" - exit 1 - fi -} - -setup_interrupt() { - # Use timer on host to trigger the network stack - # Also disable device interrupt to not depend on NIC interrupt - # Reduce test flakiness caused by unexpected interrupts - echo 100000 >"${FLUSH_PATH}" - echo 50 >"${IRQ_PATH}" -} - -setup_ns() { - # Set up server_ns namespace and client_ns namespace - setup_macvlan_ns "${dev}" ${server_ns} server "${SERVER_MAC}" - setup_macvlan_ns "${dev}" ${client_ns} client "${CLIENT_MAC}" -} - -cleanup_ns() { - cleanup_macvlan_ns ${server_ns} server ${client_ns} client -} - -setup() { - setup_loopback_environment "${dev}" - setup_interrupt -} - -cleanup() { - cleanup_loopback "${dev}" - - echo "${FLUSH_TIMEOUT}" >"${FLUSH_PATH}" - echo "${HARD_IRQS}" >"${IRQ_PATH}" -} diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh deleted file mode 100644 index 152bf4c65747..000000000000 --- a/tools/testing/selftests/net/setup_veth.sh +++ /dev/null @@ -1,45 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly server_ns=$(mktemp -u server-XXXXXXXX) -readonly client_ns=$(mktemp -u client-XXXXXXXX) - -setup_veth_ns() { - local -r link_dev="$1" - local -r ns_name="$2" - local -r ns_dev="$3" - local -r ns_mac="$4" - - [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - echo 200000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" - echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs" - ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 - ip -netns "${ns_name}" link set dev "${ns_dev}" up - - ip netns exec "${ns_name}" ethtool -K "${ns_dev}" gro on tso off -} - -setup_ns() { - # Set up server_ns namespace and client_ns namespace - ip link add name server type veth peer name client - - setup_veth_ns "${dev}" ${server_ns} server "${SERVER_MAC}" - setup_veth_ns "${dev}" ${client_ns} client "${CLIENT_MAC}" -} - -cleanup_ns() { - local ns_name - - for ns_name in ${client_ns} ${server_ns}; do - [[ -e /var/run/netns/"${ns_name}" ]] && ip netns del "${ns_name}" - done -} - -setup() { - # no global init setup step needed - : -} - -cleanup() { - cleanup_ns -} diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 8457b7ccbc09..b76df1efc2ef 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -174,7 +174,7 @@ static int do_recv_errqueue_timeout(int fdt) msg.msg_controllen = sizeof(control); while (1) { - const char *reason; + const char *reason = NULL; ret = recvmsg(fdt, &msg, MSG_ERRQUEUE); if (ret == -1 && errno == EAGAIN) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 5c6d8215021c..da1b50b30719 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -2856,6 +2856,147 @@ TEST_F(tls_err, oob_pressure) EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); } +/* + * Parse a stream of TLS records and ensure that each record respects + * the specified @max_payload_len. + */ +static size_t parse_tls_records(struct __test_metadata *_metadata, + const __u8 *rx_buf, int rx_len, int overhead, + __u16 max_payload_len) +{ + const __u8 *rec = rx_buf; + size_t total_plaintext_rx = 0; + const __u8 rec_header_len = 5; + + while (rec < rx_buf + rx_len) { + __u16 record_payload_len; + __u16 plaintext_len; + + /* Sanity check that it's a TLS header for application data */ + ASSERT_EQ(rec[0], 23); + ASSERT_EQ(rec[1], 0x3); + ASSERT_EQ(rec[2], 0x3); + + memcpy(&record_payload_len, rec + 3, 2); + record_payload_len = ntohs(record_payload_len); + ASSERT_GE(record_payload_len, overhead); + + plaintext_len = record_payload_len - overhead; + total_plaintext_rx += plaintext_len; + + /* Plaintext must not exceed the specified limit */ + ASSERT_LE(plaintext_len, max_payload_len); + rec += rec_header_len + record_payload_len; + } + + return total_plaintext_rx; +} + +TEST(tls_12_tx_max_payload_len) +{ + struct tls_crypto_info_keys tls12; + int cfd, ret, fd, overhead; + size_t total_plaintext_rx = 0; + __u8 tx[1024], rx[2000]; + __u16 limit = 128; + __u16 opt = 0; + unsigned int optlen = sizeof(opt); + bool notls; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); + + if (notls) + exit(KSFT_SKIP); + + /* Don't install keys on fd, we'll parse raw records */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &limit, + sizeof(limit)); + ASSERT_EQ(ret, 0); + + ret = getsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &opt, &optlen); + EXPECT_EQ(ret, 0); + EXPECT_EQ(limit, opt); + EXPECT_EQ(optlen, sizeof(limit)); + + memset(tx, 0, sizeof(tx)); + ASSERT_EQ(send(cfd, tx, sizeof(tx), 0), sizeof(tx)); + close(cfd); + + ret = recv(fd, rx, sizeof(rx), 0); + + /* + * 16B tag + 8B IV -- record header (5B) is not counted but we'll + * need it to walk the record stream + */ + overhead = 16 + 8; + total_plaintext_rx = parse_tls_records(_metadata, rx, ret, overhead, + limit); + + ASSERT_EQ(total_plaintext_rx, sizeof(tx)); + close(fd); +} + +TEST(tls_12_tx_max_payload_len_open_rec) +{ + struct tls_crypto_info_keys tls12; + int cfd, ret, fd, overhead; + size_t total_plaintext_rx = 0; + __u8 tx[1024], rx[2000]; + __u16 tx_partial = 256; + __u16 og_limit = 512, limit = 128; + bool notls; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); + + if (notls) + exit(KSFT_SKIP); + + /* Don't install keys on fd, we'll parse raw records */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &og_limit, + sizeof(og_limit)); + ASSERT_EQ(ret, 0); + + memset(tx, 0, sizeof(tx)); + ASSERT_EQ(send(cfd, tx, tx_partial, MSG_MORE), tx_partial); + + /* + * Changing the payload limit with a pending open record should + * not be allowed. + */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &limit, + sizeof(limit)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBUSY); + + ASSERT_EQ(send(cfd, tx + tx_partial, sizeof(tx) - tx_partial, MSG_EOR), + sizeof(tx) - tx_partial); + close(cfd); + + ret = recv(fd, rx, sizeof(rx), 0); + + /* + * 16B tag + 8B IV -- record header (5B) is not counted but we'll + * need it to walk the record stream + */ + overhead = 16 + 8; + total_plaintext_rx = parse_tls_records(_metadata, rx, ret, overhead, + og_limit); + ASSERT_EQ(total_plaintext_rx, sizeof(tx)); + close(fd); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; diff --git a/tools/testing/selftests/net/toeplitz.sh b/tools/testing/selftests/net/toeplitz.sh deleted file mode 100755 index 8ff172f7bb1b..000000000000 --- a/tools/testing/selftests/net/toeplitz.sh +++ /dev/null @@ -1,199 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# extended toeplitz test: test rxhash plus, optionally, either (1) rss mapping -# from rxhash to rx queue ('-rss') or (2) rps mapping from rxhash to cpu -# ('-rps <rps_map>') -# -# irq-pattern-prefix can be derived from /sys/kernel/irq/*/action, -# which is a driver-specific encoding. -# -# invoke as ./toeplitz.sh (-i <iface>) -u|-t -4|-6 \ -# [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)] - -source setup_loopback.sh -readonly SERVER_IP4="192.168.1.200/24" -readonly SERVER_IP6="fda8::1/64" -readonly SERVER_MAC="aa:00:00:00:00:02" - -readonly CLIENT_IP4="192.168.1.100/24" -readonly CLIENT_IP6="fda8::2/64" -readonly CLIENT_MAC="aa:00:00:00:00:01" - -PORT=8000 -KEY="$(</proc/sys/net/core/netdev_rss_key)" -TEST_RSS=false -RPS_MAP="" -PROTO_FLAG="" -IP_FLAG="" -DEV="eth0" - -# Return the number of rxqs among which RSS is configured to spread packets. -# This is determined by reading the RSS indirection table using ethtool. -get_rss_cfg_num_rxqs() { - echo $(ethtool -x "${DEV}" | - grep -E [[:space:]]+[0-9]+:[[:space:]]+ | - cut -d: -f2- | - awk '{$1=$1};1' | - tr ' ' '\n' | - sort -u | - wc -l) -} - -# Return a list of the receive irq handler cpus. -# The list is ordered by the irqs, so first rxq-0 cpu, then rxq-1 cpu, etc. -# Reads /sys/kernel/irq/ in order, so algorithm depends on -# irq_{rxq-0} < irq_{rxq-1}, etc. -get_rx_irq_cpus() { - CPUS="" - # sort so that irq 2 is read before irq 10 - SORTED_IRQS=$(for i in /sys/kernel/irq/*; do echo $i; done | sort -V) - # Consider only as many queues as RSS actually uses. We assume that - # if RSS_CFG_NUM_RXQS=N, then RSS uses rxqs 0-(N-1). - RSS_CFG_NUM_RXQS=$(get_rss_cfg_num_rxqs) - RXQ_COUNT=0 - - for i in ${SORTED_IRQS} - do - [[ "${RXQ_COUNT}" -lt "${RSS_CFG_NUM_RXQS}" ]] || break - # lookup relevant IRQs by action name - [[ -e "$i/actions" ]] || continue - cat "$i/actions" | grep -q "${IRQ_PATTERN}" || continue - irqname=$(<"$i/actions") - - # does the IRQ get called - irqcount=$(cat "$i/per_cpu_count" | tr -d '0,') - [[ -n "${irqcount}" ]] || continue - - # lookup CPU - irq=$(basename "$i") - cpu=$(cat "/proc/irq/$irq/smp_affinity_list") - - if [[ -z "${CPUS}" ]]; then - CPUS="${cpu}" - else - CPUS="${CPUS},${cpu}" - fi - RXQ_COUNT=$((RXQ_COUNT+1)) - done - - echo "${CPUS}" -} - -get_disable_rfs_cmd() { - echo "echo 0 > /proc/sys/net/core/rps_sock_flow_entries;" -} - -get_set_rps_bitmaps_cmd() { - CMD="" - for i in /sys/class/net/${DEV}/queues/rx-*/rps_cpus - do - CMD="${CMD} echo $1 > ${i};" - done - - echo "${CMD}" -} - -get_disable_rps_cmd() { - echo "$(get_set_rps_bitmaps_cmd 0)" -} - -die() { - echo "$1" - exit 1 -} - -check_nic_rxhash_enabled() { - local -r pattern="receive-hashing:\ on" - - ethtool -k "${DEV}" | grep -q "${pattern}" || die "rxhash must be enabled" -} - -parse_opts() { - local prog=$0 - shift 1 - - while [[ "$1" =~ "-" ]]; do - if [[ "$1" = "-irq_prefix" ]]; then - shift - IRQ_PATTERN="^$1-[0-9]*$" - elif [[ "$1" = "-u" || "$1" = "-t" ]]; then - PROTO_FLAG="$1" - elif [[ "$1" = "-4" ]]; then - IP_FLAG="$1" - SERVER_IP="${SERVER_IP4}" - CLIENT_IP="${CLIENT_IP4}" - elif [[ "$1" = "-6" ]]; then - IP_FLAG="$1" - SERVER_IP="${SERVER_IP6}" - CLIENT_IP="${CLIENT_IP6}" - elif [[ "$1" = "-rss" ]]; then - TEST_RSS=true - elif [[ "$1" = "-rps" ]]; then - shift - RPS_MAP="$1" - elif [[ "$1" = "-i" ]]; then - shift - DEV="$1" - else - die "Usage: ${prog} (-i <iface>) -u|-t -4|-6 \ - [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)]" - fi - shift - done -} - -setup() { - setup_loopback_environment "${DEV}" - - # Set up server_ns namespace and client_ns namespace - setup_macvlan_ns "${DEV}" $server_ns server \ - "${SERVER_MAC}" "${SERVER_IP}" - setup_macvlan_ns "${DEV}" $client_ns client \ - "${CLIENT_MAC}" "${CLIENT_IP}" -} - -cleanup() { - cleanup_macvlan_ns $server_ns server $client_ns client - cleanup_loopback "${DEV}" -} - -parse_opts $0 $@ - -setup -trap cleanup EXIT - -check_nic_rxhash_enabled - -# Actual test starts here -if [[ "${TEST_RSS}" = true ]]; then - # RPS/RFS must be disabled because they move packets between cpus, - # which breaks the PACKET_FANOUT_CPU identification of RSS decisions. - eval "$(get_disable_rfs_cmd) $(get_disable_rps_cmd)" \ - ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ - -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ - -C "$(get_rx_irq_cpus)" -s -v & -elif [[ ! -z "${RPS_MAP}" ]]; then - eval "$(get_disable_rfs_cmd) $(get_set_rps_bitmaps_cmd ${RPS_MAP})" \ - ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ - -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ - -r "0x${RPS_MAP}" -s -v & -else - ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ - -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 -s -v & -fi - -server_pid=$! - -ip netns exec $client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \ - "${IP_FLAG}" "${SERVER_IP%%/*}" "${PORT}" & - -client_pid=$! - -wait "${server_pid}" -exit_code=$? -kill -9 "${client_pid}" -if [[ "${exit_code}" -eq 0 ]]; then - echo "Test Succeeded!" -fi -exit "${exit_code}" diff --git a/tools/testing/selftests/net/toeplitz_client.sh b/tools/testing/selftests/net/toeplitz_client.sh deleted file mode 100755 index 2fef34f4aba1..000000000000 --- a/tools/testing/selftests/net/toeplitz_client.sh +++ /dev/null @@ -1,28 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# A simple program for generating traffic for the toeplitz test. -# -# This program sends packets periodically for, conservatively, 20 seconds. The -# intent is for the calling program to kill this program once it is no longer -# needed, rather than waiting for the 20 second expiration. - -send_traffic() { - expiration=$((SECONDS+20)) - while [[ "${SECONDS}" -lt "${expiration}" ]] - do - if [[ "${PROTO}" == "-u" ]]; then - echo "msg $i" | nc "${IPVER}" -u -w 0 "${ADDR}" "${PORT}" - else - echo "msg $i" | nc "${IPVER}" -w 0 "${ADDR}" "${PORT}" - fi - sleep 0.001 - done -} - -PROTO=$1 -IPVER=$2 -ADDR=$3 -PORT=$4 - -send_traffic diff --git a/tools/testing/selftests/net/traceroute.sh b/tools/testing/selftests/net/traceroute.sh index dbb34c7e09ce..a7c6ab8a0347 100755 --- a/tools/testing/selftests/net/traceroute.sh +++ b/tools/testing/selftests/net/traceroute.sh @@ -36,6 +36,35 @@ run_cmd() return $rc } +__check_traceroute_version() +{ + local cmd=$1; shift + local req_ver=$1; shift + local ver + + req_ver=$(echo "$req_ver" | sed 's/\.//g') + ver=$($cmd -V 2>&1 | grep -Eo '[0-9]+.[0-9]+.[0-9]+' | sed 's/\.//g') + if [[ $ver -lt $req_ver ]]; then + return 1 + else + return 0 + fi +} + +check_traceroute6_version() +{ + local req_ver=$1; shift + + __check_traceroute_version traceroute6 "$req_ver" +} + +check_traceroute_version() +{ + local req_ver=$1; shift + + __check_traceroute_version traceroute "$req_ver" +} + ################################################################################ # create namespaces and interconnects @@ -59,6 +88,8 @@ create_ns() ip netns exec ${ns} ip -6 ro add unreachable default metric 8192 ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv4.icmp_ratelimit=0 + ip netns exec ${ns} sysctl -qw net.ipv6.icmp.ratelimit=0 ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 @@ -298,6 +329,144 @@ run_traceroute6_vrf() } ################################################################################ +# traceroute6 with ICMP extensions test +# +# Verify that in this scenario +# +# ---- ---- ---- +# |H1|--------------------------|R1|--------------------------|H2| +# ---- N1 ---- N2 ---- +# +# ICMP extensions are correctly reported. The loopback interfaces on all the +# nodes are assigned global addresses and the interfaces connecting the nodes +# are assigned IPv6 link-local addresses. + +cleanup_traceroute6_ext() +{ + cleanup_all_ns +} + +setup_traceroute6_ext() +{ + # Start clean + cleanup_traceroute6_ext + + setup_ns h1 r1 h2 + create_ns "$h1" + create_ns "$r1" + create_ns "$h2" + + # Setup N1 + connect_ns "$h1" eth1 - fe80::1/64 "$r1" eth1 - fe80::2/64 + # Setup N2 + connect_ns "$r1" eth2 - fe80::3/64 "$h2" eth2 - fe80::4/64 + + # Setup H1 + ip -n "$h1" address add 2001:db8:1::1/128 dev lo + ip -n "$h1" route add ::/0 nexthop via fe80::2 dev eth1 + + # Setup R1 + ip -n "$r1" address add 2001:db8:1::2/128 dev lo + ip -n "$r1" route add 2001:db8:1::1/128 nexthop via fe80::1 dev eth1 + ip -n "$r1" route add 2001:db8:1::3/128 nexthop via fe80::4 dev eth2 + + # Setup H2 + ip -n "$h2" address add 2001:db8:1::3/128 dev lo + ip -n "$h2" route add ::/0 nexthop via fe80::3 dev eth2 + + # Prime the network + ip netns exec "$h1" ping6 -c5 2001:db8:1::3 >/dev/null 2>&1 +} + +traceroute6_ext_iio_iif_test() +{ + local r1_ifindex h2_ifindex + local pkt_len=$1; shift + + # Test that incoming interface info is not appended by default. + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended by default when should not" + + # Test that the extension is appended when enabled. + run_cmd "$r1" "bash -c \"echo 0x01 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_err $? "Failed to enable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_err $? "Incoming interface info not appended after enable" + + # Test that the extension is not appended when disabled. + run_cmd "$r1" "bash -c \"echo 0x00 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_err $? "Failed to disable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended after disable" + + # Test that the extension is sent correctly from both R1 and H2. + run_cmd "$r1" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x01" + r1_ifindex=$(ip -n "$r1" -j link show dev eth1 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1" + + run_cmd "$h2" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x01" + h2_ifindex=$(ip -n "$h2" -j link show dev eth2 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$h2_ifindex,\"eth2\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from H2" + + # Add a global address on the incoming interface of R1 and check that + # it is reported. + run_cmd "$r1" "ip address add 2001:db8:100::1/64 dev eth1 nodad" + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$r1_ifindex,2001:db8:100::1,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1 after address addition" + run_cmd "$r1" "ip address del 2001:db8:100::1/64 dev eth1" + + # Change name and MTU and make sure the result is still correct. + run_cmd "$r1" "ip link set dev eth1 name eth1tag mtu 1501" + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1tag\",mtu=1501>'" + check_err $? "Wrong incoming interface info reported from R1 after name and MTU change" + run_cmd "$r1" "ip link set dev eth1tag name eth1 mtu 1500" + + run_cmd "$r1" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x00" + run_cmd "$h2" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x00" +} + +run_traceroute6_ext() +{ + # Need at least version 2.1.5 for RFC 5837 support. + if ! check_traceroute6_version 2.1.5; then + log_test_skip "traceroute6 too old, missing ICMP extensions support" + return + fi + + setup_traceroute6_ext + + RET=0 + + ## General ICMP extensions tests + + # Test that ICMP extensions are disabled by default. + run_cmd "$h1" "sysctl net.ipv6.icmp.errors_extension_mask | grep \"= 0$\"" + check_err $? "ICMP extensions are not disabled by default" + + # Test that unsupported values are rejected. Do not use "sysctl" as + # older versions do not return an error code upon failure. + run_cmd "$h1" "bash -c \"echo 0x80 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_fail $? "Unsupported sysctl value was not rejected" + + ## Extension-specific tests + + # Incoming interface info test. Test with various packet sizes, + # including the default one. + traceroute6_ext_iio_iif_test + traceroute6_ext_iio_iif_test 127 + traceroute6_ext_iio_iif_test 128 + traceroute6_ext_iio_iif_test 129 + + log_test "IPv6 traceroute with ICMP extensions" + + cleanup_traceroute6_ext +} + +################################################################################ # traceroute test # # Verify that traceroute from H1 to H2 shows 1.0.3.1 and 1.0.1.1 when @@ -438,14 +607,157 @@ run_traceroute_vrf() } ################################################################################ +# traceroute with ICMP extensions test +# +# Verify that in this scenario +# +# ---- ---- ---- +# |H1|--------------------------|R1|--------------------------|H2| +# ---- N1 ---- N2 ---- +# +# ICMP extensions are correctly reported. The loopback interfaces on all the +# nodes are assigned global addresses and the interfaces connecting the nodes +# are assigned IPv6 link-local addresses. + +cleanup_traceroute_ext() +{ + cleanup_all_ns +} + +setup_traceroute_ext() +{ + # Start clean + cleanup_traceroute_ext + + setup_ns h1 r1 h2 + create_ns "$h1" + create_ns "$r1" + create_ns "$h2" + + # Setup N1 + connect_ns "$h1" eth1 - fe80::1/64 "$r1" eth1 - fe80::2/64 + # Setup N2 + connect_ns "$r1" eth2 - fe80::3/64 "$h2" eth2 - fe80::4/64 + + # Setup H1 + ip -n "$h1" address add 192.0.2.1/32 dev lo + ip -n "$h1" route add 0.0.0.0/0 nexthop via inet6 fe80::2 dev eth1 + + # Setup R1 + ip -n "$r1" address add 192.0.2.2/32 dev lo + ip -n "$r1" route add 192.0.2.1/32 nexthop via inet6 fe80::1 dev eth1 + ip -n "$r1" route add 192.0.2.3/32 nexthop via inet6 fe80::4 dev eth2 + + # Setup H2 + ip -n "$h2" address add 192.0.2.3/32 dev lo + ip -n "$h2" route add 0.0.0.0/0 nexthop via inet6 fe80::3 dev eth2 + + # Prime the network + ip netns exec "$h1" ping -c5 192.0.2.3 >/dev/null 2>&1 +} + +traceroute_ext_iio_iif_test() +{ + local r1_ifindex h2_ifindex + local pkt_len=$1; shift + + # Test that incoming interface info is not appended by default. + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended by default when should not" + + # Test that the extension is appended when enabled. + run_cmd "$r1" "bash -c \"echo 0x01 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_err $? "Failed to enable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_err $? "Incoming interface info not appended after enable" + + # Test that the extension is not appended when disabled. + run_cmd "$r1" "bash -c \"echo 0x00 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_err $? "Failed to disable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended after disable" + + # Test that the extension is sent correctly from both R1 and H2. + run_cmd "$r1" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x01" + r1_ifindex=$(ip -n "$r1" -j link show dev eth1 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1" + + run_cmd "$h2" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x01" + h2_ifindex=$(ip -n "$h2" -j link show dev eth2 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$h2_ifindex,\"eth2\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from H2" + + # Add a global address on the incoming interface of R1 and check that + # it is reported. + run_cmd "$r1" "ip address add 198.51.100.1/24 dev eth1" + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$r1_ifindex,198.51.100.1,\"eth1\",mtu=1500>'" + check_err $? "Wrong incoming interface info reported from R1 after address addition" + run_cmd "$r1" "ip address del 198.51.100.1/24 dev eth1" + + # Change name and MTU and make sure the result is still correct. + # Re-add the route towards H1 since it was deleted when we removed the + # last IPv4 address from eth1 on R1. + run_cmd "$r1" "ip route add 192.0.2.1/32 nexthop via inet6 fe80::1 dev eth1" + run_cmd "$r1" "ip link set dev eth1 name eth1tag mtu 1501" + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep '<INC:$r1_ifindex,\"eth1tag\",mtu=1501>'" + check_err $? "Wrong incoming interface info reported from R1 after name and MTU change" + run_cmd "$r1" "ip link set dev eth1tag name eth1 mtu 1500" + + run_cmd "$r1" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x00" + run_cmd "$h2" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x00" +} + +run_traceroute_ext() +{ + # Need at least version 2.1.5 for RFC 5837 support. + if ! check_traceroute_version 2.1.5; then + log_test_skip "traceroute too old, missing ICMP extensions support" + return + fi + + setup_traceroute_ext + + RET=0 + + ## General ICMP extensions tests + + # Test that ICMP extensions are disabled by default. + run_cmd "$h1" "sysctl net.ipv4.icmp_errors_extension_mask | grep \"= 0$\"" + check_err $? "ICMP extensions are not disabled by default" + + # Test that unsupported values are rejected. Do not use "sysctl" as + # older versions do not return an error code upon failure. + run_cmd "$h1" "bash -c \"echo 0x80 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_fail $? "Unsupported sysctl value was not rejected" + + ## Extension-specific tests + + # Incoming interface info test. Test with various packet sizes, + # including the default one. + traceroute_ext_iio_iif_test + traceroute_ext_iio_iif_test 127 + traceroute_ext_iio_iif_test 128 + traceroute_ext_iio_iif_test 129 + + log_test "IPv4 traceroute with ICMP extensions" + + cleanup_traceroute_ext +} + +################################################################################ # Run tests run_tests() { run_traceroute6 run_traceroute6_vrf + run_traceroute6_ext run_traceroute run_traceroute_vrf + run_traceroute_ext } ################################################################################ @@ -462,6 +774,7 @@ done require_command traceroute6 require_command traceroute +require_command jq run_tests diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index dae91eb97d69..bcc14688661d 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -217,7 +217,7 @@ static void print_timestamp_usr(void) static void print_timestamp(struct scm_timestamping *tss, int tstype, int tskey, int payload_len) { - const char *tsname; + const char *tsname = NULL; validate_key(tskey, tstype); diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 0091bcd91c2c..47de27fd4f90 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -1005,5 +1005,33 @@ "teardown": [ "$TC qdisc del dev $DUMMY clsact" ] + }, + { + "id": "4366", + "name": "CAKE with QFQ Parent - CAKE enqueue with packets dropping", + "category": [ + "qdisc", + "cake", + "netem" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup":[ + "$TC qdisc add dev $DUMMY handle 1: root qfq", + "$TC class add dev $DUMMY parent 1: classid 1:1 qfq maxpkt 1024", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: cake memlimit 9", + "$TC filter add dev $DUMMY protocol ip parent 1: prio 1 u32 match ip protocol 1 0xff flowid 1:1", + "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true", + "$TC qdisc replace dev $DUMMY parent 1:1 handle 3: netem delay 0ms" + ], + "cmdUnderTest": "ping -I$DUMMY -f -c1 -s64 -W1 10.10.10.1 || true", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "qdisc qfq 1:", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] } ] diff --git a/tools/testing/selftests/ublk/kublk.c b/tools/testing/selftests/ublk/kublk.c index 6b8123c12a7a..f8fa102a627f 100644 --- a/tools/testing/selftests/ublk/kublk.c +++ b/tools/testing/selftests/ublk/kublk.c @@ -836,56 +836,70 @@ static int ublk_process_io(struct ublk_thread *t) return reapped; } -static void ublk_thread_set_sched_affinity(const struct ublk_thread *t, - cpu_set_t *cpuset) -{ - if (sched_setaffinity(0, sizeof(*cpuset), cpuset) < 0) - ublk_err("ublk dev %u thread %u set affinity failed", - t->dev->dev_info.dev_id, t->idx); -} - struct ublk_thread_info { struct ublk_dev *dev; + pthread_t thread; unsigned idx; sem_t *ready; cpu_set_t *affinity; unsigned long long extra_flags; }; -static void *ublk_io_handler_fn(void *data) +static void ublk_thread_set_sched_affinity(const struct ublk_thread_info *info) { - struct ublk_thread_info *info = data; - struct ublk_thread *t = &info->dev->threads[info->idx]; + if (pthread_setaffinity_np(pthread_self(), sizeof(*info->affinity), info->affinity) < 0) + ublk_err("ublk dev %u thread %u set affinity failed", + info->dev->dev_info.dev_id, info->idx); +} + +static __attribute__((noinline)) int __ublk_io_handler_fn(struct ublk_thread_info *info) +{ + struct ublk_thread t = { + .dev = info->dev, + .idx = info->idx, + }; int dev_id = info->dev->dev_info.dev_id; int ret; - t->dev = info->dev; - t->idx = info->idx; - - ret = ublk_thread_init(t, info->extra_flags); + ret = ublk_thread_init(&t, info->extra_flags); if (ret) { ublk_err("ublk dev %d thread %u init failed\n", - dev_id, t->idx); - return NULL; + dev_id, t.idx); + return ret; } - /* IO perf is sensitive with queue pthread affinity on NUMA machine*/ - if (info->affinity) - ublk_thread_set_sched_affinity(t, info->affinity); sem_post(info->ready); ublk_dbg(UBLK_DBG_THREAD, "tid %d: ublk dev %d thread %u started\n", - gettid(), dev_id, t->idx); + gettid(), dev_id, t.idx); /* submit all io commands to ublk driver */ - ublk_submit_fetch_commands(t); + ublk_submit_fetch_commands(&t); do { - if (ublk_process_io(t) < 0) + if (ublk_process_io(&t) < 0) break; } while (1); ublk_dbg(UBLK_DBG_THREAD, "tid %d: ublk dev %d thread %d exiting\n", - gettid(), dev_id, t->idx); - ublk_thread_deinit(t); + gettid(), dev_id, t.idx); + ublk_thread_deinit(&t); + return 0; +} + +static void *ublk_io_handler_fn(void *data) +{ + struct ublk_thread_info *info = data; + + /* + * IO perf is sensitive with queue pthread affinity on NUMA machine + * + * Set sched_affinity at beginning, so following allocated memory/pages + * could be CPU/NUMA aware. + */ + if (info->affinity) + ublk_thread_set_sched_affinity(info); + + __ublk_io_handler_fn(info); + return NULL; } @@ -983,14 +997,13 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) */ if (dev->nthreads == dinfo->nr_hw_queues) tinfo[i].affinity = &affinity_buf[i]; - pthread_create(&dev->threads[i].thread, NULL, + pthread_create(&tinfo[i].thread, NULL, ublk_io_handler_fn, &tinfo[i]); } for (i = 0; i < dev->nthreads; i++) sem_wait(&ready); - free(tinfo); free(affinity_buf); /* everything is fine now, start us */ @@ -1013,7 +1026,8 @@ static int ublk_start_daemon(const struct dev_ctx *ctx, struct ublk_dev *dev) /* wait until we are terminated */ for (i = 0; i < dev->nthreads; i++) - pthread_join(dev->threads[i].thread, &thread_ret); + pthread_join(tinfo[i].thread, &thread_ret); + free(tinfo); fail: for (i = 0; i < dinfo->nr_hw_queues; i++) ublk_queue_deinit(&dev->q[i]); diff --git a/tools/testing/selftests/ublk/kublk.h b/tools/testing/selftests/ublk/kublk.h index 5e55484fb0aa..fe42705c6d42 100644 --- a/tools/testing/selftests/ublk/kublk.h +++ b/tools/testing/selftests/ublk/kublk.h @@ -175,23 +175,20 @@ struct ublk_queue { struct ublk_thread { struct ublk_dev *dev; - struct io_uring ring; - unsigned int cmd_inflight; - unsigned int io_inflight; - - pthread_t thread; unsigned idx; #define UBLKS_T_STOPPING (1U << 0) #define UBLKS_T_IDLE (1U << 1) unsigned state; + unsigned int cmd_inflight; + unsigned int io_inflight; + struct io_uring ring; }; struct ublk_dev { struct ublk_tgt tgt; struct ublksrv_ctrl_dev_info dev_info; struct ublk_queue q[UBLK_MAX_QUEUES]; - struct ublk_thread threads[UBLK_MAX_THREADS]; unsigned nthreads; unsigned per_io_tasks; diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 8ceeb8a7894f..c7b270dd77a9 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -7,6 +7,8 @@ # * virtme-ng # * busybox-static (used by virtme-ng) # * qemu (used by virtme-ng) +# +# shellcheck disable=SC2317,SC2119 readonly SCRIPT_DIR="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" readonly KERNEL_CHECKOUT=$(realpath "${SCRIPT_DIR}"/../../../../) @@ -22,8 +24,9 @@ readonly SSH_HOST_PORT=2222 readonly VSOCK_CID=1234 readonly WAIT_PERIOD=3 readonly WAIT_PERIOD_MAX=60 -readonly WAIT_TOTAL=$(( WAIT_PERIOD * WAIT_PERIOD_MAX )) -readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) +readonly WAIT_QEMU=5 +readonly PIDFILE_TEMPLATE=/tmp/vsock_vmtest_XXXX.pid +declare -A PIDFILES # virtme-ng offers a netdev for ssh when using "--ssh", but we also need a # control port forwarded for vsock_test. Because virtme-ng doesn't support @@ -33,12 +36,6 @@ readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) # add the kernel cmdline options that virtme-init uses to setup the interface. readonly QEMU_TEST_PORT_FWD="hostfwd=tcp::${TEST_HOST_PORT}-:${TEST_GUEST_PORT}" readonly QEMU_SSH_PORT_FWD="hostfwd=tcp::${SSH_HOST_PORT}-:${SSH_GUEST_PORT}" -readonly QEMU_OPTS="\ - -netdev user,id=n0,${QEMU_TEST_PORT_FWD},${QEMU_SSH_PORT_FWD} \ - -device virtio-net-pci,netdev=n0 \ - -device vhost-vsock-pci,guest-cid=${VSOCK_CID} \ - --pidfile ${QEMU_PIDFILE} \ -" readonly KERNEL_CMDLINE="\ virtme.dhcp net.ifnames=0 biosdevname=0 \ virtme.ssh virtme_ssh_channel=tcp virtme_ssh_user=$USER \ @@ -51,6 +48,8 @@ readonly TEST_DESCS=( "Run vsock_test using the loopback transport in the VM." ) +readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback) + VERBOSE=0 usage() { @@ -84,21 +83,33 @@ die() { exit "${KSFT_FAIL}" } +check_result() { + local rc arg + + rc=$1 + arg=$2 + + cnt_total=$(( cnt_total + 1 )) + + if [[ ${rc} -eq ${KSFT_PASS} ]]; then + cnt_pass=$(( cnt_pass + 1 )) + echo "ok ${cnt_total} ${arg}" + elif [[ ${rc} -eq ${KSFT_SKIP} ]]; then + cnt_skip=$(( cnt_skip + 1 )) + echo "ok ${cnt_total} ${arg} # SKIP" + elif [[ ${rc} -eq ${KSFT_FAIL} ]]; then + cnt_fail=$(( cnt_fail + 1 )) + echo "not ok ${cnt_total} ${arg} # exit=${rc}" + fi +} + vm_ssh() { ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@" return $? } cleanup() { - if [[ -s "${QEMU_PIDFILE}" ]]; then - pkill -SIGTERM -F "${QEMU_PIDFILE}" > /dev/null 2>&1 - fi - - # If failure occurred during or before qemu start up, then we need - # to clean this up ourselves. - if [[ -e "${QEMU_PIDFILE}" ]]; then - rm "${QEMU_PIDFILE}" - fi + terminate_pidfiles "${!PIDFILES[@]}" } check_args() { @@ -147,7 +158,7 @@ check_vng() { local version local ok - tested_versions=("1.33" "1.36") + tested_versions=("1.33" "1.36" "1.37") version="$(vng --version)" ok=0 @@ -188,10 +199,37 @@ handle_build() { popd &>/dev/null } +create_pidfile() { + local pidfile + + pidfile=$(mktemp "${PIDFILE_TEMPLATE}") + PIDFILES["${pidfile}"]=1 + + echo "${pidfile}" +} + +terminate_pidfiles() { + local pidfile + + for pidfile in "$@"; do + if [[ -s "${pidfile}" ]]; then + pkill -SIGTERM -F "${pidfile}" > /dev/null 2>&1 + fi + + if [[ -e "${pidfile}" ]]; then + rm -f "${pidfile}" + fi + + unset "PIDFILES[${pidfile}]" + done +} + vm_start() { + local pidfile=$1 local logfile=/dev/null local verbose_opt="" local kernel_opt="" + local qemu_opts="" local qemu qemu=$(command -v "${QEMU}") @@ -201,6 +239,13 @@ vm_start() { logfile=/dev/stdout fi + qemu_opts="\ + -netdev user,id=n0,${QEMU_TEST_PORT_FWD},${QEMU_SSH_PORT_FWD} \ + -device virtio-net-pci,netdev=n0 \ + -device vhost-vsock-pci,guest-cid=${VSOCK_CID} \ + --pidfile ${pidfile} + " + if [[ "${BUILD}" -eq 1 ]]; then kernel_opt="${KERNEL_CHECKOUT}" fi @@ -209,16 +254,14 @@ vm_start() { --run \ ${kernel_opt} \ ${verbose_opt} \ - --qemu-opts="${QEMU_OPTS}" \ + --qemu-opts="${qemu_opts}" \ --qemu="${qemu}" \ --user root \ --append "${KERNEL_CMDLINE}" \ --rw &> ${logfile} & - if ! timeout ${WAIT_TOTAL} \ - bash -c 'while [[ ! -s '"${QEMU_PIDFILE}"' ]]; do sleep 1; done; exit 0'; then - die "failed to boot VM" - fi + timeout "${WAIT_QEMU}" \ + bash -c 'while [[ ! -s '"${pidfile}"' ]]; do sleep 1; done; exit 0' } vm_wait_for_ssh() { @@ -251,9 +294,11 @@ wait_for_listener() # for tcp protocol additionally check the socket state [ "${protocol}" = "tcp" ] && pattern="${pattern}0A" + for i in $(seq "${max_intervals}"); do - if awk '{print $2" "$4}' /proc/net/"${protocol}"* | \ - grep -q "${pattern}"; then + if awk -v pattern="${pattern}" \ + 'BEGIN {rc=1} $2" "$4 ~ pattern {rc=0} END {exit rc}' \ + /proc/net/"${protocol}"*; then break fi sleep "${interval}" @@ -270,113 +315,196 @@ EOF } host_wait_for_listener() { - wait_for_listener "${TEST_HOST_PORT_LISTENER}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" + local port=$1 + + wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" } -__log_stdin() { - cat | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' +vm_vsock_test() { + local host=$1 + local cid=$2 + local port=$3 + local rc + + # log output and use pipefail to respect vsock_test errors + set -o pipefail + if [[ "${host}" != server ]]; then + vm_ssh -- "${VSOCK_TEST}" \ + --mode=client \ + --control-host="${host}" \ + --peer-cid="${cid}" \ + --control-port="${port}" \ + 2>&1 | log_guest + rc=$? + else + vm_ssh -- "${VSOCK_TEST}" \ + --mode=server \ + --peer-cid="${cid}" \ + --control-port="${port}" \ + 2>&1 | log_guest & + rc=$? + + if [[ $rc -ne 0 ]]; then + set +o pipefail + return $rc + fi + + vm_wait_for_listener "${port}" + rc=$? + fi + set +o pipefail + + return $rc } -__log_args() { - echo "$*" | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' +host_vsock_test() { + local host=$1 + local cid=$2 + local port=$3 + local rc + + # log output and use pipefail to respect vsock_test errors + set -o pipefail + if [[ "${host}" != server ]]; then + ${VSOCK_TEST} \ + --mode=client \ + --peer-cid="${cid}" \ + --control-host="${host}" \ + --control-port="${port}" 2>&1 | log_host + rc=$? + else + ${VSOCK_TEST} \ + --mode=server \ + --peer-cid="${cid}" \ + --control-port="${port}" 2>&1 | log_host & + rc=$? + + if [[ $rc -ne 0 ]]; then + set +o pipefail + return $rc + fi + + host_wait_for_listener "${port}" + rc=$? + fi + set +o pipefail + + return $rc } log() { - local prefix="$1" + local redirect + local prefix - shift - local redirect= if [[ ${VERBOSE} -eq 0 ]]; then redirect=/dev/null else redirect=/dev/stdout fi + prefix="${LOG_PREFIX:-}" + if [[ "$#" -eq 0 ]]; then - __log_stdin | tee -a "${LOG}" > ${redirect} + if [[ -n "${prefix}" ]]; then + awk -v prefix="${prefix}" '{printf "%s: %s\n", prefix, $0}' + else + cat + fi else - __log_args "$@" | tee -a "${LOG}" > ${redirect} - fi -} - -log_setup() { - log "setup" "$@" + if [[ -n "${prefix}" ]]; then + echo "${prefix}: " "$@" + else + echo "$@" + fi + fi | tee -a "${LOG}" > "${redirect}" } log_host() { - local testname=$1 - - shift - log "test:${testname}:host" "$@" + LOG_PREFIX=host log "$@" } log_guest() { - local testname=$1 - - shift - log "test:${testname}:guest" "$@" + LOG_PREFIX=guest log "$@" } test_vm_server_host_client() { - local testname="${FUNCNAME[0]#test_}" + if ! vm_vsock_test "server" 2 "${TEST_GUEST_PORT}"; then + return "${KSFT_FAIL}" + fi - vm_ssh -- "${VSOCK_TEST}" \ - --mode=server \ - --control-port="${TEST_GUEST_PORT}" \ - --peer-cid=2 \ - 2>&1 | log_guest "${testname}" & + if ! host_vsock_test "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then + return "${KSFT_FAIL}" + fi - vm_wait_for_listener "${TEST_GUEST_PORT}" + return "${KSFT_PASS}" +} - ${VSOCK_TEST} \ - --mode=client \ - --control-host=127.0.0.1 \ - --peer-cid="${VSOCK_CID}" \ - --control-port="${TEST_HOST_PORT}" 2>&1 | log_host "${testname}" +test_vm_client_host_server() { + if ! host_vsock_test "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then + return "${KSFT_FAIL}" + fi - return $? + if ! vm_vsock_test "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" } -test_vm_client_host_server() { - local testname="${FUNCNAME[0]#test_}" +test_vm_loopback() { + local port=60000 # non-forwarded local port - ${VSOCK_TEST} \ - --mode "server" \ - --control-port "${TEST_HOST_PORT_LISTENER}" \ - --peer-cid "${VSOCK_CID}" 2>&1 | log_host "${testname}" & + vm_ssh -- modprobe vsock_loopback &> /dev/null || : - host_wait_for_listener + if ! vm_vsock_test "server" 1 "${port}"; then + return "${KSFT_FAIL}" + fi - vm_ssh -- "${VSOCK_TEST}" \ - --mode=client \ - --control-host=10.0.2.2 \ - --peer-cid=2 \ - --control-port="${TEST_HOST_PORT_LISTENER}" 2>&1 | log_guest "${testname}" + if ! vm_vsock_test "127.0.0.1" 1 "${port}"; then + return "${KSFT_FAIL}" + fi - return $? + return "${KSFT_PASS}" } -test_vm_loopback() { - local testname="${FUNCNAME[0]#test_}" - local port=60000 # non-forwarded local port +shared_vm_test() { + local tname + + tname="${1}" + + for testname in "${USE_SHARED_VM[@]}"; do + if [[ "${tname}" == "${testname}" ]]; then + return 0 + fi + done - vm_ssh -- "${VSOCK_TEST}" \ - --mode=server \ - --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest "${testname}" & + return 1 +} - vm_wait_for_listener "${port}" +shared_vm_tests_requested() { + for arg in "$@"; do + if shared_vm_test "${arg}"; then + return 0 + fi + done - vm_ssh -- "${VSOCK_TEST}" \ - --mode=client \ - --control-host="127.0.0.1" \ - --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest "${testname}" + return 1 +} - return $? +run_shared_vm_tests() { + local arg + + for arg in "$@"; do + if ! shared_vm_test "${arg}"; then + continue + fi + + run_shared_vm_test "${arg}" + check_result "$?" "${arg}" + done } -run_test() { +run_shared_vm_test() { local host_oops_cnt_before local host_warn_cnt_before local vm_oops_cnt_before @@ -399,31 +527,32 @@ run_test() { host_oops_cnt_after=$(dmesg | grep -i 'Oops' | wc -l) if [[ ${host_oops_cnt_after} -gt ${host_oops_cnt_before} ]]; then - echo "FAIL: kernel oops detected on host" | log_host "${name}" + echo "FAIL: kernel oops detected on host" | log_host rc=$KSFT_FAIL fi host_warn_cnt_after=$(dmesg --level=warn | grep -c -i 'vsock') if [[ ${host_warn_cnt_after} -gt ${host_warn_cnt_before} ]]; then - echo "FAIL: kernel warning detected on host" | log_host "${name}" + echo "FAIL: kernel warning detected on host" | log_host rc=$KSFT_FAIL fi vm_oops_cnt_after=$(vm_ssh -- dmesg | grep -i 'Oops' | wc -l) if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then - echo "FAIL: kernel oops detected on vm" | log_host "${name}" + echo "FAIL: kernel oops detected on vm" | log_host rc=$KSFT_FAIL fi vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | grep -c -i 'vsock') if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then - echo "FAIL: kernel warning detected on vm" | log_host "${name}" + echo "FAIL: kernel warning detected on vm" | log_host rc=$KSFT_FAIL fi return "${rc}" } +BUILD=0 QEMU="qemu-system-$(uname -m)" while getopts :hvsq:b o @@ -452,30 +581,21 @@ handle_build echo "1..${#ARGS[@]}" -log_setup "Booting up VM" -vm_start -vm_wait_for_ssh -log_setup "VM booted up" - cnt_pass=0 cnt_fail=0 cnt_skip=0 cnt_total=0 -for arg in "${ARGS[@]}"; do - run_test "${arg}" - rc=$? - if [[ ${rc} -eq $KSFT_PASS ]]; then - cnt_pass=$(( cnt_pass + 1 )) - echo "ok ${cnt_total} ${arg}" - elif [[ ${rc} -eq $KSFT_SKIP ]]; then - cnt_skip=$(( cnt_skip + 1 )) - echo "ok ${cnt_total} ${arg} # SKIP" - elif [[ ${rc} -eq $KSFT_FAIL ]]; then - cnt_fail=$(( cnt_fail + 1 )) - echo "not ok ${cnt_total} ${arg} # exit=$rc" - fi - cnt_total=$(( cnt_total + 1 )) -done + +if shared_vm_tests_requested "${ARGS[@]}"; then + log_host "Booting up VM" + pidfile="$(create_pidfile)" + vm_start "${pidfile}" + vm_wait_for_ssh + log_host "VM booted up" + + run_shared_vm_tests "${ARGS[@]}" + terminate_pidfiles "${pidfile}" +fi echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}" echo "Log: ${LOG}" diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index d4517386e551..9e1250790f33 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -2015,6 +2015,11 @@ static void test_stream_transport_change_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + /* Although setting SO_LINGER does not affect the original test + * for null-ptr-deref, it may trigger a lockdep warning. + */ + enable_so_linger(s, 1); + ret = connect(s, (struct sockaddr *)&sa, sizeof(sa)); /* The connect can fail due to signals coming from the thread, * or because the receiver connection queue is full. @@ -2352,7 +2357,7 @@ static struct test_case test_cases[] = { .run_server = test_stream_nolinger_server, }, { - .name = "SOCK_STREAM transport change null-ptr-deref", + .name = "SOCK_STREAM transport change null-ptr-deref, lockdep warn", .run_client = test_stream_transport_change_client, .run_server = test_stream_transport_change_server, }, |