diff options
Diffstat (limited to 'samples')
41 files changed, 3083 insertions, 530 deletions
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore index 034800c4d1e6..b2f29bc8dc43 100644 --- a/samples/bpf/.gitignore +++ b/samples/bpf/.gitignore @@ -50,4 +50,5 @@ xdp_rxq_info xdp_sample_pkts xdp_tx_iptunnel xdpsock +xsk_fwd testfile.img diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index f87ee02073ba..aeebf5d12f32 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -48,6 +48,7 @@ tprogs-y += syscall_tp tprogs-y += cpustat tprogs-y += xdp_adjust_tail tprogs-y += xdpsock +tprogs-y += xsk_fwd tprogs-y += xdp_fwd tprogs-y += task_fd_query tprogs-y += xdp_sample_pkts @@ -71,12 +72,12 @@ tracex4-objs := tracex4_user.o tracex5-objs := tracex5_user.o $(TRACE_HELPERS) tracex6-objs := tracex6_user.o tracex7-objs := tracex7_user.o -test_probe_write_user-objs := bpf_load.o test_probe_write_user_user.o -trace_output-objs := bpf_load.o trace_output_user.o $(TRACE_HELPERS) -lathist-objs := bpf_load.o lathist_user.o -offwaketime-objs := bpf_load.o offwaketime_user.o $(TRACE_HELPERS) -spintest-objs := bpf_load.o spintest_user.o $(TRACE_HELPERS) -map_perf_test-objs := bpf_load.o map_perf_test_user.o +test_probe_write_user-objs := test_probe_write_user_user.o +trace_output-objs := trace_output_user.o $(TRACE_HELPERS) +lathist-objs := lathist_user.o +offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS) +spintest-objs := spintest_user.o $(TRACE_HELPERS) +map_perf_test-objs := map_perf_test_user.o test_overhead-objs := bpf_load.o test_overhead_user.o test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o test_cgrp2_attach-objs := test_cgrp2_attach.o @@ -86,7 +87,7 @@ xdp1-objs := xdp1_user.o # reuse xdp1 source intentionally xdp2-objs := xdp1_user.o xdp_router_ipv4-objs := xdp_router_ipv4_user.o -test_current_task_under_cgroup-objs := bpf_load.o $(CGROUP_HELPERS) \ +test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \ test_current_task_under_cgroup_user.o trace_event-objs := trace_event_user.o $(TRACE_HELPERS) sampleip-objs := sampleip_user.o $(TRACE_HELPERS) @@ -97,13 +98,14 @@ test_map_in_map-objs := test_map_in_map_user.o per_socket_stats_example-objs := cookie_uid_helper_example.o xdp_redirect-objs := xdp_redirect_user.o xdp_redirect_map-objs := xdp_redirect_map_user.o -xdp_redirect_cpu-objs := bpf_load.o xdp_redirect_cpu_user.o -xdp_monitor-objs := bpf_load.o xdp_monitor_user.o +xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o +xdp_monitor-objs := xdp_monitor_user.o xdp_rxq_info-objs := xdp_rxq_info_user.o -syscall_tp-objs := bpf_load.o syscall_tp_user.o -cpustat-objs := bpf_load.o cpustat_user.o +syscall_tp-objs := syscall_tp_user.o +cpustat-objs := cpustat_user.o xdp_adjust_tail-objs := xdp_adjust_tail_user.o xdpsock-objs := xdpsock_user.o +xsk_fwd-objs := xsk_fwd.o xdp_fwd-objs := xdp_fwd_user.o task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS) xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS) @@ -203,11 +205,14 @@ TPROGLDLIBS_trace_output += -lrt TPROGLDLIBS_map_perf_test += -lrt TPROGLDLIBS_test_overhead += -lrt TPROGLDLIBS_xdpsock += -pthread +TPROGLDLIBS_xsk_fwd += -pthread # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make M=samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang LLC ?= llc CLANG ?= clang +OPT ?= opt +LLVM_DIS ?= llvm-dis LLVM_OBJCOPY ?= llvm-objcopy BTF_PAHOLE ?= pahole @@ -300,6 +305,11 @@ $(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h # asm/sysreg.h - inline assembly used by it is incompatible with llvm. # But, there is no easy way to fix it, so just exclude it since it is # useless for BPF samples. +# below we use long chain of commands, clang | opt | llvm-dis | llc, +# to generate final object file. 'clang' compiles the source into IR +# with native target, e.g., x64, arm64, etc. 'opt' does bpf CORE IR builtin +# processing (llvm12) and IR optimizations. 'llvm-dis' converts +# 'opt' output to IR, and finally 'llc' generates bpf byte code. $(obj)/%.o: $(src)/%.c @echo " CLANG-bpf " $@ $(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \ @@ -311,7 +321,9 @@ $(obj)/%.o: $(src)/%.c -Wno-address-of-packed-member -Wno-tautological-compare \ -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ -I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \ - -O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@ + -O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \ + $(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \ + $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c index a86a19d5f033..5aefd19cdfa1 100644 --- a/samples/bpf/cpustat_kern.c +++ b/samples/bpf/cpustat_kern.c @@ -51,28 +51,28 @@ static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 }; #define MAP_OFF_PSTATE_IDX 3 #define MAP_OFF_NUM 4 -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = MAX_CPU * MAP_OFF_NUM, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAP_OFF_NUM); +} my_map SEC(".maps"); /* cstate_duration records duration time for every idle state per CPU */ -struct bpf_map_def SEC("maps") cstate_duration = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = MAX_CPU * MAX_CSTATE_ENTRIES, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_CSTATE_ENTRIES); +} cstate_duration SEC(".maps"); /* pstate_duration records duration time for every operating point per CPU */ -struct bpf_map_def SEC("maps") pstate_duration = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = MAX_CPU * MAX_PSTATE_ENTRIES, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, MAX_CPU * MAX_PSTATE_ENTRIES); +} pstate_duration SEC(".maps"); /* * The trace events for cpu_idle and cpu_frequency are taken from: diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c index 869a99406dbf..96675985e9e0 100644 --- a/samples/bpf/cpustat_user.c +++ b/samples/bpf/cpustat_user.c @@ -9,7 +9,6 @@ #include <string.h> #include <unistd.h> #include <fcntl.h> -#include <linux/bpf.h> #include <locale.h> #include <sys/types.h> #include <sys/stat.h> @@ -18,7 +17,9 @@ #include <sys/wait.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> + +static int cstate_map_fd, pstate_map_fd; #define MAX_CPU 8 #define MAX_PSTATE_ENTRIES 5 @@ -181,21 +182,50 @@ static void int_exit(int sig) { cpu_stat_inject_cpu_idle_event(); cpu_stat_inject_cpu_frequency_event(); - cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_update(cstate_map_fd, pstate_map_fd); cpu_stat_print(); exit(0); } int main(int argc, char **argv) { + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; char filename[256]; int ret; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + cstate_map_fd = bpf_object__find_map_fd_by_name(obj, "cstate_duration"); + pstate_map_fd = bpf_object__find_map_fd_by_name(obj, "pstate_duration"); + if (cstate_map_fd < 0 || pstate_map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } ret = cpu_stat_inject_cpu_idle_event(); @@ -210,10 +240,13 @@ int main(int argc, char **argv) signal(SIGTERM, int_exit); while (1) { - cpu_stat_update(map_fd[1], map_fd[2]); + cpu_stat_update(cstate_map_fd, pstate_map_fd); cpu_stat_print(); sleep(5); } +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 4b22ace52f80..ff4c533dfac2 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -40,6 +40,7 @@ #include <errno.h> #include <fcntl.h> #include <linux/unistd.h> +#include <linux/compiler.h> #include <linux/bpf.h> #include <bpf/bpf.h> @@ -483,7 +484,7 @@ int main(int argc, char **argv) "Option -%c requires an argument.\n\n", optopt); case 'h': - fallthrough; + __fallthrough; default: Usage(); return 0; diff --git a/samples/bpf/lathist_kern.c b/samples/bpf/lathist_kern.c index ca9c2e4e69aa..4adfcbbe6ef4 100644 --- a/samples/bpf/lathist_kern.c +++ b/samples/bpf/lathist_kern.c @@ -18,12 +18,12 @@ * trace_preempt_[on|off] tracepoints hooks is not supported. */ -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u64), - .max_entries = MAX_CPU, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, u64); + __uint(max_entries, MAX_CPU); +} my_map SEC(".maps"); SEC("kprobe/trace_preempt_off") int bpf_prog1(struct pt_regs *ctx) @@ -61,12 +61,12 @@ static unsigned int log2l(unsigned long v) return log2(v); } -struct bpf_map_def SEC("maps") my_lat = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(long), - .max_entries = MAX_CPU * MAX_ENTRIES, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, long); + __uint(max_entries, MAX_CPU * MAX_ENTRIES); +} my_lat SEC(".maps"); SEC("kprobe/trace_preempt_on") int bpf_prog2(struct pt_regs *ctx) diff --git a/samples/bpf/lathist_user.c b/samples/bpf/lathist_user.c index 2ff2839a52d5..7d8ff2418303 100644 --- a/samples/bpf/lathist_user.c +++ b/samples/bpf/lathist_user.c @@ -6,9 +6,8 @@ #include <unistd.h> #include <stdlib.h> #include <signal.h> -#include <linux/bpf.h> +#include <bpf/libbpf.h> #include <bpf/bpf.h> -#include "bpf_load.h" #define MAX_ENTRIES 20 #define MAX_CPU 4 @@ -81,20 +80,51 @@ static void get_data(int fd) int main(int argc, char **argv) { + struct bpf_link *links[2]; + struct bpf_program *prog; + struct bpf_object *obj; char filename[256]; + int map_fd, i = 0; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + map_fd = bpf_object__find_map_fd_by_name(obj, "my_lat"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; } while (1) { - get_data(map_fd[1]); + get_data(map_fd); print_hist(); sleep(5); } +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/offwaketime_kern.c b/samples/bpf/offwaketime_kern.c index e74ee1cd4b9c..14b792915a9c 100644 --- a/samples/bpf/offwaketime_kern.c +++ b/samples/bpf/offwaketime_kern.c @@ -28,38 +28,38 @@ struct key_t { u32 tret; }; -struct bpf_map_def SEC("maps") counts = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct key_t), - .value_size = sizeof(u64), - .max_entries = 10000, -}; - -struct bpf_map_def SEC("maps") start = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = 10000, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct key_t); + __type(value, u64); + __uint(max_entries, 10000); +} counts SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 10000); +} start SEC(".maps"); struct wokeby_t { char name[TASK_COMM_LEN]; u32 ret; }; -struct bpf_map_def SEC("maps") wokeby = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(u32), - .value_size = sizeof(struct wokeby_t), - .max_entries = 10000, -}; - -struct bpf_map_def SEC("maps") stackmap = { - .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(u32), - .value_size = PERF_MAX_STACK_DEPTH * sizeof(u64), - .max_entries = 10000, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, u32); + __type(value, struct wokeby_t); + __uint(max_entries, 10000); +} wokeby SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(key_size, sizeof(u32)); + __uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64)); + __uint(max_entries, 10000); +} stackmap SEC(".maps"); #define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP) diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 51c7da5341cc..5734cfdaaacb 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -5,19 +5,19 @@ #include <unistd.h> #include <stdlib.h> #include <signal.h> -#include <linux/bpf.h> -#include <string.h> #include <linux/perf_event.h> #include <errno.h> -#include <assert.h> #include <stdbool.h> #include <sys/resource.h> #include <bpf/libbpf.h> -#include "bpf_load.h" +#include <bpf/bpf.h> #include "trace_helpers.h" #define PRINT_RAW_ADDR 0 +/* counts, stackmap */ +static int map_fd[2]; + static void print_ksym(__u64 addr) { struct ksym *sym; @@ -52,14 +52,14 @@ static void print_stack(struct key_t *key, __u64 count) int i; printf("%s;", key->target); - if (bpf_map_lookup_elem(map_fd[3], &key->tret, ip) != 0) { + if (bpf_map_lookup_elem(map_fd[1], &key->tret, ip) != 0) { printf("---;"); } else { for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--) print_ksym(ip[i]); } printf("-;"); - if (bpf_map_lookup_elem(map_fd[3], &key->wret, ip) != 0) { + if (bpf_map_lookup_elem(map_fd[1], &key->wret, ip) != 0) { printf("---;"); } else { for (i = 0; i < PERF_MAX_STACK_DEPTH; i++) @@ -96,23 +96,54 @@ static void int_exit(int sig) int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj = NULL; + struct bpf_link *links[2]; + struct bpf_program *prog; + int delay = 1, i = 0; char filename[256]; - int delay = 1; - - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); - signal(SIGINT, int_exit); - signal(SIGTERM, int_exit); + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + bpf_object__for_each_program(prog, obj) { + links[i] = bpf_program__attach(prog); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; } if (argc > 1) @@ -120,5 +151,10 @@ int main(int argc, char **argv) sleep(delay); print_stacks(map_fd[0]); +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/sockex3_kern.c b/samples/bpf/sockex3_kern.c index cab9cca0b8eb..b363503357e5 100644 --- a/samples/bpf/sockex3_kern.c +++ b/samples/bpf/sockex3_kern.c @@ -31,11 +31,13 @@ struct { #define PARSE_IP 3 #define PARSE_IPV6 4 -/* protocol dispatch routine. - * It tail-calls next BPF program depending on eth proto - * Note, we could have used: - * bpf_tail_call(skb, &jmp_table, proto); - * but it would need large prog_array +/* Protocol dispatch routine. It tail-calls next BPF program depending + * on eth proto. Note, we could have used ... + * + * bpf_tail_call(skb, &jmp_table, proto); + * + * ... but it would need large prog_array and cannot be optimised given + * the map key is not static. */ static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto) { diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c index 4dbee7427d47..7793f6a6ae7e 100644 --- a/samples/bpf/sockex3_user.c +++ b/samples/bpf/sockex3_user.c @@ -29,8 +29,8 @@ int main(int argc, char **argv) struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_program *prog; struct bpf_object *obj; + const char *section; char filename[256]; - const char *title; FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); @@ -58,8 +58,8 @@ int main(int argc, char **argv) bpf_object__for_each_program(prog, obj) { fd = bpf_program__fd(prog); - title = bpf_program__title(prog, false); - if (sscanf(title, "socket/%d", &key) != 1) { + section = bpf_program__section_name(prog); + if (sscanf(section, "socket/%d", &key) != 1) { fprintf(stderr, "ERROR: finding prog failed\n"); goto cleanup; } diff --git a/samples/bpf/spintest_kern.c b/samples/bpf/spintest_kern.c index f508af357251..455da77319d9 100644 --- a/samples/bpf/spintest_kern.c +++ b/samples/bpf/spintest_kern.c @@ -12,25 +12,25 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(long), - .value_size = sizeof(long), - .max_entries = 1024, -}; -struct bpf_map_def SEC("maps") my_map2 = { - .type = BPF_MAP_TYPE_PERCPU_HASH, - .key_size = sizeof(long), - .value_size = sizeof(long), - .max_entries = 1024, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, long); + __type(value, long); + __uint(max_entries, 1024); +} my_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(long)); + __uint(value_size, sizeof(long)); + __uint(max_entries, 1024); +} my_map2 SEC(".maps"); -struct bpf_map_def SEC("maps") stackmap = { - .type = BPF_MAP_TYPE_STACK_TRACE, - .key_size = sizeof(u32), - .value_size = PERF_MAX_STACK_DEPTH * sizeof(u64), - .max_entries = 10000, -}; +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(key_size, sizeof(u32)); + __uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64)); + __uint(max_entries, 10000); +} stackmap SEC(".maps"); #define PROG(foo) \ int foo(struct pt_regs *ctx) \ diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c index fb430ea2ef51..f090d0dc60d6 100644 --- a/samples/bpf/spintest_user.c +++ b/samples/bpf/spintest_user.c @@ -1,40 +1,77 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <unistd.h> -#include <linux/bpf.h> #include <string.h> #include <assert.h> #include <sys/resource.h> #include <bpf/libbpf.h> -#include "bpf_load.h" +#include <bpf/bpf.h> #include "trace_helpers.h" int main(int ac, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256], symbol[256]; + struct bpf_object *obj = NULL; + struct bpf_link *links[20]; long key, next_key, value; - char filename[256]; + struct bpf_program *prog; + int map_fd, i, j = 0; + const char *section; struct ksym *sym; - int i; - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + section = bpf_program__section_name(prog); + if (sscanf(section, "kprobe/%s", symbol) != 1) + continue; + + /* Attach prog only when symbol exists */ + if (ksym_get_addr(symbol)) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } } for (i = 0; i < 5; i++) { key = 0; printf("kprobing funcs:"); - while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) { - bpf_map_lookup_elem(map_fd[0], &next_key, &value); + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) { + bpf_map_lookup_elem(map_fd, &next_key, &value); assert(next_key == value); sym = ksym_search(value); key = next_key; @@ -48,10 +85,15 @@ int main(int ac, char **argv) if (key) printf("\n"); key = 0; - while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) - bpf_map_delete_elem(map_fd[0], &next_key); + while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) + bpf_map_delete_elem(map_fd, &next_key); sleep(1); } +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c index 5a62b03b1f88..50231c2eff9c 100644 --- a/samples/bpf/syscall_tp_kern.c +++ b/samples/bpf/syscall_tp_kern.c @@ -18,19 +18,19 @@ struct syscalls_exit_open_args { long ret; }; -struct bpf_map_def SEC("maps") enter_open_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} enter_open_map SEC(".maps"); -struct bpf_map_def SEC("maps") exit_open_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 1); +} exit_open_map SEC(".maps"); static __always_inline void count(void *map) { diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c index 57014bab7cbe..76a1d00128fb 100644 --- a/samples/bpf/syscall_tp_user.c +++ b/samples/bpf/syscall_tp_user.c @@ -5,16 +5,12 @@ #include <unistd.h> #include <fcntl.h> #include <stdlib.h> -#include <signal.h> -#include <linux/bpf.h> #include <string.h> #include <linux/perf_event.h> #include <errno.h> -#include <assert.h> -#include <stdbool.h> #include <sys/resource.h> +#include <bpf/libbpf.h> #include <bpf/bpf.h> -#include "bpf_load.h" /* This program verifies bpf attachment to tracepoint sys_enter_* and sys_exit_*. * This requires kernel CONFIG_FTRACE_SYSCALLS to be set. @@ -49,16 +45,44 @@ static void verify_map(int map_id) static int test(char *filename, int num_progs) { - int i, fd, map0_fds[num_progs], map1_fds[num_progs]; + int map0_fds[num_progs], map1_fds[num_progs], fd, i, j = 0; + struct bpf_link *links[num_progs * 4]; + struct bpf_object *objs[num_progs]; + struct bpf_program *prog; for (i = 0; i < num_progs; i++) { - if (load_bpf_file(filename)) { - fprintf(stderr, "%s", bpf_log_buf); - return 1; + objs[i] = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(objs[i])) { + fprintf(stderr, "opening BPF object file failed\n"); + objs[i] = NULL; + goto cleanup; } - printf("prog #%d: map ids %d %d\n", i, map_fd[0], map_fd[1]); - map0_fds[i] = map_fd[0]; - map1_fds[i] = map_fd[1]; + + /* load BPF program */ + if (bpf_object__load(objs[i])) { + fprintf(stderr, "loading BPF object file failed\n"); + goto cleanup; + } + + map0_fds[i] = bpf_object__find_map_fd_by_name(objs[i], + "enter_open_map"); + map1_fds[i] = bpf_object__find_map_fd_by_name(objs[i], + "exit_open_map"); + if (map0_fds[i] < 0 || map1_fds[i] < 0) { + fprintf(stderr, "finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, objs[i]) { + links[j] = bpf_program__attach(prog); + if (libbpf_get_error(links[j])) { + fprintf(stderr, "bpf_program__attach failed\n"); + links[j] = NULL; + goto cleanup; + } + j++; + } + printf("prog #%d: map ids %d %d\n", i, map0_fds[i], map1_fds[i]); } /* current load_bpf_file has perf_event_open default pid = -1 @@ -80,6 +104,12 @@ static int test(char *filename, int num_progs) verify_map(map1_fds[i]); } +cleanup: + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + for (i--; i >= 0; i--) + bpf_object__close(objs[i]); return 0; } diff --git a/samples/bpf/task_fd_query_kern.c b/samples/bpf/task_fd_query_kern.c index 278ade5427c8..c821294e1774 100644 --- a/samples/bpf/task_fd_query_kern.c +++ b/samples/bpf/task_fd_query_kern.c @@ -10,7 +10,7 @@ int bpf_prog1(struct pt_regs *ctx) return 0; } -SEC("kretprobe/blk_account_io_completion") +SEC("kretprobe/blk_account_io_done") int bpf_prog2(struct pt_regs *ctx) { return 0; diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index ff2e9c1c7266..4a74531dc403 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -314,7 +314,7 @@ int main(int argc, char **argv) /* test two functions in the corresponding *_kern.c file */ CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_mq_start_request", BPF_FD_TYPE_KPROBE)); - CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_completion", + CHECK_AND_RET(test_debug_fs_kprobe(1, "blk_account_io_done", BPF_FD_TYPE_KRETPROBE)); /* test nondebug fs kprobe */ diff --git a/samples/bpf/test_current_task_under_cgroup_kern.c b/samples/bpf/test_current_task_under_cgroup_kern.c index 6dc4f41bb6cb..fbd43e2bb4d3 100644 --- a/samples/bpf/test_current_task_under_cgroup_kern.c +++ b/samples/bpf/test_current_task_under_cgroup_kern.c @@ -10,23 +10,24 @@ #include <linux/version.h> #include <bpf/bpf_helpers.h> #include <uapi/linux/utsname.h> +#include "trace_common.h" -struct bpf_map_def SEC("maps") cgroup_map = { - .type = BPF_MAP_TYPE_CGROUP_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u32), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_CGROUP_ARRAY); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 1); +} cgroup_map SEC(".maps"); -struct bpf_map_def SEC("maps") perf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 1); +} perf_map SEC(".maps"); /* Writes the last PID that called sync to a map at index 0 */ -SEC("kprobe/sys_sync") +SEC("kprobe/" SYSCALL(sys_sync)) int bpf_prog1(struct pt_regs *ctx) { u64 pid = bpf_get_current_pid_tgid(); diff --git a/samples/bpf/test_current_task_under_cgroup_user.c b/samples/bpf/test_current_task_under_cgroup_user.c index 06e9f8ce42e2..ac251a417f45 100644 --- a/samples/bpf/test_current_task_under_cgroup_user.c +++ b/samples/bpf/test_current_task_under_cgroup_user.c @@ -4,10 +4,9 @@ #define _GNU_SOURCE #include <stdio.h> -#include <linux/bpf.h> #include <unistd.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> #include "cgroup_helpers.h" #define CGROUP_PATH "/my-cgroup" @@ -15,13 +14,44 @@ int main(int argc, char **argv) { pid_t remote_pid, local_pid = getpid(); - int cg2, idx = 0, rc = 0; + struct bpf_link *link = NULL; + struct bpf_program *prog; + int cg2, idx = 0, rc = 1; + struct bpf_object *obj; char filename[256]; + int map_fd[2]; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (!prog) { + printf("finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "cgroup_map"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "perf_map"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } if (setup_cgroup_environment()) @@ -70,12 +100,14 @@ int main(int argc, char **argv) goto err; } - goto out; -err: - rc = 1; + rc = 0; -out: +err: close(cg2); cleanup_cgroup_environment(); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return rc; } diff --git a/samples/bpf/test_map_in_map_kern.c b/samples/bpf/test_map_in_map_kern.c index 8def45c5b697..b0200c8eac09 100644 --- a/samples/bpf/test_map_in_map_kern.c +++ b/samples/bpf/test_map_in_map_kern.c @@ -103,10 +103,9 @@ static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port) return result ? *result : -ENOENT; } -SEC("kprobe/" SYSCALL(sys_connect)) +SEC("kprobe/__sys_connect") int trace_sys_connect(struct pt_regs *ctx) { - struct pt_regs *real_regs = (struct pt_regs *)PT_REGS_PARM1_CORE(ctx); struct sockaddr_in6 *in6; u16 test_case, port, dst6[8]; int addrlen, ret, inline_ret, ret_key = 0; @@ -114,8 +113,8 @@ int trace_sys_connect(struct pt_regs *ctx) void *outer_map, *inner_map; bool inline_hash = false; - in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(real_regs); - addrlen = (int)PT_REGS_PARM3_CORE(real_regs); + in6 = (struct sockaddr_in6 *)PT_REGS_PARM2_CORE(ctx); + addrlen = (int)PT_REGS_PARM3_CORE(ctx); if (addrlen != sizeof(*in6)) return 0; diff --git a/samples/bpf/test_probe_write_user_kern.c b/samples/bpf/test_probe_write_user_kern.c index fd651a65281e..220a96438d75 100644 --- a/samples/bpf/test_probe_write_user_kern.c +++ b/samples/bpf/test_probe_write_user_kern.c @@ -13,12 +13,12 @@ #include <bpf/bpf_core_read.h> #include "trace_common.h" -struct bpf_map_def SEC("maps") dnat_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(struct sockaddr_in), - .value_size = sizeof(struct sockaddr_in), - .max_entries = 256, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, struct sockaddr_in); + __type(value, struct sockaddr_in); + __uint(max_entries, 256); +} dnat_map SEC(".maps"); /* kprobe is NOT a stable ABI * kernel functions can be removed, renamed or completely change semantics. diff --git a/samples/bpf/test_probe_write_user_user.c b/samples/bpf/test_probe_write_user_user.c index 045eb5e30f54..00ccfb834e45 100644 --- a/samples/bpf/test_probe_write_user_user.c +++ b/samples/bpf/test_probe_write_user_user.c @@ -1,21 +1,22 @@ // SPDX-License-Identifier: GPL-2.0 #include <stdio.h> #include <assert.h> -#include <linux/bpf.h> #include <unistd.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> #include <sys/socket.h> -#include <string.h> #include <netinet/in.h> #include <arpa/inet.h> int main(int ac, char **argv) { - int serverfd, serverconnfd, clientfd; - socklen_t sockaddr_len; - struct sockaddr serv_addr, mapped_addr, tmp_addr; struct sockaddr_in *serv_addr_in, *mapped_addr_in, *tmp_addr_in; + struct sockaddr serv_addr, mapped_addr, tmp_addr; + int serverfd, serverconnfd, clientfd, map_fd; + struct bpf_link *link = NULL; + struct bpf_program *prog; + struct bpf_object *obj; + socklen_t sockaddr_len; char filename[256]; char *ip; @@ -24,10 +25,35 @@ int main(int ac, char **argv) tmp_addr_in = (struct sockaddr_in *)&tmp_addr; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (libbpf_get_error(prog)) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "dnat_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } assert((serverfd = socket(AF_INET, SOCK_STREAM, 0)) > 0); @@ -51,7 +77,7 @@ int main(int ac, char **argv) mapped_addr_in->sin_port = htons(5555); mapped_addr_in->sin_addr.s_addr = inet_addr("255.255.255.255"); - assert(!bpf_map_update_elem(map_fd[0], &mapped_addr, &serv_addr, BPF_ANY)); + assert(!bpf_map_update_elem(map_fd, &mapped_addr, &serv_addr, BPF_ANY)); assert(listen(serverfd, 5) == 0); @@ -75,5 +101,8 @@ int main(int ac, char **argv) /* Is the server's getsockname = the socket getpeername */ assert(memcmp(&serv_addr, &tmp_addr, sizeof(struct sockaddr_in)) == 0); +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return 0; } diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c index 1d7d422cae6f..b64815af0943 100644 --- a/samples/bpf/trace_output_kern.c +++ b/samples/bpf/trace_output_kern.c @@ -2,15 +2,16 @@ #include <linux/version.h> #include <uapi/linux/bpf.h> #include <bpf/bpf_helpers.h> +#include "trace_common.h" -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u32), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(u32)); + __uint(max_entries, 2); +} my_map SEC(".maps"); -SEC("kprobe/sys_write") +SEC("kprobe/" SYSCALL(sys_write)) int bpf_prog1(struct pt_regs *ctx) { struct S { diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index 60a17dd05345..364b98764d54 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -1,23 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only #include <stdio.h> -#include <unistd.h> -#include <stdlib.h> -#include <stdbool.h> -#include <string.h> #include <fcntl.h> #include <poll.h> -#include <linux/perf_event.h> -#include <linux/bpf.h> -#include <errno.h> -#include <assert.h> -#include <sys/syscall.h> -#include <sys/ioctl.h> -#include <sys/mman.h> #include <time.h> #include <signal.h> #include <bpf/libbpf.h> -#include "bpf_load.h" -#include "perf-sys.h" static __u64 time_get_ns(void) { @@ -57,20 +44,48 @@ static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) int main(int argc, char **argv) { struct perf_buffer_opts pb_opts = {}; + struct bpf_link *link = NULL; + struct bpf_program *prog; struct perf_buffer *pb; + struct bpf_object *obj; + int map_fd, ret = 0; char filename[256]; FILE *f; - int ret; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return 0; + } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); + if (map_fd < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + prog = bpf_object__find_program_by_name(obj, "bpf_prog1"); + if (libbpf_get_error(prog)) { + fprintf(stderr, "ERROR: finding a prog in obj file failed\n"); + goto cleanup; + } + + link = bpf_program__attach(prog); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } pb_opts.sample_cb = print_bpf_output; - pb = perf_buffer__new(map_fd[0], 8, &pb_opts); + pb = perf_buffer__new(map_fd, 8, &pb_opts); ret = libbpf_get_error(pb); if (ret) { printf("failed to setup perf_buffer: %d\n", ret); @@ -84,5 +99,9 @@ int main(int argc, char **argv) while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) { } kill(0, SIGINT); + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); return ret; } diff --git a/samples/bpf/tracex3_kern.c b/samples/bpf/tracex3_kern.c index 659613c19a82..710a4410b2fb 100644 --- a/samples/bpf/tracex3_kern.c +++ b/samples/bpf/tracex3_kern.c @@ -49,7 +49,7 @@ struct { __uint(max_entries, SLOTS); } lat_map SEC(".maps"); -SEC("kprobe/blk_account_io_completion") +SEC("kprobe/blk_account_io_done") int bpf_prog2(struct pt_regs *ctx) { long rq = PT_REGS_PARM1(ctx); diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c index 98dad57a96c4..c17d3fb5fd64 100644 --- a/samples/bpf/tracex5_user.c +++ b/samples/bpf/tracex5_user.c @@ -39,8 +39,8 @@ int main(int ac, char **argv) struct bpf_program *prog; struct bpf_object *obj; int key, fd, progs_fd; + const char *section; char filename[256]; - const char *title; FILE *f; setrlimit(RLIMIT_MEMLOCK, &r); @@ -78,9 +78,9 @@ int main(int ac, char **argv) } bpf_object__for_each_program(prog, obj) { - title = bpf_program__title(prog, false); + section = bpf_program__section_name(prog); /* register only syscalls to PROG_ARRAY */ - if (sscanf(title, "kprobe/%d", &key) != 1) + if (sscanf(section, "kprobe/%d", &key) != 1) continue; fd = bpf_program__fd(prog); diff --git a/samples/bpf/xdp_monitor_kern.c b/samples/bpf/xdp_monitor_kern.c index 3d33cca2d48a..5c955b812c47 100644 --- a/samples/bpf/xdp_monitor_kern.c +++ b/samples/bpf/xdp_monitor_kern.c @@ -6,21 +6,21 @@ #include <uapi/linux/bpf.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") redirect_err_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = 2, +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, 2); /* TODO: have entries for all possible errno's */ -}; +} redirect_err_cnt SEC(".maps"); #define XDP_UNKNOWN XDP_REDIRECT + 1 -struct bpf_map_def SEC("maps") exception_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(u64), - .max_entries = XDP_UNKNOWN + 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, u64); + __uint(max_entries, XDP_UNKNOWN + 1); +} exception_cnt SEC(".maps"); /* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format * Code in: kernel/include/trace/events/xdp.h @@ -129,19 +129,19 @@ struct datarec { }; #define MAX_CPUS 64 -struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = MAX_CPUS, -}; +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, MAX_CPUS); +} cpumap_enqueue_cnt SEC(".maps"); -struct bpf_map_def SEC("maps") cpumap_kthread_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, 1); +} cpumap_kthread_cnt SEC(".maps"); /* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format * Code in: kernel/include/trace/events/xdp.h @@ -210,12 +210,12 @@ int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx) return 0; } -struct bpf_map_def SEC("maps") devmap_xmit_cnt = { - .type = BPF_MAP_TYPE_PERCPU_ARRAY, - .key_size = sizeof(u32), - .value_size = sizeof(struct datarec), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, struct datarec); + __uint(max_entries, 1); +} devmap_xmit_cnt SEC(".maps"); /* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_devmap_xmit/format * Code in: kernel/include/trace/events/xdp.h diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index ef53b93db573..03d0a182913f 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -26,12 +26,37 @@ static const char *__doc_err_only__= #include <net/if.h> #include <time.h> +#include <signal.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> #include "bpf_util.h" +enum map_type { + REDIRECT_ERR_CNT, + EXCEPTION_CNT, + CPUMAP_ENQUEUE_CNT, + CPUMAP_KTHREAD_CNT, + DEVMAP_XMIT_CNT, +}; + +static const char *const map_type_strings[] = { + [REDIRECT_ERR_CNT] = "redirect_err_cnt", + [EXCEPTION_CNT] = "exception_cnt", + [CPUMAP_ENQUEUE_CNT] = "cpumap_enqueue_cnt", + [CPUMAP_KTHREAD_CNT] = "cpumap_kthread_cnt", + [DEVMAP_XMIT_CNT] = "devmap_xmit_cnt", +}; + +#define NUM_MAP 5 +#define NUM_TP 8 + +static int tp_cnt; +static int map_cnt; static int verbose = 1; static bool debug = false; +struct bpf_map *map_data[NUM_MAP] = {}; +struct bpf_link *tp_links[NUM_TP] = {}; +struct bpf_object *obj; static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, @@ -41,6 +66,16 @@ static const struct option long_options[] = { {0, 0, NULL, 0 } }; +static void int_exit(int sig) +{ + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); + + bpf_object__close(obj); + exit(0); +} + /* C standard specifies two constants, EXIT_SUCCESS(0) and EXIT_FAILURE(1) */ #define EXIT_FAIL_MEM 5 @@ -483,23 +518,23 @@ static bool stats_collect(struct stats_record *rec) * this can happen by someone running perf-record -e */ - fd = map_data[0].fd; /* map0: redirect_err_cnt */ + fd = bpf_map__fd(map_data[REDIRECT_ERR_CNT]); for (i = 0; i < REDIR_RES_MAX; i++) map_collect_record_u64(fd, i, &rec->xdp_redirect[i]); - fd = map_data[1].fd; /* map1: exception_cnt */ + fd = bpf_map__fd(map_data[EXCEPTION_CNT]); for (i = 0; i < XDP_ACTION_MAX; i++) { map_collect_record_u64(fd, i, &rec->xdp_exception[i]); } - fd = map_data[2].fd; /* map2: cpumap_enqueue_cnt */ + fd = bpf_map__fd(map_data[CPUMAP_ENQUEUE_CNT]); for (i = 0; i < MAX_CPUS; i++) map_collect_record(fd, i, &rec->xdp_cpumap_enqueue[i]); - fd = map_data[3].fd; /* map3: cpumap_kthread_cnt */ + fd = bpf_map__fd(map_data[CPUMAP_KTHREAD_CNT]); map_collect_record(fd, 0, &rec->xdp_cpumap_kthread); - fd = map_data[4].fd; /* map4: devmap_xmit_cnt */ + fd = bpf_map__fd(map_data[DEVMAP_XMIT_CNT]); map_collect_record(fd, 0, &rec->xdp_devmap_xmit); return true; @@ -598,8 +633,8 @@ static void stats_poll(int interval, bool err_only) /* TODO Need more advanced stats on error types */ if (verbose) { - printf(" - Stats map0: %s\n", map_data[0].name); - printf(" - Stats map1: %s\n", map_data[1].name); + printf(" - Stats map0: %s\n", bpf_map__name(map_data[0])); + printf(" - Stats map1: %s\n", bpf_map__name(map_data[1])); printf("\n"); } fflush(stdout); @@ -618,44 +653,51 @@ static void stats_poll(int interval, bool err_only) static void print_bpf_prog_info(void) { - int i; + struct bpf_program *prog; + struct bpf_map *map; + int i = 0; /* Prog info */ - printf("Loaded BPF prog have %d bpf program(s)\n", prog_cnt); - for (i = 0; i < prog_cnt; i++) { - printf(" - prog_fd[%d] = fd(%d)\n", i, prog_fd[i]); + printf("Loaded BPF prog have %d bpf program(s)\n", tp_cnt); + bpf_object__for_each_program(prog, obj) { + printf(" - prog_fd[%d] = fd(%d)\n", i, bpf_program__fd(prog)); + i++; } + i = 0; /* Maps info */ - printf("Loaded BPF prog have %d map(s)\n", map_data_count); - for (i = 0; i < map_data_count; i++) { - char *name = map_data[i].name; - int fd = map_data[i].fd; + printf("Loaded BPF prog have %d map(s)\n", map_cnt); + bpf_object__for_each_map(map, obj) { + const char *name = bpf_map__name(map); + int fd = bpf_map__fd(map); printf(" - map_data[%d] = fd(%d) name:%s\n", i, fd, name); + i++; } /* Event info */ - printf("Searching for (max:%d) event file descriptor(s)\n", prog_cnt); - for (i = 0; i < prog_cnt; i++) { - if (event_fd[i] != -1) - printf(" - event_fd[%d] = fd(%d)\n", i, event_fd[i]); + printf("Searching for (max:%d) event file descriptor(s)\n", tp_cnt); + for (i = 0; i < tp_cnt; i++) { + int fd = bpf_link__fd(tp_links[i]); + + if (fd != -1) + printf(" - event_fd[%d] = fd(%d)\n", i, fd); } } int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_program *prog; int longindex = 0, opt; - int ret = EXIT_SUCCESS; - char bpf_obj_file[256]; + int ret = EXIT_FAILURE; + enum map_type type; + char filename[256]; /* Default settings: */ bool errors_only = true; int interval = 2; - snprintf(bpf_obj_file, sizeof(bpf_obj_file), "%s_kern.o", argv[0]); - /* Parse commands line args */ while ((opt = getopt_long(argc, argv, "hDSs:", long_options, &longindex)) != -1) { @@ -672,40 +714,79 @@ int main(int argc, char **argv) case 'h': default: usage(argv); - return EXIT_FAILURE; + return ret; } } + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); if (setrlimit(RLIMIT_MEMLOCK, &r)) { perror("setrlimit(RLIMIT_MEMLOCK)"); - return EXIT_FAILURE; + return ret; } - if (load_bpf_file(bpf_obj_file)) { - printf("ERROR - bpf_log_buf: %s", bpf_log_buf); - return EXIT_FAILURE; + /* Remove tracepoint program when program is interrupted or killed */ + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + printf("ERROR: opening BPF object file failed\n"); + obj = NULL; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + for (type = 0; type < NUM_MAP; type++) { + map_data[type] = + bpf_object__find_map_by_name(obj, map_type_strings[type]); + + if (libbpf_get_error(map_data[type])) { + printf("ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + map_cnt++; } - if (!prog_fd[0]) { - printf("ERROR - load_bpf_file: %s\n", strerror(errno)); - return EXIT_FAILURE; + + bpf_object__for_each_program(prog, obj) { + tp_links[tp_cnt] = bpf_program__attach(prog); + if (libbpf_get_error(tp_links[tp_cnt])) { + printf("ERROR: bpf_program__attach failed\n"); + tp_links[tp_cnt] = NULL; + goto cleanup; + } + tp_cnt++; } if (debug) { print_bpf_prog_info(); } - /* Unload/stop tracepoint event by closing fd's */ + /* Unload/stop tracepoint event by closing bpf_link's */ if (errors_only) { - /* The prog_fd[i] and event_fd[i] depend on the - * order the functions was defined in _kern.c + /* The bpf_link[i] depend on the order of + * the functions was defined in _kern.c */ - close(event_fd[2]); /* tracepoint/xdp/xdp_redirect */ - close(prog_fd[2]); /* func: trace_xdp_redirect */ - close(event_fd[3]); /* tracepoint/xdp/xdp_redirect_map */ - close(prog_fd[3]); /* func: trace_xdp_redirect_map */ + bpf_link__destroy(tp_links[2]); /* tracepoint/xdp/xdp_redirect */ + tp_links[2] = NULL; + + bpf_link__destroy(tp_links[3]); /* tracepoint/xdp/xdp_redirect_map */ + tp_links[3] = NULL; } stats_poll(interval, errors_only); + ret = EXIT_SUCCESS; + +cleanup: + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); + + bpf_object__close(obj); return ret; } diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 004c0622c913..6fb8dbde62c5 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -37,18 +37,35 @@ static __u32 prog_id; static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static int n_cpus; -static int cpu_map_fd; -static int rx_cnt_map_fd; -static int redirect_err_cnt_map_fd; -static int cpumap_enqueue_cnt_map_fd; -static int cpumap_kthread_cnt_map_fd; -static int cpus_available_map_fd; -static int cpus_count_map_fd; -static int cpus_iterator_map_fd; -static int exception_cnt_map_fd; + +enum map_type { + CPU_MAP, + RX_CNT, + REDIRECT_ERR_CNT, + CPUMAP_ENQUEUE_CNT, + CPUMAP_KTHREAD_CNT, + CPUS_AVAILABLE, + CPUS_COUNT, + CPUS_ITERATOR, + EXCEPTION_CNT, +}; + +static const char *const map_type_strings[] = { + [CPU_MAP] = "cpu_map", + [RX_CNT] = "rx_cnt", + [REDIRECT_ERR_CNT] = "redirect_err_cnt", + [CPUMAP_ENQUEUE_CNT] = "cpumap_enqueue_cnt", + [CPUMAP_KTHREAD_CNT] = "cpumap_kthread_cnt", + [CPUS_AVAILABLE] = "cpus_available", + [CPUS_COUNT] = "cpus_count", + [CPUS_ITERATOR] = "cpus_iterator", + [EXCEPTION_CNT] = "exception_cnt", +}; #define NUM_TP 5 -struct bpf_link *tp_links[NUM_TP] = { 0 }; +#define NUM_MAP 9 +struct bpf_link *tp_links[NUM_TP] = {}; +static int map_fds[NUM_MAP]; static int tp_cnt = 0; /* Exit return codes */ @@ -111,7 +128,7 @@ static void print_avail_progs(struct bpf_object *obj) bpf_object__for_each_program(pos, obj) { if (bpf_program__is_xdp(pos)) - printf(" %s\n", bpf_program__title(pos, false)); + printf(" %s\n", bpf_program__section_name(pos)); } } @@ -527,20 +544,20 @@ static void stats_collect(struct stats_record *rec) { int fd, i; - fd = rx_cnt_map_fd; + fd = map_fds[RX_CNT]; map_collect_percpu(fd, 0, &rec->rx_cnt); - fd = redirect_err_cnt_map_fd; + fd = map_fds[REDIRECT_ERR_CNT]; map_collect_percpu(fd, 1, &rec->redir_err); - fd = cpumap_enqueue_cnt_map_fd; + fd = map_fds[CPUMAP_ENQUEUE_CNT]; for (i = 0; i < n_cpus; i++) map_collect_percpu(fd, i, &rec->enq[i]); - fd = cpumap_kthread_cnt_map_fd; + fd = map_fds[CPUMAP_KTHREAD_CNT]; map_collect_percpu(fd, 0, &rec->kthread); - fd = exception_cnt_map_fd; + fd = map_fds[EXCEPTION_CNT]; map_collect_percpu(fd, 0, &rec->exception); } @@ -565,7 +582,7 @@ static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value, /* Add a CPU entry to cpumap, as this allocate a cpu entry in * the kernel for the cpu. */ - ret = bpf_map_update_elem(cpu_map_fd, &cpu, value, 0); + ret = bpf_map_update_elem(map_fds[CPU_MAP], &cpu, value, 0); if (ret) { fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret); exit(EXIT_FAIL_BPF); @@ -574,21 +591,21 @@ static int create_cpu_entry(__u32 cpu, struct bpf_cpumap_val *value, /* Inform bpf_prog's that a new CPU is available to select * from via some control maps. */ - ret = bpf_map_update_elem(cpus_available_map_fd, &avail_idx, &cpu, 0); + ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &avail_idx, &cpu, 0); if (ret) { fprintf(stderr, "Add to avail CPUs failed\n"); exit(EXIT_FAIL_BPF); } /* When not replacing/updating existing entry, bump the count */ - ret = bpf_map_lookup_elem(cpus_count_map_fd, &key, &curr_cpus_count); + ret = bpf_map_lookup_elem(map_fds[CPUS_COUNT], &key, &curr_cpus_count); if (ret) { fprintf(stderr, "Failed reading curr cpus_count\n"); exit(EXIT_FAIL_BPF); } if (new) { curr_cpus_count++; - ret = bpf_map_update_elem(cpus_count_map_fd, &key, + ret = bpf_map_update_elem(map_fds[CPUS_COUNT], &key, &curr_cpus_count, 0); if (ret) { fprintf(stderr, "Failed write curr cpus_count\n"); @@ -612,7 +629,7 @@ static void mark_cpus_unavailable(void) int ret, i; for (i = 0; i < n_cpus; i++) { - ret = bpf_map_update_elem(cpus_available_map_fd, &i, + ret = bpf_map_update_elem(map_fds[CPUS_AVAILABLE], &i, &invalid_cpu, 0); if (ret) { fprintf(stderr, "Failed marking CPU unavailable\n"); @@ -665,68 +682,37 @@ static void stats_poll(int interval, bool use_separators, char *prog_name, free_stats_record(prev); } -static struct bpf_link * attach_tp(struct bpf_object *obj, - const char *tp_category, - const char* tp_name) +static int init_tracepoints(struct bpf_object *obj) { struct bpf_program *prog; - struct bpf_link *link; - char sec_name[PATH_MAX]; - int len; - len = snprintf(sec_name, PATH_MAX, "tracepoint/%s/%s", - tp_category, tp_name); - if (len < 0) - exit(EXIT_FAIL); + bpf_object__for_each_program(prog, obj) { + if (bpf_program__is_tracepoint(prog) != true) + continue; - prog = bpf_object__find_program_by_title(obj, sec_name); - if (!prog) { - fprintf(stderr, "ERR: finding progsec: %s\n", sec_name); - exit(EXIT_FAIL_BPF); + tp_links[tp_cnt] = bpf_program__attach(prog); + if (libbpf_get_error(tp_links[tp_cnt])) { + tp_links[tp_cnt] = NULL; + return -EINVAL; + } + tp_cnt++; } - link = bpf_program__attach_tracepoint(prog, tp_category, tp_name); - if (libbpf_get_error(link)) - exit(EXIT_FAIL_BPF); - - return link; -} - -static void init_tracepoints(struct bpf_object *obj) { - tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_err"); - tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_redirect_map_err"); - tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_exception"); - tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_enqueue"); - tp_links[tp_cnt++] = attach_tp(obj, "xdp", "xdp_cpumap_kthread"); + return 0; } static int init_map_fds(struct bpf_object *obj) { - /* Maps updated by tracepoints */ - redirect_err_cnt_map_fd = - bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt"); - exception_cnt_map_fd = - bpf_object__find_map_fd_by_name(obj, "exception_cnt"); - cpumap_enqueue_cnt_map_fd = - bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt"); - cpumap_kthread_cnt_map_fd = - bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt"); - - /* Maps used by XDP */ - rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt"); - cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map"); - cpus_available_map_fd = - bpf_object__find_map_fd_by_name(obj, "cpus_available"); - cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count"); - cpus_iterator_map_fd = - bpf_object__find_map_fd_by_name(obj, "cpus_iterator"); - - if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 || - redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 || - cpumap_kthread_cnt_map_fd < 0 || cpus_available_map_fd < 0 || - cpus_count_map_fd < 0 || cpus_iterator_map_fd < 0 || - exception_cnt_map_fd < 0) - return -ENOENT; + enum map_type type; + + for (type = 0; type < NUM_MAP; type++) { + map_fds[type] = + bpf_object__find_map_fd_by_name(obj, + map_type_strings[type]); + + if (map_fds[type] < 0) + return -ENOENT; + } return 0; } @@ -795,13 +781,13 @@ int main(int argc, char **argv) bool stress_mode = false; struct bpf_program *prog; struct bpf_object *obj; + int err = EXIT_FAIL; char filename[256]; int added_cpus = 0; int longindex = 0; int interval = 2; int add_cpu = -1; - int opt, err; - int prog_fd; + int opt, prog_fd; int *cpu, i; __u32 qsize; @@ -824,24 +810,29 @@ int main(int argc, char **argv) } if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) - return EXIT_FAIL; + return err; if (prog_fd < 0) { fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", strerror(errno)); - return EXIT_FAIL; + return err; } - init_tracepoints(obj); + + if (init_tracepoints(obj) < 0) { + fprintf(stderr, "ERR: bpf_program__attach failed\n"); + return err; + } + if (init_map_fds(obj) < 0) { fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n"); - return EXIT_FAIL; + return err; } mark_cpus_unavailable(); cpu = malloc(n_cpus * sizeof(int)); if (!cpu) { fprintf(stderr, "failed to allocate cpu array\n"); - return EXIT_FAIL; + return err; } memset(cpu, 0, n_cpus * sizeof(int)); @@ -960,14 +951,12 @@ int main(int argc, char **argv) prog = bpf_object__find_program_by_title(obj, prog_name); if (!prog) { fprintf(stderr, "bpf_object__find_program_by_title failed\n"); - err = EXIT_FAIL; goto out; } prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { fprintf(stderr, "bpf_program__fd failed\n"); - err = EXIT_FAIL; goto out; } @@ -986,6 +975,8 @@ int main(int argc, char **argv) stats_poll(interval, use_separators, prog_name, mprog_name, &value, stress_mode); + + err = EXIT_OK; out: free(cpu); return err; diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c index 33377289e2a8..9cf76b340dd7 100644 --- a/samples/bpf/xdp_sample_pkts_kern.c +++ b/samples/bpf/xdp_sample_pkts_kern.c @@ -5,14 +5,12 @@ #include <bpf/bpf_helpers.h> #define SAMPLE_SIZE 64ul -#define MAX_CPUS 128 - -struct bpf_map_def SEC("maps") my_map = { - .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(u32), - .max_entries = MAX_CPUS, -}; + +struct { + __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(u32)); +} my_map SEC(".maps"); SEC("xdp_sample") int xdp_sample_prog(struct xdp_md *ctx) diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index 991ef6f0880b..4b2a300c750c 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -18,7 +18,6 @@ #include "perf-sys.h" -#define MAX_CPUS 128 static int if_idx; static char *if_name; static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 19c679456a0e..1149e94ca32f 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -11,6 +11,7 @@ #include <linux/if_xdp.h> #include <linux/if_ether.h> #include <linux/ip.h> +#include <linux/limits.h> #include <linux/udp.h> #include <arpa/inet.h> #include <locale.h> @@ -78,6 +79,11 @@ static int opt_pkt_count; static u16 opt_pkt_size = MIN_PKT_SIZE; static u32 opt_pkt_fill_pattern = 0x12345678; static bool opt_extra_stats; +static bool opt_quiet; +static bool opt_app_stats; +static const char *opt_irq_str = ""; +static u32 irq_no; +static int irqs_at_init = -1; static int opt_poll; static int opt_interval = 1; static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP; @@ -90,18 +96,7 @@ static bool opt_need_wakeup = true; static u32 opt_num_xsks = 1; static u32 prog_id; -struct xsk_umem_info { - struct xsk_ring_prod fq; - struct xsk_ring_cons cq; - struct xsk_umem *umem; - void *buffer; -}; - -struct xsk_socket_info { - struct xsk_ring_cons rx; - struct xsk_ring_prod tx; - struct xsk_umem_info *umem; - struct xsk_socket *xsk; +struct xsk_ring_stats { unsigned long rx_npkts; unsigned long tx_npkts; unsigned long rx_dropped_npkts; @@ -118,6 +113,41 @@ struct xsk_socket_info { unsigned long prev_rx_full_npkts; unsigned long prev_rx_fill_empty_npkts; unsigned long prev_tx_empty_npkts; +}; + +struct xsk_driver_stats { + unsigned long intrs; + unsigned long prev_intrs; +}; + +struct xsk_app_stats { + unsigned long rx_empty_polls; + unsigned long fill_fail_polls; + unsigned long copy_tx_sendtos; + unsigned long tx_wakeup_sendtos; + unsigned long opt_polls; + unsigned long prev_rx_empty_polls; + unsigned long prev_fill_fail_polls; + unsigned long prev_copy_tx_sendtos; + unsigned long prev_tx_wakeup_sendtos; + unsigned long prev_opt_polls; +}; + +struct xsk_umem_info { + struct xsk_ring_prod fq; + struct xsk_ring_cons cq; + struct xsk_umem *umem; + void *buffer; +}; + +struct xsk_socket_info { + struct xsk_ring_cons rx; + struct xsk_ring_prod tx; + struct xsk_umem_info *umem; + struct xsk_socket *xsk; + struct xsk_ring_stats ring_stats; + struct xsk_app_stats app_stats; + struct xsk_driver_stats drv_stats; u32 outstanding_tx; }; @@ -172,18 +202,151 @@ static int xsk_get_xdp_stats(int fd, struct xsk_socket_info *xsk) return err; if (optlen == sizeof(struct xdp_statistics)) { - xsk->rx_dropped_npkts = stats.rx_dropped; - xsk->rx_invalid_npkts = stats.rx_invalid_descs; - xsk->tx_invalid_npkts = stats.tx_invalid_descs; - xsk->rx_full_npkts = stats.rx_ring_full; - xsk->rx_fill_empty_npkts = stats.rx_fill_ring_empty_descs; - xsk->tx_empty_npkts = stats.tx_ring_empty_descs; + xsk->ring_stats.rx_dropped_npkts = stats.rx_dropped; + xsk->ring_stats.rx_invalid_npkts = stats.rx_invalid_descs; + xsk->ring_stats.tx_invalid_npkts = stats.tx_invalid_descs; + xsk->ring_stats.rx_full_npkts = stats.rx_ring_full; + xsk->ring_stats.rx_fill_empty_npkts = stats.rx_fill_ring_empty_descs; + xsk->ring_stats.tx_empty_npkts = stats.tx_ring_empty_descs; return 0; } return -EINVAL; } +static void dump_app_stats(long dt) +{ + int i; + + for (i = 0; i < num_socks && xsks[i]; i++) { + char *fmt = "%-18s %'-14.0f %'-14lu\n"; + double rx_empty_polls_ps, fill_fail_polls_ps, copy_tx_sendtos_ps, + tx_wakeup_sendtos_ps, opt_polls_ps; + + rx_empty_polls_ps = (xsks[i]->app_stats.rx_empty_polls - + xsks[i]->app_stats.prev_rx_empty_polls) * 1000000000. / dt; + fill_fail_polls_ps = (xsks[i]->app_stats.fill_fail_polls - + xsks[i]->app_stats.prev_fill_fail_polls) * 1000000000. / dt; + copy_tx_sendtos_ps = (xsks[i]->app_stats.copy_tx_sendtos - + xsks[i]->app_stats.prev_copy_tx_sendtos) * 1000000000. / dt; + tx_wakeup_sendtos_ps = (xsks[i]->app_stats.tx_wakeup_sendtos - + xsks[i]->app_stats.prev_tx_wakeup_sendtos) + * 1000000000. / dt; + opt_polls_ps = (xsks[i]->app_stats.opt_polls - + xsks[i]->app_stats.prev_opt_polls) * 1000000000. / dt; + + printf("\n%-18s %-14s %-14s\n", "", "calls/s", "count"); + printf(fmt, "rx empty polls", rx_empty_polls_ps, xsks[i]->app_stats.rx_empty_polls); + printf(fmt, "fill fail polls", fill_fail_polls_ps, + xsks[i]->app_stats.fill_fail_polls); + printf(fmt, "copy tx sendtos", copy_tx_sendtos_ps, + xsks[i]->app_stats.copy_tx_sendtos); + printf(fmt, "tx wakeup sendtos", tx_wakeup_sendtos_ps, + xsks[i]->app_stats.tx_wakeup_sendtos); + printf(fmt, "opt polls", opt_polls_ps, xsks[i]->app_stats.opt_polls); + + xsks[i]->app_stats.prev_rx_empty_polls = xsks[i]->app_stats.rx_empty_polls; + xsks[i]->app_stats.prev_fill_fail_polls = xsks[i]->app_stats.fill_fail_polls; + xsks[i]->app_stats.prev_copy_tx_sendtos = xsks[i]->app_stats.copy_tx_sendtos; + xsks[i]->app_stats.prev_tx_wakeup_sendtos = xsks[i]->app_stats.tx_wakeup_sendtos; + xsks[i]->app_stats.prev_opt_polls = xsks[i]->app_stats.opt_polls; + } +} + +static bool get_interrupt_number(void) +{ + FILE *f_int_proc; + char line[4096]; + bool found = false; + + f_int_proc = fopen("/proc/interrupts", "r"); + if (f_int_proc == NULL) { + printf("Failed to open /proc/interrupts.\n"); + return found; + } + + while (!feof(f_int_proc) && !found) { + /* Make sure to read a full line at a time */ + if (fgets(line, sizeof(line), f_int_proc) == NULL || + line[strlen(line) - 1] != '\n') { + printf("Error reading from interrupts file\n"); + break; + } + + /* Extract interrupt number from line */ + if (strstr(line, opt_irq_str) != NULL) { + irq_no = atoi(line); + found = true; + break; + } + } + + fclose(f_int_proc); + + return found; +} + +static int get_irqs(void) +{ + char count_path[PATH_MAX]; + int total_intrs = -1; + FILE *f_count_proc; + char line[4096]; + + snprintf(count_path, sizeof(count_path), + "/sys/kernel/irq/%i/per_cpu_count", irq_no); + f_count_proc = fopen(count_path, "r"); + if (f_count_proc == NULL) { + printf("Failed to open %s\n", count_path); + return total_intrs; + } + + if (fgets(line, sizeof(line), f_count_proc) == NULL || + line[strlen(line) - 1] != '\n') { + printf("Error reading from %s\n", count_path); + } else { + static const char com[2] = ","; + char *token; + + total_intrs = 0; + token = strtok(line, com); + while (token != NULL) { + /* sum up interrupts across all cores */ + total_intrs += atoi(token); + token = strtok(NULL, com); + } + } + + fclose(f_count_proc); + + return total_intrs; +} + +static void dump_driver_stats(long dt) +{ + int i; + + for (i = 0; i < num_socks && xsks[i]; i++) { + char *fmt = "%-18s %'-14.0f %'-14lu\n"; + double intrs_ps; + int n_ints = get_irqs(); + + if (n_ints < 0) { + printf("error getting intr info for intr %i\n", irq_no); + return; + } + xsks[i]->drv_stats.intrs = n_ints - irqs_at_init; + + intrs_ps = (xsks[i]->drv_stats.intrs - xsks[i]->drv_stats.prev_intrs) * + 1000000000. / dt; + + printf("\n%-18s %-14s %-14s\n", "", "intrs/s", "count"); + printf(fmt, "irqs", intrs_ps, xsks[i]->drv_stats.intrs); + + xsks[i]->drv_stats.prev_intrs = xsks[i]->drv_stats.intrs; + } +} + static void dump_stats(void) { unsigned long now = get_nsecs(); @@ -193,67 +356,83 @@ static void dump_stats(void) prev_time = now; for (i = 0; i < num_socks && xsks[i]; i++) { - char *fmt = "%-15s %'-11.0f %'-11lu\n"; + char *fmt = "%-18s %'-14.0f %'-14lu\n"; double rx_pps, tx_pps, dropped_pps, rx_invalid_pps, full_pps, fill_empty_pps, tx_invalid_pps, tx_empty_pps; - rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) * + rx_pps = (xsks[i]->ring_stats.rx_npkts - xsks[i]->ring_stats.prev_rx_npkts) * 1000000000. / dt; - tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) * + tx_pps = (xsks[i]->ring_stats.tx_npkts - xsks[i]->ring_stats.prev_tx_npkts) * 1000000000. / dt; printf("\n sock%d@", i); print_benchmark(false); printf("\n"); - printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts", + printf("%-18s %-14s %-14s %-14.2f\n", "", "pps", "pkts", dt / 1000000000.); - printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts); - printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts); + printf(fmt, "rx", rx_pps, xsks[i]->ring_stats.rx_npkts); + printf(fmt, "tx", tx_pps, xsks[i]->ring_stats.tx_npkts); - xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts; - xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts; + xsks[i]->ring_stats.prev_rx_npkts = xsks[i]->ring_stats.rx_npkts; + xsks[i]->ring_stats.prev_tx_npkts = xsks[i]->ring_stats.tx_npkts; if (opt_extra_stats) { if (!xsk_get_xdp_stats(xsk_socket__fd(xsks[i]->xsk), xsks[i])) { - dropped_pps = (xsks[i]->rx_dropped_npkts - - xsks[i]->prev_rx_dropped_npkts) * 1000000000. / dt; - rx_invalid_pps = (xsks[i]->rx_invalid_npkts - - xsks[i]->prev_rx_invalid_npkts) * 1000000000. / dt; - tx_invalid_pps = (xsks[i]->tx_invalid_npkts - - xsks[i]->prev_tx_invalid_npkts) * 1000000000. / dt; - full_pps = (xsks[i]->rx_full_npkts - - xsks[i]->prev_rx_full_npkts) * 1000000000. / dt; - fill_empty_pps = (xsks[i]->rx_fill_empty_npkts - - xsks[i]->prev_rx_fill_empty_npkts) - * 1000000000. / dt; - tx_empty_pps = (xsks[i]->tx_empty_npkts - - xsks[i]->prev_tx_empty_npkts) * 1000000000. / dt; + dropped_pps = (xsks[i]->ring_stats.rx_dropped_npkts - + xsks[i]->ring_stats.prev_rx_dropped_npkts) * + 1000000000. / dt; + rx_invalid_pps = (xsks[i]->ring_stats.rx_invalid_npkts - + xsks[i]->ring_stats.prev_rx_invalid_npkts) * + 1000000000. / dt; + tx_invalid_pps = (xsks[i]->ring_stats.tx_invalid_npkts - + xsks[i]->ring_stats.prev_tx_invalid_npkts) * + 1000000000. / dt; + full_pps = (xsks[i]->ring_stats.rx_full_npkts - + xsks[i]->ring_stats.prev_rx_full_npkts) * + 1000000000. / dt; + fill_empty_pps = (xsks[i]->ring_stats.rx_fill_empty_npkts - + xsks[i]->ring_stats.prev_rx_fill_empty_npkts) * + 1000000000. / dt; + tx_empty_pps = (xsks[i]->ring_stats.tx_empty_npkts - + xsks[i]->ring_stats.prev_tx_empty_npkts) * + 1000000000. / dt; printf(fmt, "rx dropped", dropped_pps, - xsks[i]->rx_dropped_npkts); + xsks[i]->ring_stats.rx_dropped_npkts); printf(fmt, "rx invalid", rx_invalid_pps, - xsks[i]->rx_invalid_npkts); + xsks[i]->ring_stats.rx_invalid_npkts); printf(fmt, "tx invalid", tx_invalid_pps, - xsks[i]->tx_invalid_npkts); + xsks[i]->ring_stats.tx_invalid_npkts); printf(fmt, "rx queue full", full_pps, - xsks[i]->rx_full_npkts); + xsks[i]->ring_stats.rx_full_npkts); printf(fmt, "fill ring empty", fill_empty_pps, - xsks[i]->rx_fill_empty_npkts); + xsks[i]->ring_stats.rx_fill_empty_npkts); printf(fmt, "tx ring empty", tx_empty_pps, - xsks[i]->tx_empty_npkts); - - xsks[i]->prev_rx_dropped_npkts = xsks[i]->rx_dropped_npkts; - xsks[i]->prev_rx_invalid_npkts = xsks[i]->rx_invalid_npkts; - xsks[i]->prev_tx_invalid_npkts = xsks[i]->tx_invalid_npkts; - xsks[i]->prev_rx_full_npkts = xsks[i]->rx_full_npkts; - xsks[i]->prev_rx_fill_empty_npkts = xsks[i]->rx_fill_empty_npkts; - xsks[i]->prev_tx_empty_npkts = xsks[i]->tx_empty_npkts; + xsks[i]->ring_stats.tx_empty_npkts); + + xsks[i]->ring_stats.prev_rx_dropped_npkts = + xsks[i]->ring_stats.rx_dropped_npkts; + xsks[i]->ring_stats.prev_rx_invalid_npkts = + xsks[i]->ring_stats.rx_invalid_npkts; + xsks[i]->ring_stats.prev_tx_invalid_npkts = + xsks[i]->ring_stats.tx_invalid_npkts; + xsks[i]->ring_stats.prev_rx_full_npkts = + xsks[i]->ring_stats.rx_full_npkts; + xsks[i]->ring_stats.prev_rx_fill_empty_npkts = + xsks[i]->ring_stats.rx_fill_empty_npkts; + xsks[i]->ring_stats.prev_tx_empty_npkts = + xsks[i]->ring_stats.tx_empty_npkts; } else { printf("%-15s\n", "Error retrieving extra stats"); } } } + + if (opt_app_stats) + dump_app_stats(dt); + if (irq_no) + dump_driver_stats(dt); } static bool is_benchmark_done(void) @@ -613,7 +792,16 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) { struct xsk_umem_info *umem; struct xsk_umem_config cfg = { - .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + /* We recommend that you set the fill ring size >= HW RX ring size + + * AF_XDP RX ring size. Make sure you fill up the fill ring + * with buffers at regular intervals, and you will with this setting + * avoid allocation failures in the driver. These are usually quite + * expensive since drivers have not been written to assume that + * allocation failures are common. For regular sockets, kernel + * allocated memory is used that only runs out in OOM situations + * that should be rare. + */ + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, .frame_size = opt_xsk_frame_size, .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, @@ -640,13 +828,13 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem) u32 idx; ret = xsk_ring_prod__reserve(&umem->fq, - XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) + XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, &idx); + if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS * 2) exit_with_error(-ret); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) + for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS * 2; i++) *xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * opt_xsk_frame_size; - xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); + xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS * 2); } static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, @@ -683,6 +871,17 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, if (ret) exit_with_error(-ret); + xsk->app_stats.rx_empty_polls = 0; + xsk->app_stats.fill_fail_polls = 0; + xsk->app_stats.copy_tx_sendtos = 0; + xsk->app_stats.tx_wakeup_sendtos = 0; + xsk->app_stats.opt_polls = 0; + xsk->app_stats.prev_rx_empty_polls = 0; + xsk->app_stats.prev_fill_fail_polls = 0; + xsk->app_stats.prev_copy_tx_sendtos = 0; + xsk->app_stats.prev_tx_wakeup_sendtos = 0; + xsk->app_stats.prev_opt_polls = 0; + return xsk; } @@ -709,6 +908,9 @@ static struct option long_options[] = { {"tx-pkt-size", required_argument, 0, 's'}, {"tx-pkt-pattern", required_argument, 0, 'P'}, {"extra-stats", no_argument, 0, 'x'}, + {"quiet", no_argument, 0, 'Q'}, + {"app-stats", no_argument, 0, 'a'}, + {"irq-string", no_argument, 0, 'I'}, {0, 0, 0, 0} }; @@ -744,6 +946,9 @@ static void usage(const char *prog) " Min size: %d, Max size %d.\n" " -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n" " -x, --extra-stats Display extra statistics.\n" + " -Q, --quiet Do not display any stats.\n" + " -a, --app-stats Display application (syscall) statistics.\n" + " -I, --irq-string Display driver interrupt statistics for interface associated with irq-string.\n" "\n"; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE, opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE, @@ -759,7 +964,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:x", + c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:", long_options, &option_index); if (c == -1) break; @@ -843,6 +1048,22 @@ static void parse_command_line(int argc, char **argv) case 'x': opt_extra_stats = 1; break; + case 'Q': + opt_quiet = 1; + break; + case 'a': + opt_app_stats = 1; + break; + case 'I': + opt_irq_str = optarg; + if (get_interrupt_number()) + irqs_at_init = get_irqs(); + if (irqs_at_init < 0) { + fprintf(stderr, "ERROR: Failed to get irqs for %s\n", opt_irq_str); + usage(basename(argv[0])); + } + + break; default: usage(basename(argv[0])); } @@ -888,8 +1109,15 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, if (!xsk->outstanding_tx) return; - if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) + /* In copy mode, Tx is driven by a syscall so we need to use e.g. sendto() to + * really send the packets. In zero-copy mode we do not have to do this, since Tx + * is driven by the NAPI loop. So as an optimization, we do not have to call + * sendto() all the time in zero-copy mode for l2fwd. + */ + if (opt_xdp_bind_flags & XDP_COPY) { + xsk->app_stats.copy_tx_sendtos++; kick_tx(xsk); + } ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size : xsk->outstanding_tx; @@ -904,8 +1132,10 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&umem->fq)) + if (xsk_ring_prod__needs_wakeup(&umem->fq)) { + xsk->app_stats.fill_fail_polls++; ret = poll(fds, num_socks, opt_timeout); + } ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } @@ -916,7 +1146,7 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, xsk_ring_prod__submit(&xsk->umem->fq, rcvd); xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; - xsk->tx_npkts += rcvd; + xsk->ring_stats.tx_npkts += rcvd; } } @@ -929,14 +1159,16 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk, if (!xsk->outstanding_tx) return; - if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) + if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx)) { + xsk->app_stats.tx_wakeup_sendtos++; kick_tx(xsk); + } rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); if (rcvd > 0) { xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; - xsk->tx_npkts += rcvd; + xsk->ring_stats.tx_npkts += rcvd; } } @@ -948,8 +1180,10 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + xsk->app_stats.rx_empty_polls++; ret = poll(fds, num_socks, opt_timeout); + } return; } @@ -957,8 +1191,10 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + xsk->app_stats.fill_fail_polls++; ret = poll(fds, num_socks, opt_timeout); + } ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); } @@ -976,7 +1212,7 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) xsk_ring_prod__submit(&xsk->umem->fq, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); - xsk->rx_npkts += rcvd; + xsk->ring_stats.rx_npkts += rcvd; } static void rx_drop_all(void) @@ -991,6 +1227,8 @@ static void rx_drop_all(void) for (;;) { if (opt_poll) { + for (i = 0; i < num_socks; i++) + xsks[i]->app_stats.opt_polls++; ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; @@ -1004,7 +1242,7 @@ static void rx_drop_all(void) } } -static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size) +static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) { u32 idx; unsigned int i; @@ -1017,14 +1255,14 @@ static void tx_only(struct xsk_socket_info *xsk, u32 frame_nb, int batch_size) for (i = 0; i < batch_size; i++) { struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i); - tx_desc->addr = (frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; + tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT; tx_desc->len = PKT_SIZE; } xsk_ring_prod__submit(&xsk->tx, batch_size); xsk->outstanding_tx += batch_size; - frame_nb += batch_size; - frame_nb %= NUM_FRAMES; + *frame_nb += batch_size; + *frame_nb %= NUM_FRAMES; complete_tx_only(xsk, batch_size); } @@ -1071,6 +1309,8 @@ static void tx_only_all(void) int batch_size = get_batch_size(pkt_cnt); if (opt_poll) { + for (i = 0; i < num_socks; i++) + xsks[i]->app_stats.opt_polls++; ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; @@ -1080,7 +1320,7 @@ static void tx_only_all(void) } for (i = 0; i < num_socks; i++) - tx_only(xsks[i], frame_nb[i], batch_size); + tx_only(xsks[i], &frame_nb[i], batch_size); pkt_cnt += batch_size; @@ -1102,8 +1342,10 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) + if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + xsk->app_stats.rx_empty_polls++; ret = poll(fds, num_socks, opt_timeout); + } return; } @@ -1111,8 +1353,11 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) + complete_tx_l2fwd(xsk, fds); + if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { + xsk->app_stats.tx_wakeup_sendtos++; kick_tx(xsk); + } ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); } @@ -1134,7 +1379,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) xsk_ring_prod__submit(&xsk->tx, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); - xsk->rx_npkts += rcvd; + xsk->ring_stats.rx_npkts += rcvd; xsk->outstanding_tx += rcvd; } @@ -1150,6 +1395,8 @@ static void l2fwd_all(void) for (;;) { if (opt_poll) { + for (i = 0; i < num_socks; i++) + xsks[i]->app_stats.opt_polls++; ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; @@ -1271,9 +1518,11 @@ int main(int argc, char **argv) setlocale(LC_ALL, ""); - ret = pthread_create(&pt, NULL, poller, NULL); - if (ret) - exit_with_error(ret); + if (!opt_quiet) { + ret = pthread_create(&pt, NULL, poller, NULL); + if (ret) + exit_with_error(ret); + } prev_time = get_nsecs(); start_time = prev_time; @@ -1287,7 +1536,8 @@ int main(int argc, char **argv) benchmark_done = true; - pthread_join(pt, NULL); + if (!opt_quiet) + pthread_join(pt, NULL); xdpsock_cleanup(); diff --git a/samples/bpf/xsk_fwd.c b/samples/bpf/xsk_fwd.c new file mode 100644 index 000000000000..1cd97c84c337 --- /dev/null +++ b/samples/bpf/xsk_fwd.c @@ -0,0 +1,1085 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2020 Intel Corporation. */ + +#define _GNU_SOURCE +#include <poll.h> +#include <pthread.h> +#include <signal.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/resource.h> +#include <sys/socket.h> +#include <sys/types.h> +#include <time.h> +#include <unistd.h> +#include <getopt.h> +#include <netinet/ether.h> +#include <net/if.h> + +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <linux/if_xdp.h> + +#include <bpf/libbpf.h> +#include <bpf/xsk.h> +#include <bpf/bpf.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef __u64 u64; +typedef __u32 u32; +typedef __u16 u16; +typedef __u8 u8; + +/* This program illustrates the packet forwarding between multiple AF_XDP + * sockets in multi-threaded environment. All threads are sharing a common + * buffer pool, with each socket having its own private buffer cache. + * + * Example 1: Single thread handling two sockets. The packets received by socket + * A (interface IFA, queue QA) are forwarded to socket B (interface IFB, queue + * QB), while the packets received by socket B are forwarded to socket A. The + * thread is running on CPU core X: + * + * ./xsk_fwd -i IFA -q QA -i IFB -q QB -c X + * + * Example 2: Two threads, each handling two sockets. The thread running on CPU + * core X forwards all the packets received by socket A to socket B, and all the + * packets received by socket B to socket A. The thread running on CPU core Y is + * performing the same packet forwarding between sockets C and D: + * + * ./xsk_fwd -i IFA -q QA -i IFB -q QB -i IFC -q QC -i IFD -q QD + * -c CX -c CY + */ + +/* + * Buffer pool and buffer cache + * + * For packet forwarding, the packet buffers are typically allocated from the + * pool for packet reception and freed back to the pool for further reuse once + * the packet transmission is completed. + * + * The buffer pool is shared between multiple threads. In order to minimize the + * access latency to the shared buffer pool, each thread creates one (or + * several) buffer caches, which, unlike the buffer pool, are private to the + * thread that creates them and therefore cannot be shared with other threads. + * The access to the shared pool is only needed either (A) when the cache gets + * empty due to repeated buffer allocations and it needs to be replenished from + * the pool, or (B) when the cache gets full due to repeated buffer free and it + * needs to be flushed back to the pull. + * + * In a packet forwarding system, a packet received on any input port can + * potentially be transmitted on any output port, depending on the forwarding + * configuration. For AF_XDP sockets, for this to work with zero-copy of the + * packet buffers when, it is required that the buffer pool memory fits into the + * UMEM area shared by all the sockets. + */ + +struct bpool_params { + u32 n_buffers; + u32 buffer_size; + int mmap_flags; + + u32 n_users_max; + u32 n_buffers_per_slab; +}; + +/* This buffer pool implementation organizes the buffers into equally sized + * slabs of *n_buffers_per_slab*. Initially, there are *n_slabs* slabs in the + * pool that are completely filled with buffer pointers (full slabs). + * + * Each buffer cache has a slab for buffer allocation and a slab for buffer + * free, with both of these slabs initially empty. When the cache's allocation + * slab goes empty, it is swapped with one of the available full slabs from the + * pool, if any is available. When the cache's free slab goes full, it is + * swapped for one of the empty slabs from the pool, which is guaranteed to + * succeed. + * + * Partially filled slabs never get traded between the cache and the pool + * (except when the cache itself is destroyed), which enables fast operation + * through pointer swapping. + */ +struct bpool { + struct bpool_params params; + pthread_mutex_t lock; + void *addr; + + u64 **slabs; + u64 **slabs_reserved; + u64 *buffers; + u64 *buffers_reserved; + + u64 n_slabs; + u64 n_slabs_reserved; + u64 n_buffers; + + u64 n_slabs_available; + u64 n_slabs_reserved_available; + + struct xsk_umem_config umem_cfg; + struct xsk_ring_prod umem_fq; + struct xsk_ring_cons umem_cq; + struct xsk_umem *umem; +}; + +static struct bpool * +bpool_init(struct bpool_params *params, + struct xsk_umem_config *umem_cfg) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + u64 n_slabs, n_slabs_reserved, n_buffers, n_buffers_reserved; + u64 slabs_size, slabs_reserved_size; + u64 buffers_size, buffers_reserved_size; + u64 total_size, i; + struct bpool *bp; + u8 *p; + int status; + + /* mmap prep. */ + if (setrlimit(RLIMIT_MEMLOCK, &r)) + return NULL; + + /* bpool internals dimensioning. */ + n_slabs = (params->n_buffers + params->n_buffers_per_slab - 1) / + params->n_buffers_per_slab; + n_slabs_reserved = params->n_users_max * 2; + n_buffers = n_slabs * params->n_buffers_per_slab; + n_buffers_reserved = n_slabs_reserved * params->n_buffers_per_slab; + + slabs_size = n_slabs * sizeof(u64 *); + slabs_reserved_size = n_slabs_reserved * sizeof(u64 *); + buffers_size = n_buffers * sizeof(u64); + buffers_reserved_size = n_buffers_reserved * sizeof(u64); + + total_size = sizeof(struct bpool) + + slabs_size + slabs_reserved_size + + buffers_size + buffers_reserved_size; + + /* bpool memory allocation. */ + p = calloc(total_size, sizeof(u8)); + if (!p) + return NULL; + + /* bpool memory initialization. */ + bp = (struct bpool *)p; + memcpy(&bp->params, params, sizeof(*params)); + bp->params.n_buffers = n_buffers; + + bp->slabs = (u64 **)&p[sizeof(struct bpool)]; + bp->slabs_reserved = (u64 **)&p[sizeof(struct bpool) + + slabs_size]; + bp->buffers = (u64 *)&p[sizeof(struct bpool) + + slabs_size + slabs_reserved_size]; + bp->buffers_reserved = (u64 *)&p[sizeof(struct bpool) + + slabs_size + slabs_reserved_size + buffers_size]; + + bp->n_slabs = n_slabs; + bp->n_slabs_reserved = n_slabs_reserved; + bp->n_buffers = n_buffers; + + for (i = 0; i < n_slabs; i++) + bp->slabs[i] = &bp->buffers[i * params->n_buffers_per_slab]; + bp->n_slabs_available = n_slabs; + + for (i = 0; i < n_slabs_reserved; i++) + bp->slabs_reserved[i] = &bp->buffers_reserved[i * + params->n_buffers_per_slab]; + bp->n_slabs_reserved_available = n_slabs_reserved; + + for (i = 0; i < n_buffers; i++) + bp->buffers[i] = i * params->buffer_size; + + /* lock. */ + status = pthread_mutex_init(&bp->lock, NULL); + if (status) { + free(p); + return NULL; + } + + /* mmap. */ + bp->addr = mmap(NULL, + n_buffers * params->buffer_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | params->mmap_flags, + -1, + 0); + if (bp->addr == MAP_FAILED) { + pthread_mutex_destroy(&bp->lock); + free(p); + return NULL; + } + + /* umem. */ + status = xsk_umem__create(&bp->umem, + bp->addr, + bp->params.n_buffers * bp->params.buffer_size, + &bp->umem_fq, + &bp->umem_cq, + umem_cfg); + if (status) { + munmap(bp->addr, bp->params.n_buffers * bp->params.buffer_size); + pthread_mutex_destroy(&bp->lock); + free(p); + return NULL; + } + memcpy(&bp->umem_cfg, umem_cfg, sizeof(*umem_cfg)); + + return bp; +} + +static void +bpool_free(struct bpool *bp) +{ + if (!bp) + return; + + xsk_umem__delete(bp->umem); + munmap(bp->addr, bp->params.n_buffers * bp->params.buffer_size); + pthread_mutex_destroy(&bp->lock); + free(bp); +} + +struct bcache { + struct bpool *bp; + + u64 *slab_cons; + u64 *slab_prod; + + u64 n_buffers_cons; + u64 n_buffers_prod; +}; + +static u32 +bcache_slab_size(struct bcache *bc) +{ + struct bpool *bp = bc->bp; + + return bp->params.n_buffers_per_slab; +} + +static struct bcache * +bcache_init(struct bpool *bp) +{ + struct bcache *bc; + + bc = calloc(1, sizeof(struct bcache)); + if (!bc) + return NULL; + + bc->bp = bp; + bc->n_buffers_cons = 0; + bc->n_buffers_prod = 0; + + pthread_mutex_lock(&bp->lock); + if (bp->n_slabs_reserved_available == 0) { + pthread_mutex_unlock(&bp->lock); + free(bc); + return NULL; + } + + bc->slab_cons = bp->slabs_reserved[bp->n_slabs_reserved_available - 1]; + bc->slab_prod = bp->slabs_reserved[bp->n_slabs_reserved_available - 2]; + bp->n_slabs_reserved_available -= 2; + pthread_mutex_unlock(&bp->lock); + + return bc; +} + +static void +bcache_free(struct bcache *bc) +{ + struct bpool *bp; + + if (!bc) + return; + + /* In order to keep this example simple, the case of freeing any + * existing buffers from the cache back to the pool is ignored. + */ + + bp = bc->bp; + pthread_mutex_lock(&bp->lock); + bp->slabs_reserved[bp->n_slabs_reserved_available] = bc->slab_prod; + bp->slabs_reserved[bp->n_slabs_reserved_available + 1] = bc->slab_cons; + bp->n_slabs_reserved_available += 2; + pthread_mutex_unlock(&bp->lock); + + free(bc); +} + +/* To work correctly, the implementation requires that the *n_buffers* input + * argument is never greater than the buffer pool's *n_buffers_per_slab*. This + * is typically the case, with one exception taking place when large number of + * buffers are allocated at init time (e.g. for the UMEM fill queue setup). + */ +static inline u32 +bcache_cons_check(struct bcache *bc, u32 n_buffers) +{ + struct bpool *bp = bc->bp; + u64 n_buffers_per_slab = bp->params.n_buffers_per_slab; + u64 n_buffers_cons = bc->n_buffers_cons; + u64 n_slabs_available; + u64 *slab_full; + + /* + * Consumer slab is not empty: Use what's available locally. Do not + * look for more buffers from the pool when the ask can only be + * partially satisfied. + */ + if (n_buffers_cons) + return (n_buffers_cons < n_buffers) ? + n_buffers_cons : + n_buffers; + + /* + * Consumer slab is empty: look to trade the current consumer slab + * (full) for a full slab from the pool, if any is available. + */ + pthread_mutex_lock(&bp->lock); + n_slabs_available = bp->n_slabs_available; + if (!n_slabs_available) { + pthread_mutex_unlock(&bp->lock); + return 0; + } + + n_slabs_available--; + slab_full = bp->slabs[n_slabs_available]; + bp->slabs[n_slabs_available] = bc->slab_cons; + bp->n_slabs_available = n_slabs_available; + pthread_mutex_unlock(&bp->lock); + + bc->slab_cons = slab_full; + bc->n_buffers_cons = n_buffers_per_slab; + return n_buffers; +} + +static inline u64 +bcache_cons(struct bcache *bc) +{ + u64 n_buffers_cons = bc->n_buffers_cons - 1; + u64 buffer; + + buffer = bc->slab_cons[n_buffers_cons]; + bc->n_buffers_cons = n_buffers_cons; + return buffer; +} + +static inline void +bcache_prod(struct bcache *bc, u64 buffer) +{ + struct bpool *bp = bc->bp; + u64 n_buffers_per_slab = bp->params.n_buffers_per_slab; + u64 n_buffers_prod = bc->n_buffers_prod; + u64 n_slabs_available; + u64 *slab_empty; + + /* + * Producer slab is not yet full: store the current buffer to it. + */ + if (n_buffers_prod < n_buffers_per_slab) { + bc->slab_prod[n_buffers_prod] = buffer; + bc->n_buffers_prod = n_buffers_prod + 1; + return; + } + + /* + * Producer slab is full: trade the cache's current producer slab + * (full) for an empty slab from the pool, then store the current + * buffer to the new producer slab. As one full slab exists in the + * cache, it is guaranteed that there is at least one empty slab + * available in the pool. + */ + pthread_mutex_lock(&bp->lock); + n_slabs_available = bp->n_slabs_available; + slab_empty = bp->slabs[n_slabs_available]; + bp->slabs[n_slabs_available] = bc->slab_prod; + bp->n_slabs_available = n_slabs_available + 1; + pthread_mutex_unlock(&bp->lock); + + slab_empty[0] = buffer; + bc->slab_prod = slab_empty; + bc->n_buffers_prod = 1; +} + +/* + * Port + * + * Each of the forwarding ports sits on top of an AF_XDP socket. In order for + * packet forwarding to happen with no packet buffer copy, all the sockets need + * to share the same UMEM area, which is used as the buffer pool memory. + */ +#ifndef MAX_BURST_RX +#define MAX_BURST_RX 64 +#endif + +#ifndef MAX_BURST_TX +#define MAX_BURST_TX 64 +#endif + +struct burst_rx { + u64 addr[MAX_BURST_RX]; + u32 len[MAX_BURST_RX]; +}; + +struct burst_tx { + u64 addr[MAX_BURST_TX]; + u32 len[MAX_BURST_TX]; + u32 n_pkts; +}; + +struct port_params { + struct xsk_socket_config xsk_cfg; + struct bpool *bp; + const char *iface; + u32 iface_queue; +}; + +struct port { + struct port_params params; + + struct bcache *bc; + + struct xsk_ring_cons rxq; + struct xsk_ring_prod txq; + struct xsk_ring_prod umem_fq; + struct xsk_ring_cons umem_cq; + struct xsk_socket *xsk; + int umem_fq_initialized; + + u64 n_pkts_rx; + u64 n_pkts_tx; +}; + +static void +port_free(struct port *p) +{ + if (!p) + return; + + /* To keep this example simple, the code to free the buffers from the + * socket's receive and transmit queues, as well as from the UMEM fill + * and completion queues, is not included. + */ + + if (p->xsk) + xsk_socket__delete(p->xsk); + + bcache_free(p->bc); + + free(p); +} + +static struct port * +port_init(struct port_params *params) +{ + struct port *p; + u32 umem_fq_size, pos = 0; + int status, i; + + /* Memory allocation and initialization. */ + p = calloc(sizeof(struct port), 1); + if (!p) + return NULL; + + memcpy(&p->params, params, sizeof(p->params)); + umem_fq_size = params->bp->umem_cfg.fill_size; + + /* bcache. */ + p->bc = bcache_init(params->bp); + if (!p->bc || + (bcache_slab_size(p->bc) < umem_fq_size) || + (bcache_cons_check(p->bc, umem_fq_size) < umem_fq_size)) { + port_free(p); + return NULL; + } + + /* xsk socket. */ + status = xsk_socket__create_shared(&p->xsk, + params->iface, + params->iface_queue, + params->bp->umem, + &p->rxq, + &p->txq, + &p->umem_fq, + &p->umem_cq, + ¶ms->xsk_cfg); + if (status) { + port_free(p); + return NULL; + } + + /* umem fq. */ + xsk_ring_prod__reserve(&p->umem_fq, umem_fq_size, &pos); + + for (i = 0; i < umem_fq_size; i++) + *xsk_ring_prod__fill_addr(&p->umem_fq, pos + i) = + bcache_cons(p->bc); + + xsk_ring_prod__submit(&p->umem_fq, umem_fq_size); + p->umem_fq_initialized = 1; + + return p; +} + +static inline u32 +port_rx_burst(struct port *p, struct burst_rx *b) +{ + u32 n_pkts, pos, i; + + /* Free buffers for FQ replenish. */ + n_pkts = ARRAY_SIZE(b->addr); + + n_pkts = bcache_cons_check(p->bc, n_pkts); + if (!n_pkts) + return 0; + + /* RXQ. */ + n_pkts = xsk_ring_cons__peek(&p->rxq, n_pkts, &pos); + if (!n_pkts) { + if (xsk_ring_prod__needs_wakeup(&p->umem_fq)) { + struct pollfd pollfd = { + .fd = xsk_socket__fd(p->xsk), + .events = POLLIN, + }; + + poll(&pollfd, 1, 0); + } + return 0; + } + + for (i = 0; i < n_pkts; i++) { + b->addr[i] = xsk_ring_cons__rx_desc(&p->rxq, pos + i)->addr; + b->len[i] = xsk_ring_cons__rx_desc(&p->rxq, pos + i)->len; + } + + xsk_ring_cons__release(&p->rxq, n_pkts); + p->n_pkts_rx += n_pkts; + + /* UMEM FQ. */ + for ( ; ; ) { + int status; + + status = xsk_ring_prod__reserve(&p->umem_fq, n_pkts, &pos); + if (status == n_pkts) + break; + + if (xsk_ring_prod__needs_wakeup(&p->umem_fq)) { + struct pollfd pollfd = { + .fd = xsk_socket__fd(p->xsk), + .events = POLLIN, + }; + + poll(&pollfd, 1, 0); + } + } + + for (i = 0; i < n_pkts; i++) + *xsk_ring_prod__fill_addr(&p->umem_fq, pos + i) = + bcache_cons(p->bc); + + xsk_ring_prod__submit(&p->umem_fq, n_pkts); + + return n_pkts; +} + +static inline void +port_tx_burst(struct port *p, struct burst_tx *b) +{ + u32 n_pkts, pos, i; + int status; + + /* UMEM CQ. */ + n_pkts = p->params.bp->umem_cfg.comp_size; + + n_pkts = xsk_ring_cons__peek(&p->umem_cq, n_pkts, &pos); + + for (i = 0; i < n_pkts; i++) { + u64 addr = *xsk_ring_cons__comp_addr(&p->umem_cq, pos + i); + + bcache_prod(p->bc, addr); + } + + xsk_ring_cons__release(&p->umem_cq, n_pkts); + + /* TXQ. */ + n_pkts = b->n_pkts; + + for ( ; ; ) { + status = xsk_ring_prod__reserve(&p->txq, n_pkts, &pos); + if (status == n_pkts) + break; + + if (xsk_ring_prod__needs_wakeup(&p->txq)) + sendto(xsk_socket__fd(p->xsk), NULL, 0, MSG_DONTWAIT, + NULL, 0); + } + + for (i = 0; i < n_pkts; i++) { + xsk_ring_prod__tx_desc(&p->txq, pos + i)->addr = b->addr[i]; + xsk_ring_prod__tx_desc(&p->txq, pos + i)->len = b->len[i]; + } + + xsk_ring_prod__submit(&p->txq, n_pkts); + if (xsk_ring_prod__needs_wakeup(&p->txq)) + sendto(xsk_socket__fd(p->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0); + p->n_pkts_tx += n_pkts; +} + +/* + * Thread + * + * Packet forwarding threads. + */ +#ifndef MAX_PORTS_PER_THREAD +#define MAX_PORTS_PER_THREAD 16 +#endif + +struct thread_data { + struct port *ports_rx[MAX_PORTS_PER_THREAD]; + struct port *ports_tx[MAX_PORTS_PER_THREAD]; + u32 n_ports_rx; + struct burst_rx burst_rx; + struct burst_tx burst_tx[MAX_PORTS_PER_THREAD]; + u32 cpu_core_id; + int quit; +}; + +static void swap_mac_addresses(void *data) +{ + struct ether_header *eth = (struct ether_header *)data; + struct ether_addr *src_addr = (struct ether_addr *)ð->ether_shost; + struct ether_addr *dst_addr = (struct ether_addr *)ð->ether_dhost; + struct ether_addr tmp; + + tmp = *src_addr; + *src_addr = *dst_addr; + *dst_addr = tmp; +} + +static void * +thread_func(void *arg) +{ + struct thread_data *t = arg; + cpu_set_t cpu_cores; + u32 i; + + CPU_ZERO(&cpu_cores); + CPU_SET(t->cpu_core_id, &cpu_cores); + pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpu_cores); + + for (i = 0; !t->quit; i = (i + 1) & (t->n_ports_rx - 1)) { + struct port *port_rx = t->ports_rx[i]; + struct port *port_tx = t->ports_tx[i]; + struct burst_rx *brx = &t->burst_rx; + struct burst_tx *btx = &t->burst_tx[i]; + u32 n_pkts, j; + + /* RX. */ + n_pkts = port_rx_burst(port_rx, brx); + if (!n_pkts) + continue; + + /* Process & TX. */ + for (j = 0; j < n_pkts; j++) { + u64 addr = xsk_umem__add_offset_to_addr(brx->addr[j]); + u8 *pkt = xsk_umem__get_data(port_rx->params.bp->addr, + addr); + + swap_mac_addresses(pkt); + + btx->addr[btx->n_pkts] = brx->addr[j]; + btx->len[btx->n_pkts] = brx->len[j]; + btx->n_pkts++; + + if (btx->n_pkts == MAX_BURST_TX) { + port_tx_burst(port_tx, btx); + btx->n_pkts = 0; + } + } + } + + return NULL; +} + +/* + * Process + */ +static const struct bpool_params bpool_params_default = { + .n_buffers = 64 * 1024, + .buffer_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .mmap_flags = 0, + + .n_users_max = 16, + .n_buffers_per_slab = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, +}; + +static const struct xsk_umem_config umem_cfg_default = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, + .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, + .flags = 0, +}; + +static const struct port_params port_params_default = { + .xsk_cfg = { + .rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .libbpf_flags = 0, + .xdp_flags = XDP_FLAGS_DRV_MODE, + .bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY, + }, + + .bp = NULL, + .iface = NULL, + .iface_queue = 0, +}; + +#ifndef MAX_PORTS +#define MAX_PORTS 64 +#endif + +#ifndef MAX_THREADS +#define MAX_THREADS 64 +#endif + +static struct bpool_params bpool_params; +static struct xsk_umem_config umem_cfg; +static struct bpool *bp; + +static struct port_params port_params[MAX_PORTS]; +static struct port *ports[MAX_PORTS]; +static u64 n_pkts_rx[MAX_PORTS]; +static u64 n_pkts_tx[MAX_PORTS]; +static int n_ports; + +static pthread_t threads[MAX_THREADS]; +static struct thread_data thread_data[MAX_THREADS]; +static int n_threads; + +static void +print_usage(char *prog_name) +{ + const char *usage = + "Usage:\n" + "\t%s [ -b SIZE ] -c CORE -i INTERFACE [ -q QUEUE ]\n" + "\n" + "-c CORE CPU core to run a packet forwarding thread\n" + " on. May be invoked multiple times.\n" + "\n" + "-b SIZE Number of buffers in the buffer pool shared\n" + " by all the forwarding threads. Default: %u.\n" + "\n" + "-i INTERFACE Network interface. Each (INTERFACE, QUEUE)\n" + " pair specifies one forwarding port. May be\n" + " invoked multiple times.\n" + "\n" + "-q QUEUE Network interface queue for RX and TX. Each\n" + " (INTERFACE, QUEUE) pair specified one\n" + " forwarding port. Default: %u. May be invoked\n" + " multiple times.\n" + "\n"; + printf(usage, + prog_name, + bpool_params_default.n_buffers, + port_params_default.iface_queue); +} + +static int +parse_args(int argc, char **argv) +{ + struct option lgopts[] = { + { NULL, 0, 0, 0 } + }; + int opt, option_index; + + /* Parse the input arguments. */ + for ( ; ;) { + opt = getopt_long(argc, argv, "c:i:q:", lgopts, &option_index); + if (opt == EOF) + break; + + switch (opt) { + case 'b': + bpool_params.n_buffers = atoi(optarg); + break; + + case 'c': + if (n_threads == MAX_THREADS) { + printf("Max number of threads (%d) reached.\n", + MAX_THREADS); + return -1; + } + + thread_data[n_threads].cpu_core_id = atoi(optarg); + n_threads++; + break; + + case 'i': + if (n_ports == MAX_PORTS) { + printf("Max number of ports (%d) reached.\n", + MAX_PORTS); + return -1; + } + + port_params[n_ports].iface = optarg; + port_params[n_ports].iface_queue = 0; + n_ports++; + break; + + case 'q': + if (n_ports == 0) { + printf("No port specified for queue.\n"); + return -1; + } + port_params[n_ports - 1].iface_queue = atoi(optarg); + break; + + default: + printf("Illegal argument.\n"); + return -1; + } + } + + optind = 1; /* reset getopt lib */ + + /* Check the input arguments. */ + if (!n_ports) { + printf("No ports specified.\n"); + return -1; + } + + if (!n_threads) { + printf("No threads specified.\n"); + return -1; + } + + if (n_ports % n_threads) { + printf("Ports cannot be evenly distributed to threads.\n"); + return -1; + } + + return 0; +} + +static void +print_port(u32 port_id) +{ + struct port *port = ports[port_id]; + + printf("Port %u: interface = %s, queue = %u\n", + port_id, port->params.iface, port->params.iface_queue); +} + +static void +print_thread(u32 thread_id) +{ + struct thread_data *t = &thread_data[thread_id]; + u32 i; + + printf("Thread %u (CPU core %u): ", + thread_id, t->cpu_core_id); + + for (i = 0; i < t->n_ports_rx; i++) { + struct port *port_rx = t->ports_rx[i]; + struct port *port_tx = t->ports_tx[i]; + + printf("(%s, %u) -> (%s, %u), ", + port_rx->params.iface, + port_rx->params.iface_queue, + port_tx->params.iface, + port_tx->params.iface_queue); + } + + printf("\n"); +} + +static void +print_port_stats_separator(void) +{ + printf("+-%4s-+-%12s-+-%13s-+-%12s-+-%13s-+\n", + "----", + "------------", + "-------------", + "------------", + "-------------"); +} + +static void +print_port_stats_header(void) +{ + print_port_stats_separator(); + printf("| %4s | %12s | %13s | %12s | %13s |\n", + "Port", + "RX packets", + "RX rate (pps)", + "TX packets", + "TX_rate (pps)"); + print_port_stats_separator(); +} + +static void +print_port_stats_trailer(void) +{ + print_port_stats_separator(); + printf("\n"); +} + +static void +print_port_stats(int port_id, u64 ns_diff) +{ + struct port *p = ports[port_id]; + double rx_pps, tx_pps; + + rx_pps = (p->n_pkts_rx - n_pkts_rx[port_id]) * 1000000000. / ns_diff; + tx_pps = (p->n_pkts_tx - n_pkts_tx[port_id]) * 1000000000. / ns_diff; + + printf("| %4d | %12llu | %13.0f | %12llu | %13.0f |\n", + port_id, + p->n_pkts_rx, + rx_pps, + p->n_pkts_tx, + tx_pps); + + n_pkts_rx[port_id] = p->n_pkts_rx; + n_pkts_tx[port_id] = p->n_pkts_tx; +} + +static void +print_port_stats_all(u64 ns_diff) +{ + int i; + + print_port_stats_header(); + for (i = 0; i < n_ports; i++) + print_port_stats(i, ns_diff); + print_port_stats_trailer(); +} + +static int quit; + +static void +signal_handler(int sig) +{ + quit = 1; +} + +static void remove_xdp_program(void) +{ + int i; + + for (i = 0 ; i < n_ports; i++) + bpf_set_link_xdp_fd(if_nametoindex(port_params[i].iface), -1, + port_params[i].xsk_cfg.xdp_flags); +} + +int main(int argc, char **argv) +{ + struct timespec time; + u64 ns0; + int i; + + /* Parse args. */ + memcpy(&bpool_params, &bpool_params_default, + sizeof(struct bpool_params)); + memcpy(&umem_cfg, &umem_cfg_default, + sizeof(struct xsk_umem_config)); + for (i = 0; i < MAX_PORTS; i++) + memcpy(&port_params[i], &port_params_default, + sizeof(struct port_params)); + + if (parse_args(argc, argv)) { + print_usage(argv[0]); + return -1; + } + + /* Buffer pool initialization. */ + bp = bpool_init(&bpool_params, &umem_cfg); + if (!bp) { + printf("Buffer pool initialization failed.\n"); + return -1; + } + printf("Buffer pool created successfully.\n"); + + /* Ports initialization. */ + for (i = 0; i < MAX_PORTS; i++) + port_params[i].bp = bp; + + for (i = 0; i < n_ports; i++) { + ports[i] = port_init(&port_params[i]); + if (!ports[i]) { + printf("Port %d initialization failed.\n", i); + return -1; + } + print_port(i); + } + printf("All ports created successfully.\n"); + + /* Threads. */ + for (i = 0; i < n_threads; i++) { + struct thread_data *t = &thread_data[i]; + u32 n_ports_per_thread = n_ports / n_threads, j; + + for (j = 0; j < n_ports_per_thread; j++) { + t->ports_rx[j] = ports[i * n_ports_per_thread + j]; + t->ports_tx[j] = ports[i * n_ports_per_thread + + (j + 1) % n_ports_per_thread]; + } + + t->n_ports_rx = n_ports_per_thread; + + print_thread(i); + } + + for (i = 0; i < n_threads; i++) { + int status; + + status = pthread_create(&threads[i], + NULL, + thread_func, + &thread_data[i]); + if (status) { + printf("Thread %d creation failed.\n", i); + return -1; + } + } + printf("All threads created successfully.\n"); + + /* Print statistics. */ + signal(SIGINT, signal_handler); + signal(SIGTERM, signal_handler); + signal(SIGABRT, signal_handler); + + clock_gettime(CLOCK_MONOTONIC, &time); + ns0 = time.tv_sec * 1000000000UL + time.tv_nsec; + for ( ; !quit; ) { + u64 ns1, ns_diff; + + sleep(1); + clock_gettime(CLOCK_MONOTONIC, &time); + ns1 = time.tv_sec * 1000000000UL + time.tv_nsec; + ns_diff = ns1 - ns0; + ns0 = ns1; + + print_port_stats_all(ns_diff); + } + + /* Threads completion. */ + printf("Quit.\n"); + for (i = 0; i < n_threads; i++) + thread_data[i].quit = 1; + + for (i = 0; i < n_threads; i++) + pthread_join(threads[i], NULL); + + for (i = 0; i < n_ports; i++) + port_free(ports[i]); + + bpool_free(bp); + + remove_xdp_program(); + + return 0; +} diff --git a/samples/configfs/configfs_sample.c b/samples/configfs/configfs_sample.c index e2398d94e8da..f9008be7a8a1 100644 --- a/samples/configfs/configfs_sample.c +++ b/samples/configfs/configfs_sample.c @@ -7,19 +7,17 @@ * macros defined by configfs.h * * Based on sysfs: - * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel + * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * * configfs Copyright (C) 2005 Oracle. All rights reserved. */ #include <linux/init.h> +#include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> - #include <linux/configfs.h> - - /* * 01-childless * @@ -40,8 +38,8 @@ struct childless { static inline struct childless *to_childless(struct config_item *item) { - return item ? container_of(to_configfs_subsystem(to_config_group(item)), - struct childless, subsys) : NULL; + return container_of(to_configfs_subsystem(to_config_group(item)), + struct childless, subsys); } static ssize_t childless_showme_show(struct config_item *item, char *page) @@ -64,17 +62,11 @@ static ssize_t childless_storeme_store(struct config_item *item, const char *page, size_t count) { struct childless *childless = to_childless(item); - unsigned long tmp; - char *p = (char *) page; - - tmp = simple_strtoul(p, &p, 10); - if (!p || (*p && (*p != '\n'))) - return -EINVAL; - - if (tmp > INT_MAX) - return -ERANGE; + int ret; - childless->storeme = tmp; + ret = kstrtoint(page, 10, &childless->storeme); + if (ret) + return ret; return count; } @@ -117,7 +109,6 @@ static struct childless childless_subsys = { }, }; - /* ----------------------------------------------------------------- */ /* @@ -136,7 +127,7 @@ struct simple_child { static inline struct simple_child *to_simple_child(struct config_item *item) { - return item ? container_of(item, struct simple_child, item) : NULL; + return container_of(item, struct simple_child, item); } static ssize_t simple_child_storeme_show(struct config_item *item, char *page) @@ -148,17 +139,11 @@ static ssize_t simple_child_storeme_store(struct config_item *item, const char *page, size_t count) { struct simple_child *simple_child = to_simple_child(item); - unsigned long tmp; - char *p = (char *) page; - - tmp = simple_strtoul(p, &p, 10); - if (!p || (*p && (*p != '\n'))) - return -EINVAL; - - if (tmp > INT_MAX) - return -ERANGE; + int ret; - simple_child->storeme = tmp; + ret = kstrtoint(page, 10, &simple_child->storeme); + if (ret) + return ret; return count; } @@ -176,7 +161,7 @@ static void simple_child_release(struct config_item *item) } static struct configfs_item_operations simple_child_item_ops = { - .release = simple_child_release, + .release = simple_child_release, }; static const struct config_item_type simple_child_type = { @@ -185,15 +170,14 @@ static const struct config_item_type simple_child_type = { .ct_owner = THIS_MODULE, }; - struct simple_children { struct config_group group; }; static inline struct simple_children *to_simple_children(struct config_item *item) { - return item ? container_of(to_config_group(item), - struct simple_children, group) : NULL; + return container_of(to_config_group(item), + struct simple_children, group); } static struct config_item *simple_children_make_item(struct config_group *group, @@ -208,8 +192,6 @@ static struct config_item *simple_children_make_item(struct config_group *group, config_item_init_type_name(&simple_child->item, name, &simple_child_type); - simple_child->storeme = 0; - return &simple_child->item; } @@ -263,7 +245,6 @@ static struct configfs_subsystem simple_children_subsys = { }, }; - /* ----------------------------------------------------------------- */ /* @@ -350,9 +331,8 @@ static struct configfs_subsystem *example_subsys[] = { static int __init configfs_example_init(void) { - int ret; - int i; struct configfs_subsystem *subsys; + int ret, i; for (i = 0; example_subsys[i]; i++) { subsys = example_subsys[i]; @@ -361,9 +341,8 @@ static int __init configfs_example_init(void) mutex_init(&subsys->su_mutex); ret = configfs_register_subsystem(subsys); if (ret) { - printk(KERN_ERR "Error %d while registering subsystem %s\n", - ret, - subsys->su_group.cg_item.ci_namebuf); + pr_err("Error %d while registering subsystem %s\n", + ret, subsys->su_group.cg_item.ci_namebuf); goto out_unregister; } } diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c index 8b718943d603..365905cb24b1 100644 --- a/samples/kprobes/kprobe_example.c +++ b/samples/kprobes/kprobe_example.c @@ -2,13 +2,13 @@ /* * NOTE: This example is works on x86 and powerpc. * Here's a sample kernel module showing the use of kprobes to dump a - * stack trace and selected registers when _do_fork() is called. + * stack trace and selected registers when kernel_clone() is called. * * For more information on theory of operation of kprobes, see * Documentation/trace/kprobes.rst * * You will see the trace data in /var/log/messages and on the console - * whenever _do_fork() is invoked to create a new process. + * whenever kernel_clone() is invoked to create a new process. */ #include <linux/kernel.h> @@ -16,7 +16,7 @@ #include <linux/kprobes.h> #define MAX_SYMBOL_LEN 64 -static char symbol[MAX_SYMBOL_LEN] = "_do_fork"; +static char symbol[MAX_SYMBOL_LEN] = "kernel_clone"; module_param_string(symbol, symbol, sizeof(symbol), 0644); /* For each probe you need to allocate a kprobe structure */ diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c index 69fd1235108a..5dc1bf3baa98 100644 --- a/samples/kprobes/kretprobe_example.c +++ b/samples/kprobes/kretprobe_example.c @@ -8,7 +8,7 @@ * * usage: insmod kretprobe_example.ko func=<func_name> * - * If no func_name is specified, _do_fork is instrumented + * If no func_name is specified, kernel_clone is instrumented * * For more information on theory of operation of kretprobes, see * Documentation/trace/kprobes.rst @@ -26,7 +26,7 @@ #include <linux/limits.h> #include <linux/sched.h> -static char func_name[NAME_MAX] = "_do_fork"; +static char func_name[NAME_MAX] = "kernel_clone"; module_param_string(func, func_name, NAME_MAX, S_IRUGO); MODULE_PARM_DESC(func, "Function to kretprobe; this module will report the" " function's execution time"); diff --git a/samples/mic/mpssd/mpssd.c b/samples/mic/mpssd/mpssd.c index a11bf6c5b53b..c03a05d498f0 100644 --- a/samples/mic/mpssd/mpssd.c +++ b/samples/mic/mpssd/mpssd.c @@ -403,9 +403,9 @@ mic_virtio_copy(struct mic_info *mic, int fd, static inline unsigned _vring_size(unsigned int num, unsigned long align) { - return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num) + return _ALIGN_UP(((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num) + align - 1) & ~(align - 1)) - + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num; + + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num, 4); } /* @@ -612,7 +612,7 @@ virtio_net(void *arg) copy.out_len, hdr->gso_type); #endif #ifdef DEBUG - disp_iovec(mic, copy, __func__, __LINE__); + disp_iovec(mic, ©, __func__, __LINE__); mpsslog("%s %s %d read from tap 0x%lx\n", mic->name, __func__, __LINE__, len); @@ -632,7 +632,7 @@ virtio_net(void *arg) if (!err) verify_out_len(mic, ©); #ifdef DEBUG - disp_iovec(mic, copy, __func__, __LINE__); + disp_iovec(mic, ©, __func__, __LINE__); mpsslog("%s %s %d wrote to net 0x%lx\n", mic->name, __func__, __LINE__, sum_iovec_len(©)); @@ -681,12 +681,12 @@ virtio_net(void *arg) sizeof(struct virtio_net_hdr); verify_out_len(mic, ©); #ifdef DEBUG - disp_iovec(mic, copy, __func__, + disp_iovec(mic, ©, __func__, __LINE__); mpsslog("%s %s %d ", mic->name, __func__, __LINE__); mpsslog("read from net 0x%lx\n", - sum_iovec_len(copy)); + sum_iovec_len(©)); #endif len = writev(net_poll[NET_FD_TUN].fd, copy.iov, copy.iovcnt); @@ -814,7 +814,7 @@ virtio_console(void *arg) len = readv(pty_fd, copy.iov, copy.iovcnt); if (len > 0) { #ifdef DEBUG - disp_iovec(mic, copy, __func__, __LINE__); + disp_iovec(mic, ©, __func__, __LINE__); mpsslog("%s %s %d read from tap 0x%lx\n", mic->name, __func__, __LINE__, len); @@ -834,10 +834,10 @@ virtio_console(void *arg) if (!err) verify_out_len(mic, ©); #ifdef DEBUG - disp_iovec(mic, copy, __func__, __LINE__); + disp_iovec(mic, ©, __func__, __LINE__); mpsslog("%s %s %d wrote to net 0x%lx\n", mic->name, __func__, __LINE__, - sum_iovec_len(copy)); + sum_iovec_len(©)); #endif /* Reinitialize IOV for next run */ iov0->iov_len = PAGE_SIZE; @@ -866,12 +866,12 @@ virtio_console(void *arg) iov1->iov_len = copy.out_len; verify_out_len(mic, ©); #ifdef DEBUG - disp_iovec(mic, copy, __func__, + disp_iovec(mic, ©, __func__, __LINE__); mpsslog("%s %s %d ", mic->name, __func__, __LINE__); mpsslog("read from net 0x%lx\n", - sum_iovec_len(copy)); + sum_iovec_len(©)); #endif len = writev(pty_fd, copy.iov, copy.iovcnt); @@ -883,7 +883,7 @@ virtio_console(void *arg) sum_iovec_len(©)); } else { #ifdef DEBUG - disp_iovec(mic, copy, __func__, + disp_iovec(mic, ©, __func__, __LINE__); mpsslog("%s %s %d ", mic->name, __func__, diff --git a/samples/nitro_enclaves/.gitignore b/samples/nitro_enclaves/.gitignore new file mode 100644 index 000000000000..827934129c90 --- /dev/null +++ b/samples/nitro_enclaves/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +ne_ioctl_sample diff --git a/samples/nitro_enclaves/Makefile b/samples/nitro_enclaves/Makefile new file mode 100644 index 000000000000..a3ec78fefb52 --- /dev/null +++ b/samples/nitro_enclaves/Makefile @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + +# Enclave lifetime management support for Nitro Enclaves (NE) - ioctl sample +# usage. + +.PHONY: all clean + +CFLAGS += -Wall + +all: + $(CC) $(CFLAGS) -o ne_ioctl_sample ne_ioctl_sample.c -lpthread + +clean: + rm -f ne_ioctl_sample diff --git a/samples/nitro_enclaves/ne_ioctl_sample.c b/samples/nitro_enclaves/ne_ioctl_sample.c new file mode 100644 index 000000000000..480b763142b3 --- /dev/null +++ b/samples/nitro_enclaves/ne_ioctl_sample.c @@ -0,0 +1,883 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + */ + +/** + * DOC: Sample flow of using the ioctl interface provided by the Nitro Enclaves (NE) + * kernel driver. + * + * Usage + * ----- + * + * Load the nitro_enclaves module, setting also the enclave CPU pool. The + * enclave CPUs need to be full cores from the same NUMA node. CPU 0 and its + * siblings have to remain available for the primary / parent VM, so they + * cannot be included in the enclave CPU pool. + * + * See the cpu list section from the kernel documentation. + * https://www.kernel.org/doc/html/latest/admin-guide/kernel-parameters.html#cpu-lists + * + * insmod drivers/virt/nitro_enclaves/nitro_enclaves.ko + * lsmod + * + * The CPU pool can be set at runtime, after the kernel module is loaded. + * + * echo <cpu-list> > /sys/module/nitro_enclaves/parameters/ne_cpus + * + * NUMA and CPU siblings information can be found using: + * + * lscpu + * /proc/cpuinfo + * + * Check the online / offline CPU list. The CPUs from the pool should be + * offlined. + * + * lscpu + * + * Check dmesg for any warnings / errors through the NE driver lifetime / usage. + * The NE logs contain the "nitro_enclaves" or "pci 0000:00:02.0" pattern. + * + * dmesg + * + * Setup hugetlbfs huge pages. The memory needs to be from the same NUMA node as + * the enclave CPUs. + * + * https://www.kernel.org/doc/html/latest/admin-guide/mm/hugetlbpage.html + * + * By default, the allocation of hugetlb pages are distributed on all possible + * NUMA nodes. Use the following configuration files to set the number of huge + * pages from a NUMA node: + * + * /sys/devices/system/node/node<X>/hugepages/hugepages-2048kB/nr_hugepages + * /sys/devices/system/node/node<X>/hugepages/hugepages-1048576kB/nr_hugepages + * + * or, if not on a system with multiple NUMA nodes, can also set the number + * of 2 MiB / 1 GiB huge pages using + * + * /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages + * /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages + * + * In this example 256 hugepages of 2 MiB are used. + * + * Build and run the NE sample. + * + * make -C samples/nitro_enclaves clean + * make -C samples/nitro_enclaves + * ./samples/nitro_enclaves/ne_ioctl_sample <path_to_enclave_image> + * + * Unload the nitro_enclaves module. + * + * rmmod nitro_enclaves + * lsmod + */ + +#include <stdio.h> +#include <stdlib.h> +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <poll.h> +#include <pthread.h> +#include <string.h> +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#include <linux/mman.h> +#include <linux/nitro_enclaves.h> +#include <linux/vm_sockets.h> + +/** + * NE_DEV_NAME - Nitro Enclaves (NE) misc device that provides the ioctl interface. + */ +#define NE_DEV_NAME "/dev/nitro_enclaves" + +/** + * NE_POLL_WAIT_TIME - Timeout in seconds for each poll event. + */ +#define NE_POLL_WAIT_TIME (60) +/** + * NE_POLL_WAIT_TIME_MS - Timeout in milliseconds for each poll event. + */ +#define NE_POLL_WAIT_TIME_MS (NE_POLL_WAIT_TIME * 1000) + +/** + * NE_SLEEP_TIME - Amount of time in seconds for the process to keep the enclave alive. + */ +#define NE_SLEEP_TIME (300) + +/** + * NE_DEFAULT_NR_VCPUS - Default number of vCPUs set for an enclave. + */ +#define NE_DEFAULT_NR_VCPUS (2) + +/** + * NE_MIN_MEM_REGION_SIZE - Minimum size of a memory region - 2 MiB. + */ +#define NE_MIN_MEM_REGION_SIZE (2 * 1024 * 1024) + +/** + * NE_DEFAULT_NR_MEM_REGIONS - Default number of memory regions of 2 MiB set for + * an enclave. + */ +#define NE_DEFAULT_NR_MEM_REGIONS (256) + +/** + * NE_IMAGE_LOAD_HEARTBEAT_CID - Vsock CID for enclave image loading heartbeat logic. + */ +#define NE_IMAGE_LOAD_HEARTBEAT_CID (3) +/** + * NE_IMAGE_LOAD_HEARTBEAT_PORT - Vsock port for enclave image loading heartbeat logic. + */ +#define NE_IMAGE_LOAD_HEARTBEAT_PORT (9000) +/** + * NE_IMAGE_LOAD_HEARTBEAT_VALUE - Heartbeat value for enclave image loading. + */ +#define NE_IMAGE_LOAD_HEARTBEAT_VALUE (0xb7) + +/** + * struct ne_user_mem_region - User space memory region set for an enclave. + * @userspace_addr: Address of the user space memory region. + * @memory_size: Size of the user space memory region. + */ +struct ne_user_mem_region { + void *userspace_addr; + size_t memory_size; +}; + +/** + * ne_create_vm() - Create a slot for the enclave VM. + * @ne_dev_fd: The file descriptor of the NE misc device. + * @slot_uid: The generated slot uid for the enclave. + * @enclave_fd : The generated file descriptor for the enclave. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_create_vm(int ne_dev_fd, unsigned long *slot_uid, int *enclave_fd) +{ + int rc = -EINVAL; + *enclave_fd = ioctl(ne_dev_fd, NE_CREATE_VM, slot_uid); + + if (*enclave_fd < 0) { + rc = *enclave_fd; + switch (errno) { + case NE_ERR_NO_CPUS_AVAIL_IN_POOL: { + printf("Error in create VM, no CPUs available in the NE CPU pool\n"); + + break; + } + + default: + printf("Error in create VM [%m]\n"); + } + + return rc; + } + + return 0; +} + + +/** + * ne_poll_enclave_fd() - Thread function for polling the enclave fd. + * @data: Argument provided for the polling function. + * + * Context: Process context. + * Return: + * * NULL on success / failure. + */ +void *ne_poll_enclave_fd(void *data) +{ + int enclave_fd = *(int *)data; + struct pollfd fds[1] = {}; + int i = 0; + int rc = -EINVAL; + + printf("Running from poll thread, enclave fd %d\n", enclave_fd); + + fds[0].fd = enclave_fd; + fds[0].events = POLLIN | POLLERR | POLLHUP; + + /* Keep on polling until the current process is terminated. */ + while (1) { + printf("[iter %d] Polling ...\n", i); + + rc = poll(fds, 1, NE_POLL_WAIT_TIME_MS); + if (rc < 0) { + printf("Error in poll [%m]\n"); + + return NULL; + } + + i++; + + if (!rc) { + printf("Poll: %d seconds elapsed\n", + i * NE_POLL_WAIT_TIME); + + continue; + } + + printf("Poll received value 0x%x\n", fds[0].revents); + + if (fds[0].revents & POLLHUP) { + printf("Received POLLHUP\n"); + + return NULL; + } + + if (fds[0].revents & POLLNVAL) { + printf("Received POLLNVAL\n"); + + return NULL; + } + } + + return NULL; +} + +/** + * ne_alloc_user_mem_region() - Allocate a user space memory region for an enclave. + * @ne_user_mem_region: User space memory region allocated using hugetlbfs. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_alloc_user_mem_region(struct ne_user_mem_region *ne_user_mem_region) +{ + /** + * Check available hugetlb encodings for different huge page sizes in + * include/uapi/linux/mman.h. + */ + ne_user_mem_region->userspace_addr = mmap(NULL, ne_user_mem_region->memory_size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | + MAP_HUGETLB | MAP_HUGE_2MB, -1, 0); + if (ne_user_mem_region->userspace_addr == MAP_FAILED) { + printf("Error in mmap memory [%m]\n"); + + return -1; + } + + return 0; +} + +/** + * ne_load_enclave_image() - Place the enclave image in the enclave memory. + * @enclave_fd : The file descriptor associated with the enclave. + * @ne_user_mem_regions: User space memory regions allocated for the enclave. + * @enclave_image_path : The file path of the enclave image. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_load_enclave_image(int enclave_fd, struct ne_user_mem_region ne_user_mem_regions[], + char *enclave_image_path) +{ + unsigned char *enclave_image = NULL; + int enclave_image_fd = -1; + size_t enclave_image_size = 0; + size_t enclave_memory_size = 0; + unsigned long i = 0; + size_t image_written_bytes = 0; + struct ne_image_load_info image_load_info = { + .flags = NE_EIF_IMAGE, + }; + struct stat image_stat_buf = {}; + int rc = -EINVAL; + size_t temp_image_offset = 0; + + for (i = 0; i < NE_DEFAULT_NR_MEM_REGIONS; i++) + enclave_memory_size += ne_user_mem_regions[i].memory_size; + + rc = stat(enclave_image_path, &image_stat_buf); + if (rc < 0) { + printf("Error in get image stat info [%m]\n"); + + return rc; + } + + enclave_image_size = image_stat_buf.st_size; + + if (enclave_memory_size < enclave_image_size) { + printf("The enclave memory is smaller than the enclave image size\n"); + + return -ENOMEM; + } + + rc = ioctl(enclave_fd, NE_GET_IMAGE_LOAD_INFO, &image_load_info); + if (rc < 0) { + switch (errno) { + case NE_ERR_NOT_IN_INIT_STATE: { + printf("Error in get image load info, enclave not in init state\n"); + + break; + } + + case NE_ERR_INVALID_FLAG_VALUE: { + printf("Error in get image load info, provided invalid flag\n"); + + break; + } + + default: + printf("Error in get image load info [%m]\n"); + } + + return rc; + } + + printf("Enclave image offset in enclave memory is %lld\n", + image_load_info.memory_offset); + + enclave_image_fd = open(enclave_image_path, O_RDONLY); + if (enclave_image_fd < 0) { + printf("Error in open enclave image file [%m]\n"); + + return enclave_image_fd; + } + + enclave_image = mmap(NULL, enclave_image_size, PROT_READ, + MAP_PRIVATE, enclave_image_fd, 0); + if (enclave_image == MAP_FAILED) { + printf("Error in mmap enclave image [%m]\n"); + + return -1; + } + + temp_image_offset = image_load_info.memory_offset; + + for (i = 0; i < NE_DEFAULT_NR_MEM_REGIONS; i++) { + size_t bytes_to_write = 0; + size_t memory_offset = 0; + size_t memory_size = ne_user_mem_regions[i].memory_size; + size_t remaining_bytes = 0; + void *userspace_addr = ne_user_mem_regions[i].userspace_addr; + + if (temp_image_offset >= memory_size) { + temp_image_offset -= memory_size; + + continue; + } else if (temp_image_offset != 0) { + memory_offset = temp_image_offset; + memory_size -= temp_image_offset; + temp_image_offset = 0; + } + + remaining_bytes = enclave_image_size - image_written_bytes; + bytes_to_write = memory_size < remaining_bytes ? + memory_size : remaining_bytes; + + memcpy(userspace_addr + memory_offset, + enclave_image + image_written_bytes, bytes_to_write); + + image_written_bytes += bytes_to_write; + + if (image_written_bytes == enclave_image_size) + break; + } + + munmap(enclave_image, enclave_image_size); + + close(enclave_image_fd); + + return 0; +} + +/** + * ne_set_user_mem_region() - Set a user space memory region for the given enclave. + * @enclave_fd : The file descriptor associated with the enclave. + * @ne_user_mem_region : User space memory region to be set for the enclave. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_set_user_mem_region(int enclave_fd, struct ne_user_mem_region ne_user_mem_region) +{ + struct ne_user_memory_region mem_region = { + .flags = NE_DEFAULT_MEMORY_REGION, + .memory_size = ne_user_mem_region.memory_size, + .userspace_addr = (__u64)ne_user_mem_region.userspace_addr, + }; + int rc = -EINVAL; + + rc = ioctl(enclave_fd, NE_SET_USER_MEMORY_REGION, &mem_region); + if (rc < 0) { + switch (errno) { + case NE_ERR_NOT_IN_INIT_STATE: { + printf("Error in set user memory region, enclave not in init state\n"); + + break; + } + + case NE_ERR_INVALID_MEM_REGION_SIZE: { + printf("Error in set user memory region, mem size not multiple of 2 MiB\n"); + + break; + } + + case NE_ERR_INVALID_MEM_REGION_ADDR: { + printf("Error in set user memory region, invalid user space address\n"); + + break; + } + + case NE_ERR_UNALIGNED_MEM_REGION_ADDR: { + printf("Error in set user memory region, unaligned user space address\n"); + + break; + } + + case NE_ERR_MEM_REGION_ALREADY_USED: { + printf("Error in set user memory region, memory region already used\n"); + + break; + } + + case NE_ERR_MEM_NOT_HUGE_PAGE: { + printf("Error in set user memory region, not backed by huge pages\n"); + + break; + } + + case NE_ERR_MEM_DIFFERENT_NUMA_NODE: { + printf("Error in set user memory region, different NUMA node than CPUs\n"); + + break; + } + + case NE_ERR_MEM_MAX_REGIONS: { + printf("Error in set user memory region, max memory regions reached\n"); + + break; + } + + case NE_ERR_INVALID_PAGE_SIZE: { + printf("Error in set user memory region, has page not multiple of 2 MiB\n"); + + break; + } + + case NE_ERR_INVALID_FLAG_VALUE: { + printf("Error in set user memory region, provided invalid flag\n"); + + break; + } + + default: + printf("Error in set user memory region [%m]\n"); + } + + return rc; + } + + return 0; +} + +/** + * ne_free_mem_regions() - Unmap all the user space memory regions that were set + * aside for the enclave. + * @ne_user_mem_regions: The user space memory regions associated with an enclave. + * + * Context: Process context. + */ +static void ne_free_mem_regions(struct ne_user_mem_region ne_user_mem_regions[]) +{ + unsigned int i = 0; + + for (i = 0; i < NE_DEFAULT_NR_MEM_REGIONS; i++) + munmap(ne_user_mem_regions[i].userspace_addr, + ne_user_mem_regions[i].memory_size); +} + +/** + * ne_add_vcpu() - Add a vCPU to the given enclave. + * @enclave_fd : The file descriptor associated with the enclave. + * @vcpu_id: vCPU id to be set for the enclave, either provided or + * auto-generated (if provided vCPU id is 0). + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_add_vcpu(int enclave_fd, unsigned int *vcpu_id) +{ + int rc = -EINVAL; + + rc = ioctl(enclave_fd, NE_ADD_VCPU, vcpu_id); + if (rc < 0) { + switch (errno) { + case NE_ERR_NO_CPUS_AVAIL_IN_POOL: { + printf("Error in add vcpu, no CPUs available in the NE CPU pool\n"); + + break; + } + + case NE_ERR_VCPU_ALREADY_USED: { + printf("Error in add vcpu, the provided vCPU is already used\n"); + + break; + } + + case NE_ERR_VCPU_NOT_IN_CPU_POOL: { + printf("Error in add vcpu, the provided vCPU is not in the NE CPU pool\n"); + + break; + } + + case NE_ERR_VCPU_INVALID_CPU_CORE: { + printf("Error in add vcpu, the core id of the provided vCPU is invalid\n"); + + break; + } + + case NE_ERR_NOT_IN_INIT_STATE: { + printf("Error in add vcpu, enclave not in init state\n"); + + break; + } + + case NE_ERR_INVALID_VCPU: { + printf("Error in add vcpu, the provided vCPU is out of avail CPUs range\n"); + + break; + } + + default: + printf("Error in add vcpu [%m]\n"); + + } + return rc; + } + + return 0; +} + +/** + * ne_start_enclave() - Start the given enclave. + * @enclave_fd : The file descriptor associated with the enclave. + * @enclave_start_info : Enclave metadata used for starting e.g. vsock CID. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_start_enclave(int enclave_fd, struct ne_enclave_start_info *enclave_start_info) +{ + int rc = -EINVAL; + + rc = ioctl(enclave_fd, NE_START_ENCLAVE, enclave_start_info); + if (rc < 0) { + switch (errno) { + case NE_ERR_NOT_IN_INIT_STATE: { + printf("Error in start enclave, enclave not in init state\n"); + + break; + } + + case NE_ERR_NO_MEM_REGIONS_ADDED: { + printf("Error in start enclave, no memory regions have been added\n"); + + break; + } + + case NE_ERR_NO_VCPUS_ADDED: { + printf("Error in start enclave, no vCPUs have been added\n"); + + break; + } + + case NE_ERR_FULL_CORES_NOT_USED: { + printf("Error in start enclave, enclave has no full cores set\n"); + + break; + } + + case NE_ERR_ENCLAVE_MEM_MIN_SIZE: { + printf("Error in start enclave, enclave memory is less than min size\n"); + + break; + } + + case NE_ERR_INVALID_FLAG_VALUE: { + printf("Error in start enclave, provided invalid flag\n"); + + break; + } + + case NE_ERR_INVALID_ENCLAVE_CID: { + printf("Error in start enclave, provided invalid enclave CID\n"); + + break; + } + + default: + printf("Error in start enclave [%m]\n"); + } + + return rc; + } + + return 0; +} + +/** + * ne_start_enclave_check_booted() - Start the enclave and wait for a hearbeat + * from it, on a newly created vsock channel, + * to check it has booted. + * @enclave_fd : The file descriptor associated with the enclave. + * + * Context: Process context. + * Return: + * * 0 on success. + * * Negative return value on failure. + */ +static int ne_start_enclave_check_booted(int enclave_fd) +{ + struct sockaddr_vm client_vsock_addr = {}; + int client_vsock_fd = -1; + socklen_t client_vsock_len = sizeof(client_vsock_addr); + struct ne_enclave_start_info enclave_start_info = {}; + struct pollfd fds[1] = {}; + int rc = -EINVAL; + unsigned char recv_buf = 0; + struct sockaddr_vm server_vsock_addr = { + .svm_family = AF_VSOCK, + .svm_cid = NE_IMAGE_LOAD_HEARTBEAT_CID, + .svm_port = NE_IMAGE_LOAD_HEARTBEAT_PORT, + }; + int server_vsock_fd = -1; + + server_vsock_fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (server_vsock_fd < 0) { + rc = server_vsock_fd; + + printf("Error in socket [%m]\n"); + + return rc; + } + + rc = bind(server_vsock_fd, (struct sockaddr *)&server_vsock_addr, + sizeof(server_vsock_addr)); + if (rc < 0) { + printf("Error in bind [%m]\n"); + + goto out; + } + + rc = listen(server_vsock_fd, 1); + if (rc < 0) { + printf("Error in listen [%m]\n"); + + goto out; + } + + rc = ne_start_enclave(enclave_fd, &enclave_start_info); + if (rc < 0) + goto out; + + printf("Enclave started, CID %llu\n", enclave_start_info.enclave_cid); + + fds[0].fd = server_vsock_fd; + fds[0].events = POLLIN; + + rc = poll(fds, 1, NE_POLL_WAIT_TIME_MS); + if (rc < 0) { + printf("Error in poll [%m]\n"); + + goto out; + } + + if (!rc) { + printf("Poll timeout, %d seconds elapsed\n", NE_POLL_WAIT_TIME); + + rc = -ETIMEDOUT; + + goto out; + } + + if ((fds[0].revents & POLLIN) == 0) { + printf("Poll received value %d\n", fds[0].revents); + + rc = -EINVAL; + + goto out; + } + + rc = accept(server_vsock_fd, (struct sockaddr *)&client_vsock_addr, + &client_vsock_len); + if (rc < 0) { + printf("Error in accept [%m]\n"); + + goto out; + } + + client_vsock_fd = rc; + + /* + * Read the heartbeat value that the init process in the enclave sends + * after vsock connect. + */ + rc = read(client_vsock_fd, &recv_buf, sizeof(recv_buf)); + if (rc < 0) { + printf("Error in read [%m]\n"); + + goto out; + } + + if (rc != sizeof(recv_buf) || recv_buf != NE_IMAGE_LOAD_HEARTBEAT_VALUE) { + printf("Read %d instead of %d\n", recv_buf, + NE_IMAGE_LOAD_HEARTBEAT_VALUE); + + goto out; + } + + /* Write the heartbeat value back. */ + rc = write(client_vsock_fd, &recv_buf, sizeof(recv_buf)); + if (rc < 0) { + printf("Error in write [%m]\n"); + + goto out; + } + + rc = 0; + +out: + close(server_vsock_fd); + + return rc; +} + +int main(int argc, char *argv[]) +{ + int enclave_fd = -1; + unsigned int i = 0; + int ne_dev_fd = -1; + struct ne_user_mem_region ne_user_mem_regions[NE_DEFAULT_NR_MEM_REGIONS] = {}; + unsigned int ne_vcpus[NE_DEFAULT_NR_VCPUS] = {}; + int rc = -EINVAL; + pthread_t thread_id = 0; + unsigned long slot_uid = 0; + + if (argc != 2) { + printf("Usage: %s <path_to_enclave_image>\n", argv[0]); + + exit(EXIT_FAILURE); + } + + if (strlen(argv[1]) >= PATH_MAX) { + printf("The size of the path to enclave image is higher than max path\n"); + + exit(EXIT_FAILURE); + } + + ne_dev_fd = open(NE_DEV_NAME, O_RDWR | O_CLOEXEC); + if (ne_dev_fd < 0) { + printf("Error in open NE device [%m]\n"); + + exit(EXIT_FAILURE); + } + + printf("Creating enclave slot ...\n"); + + rc = ne_create_vm(ne_dev_fd, &slot_uid, &enclave_fd); + + close(ne_dev_fd); + + if (rc < 0) + exit(EXIT_FAILURE); + + printf("Enclave fd %d\n", enclave_fd); + + rc = pthread_create(&thread_id, NULL, ne_poll_enclave_fd, (void *)&enclave_fd); + if (rc < 0) { + printf("Error in thread create [%m]\n"); + + close(enclave_fd); + + exit(EXIT_FAILURE); + } + + for (i = 0; i < NE_DEFAULT_NR_MEM_REGIONS; i++) { + ne_user_mem_regions[i].memory_size = NE_MIN_MEM_REGION_SIZE; + + rc = ne_alloc_user_mem_region(&ne_user_mem_regions[i]); + if (rc < 0) { + printf("Error in alloc userspace memory region, iter %d\n", i); + + goto release_enclave_fd; + } + } + + rc = ne_load_enclave_image(enclave_fd, ne_user_mem_regions, argv[1]); + if (rc < 0) + goto release_enclave_fd; + + for (i = 0; i < NE_DEFAULT_NR_MEM_REGIONS; i++) { + rc = ne_set_user_mem_region(enclave_fd, ne_user_mem_regions[i]); + if (rc < 0) { + printf("Error in set memory region, iter %d\n", i); + + goto release_enclave_fd; + } + } + + printf("Enclave memory regions were added\n"); + + for (i = 0; i < NE_DEFAULT_NR_VCPUS; i++) { + /* + * The vCPU is chosen from the enclave vCPU pool, if the value + * of the vcpu_id is 0. + */ + ne_vcpus[i] = 0; + rc = ne_add_vcpu(enclave_fd, &ne_vcpus[i]); + if (rc < 0) { + printf("Error in add vcpu, iter %d\n", i); + + goto release_enclave_fd; + } + + printf("Added vCPU %d to the enclave\n", ne_vcpus[i]); + } + + printf("Enclave vCPUs were added\n"); + + rc = ne_start_enclave_check_booted(enclave_fd); + if (rc < 0) { + printf("Error in the enclave start / image loading heartbeat logic [rc=%d]\n", rc); + + goto release_enclave_fd; + } + + printf("Entering sleep for %d seconds ...\n", NE_SLEEP_TIME); + + sleep(NE_SLEEP_TIME); + + close(enclave_fd); + + ne_free_mem_regions(ne_user_mem_regions); + + exit(EXIT_SUCCESS); + +release_enclave_fd: + close(enclave_fd); + ne_free_mem_regions(ne_user_mem_regions); + + exit(EXIT_FAILURE); +} diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c index 3cc5e5921682..e03068917273 100644 --- a/samples/vfio-mdev/mbochs.c +++ b/samples/vfio-mdev/mbochs.c @@ -846,7 +846,7 @@ static struct sg_table *mbochs_map_dmabuf(struct dma_buf_attachment *at, if (sg_alloc_table_from_pages(sg, dmabuf->pages, dmabuf->pagecount, 0, dmabuf->mode.size, GFP_KERNEL) < 0) goto err2; - if (!dma_map_sg(at->dev, sg->sgl, sg->nents, direction)) + if (dma_map_sgtable(at->dev, sg, direction, 0)) goto err3; return sg; @@ -868,6 +868,7 @@ static void mbochs_unmap_dmabuf(struct dma_buf_attachment *at, dev_dbg(dev, "%s: %d\n", __func__, dmabuf->id); + dma_unmap_sgtable(at->dev, sg, direction, 0); sg_free_table(sg); kfree(sg); } |