public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-05-24 10:39:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
linux/tools/testing/selftests/bpf/progs/pyperf.h

359 lines
8.5 KiB
C
Raw Normal View History

selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
#include <linux/sched.h>
#include <linux/ptrace.h>
#include <stdint.h>
#include <stddef.h>
#include <stdbool.h>
#include <linux/bpf.h>
selftests: Use consistent include paths for libbpf Fix all selftests to include libbpf header files with the bpf/ prefix, to be consistent with external users of the library. Also ensure that all includes of exported libbpf header files (those that are exported on 'make install' of the library) use bracketed includes instead of quoted. To not break the build, keep the old include path until everything has been changed to the new one; a subsequent patch will remove that. Fixes: 6910d7d3867a ("selftests/bpf: Ensure bpf_helper_defs.h are taken from selftests dir") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/157952560568.1683545.9649335788846513446.stgit@toke.dk
2020-01-20 14:06:45 +01:00
#include <bpf/bpf_helpers.h>
selftests/bpf: add bpf_for_each(), bpf_for(), and bpf_repeat() macros Add bpf_for_each(), bpf_for(), and bpf_repeat() macros that make writing open-coded iterator-based loops much more convenient and natural. These macros utilize cleanup attribute to ensure proper destruction of the iterator and thanks to that manage to provide the ergonomics that is very close to C language's for() construct. Typical loop would look like: int i; int arr[N]; bpf_for(i, 0, N) { /* verifier will know that i >= 0 && i < N, so could be used to * directly access array elements with no extra checks */ arr[i] = i; } bpf_repeat() is very similar, but it doesn't expose iteration number and is meant as a simple "repeat action N times" loop: bpf_repeat(N) { /* whatever, N times */ } Note that `break` and `continue` statements inside the {} block work as expected. bpf_for_each() is a generalization over any kind of BPF open-coded iterator allowing to use for-each-like approach instead of calling low-level bpf_iter_<type>_{new,next,destroy}() APIs explicitly. E.g.: struct cgroup *cg; bpf_for_each(cgroup, cg, some, input, args) { /* do something with each cg */ } would call (not-yet-implemented) bpf_iter_cgroup_{new,next,destroy}() functions to form a loop over cgroups, where `some, input, args` are passed verbatim into constructor as bpf_iter_cgroup_new(&it, some, input, args). As a first demonstration, add pyperf variant based on the bpf_for() loop. Also clean up a few tests that either included bpf_misc.h header unnecessarily from the user-space, which is unsupported, or included it before any common types are defined (and thus leading to unnecessary compilation warnings, potentially). Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20230308184121.1165081-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-08 10:41:18 -08:00
#include "bpf_misc.h"
bpf: Abstract loop unrolling pragmas in BPF selftests [Changes from V1: - Avoid conflict by rebasing with latest master.] Some BPF tests use loop unrolling compiler pragmas that are clang specific and not supported by GCC. These pragmas, along with their GCC equivalences are: #pragma clang loop unroll_count(N) #pragma GCC unroll N #pragma clang loop unroll(full) #pragma GCC unroll 65534 #pragma clang loop unroll(disable) #pragma GCC unroll 1 #pragma unroll [aka #pragma clang loop unroll(enable)] There is no GCC equivalence to this pragma. It enables unrolling on loops that the compiler would not ordinarily unroll even with -O2|-funroll-loops, but it is not equivalent to full unrolling either. This patch adds a new header progs/bpf_compiler.h that defines the following macros, which correspond to each pair of compiler-specific pragmas above: __pragma_loop_unroll_count(N) __pragma_loop_unroll_full __pragma_loop_no_unroll __pragma_loop_unroll The selftests using loop unrolling pragmas are then changed to include the header and use these macros in place of the explicit pragmas. Tested in bpf-next master. No regressions. Signed-off-by: Jose E. Marchesi <jose.marchesi@oracle.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yonghong.song@linux.dev> Link: https://lore.kernel.org/bpf/20240208203612.29611-1-jose.marchesi@oracle.com
2024-02-08 21:36:12 +01:00
#include "bpf_compiler.h"
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
#define FUNCTION_NAME_LEN 64
#define FILE_NAME_LEN 128
#define TASK_COMM_LEN 16
typedef struct {
int PyThreadState_frame;
int PyThreadState_thread;
int PyFrameObject_back;
int PyFrameObject_code;
int PyFrameObject_lineno;
int PyCodeObject_filename;
int PyCodeObject_name;
int String_data;
int String_size;
} OffsetConfig;
typedef struct {
uintptr_t current_state_addr;
uintptr_t tls_key_addr;
OffsetConfig offsets;
bool use_tls;
} PidData;
typedef struct {
uint32_t success;
} Stats;
typedef struct {
char name[FUNCTION_NAME_LEN];
char file[FILE_NAME_LEN];
} Symbol;
typedef struct {
uint32_t pid;
uint32_t tid;
char comm[TASK_COMM_LEN];
int32_t kernel_stack_id;
int32_t user_stack_id;
bool thread_current;
bool pthread_match;
bool stack_complete;
int16_t stack_len;
int32_t stack[STACK_MAX_LEN];
int has_meta;
int metadata;
char dummy_safeguard;
} Event;
typedef int pid_t;
typedef struct {
void* f_back; // PyFrameObject.f_back, previous frame
void* f_code; // PyFrameObject.f_code, pointer to PyCodeObject
void* co_filename; // PyCodeObject.co_filename
void* co_name; // PyCodeObject.co_name
} FrameData;
selftests/bpf: Add subprogs to pyperf, strobemeta, and l4lb_noinline tests Add use of non-inlined subprogs to few bigger selftests to excercise libbpf's bpf2bpf handling logic. Also split l4lb_all selftest into two sub-tests. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200903203542.15944-13-andriin@fb.com
2020-09-03 13:35:40 -07:00
#ifdef SUBPROGS
__noinline
#else
__always_inline
#endif
static void *get_thread_state(void *tls_base, PidData *pidData)
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
{
void* thread_state;
int key;
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user(&key, sizeof(key), (void*)(long)pidData->tls_key_addr);
bpf_probe_read_user(&thread_state, sizeof(thread_state),
tls_base + 0x310 + key * 0x10 + 0x08);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
return thread_state;
}
selftests: bpf: standardize to static __always_inline The progs for bpf selftests use several different notations to force function inlining. Standardize to what most of them use, static __always_inline. Suggested-by: Song Liu <liu.song.a23@gmail.com> Signed-off-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-07-02 20:26:51 +02:00
static __always_inline bool get_frame_data(void *frame_ptr, PidData *pidData,
FrameData *frame, Symbol *symbol)
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
{
// read data from PyFrameObject
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user(&frame->f_back,
sizeof(frame->f_back),
frame_ptr + pidData->offsets.PyFrameObject_back);
bpf_probe_read_user(&frame->f_code,
sizeof(frame->f_code),
frame_ptr + pidData->offsets.PyFrameObject_code);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
// read data from PyCodeObject
if (!frame->f_code)
return false;
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user(&frame->co_filename,
sizeof(frame->co_filename),
frame->f_code + pidData->offsets.PyCodeObject_filename);
bpf_probe_read_user(&frame->co_name,
sizeof(frame->co_name),
frame->f_code + pidData->offsets.PyCodeObject_name);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
// read actual names into symbol
if (frame->co_filename)
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user_str(&symbol->file,
sizeof(symbol->file),
frame->co_filename +
pidData->offsets.String_data);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
if (frame->co_name)
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user_str(&symbol->name,
sizeof(symbol->name),
frame->co_name +
pidData->offsets.String_data);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
return true;
}
selftests/bpf: convert legacy BPF maps to BTF-defined ones Convert selftests that were originally left out and new ones added recently to consistently use BTF-defined maps. Reported-by: kernel test robot <rong.a.chen@intel.com> Signed-off-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-07-05 08:50:12 -07:00
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, 1);
__type(key, int);
__type(value, PidData);
} pidmap SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, 1);
__type(key, int);
__type(value, Event);
} eventmap SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_HASH);
__uint(max_entries, 1);
__type(key, Symbol);
__type(value, int);
} symbolmap SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(max_entries, 1);
__type(key, int);
__type(value, Stats);
} statsmap SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
__uint(max_entries, 32);
__uint(key_size, sizeof(int));
__uint(value_size, sizeof(int));
} perfmap SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_STACK_TRACE);
__uint(max_entries, 1000);
__uint(key_size, sizeof(int));
__uint(value_size, sizeof(long long) * 127);
} stackmap SEC(".maps");
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
selftests/bpf: Measure bpf_loop verifier performance This patch tests bpf_loop in pyperf and strobemeta, and measures the verifier performance of replacing the traditional for loop with bpf_loop. The results are as follows: ~strobemeta~ Baseline verification time 6808200 usec stack depth 496 processed 554252 insns (limit 1000000) max_states_per_insn 16 total_states 15878 peak_states 13489 mark_read 3110 #192 verif_scale_strobemeta:OK (unrolled loop) Using bpf_loop verification time 31589 usec stack depth 96+400 processed 1513 insns (limit 1000000) max_states_per_insn 2 total_states 106 peak_states 106 mark_read 60 #193 verif_scale_strobemeta_bpf_loop:OK ~pyperf600~ Baseline verification time 29702486 usec stack depth 368 processed 626838 insns (limit 1000000) max_states_per_insn 7 total_states 30368 peak_states 30279 mark_read 748 #182 verif_scale_pyperf600:OK (unrolled loop) Using bpf_loop verification time 148488 usec stack depth 320+40 processed 10518 insns (limit 1000000) max_states_per_insn 10 total_states 705 peak_states 517 mark_read 38 #183 verif_scale_pyperf600_bpf_loop:OK Using the bpf_loop helper led to approximately a 99% decrease in the verification time and in the number of instructions. Signed-off-by: Joanne Koong <joannekoong@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20211130030622.4131246-4-joannekoong@fb.com
2021-11-29 19:06:21 -08:00
#ifdef USE_BPF_LOOP
struct process_frame_ctx {
int cur_cpu;
int32_t *symbol_counter;
void *frame_ptr;
FrameData *frame;
PidData *pidData;
Symbol *sym;
Event *event;
bool done;
};
static int process_frame_callback(__u32 i, struct process_frame_ctx *ctx)
{
int zero = 0;
void *frame_ptr = ctx->frame_ptr;
PidData *pidData = ctx->pidData;
FrameData *frame = ctx->frame;
int32_t *symbol_counter = ctx->symbol_counter;
int cur_cpu = ctx->cur_cpu;
Event *event = ctx->event;
Symbol *sym = ctx->sym;
if (frame_ptr && get_frame_data(frame_ptr, pidData, frame, sym)) {
int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu;
int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, sym);
if (!symbol_id) {
bpf_map_update_elem(&symbolmap, sym, &zero, 0);
symbol_id = bpf_map_lookup_elem(&symbolmap, sym);
if (!symbol_id) {
ctx->done = true;
return 1;
}
}
if (*symbol_id == new_symbol_id)
(*symbol_counter)++;
barrier_var(i);
if (i >= STACK_MAX_LEN)
return 1;
event->stack[i] = *symbol_id;
event->stack_len = i + 1;
frame_ptr = frame->f_back;
}
return 0;
}
#endif /* USE_BPF_LOOP */
selftests/bpf: Add a test for a large global function test results: pyperf50 with always_inlined the same function five times: processed 46378 insns pyperf50 with global function: processed 6102 insns Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200110064124.1760511-5-ast@kernel.org
2020-01-09 22:41:22 -08:00
#ifdef GLOBAL_FUNC
selftests/bpf: Add subprogs to pyperf, strobemeta, and l4lb_noinline tests Add use of non-inlined subprogs to few bigger selftests to excercise libbpf's bpf2bpf handling logic. Also split l4lb_all selftest into two sub-tests. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200903203542.15944-13-andriin@fb.com
2020-09-03 13:35:40 -07:00
__noinline
#elif defined(SUBPROGS)
static __noinline
selftests/bpf: Add a test for a large global function test results: pyperf50 with always_inlined the same function five times: processed 46378 insns pyperf50 with global function: processed 6102 insns Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200110064124.1760511-5-ast@kernel.org
2020-01-09 22:41:22 -08:00
#else
static __always_inline
#endif
int __on_event(struct bpf_raw_tracepoint_args *ctx)
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
{
uint64_t pid_tgid = bpf_get_current_pid_tgid();
pid_t pid = (pid_t)(pid_tgid >> 32);
PidData* pidData = bpf_map_lookup_elem(&pidmap, &pid);
if (!pidData)
return 0;
int zero = 0;
Event* event = bpf_map_lookup_elem(&eventmap, &zero);
if (!event)
return 0;
event->pid = pid;
event->tid = (pid_t)pid_tgid;
bpf_get_current_comm(&event->comm, sizeof(event->comm));
event->user_stack_id = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK);
event->kernel_stack_id = bpf_get_stackid(ctx, &stackmap, 0);
void* thread_state_current = (void*)0;
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user(&thread_state_current,
sizeof(thread_state_current),
(void*)(long)pidData->current_state_addr);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
struct task_struct* task = (struct task_struct*)bpf_get_current_task();
void* tls_base = (void*)task;
void* thread_state = pidData->use_tls ? get_thread_state(tls_base, pidData)
: thread_state_current;
event->thread_current = thread_state == thread_state_current;
if (pidData->use_tls) {
uint64_t pthread_created;
uint64_t pthread_self;
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user(&pthread_self, sizeof(pthread_self),
tls_base + 0x10);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user(&pthread_created,
sizeof(pthread_created),
thread_state +
pidData->offsets.PyThreadState_thread);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
event->pthread_match = pthread_created == pthread_self;
} else {
event->pthread_match = 1;
}
if (event->pthread_match || !pidData->use_tls) {
void* frame_ptr;
FrameData frame;
Symbol sym = {};
int cur_cpu = bpf_get_smp_processor_id();
bpf, testing: Convert prog tests to probe_read_{user, kernel}{, _str} helper Use probe read *_{kernel,user}{,_str}() helpers instead of bpf_probe_read() or bpf_probe_read_user_str() for program tests where appropriate. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/4a61d4b71ce3765587d8ef5cb93afa18515e5b3e.1572649915.git.daniel@iogearbox.net
2019-11-02 00:18:02 +01:00
bpf_probe_read_user(&frame_ptr,
sizeof(frame_ptr),
thread_state +
pidData->offsets.PyThreadState_frame);
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym);
if (symbol_counter == NULL)
return 0;
selftests/bpf: Measure bpf_loop verifier performance This patch tests bpf_loop in pyperf and strobemeta, and measures the verifier performance of replacing the traditional for loop with bpf_loop. The results are as follows: ~strobemeta~ Baseline verification time 6808200 usec stack depth 496 processed 554252 insns (limit 1000000) max_states_per_insn 16 total_states 15878 peak_states 13489 mark_read 3110 #192 verif_scale_strobemeta:OK (unrolled loop) Using bpf_loop verification time 31589 usec stack depth 96+400 processed 1513 insns (limit 1000000) max_states_per_insn 2 total_states 106 peak_states 106 mark_read 60 #193 verif_scale_strobemeta_bpf_loop:OK ~pyperf600~ Baseline verification time 29702486 usec stack depth 368 processed 626838 insns (limit 1000000) max_states_per_insn 7 total_states 30368 peak_states 30279 mark_read 748 #182 verif_scale_pyperf600:OK (unrolled loop) Using bpf_loop verification time 148488 usec stack depth 320+40 processed 10518 insns (limit 1000000) max_states_per_insn 10 total_states 705 peak_states 517 mark_read 38 #183 verif_scale_pyperf600_bpf_loop:OK Using the bpf_loop helper led to approximately a 99% decrease in the verification time and in the number of instructions. Signed-off-by: Joanne Koong <joannekoong@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20211130030622.4131246-4-joannekoong@fb.com
2021-11-29 19:06:21 -08:00
#ifdef USE_BPF_LOOP
struct process_frame_ctx ctx = {
.cur_cpu = cur_cpu,
.symbol_counter = symbol_counter,
.frame_ptr = frame_ptr,
.frame = &frame,
.pidData = pidData,
.sym = &sym,
.event = event,
};
bpf_loop(STACK_MAX_LEN, process_frame_callback, &ctx, 0);
if (ctx.done)
return 0;
#else
selftests/bpf: add bpf_for_each(), bpf_for(), and bpf_repeat() macros Add bpf_for_each(), bpf_for(), and bpf_repeat() macros that make writing open-coded iterator-based loops much more convenient and natural. These macros utilize cleanup attribute to ensure proper destruction of the iterator and thanks to that manage to provide the ergonomics that is very close to C language's for() construct. Typical loop would look like: int i; int arr[N]; bpf_for(i, 0, N) { /* verifier will know that i >= 0 && i < N, so could be used to * directly access array elements with no extra checks */ arr[i] = i; } bpf_repeat() is very similar, but it doesn't expose iteration number and is meant as a simple "repeat action N times" loop: bpf_repeat(N) { /* whatever, N times */ } Note that `break` and `continue` statements inside the {} block work as expected. bpf_for_each() is a generalization over any kind of BPF open-coded iterator allowing to use for-each-like approach instead of calling low-level bpf_iter_<type>_{new,next,destroy}() APIs explicitly. E.g.: struct cgroup *cg; bpf_for_each(cgroup, cg, some, input, args) { /* do something with each cg */ } would call (not-yet-implemented) bpf_iter_cgroup_{new,next,destroy}() functions to form a loop over cgroups, where `some, input, args` are passed verbatim into constructor as bpf_iter_cgroup_new(&it, some, input, args). As a first demonstration, add pyperf variant based on the bpf_for() loop. Also clean up a few tests that either included bpf_misc.h header unnecessarily from the user-space, which is unsupported, or included it before any common types are defined (and thus leading to unnecessary compilation warnings, potentially). Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20230308184121.1165081-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-08 10:41:18 -08:00
#if defined(USE_ITER)
/* no for loop, no unrolling */
#elif defined(NO_UNROLL)
bpf: Abstract loop unrolling pragmas in BPF selftests [Changes from V1: - Avoid conflict by rebasing with latest master.] Some BPF tests use loop unrolling compiler pragmas that are clang specific and not supported by GCC. These pragmas, along with their GCC equivalences are: #pragma clang loop unroll_count(N) #pragma GCC unroll N #pragma clang loop unroll(full) #pragma GCC unroll 65534 #pragma clang loop unroll(disable) #pragma GCC unroll 1 #pragma unroll [aka #pragma clang loop unroll(enable)] There is no GCC equivalence to this pragma. It enables unrolling on loops that the compiler would not ordinarily unroll even with -O2|-funroll-loops, but it is not equivalent to full unrolling either. This patch adds a new header progs/bpf_compiler.h that defines the following macros, which correspond to each pair of compiler-specific pragmas above: __pragma_loop_unroll_count(N) __pragma_loop_unroll_full __pragma_loop_no_unroll __pragma_loop_unroll The selftests using loop unrolling pragmas are then changed to include the header and use these macros in place of the explicit pragmas. Tested in bpf-next master. No regressions. Signed-off-by: Jose E. Marchesi <jose.marchesi@oracle.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yonghong.song@linux.dev> Link: https://lore.kernel.org/bpf/20240208203612.29611-1-jose.marchesi@oracle.com
2024-02-08 21:36:12 +01:00
__pragma_loop_no_unroll
selftests/bpf: add bpf_for_each(), bpf_for(), and bpf_repeat() macros Add bpf_for_each(), bpf_for(), and bpf_repeat() macros that make writing open-coded iterator-based loops much more convenient and natural. These macros utilize cleanup attribute to ensure proper destruction of the iterator and thanks to that manage to provide the ergonomics that is very close to C language's for() construct. Typical loop would look like: int i; int arr[N]; bpf_for(i, 0, N) { /* verifier will know that i >= 0 && i < N, so could be used to * directly access array elements with no extra checks */ arr[i] = i; } bpf_repeat() is very similar, but it doesn't expose iteration number and is meant as a simple "repeat action N times" loop: bpf_repeat(N) { /* whatever, N times */ } Note that `break` and `continue` statements inside the {} block work as expected. bpf_for_each() is a generalization over any kind of BPF open-coded iterator allowing to use for-each-like approach instead of calling low-level bpf_iter_<type>_{new,next,destroy}() APIs explicitly. E.g.: struct cgroup *cg; bpf_for_each(cgroup, cg, some, input, args) { /* do something with each cg */ } would call (not-yet-implemented) bpf_iter_cgroup_{new,next,destroy}() functions to form a loop over cgroups, where `some, input, args` are passed verbatim into constructor as bpf_iter_cgroup_new(&it, some, input, args). As a first demonstration, add pyperf variant based on the bpf_for() loop. Also clean up a few tests that either included bpf_misc.h header unnecessarily from the user-space, which is unsupported, or included it before any common types are defined (and thus leading to unnecessary compilation warnings, potentially). Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20230308184121.1165081-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-08 10:41:18 -08:00
#elif defined(UNROLL_COUNT)
bpf: Abstract loop unrolling pragmas in BPF selftests [Changes from V1: - Avoid conflict by rebasing with latest master.] Some BPF tests use loop unrolling compiler pragmas that are clang specific and not supported by GCC. These pragmas, along with their GCC equivalences are: #pragma clang loop unroll_count(N) #pragma GCC unroll N #pragma clang loop unroll(full) #pragma GCC unroll 65534 #pragma clang loop unroll(disable) #pragma GCC unroll 1 #pragma unroll [aka #pragma clang loop unroll(enable)] There is no GCC equivalence to this pragma. It enables unrolling on loops that the compiler would not ordinarily unroll even with -O2|-funroll-loops, but it is not equivalent to full unrolling either. This patch adds a new header progs/bpf_compiler.h that defines the following macros, which correspond to each pair of compiler-specific pragmas above: __pragma_loop_unroll_count(N) __pragma_loop_unroll_full __pragma_loop_no_unroll __pragma_loop_unroll The selftests using loop unrolling pragmas are then changed to include the header and use these macros in place of the explicit pragmas. Tested in bpf-next master. No regressions. Signed-off-by: Jose E. Marchesi <jose.marchesi@oracle.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yonghong.song@linux.dev> Link: https://lore.kernel.org/bpf/20240208203612.29611-1-jose.marchesi@oracle.com
2024-02-08 21:36:12 +01:00
__pragma_loop_unroll_count(UNROLL_COUNT)
selftests/bpf: Limit unroll_count for pyperf600 test LLVM commit [1] changed loop pragma behavior such that full loop unroll is always honored with user pragma. Previously, unroll count also depends on the unrolled code size. For pyperf600, without [1], the loop unroll count is 150. With [1], the loop unroll count is 600. The unroll count of 600 caused the program size close to 298k and this caused the following code is generated: 0: 7b 1a 00 ff 00 00 00 00 *(u64 *)(r10 - 256) = r1 ; uint64_t pid_tgid = bpf_get_current_pid_tgid(); 1: 85 00 00 00 0e 00 00 00 call 14 2: bf 06 00 00 00 00 00 00 r6 = r0 ; pid_t pid = (pid_t)(pid_tgid >> 32); 3: bf 61 00 00 00 00 00 00 r1 = r6 4: 77 01 00 00 20 00 00 00 r1 >>= 32 5: 63 1a fc ff 00 00 00 00 *(u32 *)(r10 - 4) = r1 6: bf a2 00 00 00 00 00 00 r2 = r10 7: 07 02 00 00 fc ff ff ff r2 += -4 ; PidData* pidData = bpf_map_lookup_elem(&pidmap, &pid); 8: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll 10: 85 00 00 00 01 00 00 00 call 1 11: bf 08 00 00 00 00 00 00 r8 = r0 ; if (!pidData) 12: 15 08 15 e8 00 00 00 00 if r8 == 0 goto -6123 <LBB0_27588+0xffffffffffdae100> Note that insn 12 has a branch offset -6123 which is clearly illegal and will be rejected by the verifier. The negative offset is due to the branch range is greater than INT16_MAX. This patch changed the unroll count to be 150 to avoid above branch target insn out-of-range issue. Also the llvm is enhanced ([2]) to assert if the branch target insn is out of INT16 range. [1] https://reviews.llvm.org/D119148 [2] https://reviews.llvm.org/D123877 Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20220419043230.2928530-1-yhs@fb.com
2022-04-18 21:32:30 -07:00
#else
bpf: Abstract loop unrolling pragmas in BPF selftests [Changes from V1: - Avoid conflict by rebasing with latest master.] Some BPF tests use loop unrolling compiler pragmas that are clang specific and not supported by GCC. These pragmas, along with their GCC equivalences are: #pragma clang loop unroll_count(N) #pragma GCC unroll N #pragma clang loop unroll(full) #pragma GCC unroll 65534 #pragma clang loop unroll(disable) #pragma GCC unroll 1 #pragma unroll [aka #pragma clang loop unroll(enable)] There is no GCC equivalence to this pragma. It enables unrolling on loops that the compiler would not ordinarily unroll even with -O2|-funroll-loops, but it is not equivalent to full unrolling either. This patch adds a new header progs/bpf_compiler.h that defines the following macros, which correspond to each pair of compiler-specific pragmas above: __pragma_loop_unroll_count(N) __pragma_loop_unroll_full __pragma_loop_no_unroll __pragma_loop_unroll The selftests using loop unrolling pragmas are then changed to include the header and use these macros in place of the explicit pragmas. Tested in bpf-next master. No regressions. Signed-off-by: Jose E. Marchesi <jose.marchesi@oracle.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yonghong.song@linux.dev> Link: https://lore.kernel.org/bpf/20240208203612.29611-1-jose.marchesi@oracle.com
2024-02-08 21:36:12 +01:00
__pragma_loop_unroll_full
selftests/bpf: Measure bpf_loop verifier performance This patch tests bpf_loop in pyperf and strobemeta, and measures the verifier performance of replacing the traditional for loop with bpf_loop. The results are as follows: ~strobemeta~ Baseline verification time 6808200 usec stack depth 496 processed 554252 insns (limit 1000000) max_states_per_insn 16 total_states 15878 peak_states 13489 mark_read 3110 #192 verif_scale_strobemeta:OK (unrolled loop) Using bpf_loop verification time 31589 usec stack depth 96+400 processed 1513 insns (limit 1000000) max_states_per_insn 2 total_states 106 peak_states 106 mark_read 60 #193 verif_scale_strobemeta_bpf_loop:OK ~pyperf600~ Baseline verification time 29702486 usec stack depth 368 processed 626838 insns (limit 1000000) max_states_per_insn 7 total_states 30368 peak_states 30279 mark_read 748 #182 verif_scale_pyperf600:OK (unrolled loop) Using bpf_loop verification time 148488 usec stack depth 320+40 processed 10518 insns (limit 1000000) max_states_per_insn 10 total_states 705 peak_states 517 mark_read 38 #183 verif_scale_pyperf600_bpf_loop:OK Using the bpf_loop helper led to approximately a 99% decrease in the verification time and in the number of instructions. Signed-off-by: Joanne Koong <joannekoong@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20211130030622.4131246-4-joannekoong@fb.com
2021-11-29 19:06:21 -08:00
#endif /* NO_UNROLL */
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
/* Unwind python stack */
selftests/bpf: add bpf_for_each(), bpf_for(), and bpf_repeat() macros Add bpf_for_each(), bpf_for(), and bpf_repeat() macros that make writing open-coded iterator-based loops much more convenient and natural. These macros utilize cleanup attribute to ensure proper destruction of the iterator and thanks to that manage to provide the ergonomics that is very close to C language's for() construct. Typical loop would look like: int i; int arr[N]; bpf_for(i, 0, N) { /* verifier will know that i >= 0 && i < N, so could be used to * directly access array elements with no extra checks */ arr[i] = i; } bpf_repeat() is very similar, but it doesn't expose iteration number and is meant as a simple "repeat action N times" loop: bpf_repeat(N) { /* whatever, N times */ } Note that `break` and `continue` statements inside the {} block work as expected. bpf_for_each() is a generalization over any kind of BPF open-coded iterator allowing to use for-each-like approach instead of calling low-level bpf_iter_<type>_{new,next,destroy}() APIs explicitly. E.g.: struct cgroup *cg; bpf_for_each(cgroup, cg, some, input, args) { /* do something with each cg */ } would call (not-yet-implemented) bpf_iter_cgroup_{new,next,destroy}() functions to form a loop over cgroups, where `some, input, args` are passed verbatim into constructor as bpf_iter_cgroup_new(&it, some, input, args). As a first demonstration, add pyperf variant based on the bpf_for() loop. Also clean up a few tests that either included bpf_misc.h header unnecessarily from the user-space, which is unsupported, or included it before any common types are defined (and thus leading to unnecessary compilation warnings, potentially). Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20230308184121.1165081-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-08 10:41:18 -08:00
#ifdef USE_ITER
int i;
bpf_for(i, 0, STACK_MAX_LEN) {
#else /* !USE_ITER */
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
for (int i = 0; i < STACK_MAX_LEN; ++i) {
selftests/bpf: add bpf_for_each(), bpf_for(), and bpf_repeat() macros Add bpf_for_each(), bpf_for(), and bpf_repeat() macros that make writing open-coded iterator-based loops much more convenient and natural. These macros utilize cleanup attribute to ensure proper destruction of the iterator and thanks to that manage to provide the ergonomics that is very close to C language's for() construct. Typical loop would look like: int i; int arr[N]; bpf_for(i, 0, N) { /* verifier will know that i >= 0 && i < N, so could be used to * directly access array elements with no extra checks */ arr[i] = i; } bpf_repeat() is very similar, but it doesn't expose iteration number and is meant as a simple "repeat action N times" loop: bpf_repeat(N) { /* whatever, N times */ } Note that `break` and `continue` statements inside the {} block work as expected. bpf_for_each() is a generalization over any kind of BPF open-coded iterator allowing to use for-each-like approach instead of calling low-level bpf_iter_<type>_{new,next,destroy}() APIs explicitly. E.g.: struct cgroup *cg; bpf_for_each(cgroup, cg, some, input, args) { /* do something with each cg */ } would call (not-yet-implemented) bpf_iter_cgroup_{new,next,destroy}() functions to form a loop over cgroups, where `some, input, args` are passed verbatim into constructor as bpf_iter_cgroup_new(&it, some, input, args). As a first demonstration, add pyperf variant based on the bpf_for() loop. Also clean up a few tests that either included bpf_misc.h header unnecessarily from the user-space, which is unsupported, or included it before any common types are defined (and thus leading to unnecessary compilation warnings, potentially). Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20230308184121.1165081-6-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-08 10:41:18 -08:00
#endif
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) {
int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu;
int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, &sym);
if (!symbol_id) {
bpf_map_update_elem(&symbolmap, &sym, &zero, 0);
symbol_id = bpf_map_lookup_elem(&symbolmap, &sym);
if (!symbol_id)
return 0;
}
if (*symbol_id == new_symbol_id)
(*symbol_counter)++;
event->stack[i] = *symbol_id;
event->stack_len = i + 1;
frame_ptr = frame.f_back;
}
}
selftests/bpf: Measure bpf_loop verifier performance This patch tests bpf_loop in pyperf and strobemeta, and measures the verifier performance of replacing the traditional for loop with bpf_loop. The results are as follows: ~strobemeta~ Baseline verification time 6808200 usec stack depth 496 processed 554252 insns (limit 1000000) max_states_per_insn 16 total_states 15878 peak_states 13489 mark_read 3110 #192 verif_scale_strobemeta:OK (unrolled loop) Using bpf_loop verification time 31589 usec stack depth 96+400 processed 1513 insns (limit 1000000) max_states_per_insn 2 total_states 106 peak_states 106 mark_read 60 #193 verif_scale_strobemeta_bpf_loop:OK ~pyperf600~ Baseline verification time 29702486 usec stack depth 368 processed 626838 insns (limit 1000000) max_states_per_insn 7 total_states 30368 peak_states 30279 mark_read 748 #182 verif_scale_pyperf600:OK (unrolled loop) Using bpf_loop verification time 148488 usec stack depth 320+40 processed 10518 insns (limit 1000000) max_states_per_insn 10 total_states 705 peak_states 517 mark_read 38 #183 verif_scale_pyperf600_bpf_loop:OK Using the bpf_loop helper led to approximately a 99% decrease in the verification time and in the number of instructions. Signed-off-by: Joanne Koong <joannekoong@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20211130030622.4131246-4-joannekoong@fb.com
2021-11-29 19:06:21 -08:00
#endif /* USE_BPF_LOOP */
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
event->stack_complete = frame_ptr == NULL;
} else {
event->stack_complete = 1;
}
Stats* stats = bpf_map_lookup_elem(&statsmap, &zero);
if (stats)
stats->success++;
event->has_meta = 0;
bpf_perf_event_output(ctx, &perfmap, 0, event, offsetof(Event, metadata));
return 0;
}
SEC("raw_tracepoint/kfree_skb")
selftests/bpf: Add a test for a large global function test results: pyperf50 with always_inlined the same function five times: processed 46378 insns pyperf50 with global function: processed 6102 insns Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200110064124.1760511-5-ast@kernel.org
2020-01-09 22:41:22 -08:00
int on_event(struct bpf_raw_tracepoint_args* ctx)
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
{
selftests/bpf: fix lots of silly mistakes pointed out by compiler Once we enable -Wall for BPF sources, compiler will complain about lots of unused variables, variables that are set but never read, etc. Fix all these issues first before enabling -Wall in Makefile. Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20230309054015.4068562-4-andrii@kernel.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-08 21:40:14 -08:00
int ret = 0;
selftests/bpf: add pyperf scale test Add a snippet of pyperf bpf program used to collect python stack traces as a scale test for the verifier. At 189 loop iterations llvm 9.0 starts ignoring '#pragma unroll' and generates partially unrolled loop instead. Hence use 50, 100, and 180 loop iterations to stress test. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-21 20:14:21 -07:00
ret |= __on_event(ctx);
ret |= __on_event(ctx);
ret |= __on_event(ctx);
ret |= __on_event(ctx);
ret |= __on_event(ctx);
return ret;
}
char _license[] SEC("license") = "GPL";
Reference in a new issue Copy permalink