kernel_optimize_test/tools/perf/examples/bpf/augmented_syscalls.c
Arnaldo Carvalho de Melo 7538d16397 perf augmented_syscalls: Avoid optimization to pass older BPF validators
See https://www.spinics.net/lists/netdev/msg480099.html for the whole
discussio, but to make the augmented_syscalls.c BPF program to get built
and loaded successfully in a greater range of kernels, add an extra
check.

Related patch:

  a60dd35d2e ("bpf: change bpf_perf_event_output arg5 type to ARG_CONST_SIZE_OR_ZERO")

That is in the kernel since v4.15, I couldn't figure why this is hitting
me with 4.17.17, but adding the workaround discussed there makes this
work with this fedora kernel and with 4.18.recent.

Before:

  # uname -a
  Linux seventh 4.17.17-100.fc27.x86_64 #1 SMP Mon Aug 20 15:53:11 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
  libbpf: load bpf program failed: Permission denied
  libbpf: -- BEGIN DUMP LOG ---
  libbpf:
  0: (bf) r6 = r1
  1: (b7) r1 = 0
  2: (7b) *(u64 *)(r10 -8) = r1
  3: (7b) *(u64 *)(r10 -16) = r1
  4: (7b) *(u64 *)(r10 -24) = r1
  5: (7b) *(u64 *)(r10 -32) = r1
  6: (7b) *(u64 *)(r10 -40) = r1
  7: (7b) *(u64 *)(r10 -48) = r1
  8: (7b) *(u64 *)(r10 -56) = r1
  9: (7b) *(u64 *)(r10 -64) = r1
  10: (7b) *(u64 *)(r10 -72) = r1
  11: (7b) *(u64 *)(r10 -80) = r1
  12: (7b) *(u64 *)(r10 -88) = r1
  13: (7b) *(u64 *)(r10 -96) = r1
  14: (7b) *(u64 *)(r10 -104) = r1
  15: (7b) *(u64 *)(r10 -112) = r1
  16: (7b) *(u64 *)(r10 -120) = r1
  17: (7b) *(u64 *)(r10 -128) = r1
  18: (7b) *(u64 *)(r10 -136) = r1
  19: (7b) *(u64 *)(r10 -144) = r1
  20: (7b) *(u64 *)(r10 -152) = r1
  21: (7b) *(u64 *)(r10 -160) = r1
  22: (7b) *(u64 *)(r10 -168) = r1
  23: (7b) *(u64 *)(r10 -176) = r1
  24: (7b) *(u64 *)(r10 -184) = r1
  25: (7b) *(u64 *)(r10 -192) = r1
  26: (7b) *(u64 *)(r10 -200) = r1
  27: (7b) *(u64 *)(r10 -208) = r1
  28: (7b) *(u64 *)(r10 -216) = r1
  29: (7b) *(u64 *)(r10 -224) = r1
  30: (7b) *(u64 *)(r10 -232) = r1
  31: (7b) *(u64 *)(r10 -240) = r1
  32: (7b) *(u64 *)(r10 -248) = r1
  33: (7b) *(u64 *)(r10 -256) = r1
  34: (7b) *(u64 *)(r10 -264) = r1
  35: (7b) *(u64 *)(r10 -272) = r1
  36: (7b) *(u64 *)(r10 -280) = r1
  37: (7b) *(u64 *)(r10 -288) = r1
  38: (7b) *(u64 *)(r10 -296) = r1
  39: (7b) *(u64 *)(r10 -304) = r1
  40: (7b) *(u64 *)(r10 -312) = r1
  41: (bf) r7 = r10
  42: (07) r7 += -312
  43: (bf) r1 = r7
  44: (b7) r2 = 48
  45: (bf) r3 = r6
  46: (85) call bpf_probe_read#4
  47: (79) r3 = *(u64 *)(r6 +24)
  48: (bf) r1 = r10
  49: (07) r1 += -256
  50: (b7) r8 = 256
  51: (b7) r2 = 256
  52: (85) call bpf_probe_read_str#45
  53: (bf) r1 = r0
  54: (67) r1 <<= 32
  55: (77) r1 >>= 32
  56: (bf) r5 = r0
  57: (07) r5 += 56
  58: (2d) if r8 > r1 goto pc+1
   R0=inv(id=0) R1=inv(id=0,umin_value=256,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R5=inv(id=0) R6=ctx(id=0,off=0,imm=0) R7=fp-312,call_-1 R8=inv256 R10=fp0,call_-1 fp-264=0
  59: (b7) r5 = 312
  60: (63) *(u32 *)(r10 -264) = r0
  61: (67) r5 <<= 32
  62: (77) r5 >>= 32
  63: (bf) r1 = r6
  64: (18) r2 = 0xffff8b9120cc8500
  66: (18) r3 = 0xffffffff
  68: (bf) r4 = r7
  69: (85) call bpf_perf_event_output#25
  70: (b7) r0 = 0
  71: (95) exit

  from 58 to 60: R0=inv(id=0) R1=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) R5=inv(id=0) R6=ctx(id=0,off=0,imm=0) R7=fp-312,call_-1 R8=inv256 R10=fp0,call_-1 fp-264=0
  60: (63) *(u32 *)(r10 -264) = r0
  61: (67) r5 <<= 32
  62: (77) r5 >>= 32
  63: (bf) r1 = r6
  64: (18) r2 = 0xffff8b9120cc8500
  66: (18) r3 = 0xffffffff
  68: (bf) r4 = r7
  69: (85) call bpf_perf_event_output#25
  R5 unbounded memory access, use 'var &= const' or 'if (var < const)'

  libbpf: -- END LOG --
  libbpf: failed to load program 'syscalls:sys_enter_openat'
  libbpf: failed to load object 'tools/perf/examples/bpf/augmented_syscalls.c'
  bpf: load objects failed: err=-4007: (Kernel verifier blocks program loading)
  event syntax error: 'tools/perf/examples/bpf/augmented_syscalls.c'
                       \___ Kernel verifier blocks program loading

After:

  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
     0.000 cat/29249 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
     0.008 cat/29249 syscalls:sys_exit_openat:0x3
     0.021 cat/29249 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
     0.025 cat/29249 syscalls:sys_exit_openat:0x3
     0.180 cat/29249 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
     0.185 cat/29249 syscalls:sys_exit_open:0x3
     0.242 cat/29249 openat(dfd: CWD, filename: /etc/passwd)
     0.245 cat/29249 syscalls:sys_exit_openat:0x3
  #

It also works with a more recent kernel:

  # uname -a
  Linux jouet 4.18.0-00014-g4e67b2a5df5d #6 SMP Thu Aug 30 17:34:17 -03 2018 x86_64 x86_64 x86_64 GNU/Linux
  # perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
     0.000 cat/26451 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
     0.020 cat/26451 syscalls:sys_exit_openat:0x3
     0.039 cat/26451 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
     0.044 cat/26451 syscalls:sys_exit_openat:0x3
     0.231 cat/26451 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
     0.238 cat/26451 syscalls:sys_exit_open:0x3
     0.278 cat/26451 openat(dfd: CWD, filename: /etc/passwd)
     0.282 cat/26451 syscalls:sys_exit_openat:0x3
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Gianluca Borello <g.borello@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-wkpsivs1a9afwldbul46btbv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-09-03 15:29:53 -03:00

174 lines
5.0 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Augment syscalls with the contents of the pointer arguments.
*
* Test it with:
*
* perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat /etc/passwd > /dev/null
*
* It'll catch some openat syscalls related to the dynamic linked and
* the last one should be the one for '/etc/passwd'.
*
* This matches what is marshalled into the raw_syscall:sys_enter payload
* expected by the 'perf trace' beautifiers, and can be used by them, that will
* check if perf_sample->raw_data is more than what is expected for each
* syscalls:sys_{enter,exit}_SYSCALL tracepoint, uing the extra data as the
* contents of pointer arguments.
*/
#include <stdio.h>
#include <linux/socket.h>
struct bpf_map SEC("maps") __augmented_syscalls__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = __NR_CPUS__,
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
long syscall_nr;
long ret;
};
struct augmented_filename {
unsigned int size;
int reserved;
char value[256];
};
#define augmented_filename_syscall(syscall) \
struct augmented_enter_##syscall##_args { \
struct syscall_enter_##syscall##_args args; \
struct augmented_filename filename; \
}; \
int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
{ \
struct augmented_enter_##syscall##_args augmented_args = { .filename.reserved = 0, }; \
unsigned int len = sizeof(augmented_args); \
probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, \
sizeof(augmented_args.filename.value), \
args->filename_ptr); \
if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { \
len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; \
len &= sizeof(augmented_args.filename.value) - 1; \
} \
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
&augmented_args, len); \
return 0; \
} \
int syscall_exit(syscall)(struct syscall_exit_args *args) \
{ \
return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \
}
struct syscall_enter_openat_args {
unsigned long long common_tp_fields;
long syscall_nr;
long dfd;
char *filename_ptr;
long flags;
long mode;
};
augmented_filename_syscall(openat);
struct syscall_enter_open_args {
unsigned long long common_tp_fields;
long syscall_nr;
char *filename_ptr;
long flags;
long mode;
};
augmented_filename_syscall(open);
struct syscall_enter_inotify_add_watch_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
char *filename_ptr;
long mask;
};
augmented_filename_syscall(inotify_add_watch);
struct statbuf;
struct syscall_enter_newstat_args {
unsigned long long common_tp_fields;
long syscall_nr;
char *filename_ptr;
struct stat *statbuf;
};
augmented_filename_syscall(newstat);
#ifndef _K_SS_MAXSIZE
#define _K_SS_MAXSIZE 128
#endif
#define augmented_sockaddr_syscall(syscall) \
struct augmented_enter_##syscall##_args { \
struct syscall_enter_##syscall##_args args; \
struct sockaddr_storage addr; \
}; \
int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args) \
{ \
struct augmented_enter_##syscall##_args augmented_args; \
unsigned long addrlen = sizeof(augmented_args.addr); \
probe_read(&augmented_args.args, sizeof(augmented_args.args), args); \
/* FIXME_CLANG_OPTIMIZATION_THAT_ACCESSES_USER_CONTROLLED_ADDRLEN_DESPITE_THIS_CHECK */ \
/* if (addrlen > augmented_args.args.addrlen) */ \
/* addrlen = augmented_args.args.addrlen; */ \
/* */ \
probe_read(&augmented_args.addr, addrlen, args->addr_ptr); \
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, \
&augmented_args, \
sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen); \
return 0; \
} \
int syscall_exit(syscall)(struct syscall_exit_args *args) \
{ \
return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ \
}
struct sockaddr;
struct syscall_enter_bind_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
struct sockaddr *addr_ptr;
unsigned long addrlen;
};
augmented_sockaddr_syscall(bind);
struct syscall_enter_connect_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
struct sockaddr *addr_ptr;
unsigned long addrlen;
};
augmented_sockaddr_syscall(connect);
struct syscall_enter_sendto_args {
unsigned long long common_tp_fields;
long syscall_nr;
long fd;
void *buff;
long len;
unsigned long flags;
struct sockaddr *addr_ptr;
long addr_len;
};
augmented_sockaddr_syscall(sendto);
license(GPL);