[PATCH 0/3] KCOV function entry/exit records

[Jann Horn <jannh@google.com>]

This series adds a KCOV feature that userspace can use to keep track of
the current call stack. When userspace enables the new mode
KCOV_TRACE_PC_EXT, collected instruction addresses are tagged with one
of three types:

 - function entry
 - non-entry basic block
 - function exit

This requires corresponding LLVM support; an LLVM patch implementing
this feature has been uploaded for review at
<https://github.com/llvm/llvm-project/pull/185972>, but hasn't landed yet.

A simple example of how to use KCOV_TRACE_PC_EXT:
```
user@vm:~/kcov/u$ cat kcov-u.c

  typeof(x) __res = (x);      \
  if (__res == (typeof(x))-1) \
    err(1, "SYSCHK(" #x ")"); \
  __res;                      \
})

static void indent(int depth) {
  for (int i=0; i<depth; i++)
    printf("  ");
}

int main(void) {
  int fd = SYSCHK(open("/sys/kernel/debug/kcov", O_RDWR));
  SYSCHK(ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE));
  unsigned long *cover = (unsigned long*)SYSCHK(
      mmap(NULL, COVER_SIZE * sizeof(unsigned long), PROT_READ | PROT_WRITE,
           MAP_SHARED, fd, 0));
  SYSCHK(ioctl(fd, KCOV_ENABLE, KCOV_TRACE_PC_EXT));
  usleep(1000); // fault in stuff
  __atomic_store_n(&cover[0], 0, __ATOMIC_RELAXED); // start recording
  usleep(1000);
  unsigned long cover_num = __atomic_load_n(&cover[0], __ATOMIC_RELAXED); // end

  int depth = 0;
  for (unsigned long i = 0; i < cover_num; i++) {
    unsigned long record = cover[1+i];
    unsigned long pc = record | ~KCOV_RECORD_IP_MASK;
    switch (record & KCOV_RECORDFLAG_TYPEMASK) {
    case KCOV_RECORDFLAG_TYPE_NORMAL:
      indent(depth);
      printf("BB    0x%lx\n", pc);
      break;
    case KCOV_RECORDFLAG_TYPE_ENTRY:
      indent(depth);
      printf("ENTER 0x%lx\n", pc);
      depth++;
      break;
    case KCOV_RECORDFLAG_TYPE_EXIT:
      if (depth == 0)
        errx(1, "exit at depth 0");
      depth--;
      indent(depth);
      printf("EXIT  0x%lx\n", pc);
      break;
    default: errx(1, "unknown record type in 0x%016lx", record);
    }
  }
}
user@vm:~/kcov/u$ cat symbolize.py

import sys
syms = []
with open('/proc/kallsyms') as f:
  for line in f:
    parts = line.strip().split(' ')
    if len(parts) < 3:
      continue
    syms.append((int(parts[0], 16), parts[2]))

for line in sys.stdin:
  parts = line.rstrip().split('0x')
  if len(parts) != 2:
    continue
  record_pc = int(parts[1], 16)
  for i in range(0, len(syms)-1):
    if syms[i+1][0] > record_pc:
      print(parts[0] + syms[i][1] + '+' + hex(record_pc - syms[i][0]))
      break
user@vm:~/kcov/u$ gcc -o kcov-u kcov-u.c -Wall
user@vm:~/kcov/u$ sudo ./kcov-u | sudo ./symbolize.py
ENTER __audit_syscall_entry+0x2c
  BB    __audit_syscall_entry+0xa4
  BB    __audit_syscall_entry+0xd2
  BB    __audit_syscall_entry+0x1ab
  ENTER ktime_get_coarse_real_ts64+0x1a
    BB    ktime_get_coarse_real_ts64+0x3f
    BB    ktime_get_coarse_real_ts64+0x96
  EXIT  ktime_get_coarse_real_ts64+0x9b
EXIT  __audit_syscall_entry+0x12b
ENTER __x64_sys_clock_nanosleep+0x18
  ENTER __se_sys_clock_nanosleep+0x33
    BB    __se_sys_clock_nanosleep+0x10e
    ENTER get_timespec64+0x29
      ENTER _copy_from_user+0x17
        BB    _copy_from_user+0x5d
      EXIT  _copy_from_user+0x62
      BB    get_timespec64+0xaf
    EXIT  get_timespec64+0xd5
    BB    __se_sys_clock_nanosleep+0x1c0
    ENTER common_nsleep+0x1f
      ENTER hrtimer_nanosleep+0x2f
        ENTER hrtimer_setup_sleeper_on_stack+0x20
          BB    hrtimer_setup_sleeper_on_stack+0x2a
          BB    hrtimer_setup_sleeper_on_stack+0x7e
        EXIT  hrtimer_setup_sleeper_on_stack+0x14c
        ENTER do_nanosleep+0x2d
          BB    do_nanosleep+0x3b
          ENTER hrtimer_start_range_ns+0x28
            BB    hrtimer_start_range_ns+0x67
            ENTER remove_hrtimer+0x22
              BB    remove_hrtimer+0x4b
            EXIT  remove_hrtimer+0x1ea
            BB    hrtimer_start_range_ns+0x173
            ENTER __hrtimer_cb_get_time+0x11
              BB    __hrtimer_cb_get_time+0x32
              ENTER ktime_get+0x17
                BB    ktime_get+0x33
                BB    ktime_get+0x58
                ENTER kvm_clock_get_cycles+0xc
                  BB    kvm_clock_get_cycles+0x48
                EXIT  kvm_clock_get_cycles+0x4d
                BB    ktime_get+0xb7
                BB    ktime_get+0x149
              EXIT  ktime_get+0x151
            EXIT  __hrtimer_cb_get_time+0x84
            BB    hrtimer_start_range_ns+0x3bc
            BB    hrtimer_start_range_ns+0x5a4
            ENTER enqueue_hrtimer+0x20
              BB    enqueue_hrtimer+0x2a
              BB    enqueue_hrtimer+0x5b
              ENTER timerqueue_add+0x1c
                BB    timerqueue_add+0x41
                BB    timerqueue_add+0xb2
                BB    timerqueue_add+0xb2
                BB    timerqueue_add+0xf9
              EXIT  timerqueue_add+0x150
            EXIT  enqueue_hrtimer+0xaf
            BB    hrtimer_start_range_ns+0x714
            ENTER hrtimer_reprogram+0x1b
              BB    hrtimer_reprogram+0x65
              BB    hrtimer_reprogram+0x13a
              BB    hrtimer_reprogram+0x1dc
              ENTER tick_program_event+0x25
                BB    tick_program_event+0x65
                ENTER clockevents_program_event+0x20
                  BB    clockevents_program_event+0x7e
                  ENTER ktime_get+0x17
                    BB    ktime_get+0x33
                    BB    ktime_get+0x58
                    ENTER kvm_clock_get_cycles+0xc
                      BB    kvm_clock_get_cycles+0x48
                    EXIT  kvm_clock_get_cycles+0x4d
                    BB    ktime_get+0xb7
                    BB    ktime_get+0x149
                  EXIT  ktime_get+0x151
                  BB    clockevents_program_event+0x219
                EXIT  clockevents_program_event+0x22b
              EXIT  tick_program_event+0x89
            EXIT  hrtimer_reprogram+0x211
          EXIT  hrtimer_start_range_ns+0x74d
          BB    do_nanosleep+0x9c
          ENTER sched_clock+0xc
            BB    sched_clock+0x40
          EXIT  sched_clock+0x45
          ENTER arch_scale_cpu_capacity+0x13
            BB    arch_scale_cpu_capacity+0x1a
          EXIT  arch_scale_cpu_capacity+0x24
          ENTER __cgroup_account_cputime+0x1b
            ENTER css_rstat_updated+0x2c
              BB    css_rstat_updated+0x77
              BB    css_rstat_updated+0xbe
            EXIT  css_rstat_updated+0x1bc
            BB    __cgroup_account_cputime+0x81
          EXIT  __cgroup_account_cputime+0x86
          ENTER sched_clock+0xc
            BB    sched_clock+0x40
          EXIT  sched_clock+0x45
          ENTER sched_clock+0xc
            BB    sched_clock+0x40
          EXIT  sched_clock+0x45
          ENTER __msecs_to_jiffies+0x13
            BB    __msecs_to_jiffies+0x25
          EXIT  __msecs_to_jiffies+0x4c
          ENTER prandom_u32_state+0x15
          EXIT  prandom_u32_state+0xbe
          ENTER hrtimer_try_to_cancel+0x1e
            BB    hrtimer_try_to_cancel+0x6a
            BB    hrtimer_try_to_cancel+0x1da
          EXIT  hrtimer_try_to_cancel+0x1be
          BB    do_nanosleep+0xbf
          BB    do_nanosleep+0x166
          BB    do_nanosleep+0x177
          BB    do_nanosleep+0x275
        EXIT  do_nanosleep+0x2d5
        BB    hrtimer_nanosleep+0x182
      EXIT  hrtimer_nanosleep+0x194
    EXIT  common_nsleep+0x77
  EXIT  __se_sys_clock_nanosleep+0x15d
EXIT  __x64_sys_clock_nanosleep+0x62
ENTER __audit_syscall_exit+0x1d
  BB    __audit_syscall_exit+0x5c
  ENTER audit_reset_context+0x1e
    BB    audit_reset_context+0x52
  EXIT  audit_reset_context+0x5f6
EXIT  __audit_syscall_exit+0x168
ENTER fpregs_assert_state_consistent+0x11
  BB    fpregs_assert_state_consistent+0x48
  BB    fpregs_assert_state_consistent+0xa6
EXIT  fpregs_assert_state_consistent+0xcc
ENTER switch_fpu_return+0xe
  ENTER fpregs_restore_userregs+0x12
    BB    fpregs_restore_userregs+0x4c
    BB    fpregs_restore_userregs+0xb8
  EXIT  fpregs_restore_userregs+0x107
EXIT  switch_fpu_return+0x18
```

Signed-off-by: Jann Horn <jannh@google.com>
---
Jann Horn (3):
      sched: Ensure matching stack state for kcov disable/enable on switch
      kcov: wire up compiler instrumentation for CONFIG_KCOV_EXT_RECORDS
      kcov: introduce extended PC coverage collection mode

 include/linux/kcov.h      |  2 ++
 include/linux/sched.h     |  6 ++--
 include/uapi/linux/kcov.h | 12 ++++++++
 kernel/kcov.c             | 76 +++++++++++++++++++++++++++++++++++++++--------
 kernel/sched/core.c       | 13 ++++++--
 lib/Kconfig.debug         | 14 +++++++++
 scripts/Makefile.kcov     |  2 ++
 tools/objtool/check.c     |  2 ++
 8 files changed, 110 insertions(+), 17 deletions(-)
---
base-commit: b29fb8829bff243512bb8c8908fd39406f9fd4c3
change-id: 20260311-kcov-extrecord-6e0d9a2b0a8c

--  
Jann Horn <jannh@google.com>