Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 20 7月, 2022 3 次提交
    • A
      libbpf: add ksyscall/kretsyscall sections support for syscall kprobes · 708ac5be
      由 Andrii Nakryiko 提交于 
      Add SEC("ksyscall")/SEC("ksyscall/<syscall_name>") and corresponding
kretsyscall variants (for return kprobes) to allow users to kprobe
syscall functions in kernel. These special sections allow to ignore
complexities and differences between kernel versions and host
architectures when it comes to syscall wrapper and corresponding
__<arch>_sys_<syscall> vs __se_sys_<syscall> differences, depending on
whether host kernel has CONFIG_ARCH_HAS_SYSCALL_WRAPPER (though libbpf
itself doesn't rely on /proc/config.gz for detecting this, see
BPF_KSYSCALL patch for how it's done internally).

Combined with the use of BPF_KSYSCALL() macro, this allows to just
specify intended syscall name and expected input arguments and leave
dealing with all the variations to libbpf.

In addition to SEC("ksyscall+") and SEC("kretsyscall+") add
bpf_program__attach_ksyscall() API which allows to specify syscall name
at runtime and provide associated BPF cookie value.

At the moment SEC("ksyscall") and bpf_program__attach_ksyscall() do not
handle all the calling convention quirks for mmap(), clone() and compat
syscalls. It also only attaches to "native" syscall interfaces. If host
system supports compat syscalls or defines 32-bit syscalls in 64-bit
kernel, such syscall interfaces won't be attached to by libbpf.

These limitations may or may not change in the future. Therefore it is
recommended to use SEC("kprobe") for these syscalls or if working with
compat and 32-bit interfaces is required.
Tested-by: NAlan Maguire <alan.maguire@oracle.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220714070755.3235561-5-andrii@kernel.orgSigned-off-by: NAlexei Starovoitov <ast@kernel.org>
      708ac5be
    • A
      libbpf: improve BPF_KPROBE_SYSCALL macro and rename it to BPF_KSYSCALL · 6f5d467d
      由 Andrii Nakryiko 提交于 
      Improve BPF_KPROBE_SYSCALL (and rename it to shorter BPF_KSYSCALL to
match libbpf's SEC("ksyscall") section name, added in next patch) to use
__kconfig variable to determine how to properly fetch syscall arguments.

Instead of relying on hard-coded knowledge of whether kernel's
architecture uses syscall wrapper or not (which only reflects the latest
kernel versions, but is not necessarily true for older kernels and won't
necessarily hold for later kernel versions on some particular host
architecture), determine this at runtime by attempting to create
perf_event (with fallback to kprobe event creation through tracefs on
legacy kernels, just like kprobe attachment code is doing) for kernel
function that would correspond to bpf() syscall on a system that has
CONFIG_ARCH_HAS_SYSCALL_WRAPPER set (e.g., for x86-64 it would try
'__x64_sys_bpf').

If host kernel uses syscall wrapper, syscall kernel function's first
argument is a pointer to struct pt_regs that then contains syscall
arguments. In such case we need to use bpf_probe_read_kernel() to fetch
actual arguments (which we do through BPF_CORE_READ() macro) from inner
pt_regs.

But if the kernel doesn't use syscall wrapper approach, input
arguments can be read from struct pt_regs directly with no probe reading.

All this feature detection is done without requiring /proc/config.gz
existence and parsing, and BPF-side helper code uses newly added
LINUX_HAS_SYSCALL_WRAPPER virtual __kconfig extern to keep in sync with
user-side feature detection of libbpf.

BPF_KSYSCALL() macro can be used both with SEC("kprobe") programs that
define syscall function explicitly (e.g., SEC("kprobe/__x64_sys_bpf"))
and SEC("ksyscall") program added in the next patch (which are the same
kprobe program with added benefit of libbpf determining correct kernel
function name automatically).

Kretprobe and kretsyscall (added in next patch) programs don't need
BPF_KSYSCALL as they don't provide access to input arguments. Normal
BPF_KRETPROBE is completely sufficient and is recommended.
Tested-by: NAlan Maguire <alan.maguire@oracle.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220714070755.3235561-4-andrii@kernel.orgSigned-off-by: NAlexei Starovoitov <ast@kernel.org>
      6f5d467d
    • A
      libbpf: generalize virtual __kconfig externs and use it for USDT · 55d00c37
      由 Andrii Nakryiko 提交于 
      Libbpf supports single virtual __kconfig extern currently: LINUX_KERNEL_VERSION.
LINUX_KERNEL_VERSION isn't coming from /proc/kconfig.gz and is intead
customly filled out by libbpf.

This patch generalizes this approach to support more such virtual
__kconfig externs. One such extern added in this patch is
LINUX_HAS_BPF_COOKIE which is used for BPF-side USDT supporting code in
usdt.bpf.h instead of using CO-RE-based enum detection approach for
detecting bpf_get_attach_cookie() BPF helper. This allows to remove
otherwise not needed CO-RE dependency and keeps user-space and BPF-side
parts of libbpf's USDT support strictly in sync in terms of their
feature detection.

We'll use similar approach for syscall wrapper detection for
BPF_KSYSCALL() BPF-side macro in follow up patch.

Generally, currently libbpf reserves CONFIG_ prefix for Kconfig values
and LINUX_ for virtual libbpf-backed externs. In the future we might
extend the set of prefixes that are supported. This can be done without
any breaking changes, as currently any __kconfig extern with
unrecognized name is rejected.

For LINUX_xxx externs we support the normal "weak rule": if libbpf
doesn't recognize given LINUX_xxx extern but such extern is marked as
__weak, it is not rejected and defaults to zero.  This follows
CONFIG_xxx handling logic and will allow BPF applications to
opportunistically use newer libbpf virtual externs without breaking on
older libbpf versions unnecessarily.
Tested-by: NAlan Maguire <alan.maguire@oracle.com>
Reviewed-by: NAlan Maguire <alan.maguire@oracle.com>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20220714070755.3235561-2-andrii@kernel.orgSigned-off-by: NAlexei Starovoitov <ast@kernel.org>
      55d00c37
  3. 16 7月, 2022 1 次提交
    • J
      libbpf: perfbuf: Add API to get the ring buffer · 9ff5efde
      由 Jon Doron 提交于 
      Add support for writing a custom event reader, by exposing the ring
buffer.

With the new API perf_buffer__buffer() you will get access to the
raw mmaped()'ed per-cpu underlying memory of the ring buffer.

This region contains both the perf buffer data and header
(struct perf_event_mmap_page), which manages the ring buffer
state (head/tail positions, when accessing the head/tail position
it's important to take into consideration SMP).
With this type of low level access one can implement different types of
consumers here are few simple examples where this API helps with:

1. perf_event_read_simple is allocating using malloc, perhaps you want
   to handle the wrap-around in some other way.
2. Since perf buf is per-cpu then the order of the events is not
   guarnteed, for example:
   Given 3 events where each event has a timestamp t0 < t1 < t2,
   and the events are spread on more than 1 CPU, then we can end
   up with the following state in the ring buf:
   CPU[0] => [t0, t2]
   CPU[1] => [t1]
   When you consume the events from CPU[0], you could know there is
   a t1 missing, (assuming there are no drops, and your event data
   contains a sequential index).
   So now one can simply do the following, for CPU[0], you can store
   the address of t0 and t2 in an array (without moving the tail, so
   there data is not perished) then move on the CPU[1] and set the
   address of t1 in the same array.
   So you end up with something like:
   void **arr[] = [&t0, &t1, &t2], now you can consume it orderely
   and move the tails as you process in order.
3. Assuming there are multiple CPUs and we want to start draining the
   messages from them, then we can "pick" with which one to start with
   according to the remaining free space in the ring buffer.
Signed-off-by: NJon Doron <jond@wiz.io>
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220715181122.149224-1-arilou@gmail.com
      9ff5efde
  5. 14 7月, 2022 2 次提交
  7. 06 7月, 2022 4 次提交
  9. 30 6月, 2022 1 次提交
  11. 29 6月, 2022 9 次提交
  13. 25 6月, 2022 1 次提交
  15. 17 6月, 2022 1 次提交
  17. 14 6月, 2022 1 次提交
  19. 09 6月, 2022 1 次提交
  21. 08 6月, 2022 2 次提交
  23. 04 6月, 2022 1 次提交
  25. 03 6月, 2022 4 次提交
  27. 24 5月, 2022 1 次提交
  29. 17 5月, 2022 1 次提交
  31. 13 5月, 2022 1 次提交
    • A
      libbpf: Add safer high-level wrappers for map operations · 737d0646
      由 Andrii Nakryiko 提交于 
      Add high-level API wrappers for most common and typical BPF map
operations that works directly on instances of struct bpf_map * (so
you don't have to call bpf_map__fd()) and validate key/value size
expectations.

These helpers require users to specify key (and value, where
appropriate) sizes when performing lookup/update/delete/etc. This forces
user to actually think and validate (for themselves) those. This is
a good thing as user is expected by kernel to implicitly provide correct
key/value buffer sizes and kernel will just read/write necessary amount
of data. If it so happens that user doesn't set up buffers correctly
(which bit people for per-CPU maps especially) kernel either randomly
overwrites stack data or return -EFAULT, depending on user's luck and
circumstances. These high-level APIs are meant to prevent such
unpleasant and hard to debug bugs.

This patch also adds bpf_map_delete_elem_flags() low-level API and
requires passing flags to bpf_map__delete_elem() API for consistency
across all similar APIs, even though currently kernel doesn't expect
any extra flags for BPF_MAP_DELETE_ELEM operation.

List of map operations that get these high-level APIs:

  - bpf_map_lookup_elem;
  - bpf_map_update_elem;
  - bpf_map_delete_elem;
  - bpf_map_lookup_and_delete_elem;
  - bpf_map_get_next_key.
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220512220713.2617964-1-andrii@kernel.org
      737d0646
  33. 11 5月, 2022 3 次提交
  35. 09 5月, 2022 1 次提交
  37. 29 4月, 2022 2 次提交
    • A
      libbpf: Allow to opt-out from creating BPF maps · ec41817b
      由 Andrii Nakryiko 提交于 
      Add bpf_map__set_autocreate() API that allows user to opt-out from
libbpf automatically creating BPF map during BPF object load.

This is a useful feature when building CO-RE-enabled BPF application
that takes advantage of some new-ish BPF map type (e.g., socket-local
storage) if kernel supports it, but otherwise uses some alternative way
(e.g., extra HASH map). In such case, being able to disable the creation
of a map that kernel doesn't support allows to successfully create and
load BPF object file with all its other maps and programs.

It's still up to user to make sure that no "live" code in any of their BPF
programs are referencing such map instance, which can be achieved by
guarding such code with CO-RE relocation check or by using .rodata
global variables.

If user fails to properly guard such code to turn it into "dead code",
libbpf will helpfully post-process BPF verifier log and will provide
more meaningful error and map name that needs to be guarded properly. As
such, instead of:

  ; value = bpf_map_lookup_elem(&missing_map, &zero);
  4: (85) call unknown#2001000000
  invalid func unknown#2001000000

... user will see:

  ; value = bpf_map_lookup_elem(&missing_map, &zero);
  4: <invalid BPF map reference>
  BPF map 'missing_map' is referenced but wasn't created
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220428041523.4089853-4-andrii@kernel.org
      ec41817b
    • A
      libbpf: Use libbpf_mem_ensure() when allocating new map · 69721203
      由 Andrii Nakryiko 提交于 
      Reuse libbpf_mem_ensure() when adding a new map to the list of maps
inside bpf_object. It takes care of proper resizing and reallocating of
map array and zeroing out newly allocated memory.
Signed-off-by: NAndrii Nakryiko <andrii@kernel.org>
Signed-off-by: NAlexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20220428041523.4089853-3-andrii@kernel.org
      69721203