From: Eduard Zingerman <eddyz87@gmail.com>
To: bpf@vger.kernel.org, ast@kernel.org
Cc: andrii@kernel.org, daniel@iogearbox.net, martin.lau@linux.dev,
kernel-team@fb.com, yonghong.song@linux.dev,
jose.marchesi@oracle.com, Eduard Zingerman <eddyz87@gmail.com>
Subject: [RFC bpf-next v1 0/8] no_caller_saved_registers attribute for helper calls
Date: Sat, 29 Jun 2024 02:47:25 -0700 [thread overview]
Message-ID: <20240629094733.3863850-1-eddyz87@gmail.com> (raw)
This RFC seeks to allow using no_caller_saved_registers gcc/clang
attribute with some BPF helper functions (and kfuncs in the future).
As documented in [1], this attribute means that function scratches
only some of the caller saved registers defined by ABI.
For BPF the set of such registers could be defined as follows:
- R0 is scratched only if function is non-void;
- R1-R5 are scratched only if corresponding parameter type is defined
in the function prototype.
The goal of the RFC is to implement no_caller_saved_registers
(nocsr for short) in a backwards compatible manner:
- for kernels that support the feature, gain some performance boost
from better register allocation;
- for kernels that don't support the feature, allow programs execution
with minor performance losses.
To achieve this, use a scheme suggested by Alexei Starovoitov:
- for nocsr calls clang allocates registers as-if relevant r0-r5
registers are not scratched by the call;
- as a post-processing step, clang visits each nocsr call and adds
spill/fill for every live r0-r5;
- stack offsets used for spills/fills are allocated as minimal
stack offsets in whole function and are not used for any other
purposes;
- when kernel loads a program, it looks for such patterns
(nocsr function surrounded by spills/fills) and checks if
spill/fill stack offsets are used exclusively in nocsr patterns;
- if so, and if current JIT inlines the call to the nocsr function
(e.g. a helper call), kernel removes unnecessary spill/fill pairs;
- when old kernel loads a program, presence of spill/fill pairs
keeps BPF program valid, albeit slightly less efficient.
Corresponding clang/llvm changes are available in [2].
The patch-set uses bpf_get_smp_processor_id() function as a canary,
making it the first helper with nocsr attribute.
For example, consider the following program:
#define __no_csr __attribute__((no_caller_saved_registers))
#define SEC(name) __attribute__((section(name), used))
#define bpf_printk(fmt, ...) bpf_trace_printk((fmt), sizeof(fmt), __VA_ARGS__)
typedef unsigned int __u32;
static long (* const bpf_trace_printk)(const char *fmt, __u32 fmt_size, ...) = (void *) 6;
static __u32 (*const bpf_get_smp_processor_id)(void) __no_csr = (void *)8;
SEC("raw_tp")
int test(void *ctx)
{
__u32 task = bpf_get_smp_processor_id();
bpf_printk("ctx=%p, smp=%d", ctx, task);
return 0;
}
char _license[] SEC("license") = "GPL";
Compiled (using [2]) as follows:
$ clang --target=bpf -O2 -g -c -o nocsr.bpf.o nocsr.bpf.c
$ llvm-objdump --no-show-raw-insn -Sd nocsr.bpf.o
...
3rd parameter for printk call removable spill/fill pair
.--- 0: r3 = r1 |
; | __u32 task = bpf_get_smp_processor_id(); |
| 1: *(u64 *)(r10 - 0x8) = r3 <----------|
| 2: call 0x8 |
| 3: r3 = *(u64 *)(r10 - 0x8) <----------'
; | bpf_printk("ctx=%p, smp=%d", ctx, task);
| 4: r1 = 0x0 ll
| 6: r2 = 0xf
| 7: r4 = r0
'--> 8: call 0x6
; return 0;
9: r0 = 0x0
10: exit
Here is how the program looks after verifier processing:
# bpftool prog load ./nocsr.bpf.o /sys/fs/bpf/nocsr-test
# bpftool prog dump xlated pinned /sys/fs/bpf/nocsr-test
int test(void * ctx):
; int test(void *ctx)
0: (bf) r3 = r1 <--------- 3rd printk parameter
; __u32 task = bpf_get_smp_processor_id();
1: (b4) w0 = 197132 <--------- inlined helper call,
2: (bf) r0 = r0 <--------- spill/fill pair removed
3: (61) r0 = *(u32 *)(r0 +0) <---------
; bpf_printk("ctx=%p, smp=%d", ctx, task);
4: (18) r1 = map[id:13][0]+0
6: (b7) r2 = 15
7: (bf) r4 = r0
8: (85) call bpf_trace_printk#-125920
; return 0;
9: (b7) r0 = 0
10: (95) exit
[1] https://clang.llvm.org/docs/AttributeReference.html#no-caller-saved-registers
[2] https://github.com/eddyz87/llvm-project/tree/bpf-no-caller-saved-registers
Eduard Zingerman (8):
bpf: add a get_helper_proto() utility function
bpf: no_caller_saved_registers attribute for helper calls
bpf, x86: no_caller_saved_registers for bpf_get_smp_processor_id()
selftests/bpf: extract utility function for BPF disassembly
selftests/bpf: no need to track next_match_pos in struct test_loader
selftests/bpf: extract test_loader->expect_msgs as a data structure
selftests/bpf: allow checking xlated programs in verifier_* tests
selftests/bpf: test no_caller_saved_registers spill/fill removal
include/linux/bpf.h | 6 +
include/linux/bpf_verifier.h | 9 +
kernel/bpf/helpers.c | 1 +
kernel/bpf/verifier.c | 346 +++++++++++++-
tools/testing/selftests/bpf/Makefile | 1 +
tools/testing/selftests/bpf/disasm_helpers.c | 50 ++
tools/testing/selftests/bpf/disasm_helpers.h | 12 +
.../selftests/bpf/prog_tests/ctx_rewrite.c | 71 +--
.../selftests/bpf/prog_tests/verifier.c | 7 +
tools/testing/selftests/bpf/progs/bpf_misc.h | 6 +
.../selftests/bpf/progs/verifier_nocsr.c | 437 ++++++++++++++++++
tools/testing/selftests/bpf/test_loader.c | 170 +++++--
tools/testing/selftests/bpf/test_progs.h | 1 -
tools/testing/selftests/bpf/testing_helpers.c | 1 +
14 files changed, 986 insertions(+), 132 deletions(-)
create mode 100644 tools/testing/selftests/bpf/disasm_helpers.c
create mode 100644 tools/testing/selftests/bpf/disasm_helpers.h
create mode 100644 tools/testing/selftests/bpf/progs/verifier_nocsr.c
--
2.45.2
next reply other threads:[~2024-06-29 9:48 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-29 9:47 Eduard Zingerman [this message]
2024-06-29 9:47 ` [RFC bpf-next v1 1/8] bpf: add a get_helper_proto() utility function Eduard Zingerman
2024-07-02 0:41 ` Andrii Nakryiko
2024-07-02 20:07 ` Eduard Zingerman
2024-06-29 9:47 ` [RFC bpf-next v1 2/8] bpf: no_caller_saved_registers attribute for helper calls Eduard Zingerman
2024-07-01 19:01 ` Eduard Zingerman
2024-07-02 0:41 ` Andrii Nakryiko
2024-07-02 20:38 ` Eduard Zingerman
2024-07-02 21:09 ` Andrii Nakryiko
2024-07-02 21:19 ` Eduard Zingerman
2024-07-02 21:22 ` Andrii Nakryiko
2024-07-03 11:57 ` Puranjay Mohan
2024-07-03 16:13 ` Eduard Zingerman
2024-07-04 10:55 ` Puranjay Mohan
2024-06-29 9:47 ` [RFC bpf-next v1 3/8] bpf, x86: no_caller_saved_registers for bpf_get_smp_processor_id() Eduard Zingerman
2024-07-02 0:41 ` Andrii Nakryiko
2024-07-02 20:43 ` Eduard Zingerman
2024-07-02 21:11 ` Andrii Nakryiko
2024-07-02 21:25 ` Eduard Zingerman
2024-07-03 11:27 ` Puranjay Mohan
2024-07-03 23:14 ` Eduard Zingerman
2024-07-04 11:19 ` Puranjay Mohan
2024-07-04 16:39 ` Eduard Zingerman
2024-07-04 17:00 ` Eduard Zingerman
2024-07-04 17:24 ` Puranjay Mohan
2024-07-04 17:39 ` Eduard Zingerman
2024-06-29 9:47 ` [RFC bpf-next v1 4/8] selftests/bpf: extract utility function for BPF disassembly Eduard Zingerman
2024-07-02 0:41 ` Andrii Nakryiko
2024-07-02 20:59 ` Eduard Zingerman
2024-07-02 21:16 ` Andrii Nakryiko
2024-07-02 21:23 ` Eduard Zingerman
2024-06-29 9:47 ` [RFC bpf-next v1 5/8] selftests/bpf: no need to track next_match_pos in struct test_loader Eduard Zingerman
2024-07-02 0:41 ` Andrii Nakryiko
2024-07-02 21:05 ` Eduard Zingerman
2024-07-02 21:18 ` Andrii Nakryiko
2024-06-29 9:47 ` [RFC bpf-next v1 6/8] selftests/bpf: extract test_loader->expect_msgs as a data structure Eduard Zingerman
2024-07-02 0:42 ` Andrii Nakryiko
2024-07-02 21:06 ` Eduard Zingerman
2024-06-29 9:47 ` [RFC bpf-next v1 7/8] selftests/bpf: allow checking xlated programs in verifier_* tests Eduard Zingerman
2024-07-02 0:42 ` Andrii Nakryiko
2024-07-02 21:07 ` Eduard Zingerman
2024-07-02 21:19 ` Andrii Nakryiko
2024-06-29 9:47 ` [RFC bpf-next v1 8/8] selftests/bpf: test no_caller_saved_registers spill/fill removal Eduard Zingerman
2024-07-02 0:42 ` Andrii Nakryiko
2024-07-02 21:12 ` Eduard Zingerman
2024-07-02 21:20 ` Andrii Nakryiko
2024-07-02 0:41 ` [RFC bpf-next v1 0/8] no_caller_saved_registers attribute for helper calls Andrii Nakryiko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240629094733.3863850-1-eddyz87@gmail.com \
--to=eddyz87@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=jose.marchesi@oracle.com \
--cc=kernel-team@fb.com \
--cc=martin.lau@linux.dev \
--cc=yonghong.song@linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox