[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Fri, 5 May 2023 10:18:05 -0300
From: Arnaldo Carvalho de Melo <acme@...nel.org>
To: Yang Jihong <yangjihong1@...wei.com>,
Andrii Nakryiko <andrii.nakryiko@...il.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
Song Liu <song@...nel.org>,
Andrii Nakryiko <andrii@...nel.org>,
Ingo Molnar <mingo@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Jiri Olsa <jolsa@...nel.org>,
Clark Williams <williams@...hat.com>,
Kate Carcia <kcarcia@...hat.com>, linux-kernel@...r.kernel.org,
linux-perf-users@...r.kernel.org,
Adrian Hunter <adrian.hunter@...el.com>,
Changbin Du <changbin.du@...wei.com>,
Hao Luo <haoluo@...gle.com>, Ian Rogers <irogers@...gle.com>,
James Clark <james.clark@....com>,
Kan Liang <kan.liang@...ux.intel.com>,
Roman Lozko <lozko.roma@...il.com>,
Stephane Eranian <eranian@...gle.com>,
Thomas Richter <tmricht@...ux.ibm.com>,
Arnaldo Carvalho de Melo <acme@...hat.com>,
bpf <bpf@...r.kernel.org>
Subject: Re: BPF skels in perf .Re: [GIT PULL] perf tools changes for v6.4
Em Thu, May 04, 2023 at 07:01:51PM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Thu, May 04, 2023 at 06:48:50PM -0300, Arnaldo Carvalho de Melo escreveu:
> > Em Thu, May 04, 2023 at 04:07:29PM -0300, Arnaldo Carvalho de Melo escreveu:
> > > Em Thu, May 04, 2023 at 11:50:07AM -0700, Andrii Nakryiko escreveu:
> > > > On Thu, May 4, 2023 at 10:52 AM Arnaldo Carvalho de Melo <acme@...nel.org> wrote:
> > > > > Andrii, can you add some more information about the usage of vmlinux.h
> > > > > instead of using kernel headers?
> > >
> > > > I'll just say that vmlinux.h is not a hard requirement to build BPF
> > > > programs, it's more a convenience allowing easy access to definitions
> > > > of both UAPI and kernel-internal structures for tracing needs and
> > > > marking them relocatable using BPF CO-RE machinery. Lots of real-world
> > > > applications just check-in pregenerated vmlinux.h to avoid build-time
> > > > dependency on up-to-date host kernel and such.
> > >
> > > > If vmlinux.h generation and usage is causing issues, though, given
> > > > that perf's BPF programs don't seem to be using many different kernel
> > > > types, it might be a better option to just use UAPI headers for public
> > > > kernel type definitions, and just define CO-RE-relocatable minimal
> > > > definitions locally in perf's BPF code for the other types necessary.
> > > > E.g., if perf needs only pid and tgid from task_struct, this would
> > > > suffice:
> > >
> > > > struct task_struct {
> > > > int pid;
> > > > int tgid;
> > > > } __attribute__((preserve_access_index));
> > >
> > > Yeah, that seems like a way better approach, no vmlinux involved, libbpf
> > > CO-RE notices that task_struct changed from this two integers version
> > > (of course) and does the relocation to where it is in the running kernel
> > > by using /sys/kernel/btf/vmlinux.
> >
> > Doing it for one of the skels, build tested, runtime untested, but not
> > using any vmlinux, BTF to help, not that bad, more verbose, but at least
> > we state what are the fields we actually use, have those attribute
> > documenting that those offsets will be recorded for future use, etc.
Yang, can you please check that this works?
>From bd6289bc3ffc89aecad3bd8798d76626c8c16d39 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@...hat.com>
Date: Fri, 5 May 2023 10:13:09 -0300
Subject: [PATCH 1/1] perf kwork_trace.bpf: Stop using vmlinux.h, grab copies
of used structs
And mark them with __attribute__((preserve_access_index)) so that
libbpf's CO-RE code can fixup offsets if they differ with the kernel
data structure.
Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>
---
tools/perf/util/bpf_skel/kwork_trace.bpf.c | 70 +++++++++++++++++++++-
1 file changed, 69 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/bpf_skel/kwork_trace.bpf.c b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
index 063c124e099938ed..e38fe54c7667fa74 100644
--- a/tools/perf/util/bpf_skel/kwork_trace.bpf.c
+++ b/tools/perf/util/bpf_skel/kwork_trace.bpf.c
@@ -1,13 +1,81 @@
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
// Copyright (c) 2022, Huawei
-#include "vmlinux.h"
+#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#define KWORK_COUNT 100
#define MAX_KWORKNAME 128
+
+// non-UAPI kernel data structures, just the fields used in this tool,
+// preserving the access index so that libbpf can fixup offsets with the ones
+// used in the kernel when loading the BPF bytecode, if they differ from what
+// is used here.
+
+enum {
+ HI_SOFTIRQ = 0,
+ TIMER_SOFTIRQ,
+ NET_TX_SOFTIRQ,
+ NET_RX_SOFTIRQ,
+ BLOCK_SOFTIRQ,
+ IRQ_POLL_SOFTIRQ,
+ TASKLET_SOFTIRQ,
+ SCHED_SOFTIRQ,
+ HRTIMER_SOFTIRQ,
+ RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */
+
+ NR_SOFTIRQS
+};
+
+struct trace_entry {
+ short unsigned int type;
+ unsigned char flags;
+ unsigned char preempt_count;
+ int pid;
+} __attribute__((preserve_access_index));
+
+struct trace_event_raw_irq_handler_entry {
+ struct trace_entry ent;
+ int irq;
+ __u32 __data_loc_name;
+ char __data[];
+} __attribute__((preserve_access_index));
+
+struct trace_event_raw_irq_handler_exit {
+ struct trace_entry ent;
+ int irq;
+ int ret;
+ char __data[];
+} __attribute__((preserve_access_index));
+
+struct trace_event_raw_softirq {
+ struct trace_entry ent;
+ unsigned int vec;
+ char __data[];
+} __attribute__((preserve_access_index));
+
+struct trace_event_raw_workqueue_execute_start {
+ struct trace_entry ent;
+ void *work;
+ void *function;
+ char __data[];
+} __attribute__((preserve_access_index));
+
+struct trace_event_raw_workqueue_execute_end {
+ struct trace_entry ent;
+ void *work;
+ void *function;
+ char __data[];
+} __attribute__((preserve_access_index));
+
+struct trace_event_raw_workqueue_activate_work {
+ struct trace_entry ent;
+ void *work;
+ char __data[];
+} __attribute__((preserve_access_index));
+
/*
* This should be in sync with "util/kwork.h"
*/
--
2.39.2
Powered by blists - more mailing lists