From: "Wangnan (F)" <wangnan0@huawei.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: "Alexei Starovoitov" <ast@kernel.org>,
"Arnaldo Carvalho de Melo" <acme@redhat.com>,
"Brendan Gregg" <brendan.d.gregg@gmail.com>,
"Adrian Hunter" <adrian.hunter@intel.com>,
"Cody P Schafer" <dev@codyps.com>,
"David S. Miller" <davem@davemloft.net>,
"He Kuang" <hekuang@huawei.com>,
"Jérémie Galarneau" <jeremie.galarneau@efficios.com>,
"Jiri Olsa" <jolsa@kernel.org>,
"Kirill Smelkov" <kirr@nexedi.com>,
"Li Zefan" <lizefan@huawei.com>,
"Masami Hiramatsu" <masami.hiramatsu.pt@hitachi.com>,
"Namhyung Kim" <namhyung@kernel.org>,
"Peter Zijlstra" <peterz@infradead.org>,
pi3orama@163.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 10/48] perf tools: Introduce bpf-output event
Date: Wed, 24 Feb 2016 09:58:34 +0800 [thread overview]
Message-ID: <56CD0E4A.9080804@huawei.com> (raw)
In-Reply-To: <20160223174539.GG15284@kernel.org>
On 2016/2/24 1:45, Arnaldo Carvalho de Melo wrote:
> Em Mon, Feb 22, 2016 at 09:10:37AM +0000, Wang Nan escreveu:
>> Commit a43eec304259a6c637f4014a6d4767159b6a3aa3 (bpf: introduce
>> bpf_perf_event_output() helper) add a helper to enable BPF program
>> output data to perf ring buffer through a new type of perf event
>> PERF_COUNT_SW_BPF_OUTPUT. This patch enable perf to create perf
>> event of that type. Now perf user can use following cmdline to
>> receive output data from BPF programs:
>>
>> # ./perf record -a -e bpf-output/no-inherit,name=evt/ \
>> -e ./test_bpf_output.c/map:channel.event=evt/ ls /
>> # ./perf script
>> perf 1560 [004] 347747.086295: evt: ffffffff811fd201 sys_write ...
>> perf 1560 [004] 347747.086300: evt: ffffffff811fd201 sys_write ...
>> perf 1560 [004] 347747.086315: evt: ffffffff811fd201 sys_write ...
>> ...
>>
>> Test result:
>> # cat ./test_bpf_output.c
>> /************************ BEGIN **************************/
>> #include <uapi/linux/bpf.h>
>> struct bpf_map_def {
>> unsigned int type;
>> unsigned int key_size;
>> unsigned int value_size;
>> unsigned int max_entries;
>> };
>>
>> #define SEC(NAME) __attribute__((section(NAME), used))
>> static u64 (*ktime_get_ns)(void) =
>> (void *)BPF_FUNC_ktime_get_ns;
>> static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
>> (void *)BPF_FUNC_trace_printk;
>> static int (*get_smp_processor_id)(void) =
>> (void *)BPF_FUNC_get_smp_processor_id;
>> static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
>> (void *)BPF_FUNC_perf_event_output;
>>
>> struct bpf_map_def SEC("maps") channel = {
>> .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
>> .key_size = sizeof(int),
>> .value_size = sizeof(u32),
>> .max_entries = __NR_CPUS__,
>> };
>>
>> SEC("func_write=sys_write")
>> int func_write(void *ctx)
>> {
>> struct {
>> u64 ktime;
>> int cpuid;
>> } __attribute__((packed)) output_data;
>> char error_data[] = "Error: failed to output: %d\n";
>>
>> output_data.cpuid = get_smp_processor_id();
>> output_data.ktime = ktime_get_ns();
>> int err = perf_event_output(ctx, &channel, get_smp_processor_id(),
>> &output_data, sizeof(output_data));
>> if (err)
>> trace_printk(error_data, sizeof(error_data), err);
>> return 0;
>> }
>> char _license[] SEC("license") = "GPL";
>> int _version SEC("version") = LINUX_VERSION_CODE;
>> /************************ END ***************************/
>>
>> # ./perf record -a -e bpf-output/no-inherit,name=evt/ \
>> -e ./test_bpf_output.c/map:channel.event=evt/ ls /
>> # ./perf script | grep ls
>> ls 2242 [003] 347851.557563: evt: ffffffff811fd201 sys_write ...
>> ls 2242 [003] 347851.557571: evt: ffffffff811fd201 sys_write ...
> So, there is something strange here:
>
> if (unlikely(event->oncpu != smp_processor_id()))
> return -EOPNOTSUPP;
>
> This is where I am hitting, with:
>
> [acme@jouet linux]$ uname -r
> 4.5.0-rc4
>
> int err = perf_event_output(ctx, &channel, get_smp_processor_id(),
> &output_data, sizeof(output_data));
> if (err)
> trace_printk(error_data, sizeof(error_data), err);
>
> And then:
>
> [root@jouet bpf]# tail /sys/kernel/debug/tracing/trace
> perf-13040 [003] d... 12062.807729: : Error: failed to output: -95
> perf-13040 [003] d... 12062.807731: : Error: failed to output: -95
> perf-13040 [003] d... 12062.807732: : Error: failed to output: -95
> perf-13040 [003] d... 12062.807735: : Error: failed to output: -95
> perf-13040 [003] d... 12062.807737: : Error: failed to output: -95
> perf-13040 [003] d... 12062.807744: : Error: failed to output: -95
> gnome-terminal--3091 [001] d... 12062.807773: : Error: failed to output: -95
> gnome-terminal--3091 [001] d... 12062.807784: : Error: failed to output: -95
> gmain-2830 [002] d... 12062.811791: : Error: failed to output: -95
> gmain-2830 [002] d... 12062.811810: : Error: failed to output: -95
> [root@jouet bpf]#
>
> Ideas? AFK for a while, will continue investigating.
I also noticed this output, but didn't digg into it because all events
I concerned is okay. I'll look into this today.
> This already was submitted to Ingo, BTW.
>
> I used, as in the changeset comment tests:
>
> perf record -a -e bpf-output/no-inherit,name=evt/ -e ./test_bpf_output.c/map:channel.event=evt/ ls /
>
> And perf script told me:
>
> [root@jouet bpf]# perf script | tail
> perf 13040 [003] 12062.708337: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708339: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708340: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708341: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708343: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708344: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708346: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708347: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708348: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> perf 13040 [003] 12062.708350: evt: ffffffff81234eb1 sys_write (/lib/modules/4.5.0-rc4/build/vmlinux)
> [root@jouet bpf]#
>
> Wonder where that /lib/modules/4.5.0-rc4/build/vmlinux came from...
>
> [root@jouet bpf]# perf script | cut -d'(' -f2 | sort | uniq -c
> 1141 /lib/modules/4.5.0-rc4/build/vmlinux)
It's a standard directory for perf searching vmlinux. Isn't it?
tools/perf/util/symbol.c:
static const char * const vmlinux_paths_upd[] = {
"/boot/vmlinux-%s",
"/usr/lib/debug/boot/vmlinux-%s",
"/lib/modules/%s/build/vmlinux",
"/usr/lib/debug/lib/modules/%s/vmlinux",
"/usr/lib/debug/boot/vmlinux-%s.debug"
};
So what's your problem?
Thank you.
next prev parent reply other threads:[~2016-02-24 2:01 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-22 9:10 [PATCH 00/48] perf tools: Bugfix, BPF improvements and overwrite ring buffer support Wang Nan
2016-02-22 9:10 ` [PATCH 01/48] perf tools: Record text offset in dso to calculate objdump address Wang Nan
2016-02-22 9:10 ` [PATCH 02/48] perf tools: Adjust symbol for shared objects Wang Nan
2016-02-22 9:10 ` [PATCH 03/48] perf bpf: Add API to set values to map entries in a bpf object Wang Nan
2016-02-25 5:39 ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 04/48] perf tools: Enable BPF object configure syntax Wang Nan
2016-02-25 5:39 ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 05/48] perf record: Apply config to BPF objects before recording Wang Nan
2016-02-25 5:39 ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 06/48] perf tools: Enable passing event to BPF object Wang Nan
2016-02-25 5:40 ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 07/48] perf tools: Support setting different slots in a BPF map separately Wang Nan
2016-02-25 5:40 ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 08/48] perf tools: Enable indices setting syntax for BPF map Wang Nan
2016-02-25 5:40 ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 09/48] perf tools: Pass tracepoint options to BPF script Wang Nan
2016-02-25 5:41 ` [tip:perf/core] perf tools: Apply tracepoint event definition " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 10/48] perf tools: Introduce bpf-output event Wang Nan
2016-02-23 17:45 ` Arnaldo Carvalho de Melo
2016-02-24 1:58 ` Wangnan (F) [this message]
2016-02-24 2:04 ` Wangnan (F)
2016-02-24 4:03 ` Wangnan (F)
2016-02-24 5:03 ` Wangnan (F)
2016-02-24 13:36 ` Arnaldo Carvalho de Melo
2016-02-25 5:41 ` [tip:perf/core] " tip-bot for Wang Nan
2016-02-22 9:10 ` [PATCH 11/48] perf data: Support converting data from bpf_perf_event_output() Wang Nan
2016-02-23 16:14 ` Arnaldo Carvalho de Melo
2016-02-23 17:23 ` Jiri Olsa
2016-02-23 17:24 ` Jiri Olsa
2016-02-23 19:22 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 12/48] perf data: Explicitly set byte order for integer types Wang Nan
2016-02-22 9:10 ` [PATCH 13/48] perf core: Introduce new ioctl options to pause and resume ring buffer Wang Nan
2016-02-22 9:10 ` [PATCH 14/48] perf core: Set event's default overflow_handler Wang Nan
2016-02-22 9:10 ` [PATCH 15/48] perf core: Prepare writing into ring buffer from end Wang Nan
2016-02-22 9:10 ` [PATCH 16/48] perf core: Add backward attribute to perf event Wang Nan
2016-02-24 13:08 ` Jiri Olsa
2016-02-24 13:21 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 17/48] perf core: Reduce perf event output overhead by new overflow handler Wang Nan
2016-02-22 9:10 ` [PATCH 18/48] perf tools: Only validate is_pos for tracking evsels Wang Nan
2016-02-24 14:21 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 19/48] perf tools: Print write_backward value in perf_event_attr__fprintf Wang Nan
2016-02-22 9:10 ` [PATCH 20/48] perf tools: Make ordered_events reusable Wang Nan
2016-02-24 14:18 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 21/48] perf record: Extract synthesize code to record__synthesize() Wang Nan
2016-02-24 14:29 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 22/48] perf tools: Add perf_data_file__switch() helper Wang Nan
2016-02-24 14:34 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 23/48] perf record: Turns auxtrace_snapshot_enable into 3 states Wang Nan
2016-02-24 14:43 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 24/48] perf record: Introduce record__finish_output() to finish a perf.data Wang Nan
2016-02-22 9:10 ` [PATCH 25/48] perf record: Add '--timestamp-filename' option to append timestamp to output filename Wang Nan
2016-02-22 9:10 ` [PATCH 26/48] perf record: Split output into multiple files via '--switch-output' Wang Nan
2016-02-22 9:10 ` [PATCH 27/48] perf record: Force enable --timestamp-filename when --switch-output is provided Wang Nan
2016-02-22 9:10 ` [PATCH 28/48] perf record: Disable buildid cache options by default in switch output mode Wang Nan
2016-02-22 9:10 ` [PATCH 29/48] perf record: Re-synthesize tracking events after output switching Wang Nan
2016-02-24 14:57 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 30/48] perf record: Generate tracking events for process forked by perf Wang Nan
2016-02-24 15:01 ` Jiri Olsa
2016-02-22 9:10 ` [PATCH 31/48] perf record: Ensure return non-zero rc when mmap fail Wang Nan
2016-02-22 9:10 ` [PATCH 32/48] perf record: Prevent reading invalid data in record__mmap_read Wang Nan
2016-02-22 9:11 ` [PATCH 33/48] perf tools: Add evlist channel helpers Wang Nan
2016-02-22 9:11 ` [PATCH 34/48] perf tools: Automatically add new channel according to evlist Wang Nan
2016-02-22 9:11 ` [PATCH 35/48] perf tools: Operate multiple channels Wang Nan
2016-02-22 9:11 ` [PATCH 36/48] perf tools: Squash overwrite setting into channel Wang Nan
2016-02-22 9:11 ` [PATCH 37/48] perf record: Don't read from and poll overwrite channel Wang Nan
2016-02-22 9:11 ` [PATCH 38/48] perf record: Don't poll on " Wang Nan
2016-02-22 9:11 ` [PATCH 39/48] perf tools: Detect avalibility of write_backward Wang Nan
2016-02-22 9:11 ` [PATCH 40/48] perf tools: Enable overwrite settings Wang Nan
2016-02-22 9:11 ` [PATCH 41/48] perf tools: Set write_backward attribut bit for overwrite events Wang Nan
2016-02-22 9:11 ` [PATCH 42/48] perf tools: Record fd into perf_mmap Wang Nan
2016-02-22 9:11 ` [PATCH 43/48] perf tools: Add API to pause a channel Wang Nan
2016-02-22 9:11 ` [PATCH 44/48] perf record: Toggle overwrite ring buffer for reading Wang Nan
2016-02-22 9:11 ` [PATCH 45/48] perf record: Rename variable to make code clear Wang Nan
2016-02-22 9:11 ` [PATCH 46/48] perf record: Read from backward ring buffer Wang Nan
2016-02-22 9:11 ` [PATCH 47/48] perf record: Allow generate tracking events at the end of output Wang Nan
2016-02-22 9:11 ` [PATCH 48/48] perf tools: Don't warn about out of order event if write_backward is used Wang Nan
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=56CD0E4A.9080804@huawei.com \
--to=wangnan0@huawei.com \
--cc=acme@kernel.org \
--cc=acme@redhat.com \
--cc=adrian.hunter@intel.com \
--cc=ast@kernel.org \
--cc=brendan.d.gregg@gmail.com \
--cc=davem@davemloft.net \
--cc=dev@codyps.com \
--cc=hekuang@huawei.com \
--cc=jeremie.galarneau@efficios.com \
--cc=jolsa@kernel.org \
--cc=kirr@nexedi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lizefan@huawei.com \
--cc=masami.hiramatsu.pt@hitachi.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=pi3orama@163.com \
/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