On 2016/9/18 22:56, Andi Kleen wrote:
On Sun, Sep 18, 2016 at 06:20:04PM +0800, Wangnan (F) wrote:
On 2016/9/18 9:02, Andi Kleen wrote:
From: Andi Kleen <a...@linux.intel.com>
This is a generic bug fix, but it helps with Sukadev's JSON event tree
where such events can happen.
Any event inclduing a .c/.o/.bpf currently triggers BPF compilation or loading
and then an error. This can happen for some Intel JSON events, which cannot
be used.
Fix the scanner to only match for .o or .c or .bpf at the end.
This will prevent loading multiple BPF scripts separated with comma,
but I assume this is acceptable.
Cc: wangn...@huawei.com
Cc: suka...@linux.vnet.ibm.com
Signed-off-by: Andi Kleen <a...@linux.intel.com>
I tested '.c' in middle of an event:
# perf trace --event 'aaa.ccc'
invalid or unsupported event: 'aaa.ccc'
Run 'perf list' for a list of valid events
...
It is not recongnized as a BPF source.
So could you please provide an example to show how
this potential bug breaks the parsing of new events?
This is with the upcoming JSON uncore events:
$ perf stat -e '{unc_p_clockticks,unc_p_power_state_occupancy.cores_c0}' -a -I
1000
ERROR: problems with path {unc_p_clockticks,unc_p_power_state_occupancy.c: No
such file or directory
event syntax error: '{unc_p_clockticks,unc_p_power_state_occupancy.cores_c0}'
\___ Failed to load
{unc_p_clockticks,unc_p_power_state_occupancy.c from source: Error when
compiling BPF scriptlet
(add -v to see detail)
Run 'perf list' for a list of valid events
-Andi
I see, and your patch solve problem like this.
Tested-by: Wang Nan <wangn...@huawei.com>
