Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Matt Mullins
On Tue, 2019-06-04 at 02:43 +0200, Daniel Borkmann wrote: > On 06/04/2019 01:54 AM, Alexei Starovoitov wrote: > > On Mon, Jun 3, 2019 at 4:48 PM Daniel Borkmann wrote: > > > On 06/04/2019 01:27 AM, Alexei Starovoitov wrote: > > > > On Mon, Jun 3, 2019 at 3:59 PM Matt Mullins wrote: > > > > > >

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Alexei Starovoitov
On Mon, Jun 3, 2019 at 5:44 PM Daniel Borkmann wrote: > > On 06/04/2019 01:54 AM, Alexei Starovoitov wrote: > > On Mon, Jun 3, 2019 at 4:48 PM Daniel Borkmann wrote: > >> On 06/04/2019 01:27 AM, Alexei Starovoitov wrote: > >>> On Mon, Jun 3, 2019 at 3:59 PM Matt Mullins wrote: > > If

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Daniel Borkmann
On 06/04/2019 01:54 AM, Alexei Starovoitov wrote: > On Mon, Jun 3, 2019 at 4:48 PM Daniel Borkmann wrote: >> On 06/04/2019 01:27 AM, Alexei Starovoitov wrote: >>> On Mon, Jun 3, 2019 at 3:59 PM Matt Mullins wrote: If these are invariably non-nested, I can easily keep bpf_misc_sd when

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Alexei Starovoitov
On Mon, Jun 3, 2019 at 4:48 PM Daniel Borkmann wrote: > > On 06/04/2019 01:27 AM, Alexei Starovoitov wrote: > > On Mon, Jun 3, 2019 at 3:59 PM Matt Mullins wrote: > >> > >> If these are invariably non-nested, I can easily keep bpf_misc_sd when > >> I resubmit. There was no technical reason

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Daniel Borkmann
On 06/04/2019 01:27 AM, Alexei Starovoitov wrote: > On Mon, Jun 3, 2019 at 3:59 PM Matt Mullins wrote: >> >> If these are invariably non-nested, I can easily keep bpf_misc_sd when >> I resubmit. There was no technical reason other than keeping the two >> codepaths as similar as possible. >> >>

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Alexei Starovoitov
On Mon, Jun 3, 2019 at 3:59 PM Matt Mullins wrote: > > If these are invariably non-nested, I can easily keep bpf_misc_sd when > I resubmit. There was no technical reason other than keeping the two > codepaths as similar as possible. > > What resource gives you worry about doing this for the

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Matt Mullins
On Mon, 2019-06-03 at 15:22 +0200, Daniel Borkmann wrote: > On 06/03/2019 03:08 PM, Daniel Borkmann wrote: > > On 06/01/2019 12:37 AM, Matt Mullins wrote: > > > It is possible that a BPF program can be called while another BPF > > > program is executing bpf_perf_event_output. This has been

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Daniel Borkmann
On 06/03/2019 03:08 PM, Daniel Borkmann wrote: > On 06/01/2019 12:37 AM, Matt Mullins wrote: >> It is possible that a BPF program can be called while another BPF >> program is executing bpf_perf_event_output. This has been observed with >> I/O completion occurring as a result of an interrupt: >>

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-06-03 Thread Daniel Borkmann
On 06/01/2019 12:37 AM, Matt Mullins wrote: > It is possible that a BPF program can be called while another BPF > program is executing bpf_perf_event_output. This has been observed with > I/O completion occurring as a result of an interrupt: > >

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-05-31 Thread Alexei Starovoitov
On Fri, May 31, 2019 at 6:28 PM Song Liu wrote: > > > > > On May 31, 2019, at 3:37 PM, Matt Mullins wrote: > > > > It is possible that a BPF program can be called while another BPF > > program is executing bpf_perf_event_output. This has been observed with > > I/O completion occurring as a

Re: [PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-05-31 Thread Song Liu
> On May 31, 2019, at 3:37 PM, Matt Mullins wrote: > > It is possible that a BPF program can be called while another BPF > program is executing bpf_perf_event_output. This has been observed with > I/O completion occurring as a result of an interrupt: > >

[PATCH bpf v2] bpf: preallocate a perf_sample_data per event fd

2019-05-31 Thread Matt Mullins
It is possible that a BPF program can be called while another BPF program is executing bpf_perf_event_output. This has been observed with I/O completion occurring as a result of an interrupt: bpf_prog_247fd1341cddaea4_trace_req_end+0x8d7/0x1000 ? trace_call_bpf+0x82/0x100