[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7c86c4470811270425i435a2adcq565d674070fd44db@mail.gmail.com>
Date: Thu, 27 Nov 2008 13:25:59 +0100
From: "stephane eranian" <eranian@...glemail.com>
To: "Oleg Nesterov" <oleg@...hat.com>
Cc: "Ingo Molnar" <mingo@...e.hu>, linux-kernel@...r.kernel.org,
akpm@...ux-foundation.org, x86@...nel.org, andi@...stfloor.org,
sfr@...b.auug.org.au, "Roland McGrath" <roland@...hat.com>
Subject: Re: [patch 20/24] perfmon: system calls interface
Hi,
Given that this thread discusses the syscall API, I would like to verify
something with you at this point.
The sys_pfm_create() syscall is used to create a perfmon session (context).
In the current patchset, where only counting is supported, the syscall is
defined as:
int pfm_create(int flags, pfarg_sinfo_t *sif);
The plan is to extend this syscall, instead of adding a new syscall,
to add support
for sampling. The syscall would be used to select which sampling
buffer format and for passing
potential arguments to that format. The syscall would then look like:
int pfm_create(int flags, pfarg_sinfo_t *sif, char *fmt_name, void
*fmt_arg, size_t arg_sz);
The kernel would look at the last 3 arguments ONLY if it saw the
PFM_FL_SMPL_FMT bit
set in flags. We follow the model used by open(2).
I want to double-check that you are fine with this approach.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists