[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAL_JsqLxqv=MpzWJyht-YNjpxC6JSdfOhijXhB6j8Z2CWeotjQ@mail.gmail.com>
Date: Tue, 30 Nov 2021 15:56:56 -0600
From: Rob Herring <robh@...nel.org>
To: Will Deacon <will@...nel.org>, Mark Rutland <mark.rutland@....com>,
Peter Zijlstra <peterz@...radead.org>
Cc: Jonathan Corbet <corbet@....net>,
Catalin Marinas <catalin.marinas@....com>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...hat.com>,
Namhyung Kim <namhyung@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Borislav Petkov <bp@...en8.de>, X86 ML <x86@...nel.org>,
"H. Peter Anvin" <hpa@...or.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
linux-arm-kernel <linux-arm-kernel@...ts.infradead.org>,
linux-perf-users@...r.kernel.org
Subject: Re: [PATCH v12 0/5] Another version of arm64 userspace counter access support.
On Mon, Nov 15, 2021 at 10:57 AM Rob Herring <robh@...nel.org> wrote:
>
> On Wed, Oct 27, 2021 at 3:16 PM Rob Herring <robh@...nel.org> wrote:
> >
> > The arm64 support departs from the x86 implementation by requiring the user
> > to explicitly request user access (via attr.config1) and only enables access
> > for task bound events. Since usage is explicitly requested, access is
> > enabled at perf_event_open() rather than on mmap() as that greatly
> > simplifies the implementation. Rather than trying to lock down the access
> > as the x86 implementation has been doing, we can start with only a limited
> > use case enabled and later expand it if needed.
> >
> > I've run this version thru Vince's perf tests[14] with arm64 support added.
> > I wish I'd found these tests sooner...
> >
> > This originally resurrected Raphael's series[1] to enable userspace counter
> > access on arm64. My previous versions are here
> > [2][3][4][5][6][7][8][9][10][11][12].
> > A git branch is here[13].
> >
> > Changes in v12:
> > - Zero PMSELR_EL0 when userspace access is enabled
> > - Return -EOPNOTSUPP for if h/w doesn't support 64-bit counters
>
> Will, the series rebases cleanly on v5.16-rc1. Please let me know if
> you want me to resend.
>
> Peter, Will is waiting on an ack on the core/x86 bits from you.
Ping!
Powered by blists - more mailing lists