All of lore.kernel.org
 help / color / mirror / Atom feed
From: Zachary Leaf <zachary.leaf@arm.com>
To: Rob Herring <robh@kernel.org>, Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>, Mark Rutland <mark.rutland@arm.com>
Cc: Ian Rogers <irogers@google.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	honnappa.nagarahalli@arm.com,
	Raphael Gault <raphael.gault@arm.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Itaru Kitayama <itaru.kitayama@gmail.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, nd@arm.com
Subject: Re: [PATCH v6 02/10] arm64: perf: Enable PMU counter direct access for perf event
Date: Tue, 30 Mar 2021 12:30:58 +0100	[thread overview]
Message-ID: <9e904f20-7943-ee44-9653-7aa949c3ba88@arm.com> (raw)
In-Reply-To: <20210311000837.3630499-3-robh@kernel.org>

On 11/03/2021 00:08, Rob Herring wrote:
> 
> In order to enable 64-bit counters for userspace when available, a new
> config1 bit is added for userspace to indicate it wants userspace counter
> access. This bit allows the kernel to decide if chaining should be
> disabled and chaining and userspace access are incompatible.
> The modes for config1 are as follows:
> 
> config1 = 0 or 2 : user access enabled and always 32-bit
> config1 = 1 : user access disabled and always 64-bit (using chaining if needed)
> config1 = 3 : user access enabled and counter size matches underlying counter.
> 

Thanks for this Rob. That makes it extremely easy to request 64 bit
userspace counters without having to worry about the underlying bit
width supported on your system.

The underlying PMUv3 bit width is otherwise not accessible from
userspace as far as I can tell (e.g. the relevant PMUVer bits [11:8] of
ID_AA64DFR0_EL1 are masked off when reading from EL0 [1]), and the
workaround of requesting 64 bit, checking cap_user_rdpmc for userspace
access, and retrying with 32 bit was not that user friendly. I think it
makes a lot of sense for the kernel to handle/expose it here rather than
handled in the application code.

I think it's worth mentioning here if anyone searches, is that the 32
bit counter behaviour when added to the perf_event_mmap_page->offset is
effectively the same as a single 64 bit counter due to the offset being
incremented on overflow. Using a true 64 bit counter can avoid the
overhead of handling an interrupt for each overflow (and obviously has a
lot more headroom before it overflows, if you require very long running
perf stats).

I have tested the new config1 flags on N1-SDP and the behaviour is as
expected.

[1]
https://github.com/torvalds/linux/blob/master/Documentation/arm64/cpu-feature-registers.rst

WARNING: multiple messages have this Message-ID
From: Zachary Leaf <zachary.leaf@arm.com>
To: Rob Herring <robh@kernel.org>, Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>, Mark Rutland <mark.rutland@arm.com>
Cc: Ian Rogers <irogers@google.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	honnappa.nagarahalli@arm.com,
	Raphael Gault <raphael.gault@arm.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Itaru Kitayama <itaru.kitayama@gmail.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, nd@arm.com
Subject: Re: [PATCH v6 02/10] arm64: perf: Enable PMU counter direct access for perf event
Date: Tue, 30 Mar 2021 12:30:58 +0100	[thread overview]
Message-ID: <9e904f20-7943-ee44-9653-7aa949c3ba88@arm.com> (raw)
In-Reply-To: <20210311000837.3630499-3-robh@kernel.org>

On 11/03/2021 00:08, Rob Herring wrote:
> 
> In order to enable 64-bit counters for userspace when available, a new
> config1 bit is added for userspace to indicate it wants userspace counter
> access. This bit allows the kernel to decide if chaining should be
> disabled and chaining and userspace access are incompatible.
> The modes for config1 are as follows:
> 
> config1 = 0 or 2 : user access enabled and always 32-bit
> config1 = 1 : user access disabled and always 64-bit (using chaining if needed)
> config1 = 3 : user access enabled and counter size matches underlying counter.
> 

Thanks for this Rob. That makes it extremely easy to request 64 bit
userspace counters without having to worry about the underlying bit
width supported on your system.

The underlying PMUv3 bit width is otherwise not accessible from
userspace as far as I can tell (e.g. the relevant PMUVer bits [11:8] of
ID_AA64DFR0_EL1 are masked off when reading from EL0 [1]), and the
workaround of requesting 64 bit, checking cap_user_rdpmc for userspace
access, and retrying with 32 bit was not that user friendly. I think it
makes a lot of sense for the kernel to handle/expose it here rather than
handled in the application code.

I think it's worth mentioning here if anyone searches, is that the 32
bit counter behaviour when added to the perf_event_mmap_page->offset is
effectively the same as a single 64 bit counter due to the offset being
incremented on overflow. Using a true 64 bit counter can avoid the
overhead of handling an interrupt for each overflow (and obviously has a
lot more headroom before it overflows, if you require very long running
perf stats).

I have tested the new config1 flags on N1-SDP and the behaviour is as
expected.

[1]
https://github.com/torvalds/linux/blob/master/Documentation/arm64/cpu-feature-registers.rst

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  reply	other threads:[~2021-03-30 11:32 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-11  0:08 [PATCH v6 00/10] libperf and arm64 userspace counter access support Rob Herring
2021-03-11  0:08 ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 01/10] arm64: pmu: Add function implementation to update event index in userpage Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-30 15:30   ` Will Deacon
2021-03-30 15:30     ` Will Deacon
2021-03-11  0:08 ` [PATCH v6 02/10] arm64: perf: Enable PMU counter direct access for perf event Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-30 11:30   ` Zachary Leaf [this message]
2021-03-30 11:30     ` Zachary Leaf
2021-03-30 15:31   ` Will Deacon
2021-03-30 15:31     ` Will Deacon
2021-03-30 17:09     ` Rob Herring
2021-03-30 17:09       ` Rob Herring
2021-03-30 21:08       ` Rob Herring
2021-03-30 21:08         ` Rob Herring
2021-03-31 15:38         ` Will Deacon
2021-03-31 15:38           ` Will Deacon
2021-03-31 17:52           ` Rob Herring
2021-03-31 17:52             ` Rob Herring
2021-04-01  9:04             ` Will Deacon
2021-04-01  9:04               ` Will Deacon
2021-03-31 16:00       ` Will Deacon
2021-03-31 16:00         ` Will Deacon
2021-04-01 19:45         ` Rob Herring
2021-04-01 19:45           ` Rob Herring
2021-04-07 12:44           ` Will Deacon
2021-04-07 12:44             ` Will Deacon
2021-04-08 11:08             ` Mark Rutland
2021-04-08 11:08               ` Mark Rutland
2021-04-08 18:38               ` Rob Herring
2021-04-08 18:38                 ` Rob Herring
2021-04-19 16:14                 ` Will Deacon
2021-04-19 16:14                   ` Will Deacon
2021-04-19 19:00                   ` Rob Herring
2021-04-19 19:00                     ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 03/10] tools/include: Add an initial math64.h Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 04/10] libperf: Add evsel mmap support Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-12 13:58   ` Jiri Olsa
2021-03-12 13:58     ` Jiri Olsa
2021-03-12 14:34     ` Rob Herring
2021-03-12 14:34       ` Rob Herring
2021-03-12 18:29       ` Jiri Olsa
2021-03-12 18:29         ` Jiri Olsa
2021-03-31 22:06         ` Rob Herring
2021-03-31 22:06           ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 05/10] libperf: tests: Add support for verbose printing Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 06/10] libperf: Add support for user space counter access Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-05-04 21:40   ` Ian Rogers
2021-05-04 21:40     ` Ian Rogers
2021-05-05  2:12     ` Rob Herring
2021-05-05  2:12       ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 07/10] libperf: Add arm64 support to perf_mmap__read_self() Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 08/10] perf: arm64: Add test for userspace counter access on heterogeneous systems Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-15 16:09   ` Masayoshi Mizuma
2021-03-15 16:09     ` Masayoshi Mizuma
2021-03-11  0:08 ` [PATCH v6 09/10] perf: arm64: Add tests for 32-bit and 64-bit counter size userspace access Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 10/10] Documentation: arm64: Document PMU counters access from userspace Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-31 16:00   ` Will Deacon
2021-03-31 16:00     ` Will Deacon
2021-03-30 11:31 ` [PATCH v6 00/10] libperf and arm64 userspace counter access support Zachary Leaf
2021-03-30 11:31   ` Zachary Leaf

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=9e904f20-7943-ee44-9653-7aa949c3ba88@arm.com \
    --to=zachary.leaf@arm.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=catalin.marinas@arm.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=irogers@google.com \
    --cc=itaru.kitayama@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=nd@arm.com \
    --cc=peterz@infradead.org \
    --cc=raphael.gault@arm.com \
    --cc=robh@kernel.org \
    --cc=will@kernel.org \
    --subject='Re: [PATCH v6 02/10] arm64: perf: Enable PMU counter direct access for perf event' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.