All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: "Suzuki K. Poulose" <Suzuki.Poulose@arm.com>
Cc: linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, mark.rutland@arm.com,
	punit.agrawal@arm.com, arm@kernel.org
Subject: Re: [PATCH v4 05/12] arm-cci: PMU: Add support for transactions
Date: Fri, 18 Dec 2015 12:47:51 +0100	[thread overview]
Message-ID: <20151218114751.GP6344@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <5673E6C9.7040304@arm.com>

On Fri, Dec 18, 2015 at 10:58:17AM +0000, Suzuki K. Poulose wrote:

> We have a global Enable/Disable for CCI PMU and thats what we use
> currently. To be able to reprogram the counters with the event period
> (we program the counter with a specific count in pmu::start() and at
> overflow irq handler, not to be confused with the sampling period, which
> is not supported), we need to be sure that the counter value has been updated.
> 
> May be we could check the event->hw->state to see if we need to reprogram it.

Right, have a look at arch/x86/kernel/cpu/perf_event.c:x86_pmu_enable()

If there's new events, it does two loops over the events.

The first loop does stop(PERF_EF_UPDATE) any counter that got moved.
The second loop does start(PERF_EF_RELOAD) on moved and new events.

The PERF_HES_ARCH bit is used to preserve the stopped state of counters
that were programmed but temporarily stopped.

WARNING: multiple messages have this Message-ID (diff)
From: peterz@infradead.org (Peter Zijlstra)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v4 05/12] arm-cci: PMU: Add support for transactions
Date: Fri, 18 Dec 2015 12:47:51 +0100	[thread overview]
Message-ID: <20151218114751.GP6344@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <5673E6C9.7040304@arm.com>

On Fri, Dec 18, 2015 at 10:58:17AM +0000, Suzuki K. Poulose wrote:

> We have a global Enable/Disable for CCI PMU and thats what we use
> currently. To be able to reprogram the counters with the event period
> (we program the counter with a specific count in pmu::start() and at
> overflow irq handler, not to be confused with the sampling period, which
> is not supported), we need to be sure that the counter value has been updated.
> 
> May be we could check the event->hw->state to see if we need to reprogram it.

Right, have a look at arch/x86/kernel/cpu/perf_event.c:x86_pmu_enable()

If there's new events, it does two loops over the events.

The first loop does stop(PERF_EF_UPDATE) any counter that got moved.
The second loop does start(PERF_EF_RELOAD) on moved and new events.

The PERF_HES_ARCH bit is used to preserve the stopped state of counters
that were programmed but temporarily stopped.

  reply	other threads:[~2015-12-18 11:47 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-17 17:49 [PATCHv4 00/12] arm-cci: PMU updates Suzuki K. Poulose
2015-12-17 17:49 ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 01/12] arm-cci: Define CCI counter period Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 02/12] arm-cci: Refactor pmu_write_counter Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 03/12] arm-cci: Group writes to counter Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 04/12] arm-cci: Fix the flags for pmu_start called from pmu_add Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 05/12] arm-cci: PMU: Add support for transactions Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 18:42   ` Peter Zijlstra
2015-12-17 18:42     ` Peter Zijlstra
2015-12-18 10:28     ` Suzuki K. Poulose
2015-12-18 10:28       ` Suzuki K. Poulose
2015-12-18 10:42       ` Peter Zijlstra
2015-12-18 10:42         ` Peter Zijlstra
2015-12-18 10:58         ` Suzuki K. Poulose
2015-12-18 10:58           ` Suzuki K. Poulose
2015-12-18 11:47           ` Peter Zijlstra [this message]
2015-12-18 11:47             ` Peter Zijlstra
2015-12-21 10:55             ` Suzuki K. Poulose
2015-12-21 10:55               ` Suzuki K. Poulose
2016-01-05 13:37               ` Peter Zijlstra
2016-01-05 13:37                 ` Peter Zijlstra
2016-01-05 13:43                 ` Suzuki K. Poulose
2016-01-05 13:43                   ` Suzuki K. Poulose
2016-01-05 14:53                   ` Peter Zijlstra
2016-01-05 14:53                     ` Peter Zijlstra
2015-12-17 17:49 ` [PATCH v4 06/12] arm-cci: Refactor CCI PMU enable/disable methods Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 07/12] arm-cci: Get the status of a counter Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 08/12] arm-cci: Add routines to save/restore all counters Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 09/12] arm-cci: Provide hook for writing to PMU counters Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 10/12] arm-cci: CCI-500: Work around PMU counter writes Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 11/12] arm-cci500: Rearrange PMU driver for code sharing with CCI-550 PMU Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose
2015-12-17 17:49 ` [PATCH v4 12/12] arm-cci: CoreLink CCI-550 PMU driver Suzuki K. Poulose
2015-12-17 17:49   ` Suzuki K. Poulose

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=20151218114751.GP6344@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=Suzuki.Poulose@arm.com \
    --cc=arm@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=punit.agrawal@arm.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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.