LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: <Mario.Limonciello@dell.com>
To: <hch@lst.de>
Cc: <keith.busch@intel.com>, <sagi@grimberg.me>,
	<linux-nvme@lists.infradead.org>, <rafael@kernel.org>,
	<linux-kernel@vger.kernel.org>, <linux-pm@vger.kernel.org>,
	<kai.heng.feng@canonical.com>
Subject: RE: [PATCH] nvme/pci: Use host managed power state for suspend
Date: Mon, 13 May 2019 14:43:43 +0000	[thread overview]
Message-ID: <b12ff66f8c224e4199ff1b90ed6bc393@AUSX13MPC105.AMER.DELL.COM> (raw)
In-Reply-To: <20190513143741.GA25500@lst.de>

> -----Original Message-----
> From: Christoph Hellwig <hch@lst.de>
> Sent: Monday, May 13, 2019 9:38 AM
> To: Limonciello, Mario
> Cc: keith.busch@intel.com; hch@lst.de; sagi@grimberg.me; linux-
> nvme@lists.infradead.org; rafael@kernel.org; linux-kernel@vger.kernel.org; linux-
> pm@vger.kernel.org; kai.heng.feng@canonical.com
> Subject: Re: [PATCH] nvme/pci: Use host managed power state for suspend
> 
> 
> [EXTERNAL EMAIL]
> 
> On Mon, May 13, 2019 at 02:24:41PM +0000, Mario.Limonciello@dell.com wrote:
> > I've received the result that from one of my partners this patch doesn't
> > work properly and the platform doesn't go into a lower power state.
> 
> Well, it sounds like your partners device does not work properly in this
> case.  There is nothing in the NVMe spec that says queues should be
> torn down for deep power states, and that whole idea seems rather
> counter productive to low-latency suspend/resume cycles.

Well I've got a thought, quoting the NVME spec:
"After a successful completion of a Set Features command for this feature, the controller shall be in the
Power State specified. If enabled, autonomous power state transitions continue to occur from the new state."

If APST is enabled on this disk, what is to stop an autonomous  reverse
transition from queue activity on the way down?

> 
> > This was not a disk with HMB, but with regard to the HMB I believe it
> > needs to be removed during s0ix so that there isn't any mistake that SSD
> > thinks it can access HMB memory in s0ix.
> 
> There is no mistake - the device is allowed to use the HMB from the
> point that we give it the memory range until the point where we either
> disable it, or shut the controller down.  If something else requires the
> device not to use the HMB after ->suspend is called we need to disable
> the HMB, and we better have a good reason for that and document it in
> the code.  Note that shutting down queues or having CPU memory barriers
> is not going to help with any of that.

So maybe the CPU memory barriers were probably just working around it in terms of
timing.

  reply	other threads:[~2019-05-13 14:43 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-10 21:29 Keith Busch
2019-05-11  0:52 ` Mario.Limonciello
2019-05-13 14:24   ` Mario.Limonciello
2019-05-13 14:37     ` Christoph Hellwig
2019-05-13 14:43       ` Mario.Limonciello [this message]
2019-05-13 14:54         ` Christoph Hellwig
2019-05-13 14:55         ` Keith Busch
2019-05-13 15:05           ` Mario.Limonciello
2019-05-13 15:04             ` Keith Busch
2019-05-14  8:04               ` Rafael J. Wysocki
2019-05-14 22:16                 ` Keith Busch
2019-05-15  9:00                   ` Rafael J. Wysocki
2019-05-13 14:37     ` Keith Busch
2019-05-13 14:54       ` Mario.Limonciello
2019-05-13 14:57         ` Christoph Hellwig
2019-05-13 15:16           ` Keith Busch
2019-05-13 17:16             ` Kai-Heng Feng
2019-05-13 18:16               ` Keith Busch
2019-05-13 18:01           ` Mario.Limonciello
2019-05-14  6:11             ` Christoph Hellwig
2019-05-11  1:33 ` Edmund Nadolski
2019-05-11  7:22 ` Christoph Hellwig
2019-05-12 14:34   ` Sagi Grimberg
2019-05-13 13:36   ` Keith Busch
2019-05-12  6:06 ` Chaitanya Kulkarni
2019-05-12 14:30   ` Minwoo Im
2019-05-12 15:20     ` Chaitanya Kulkarni
2019-05-13 13:47   ` Keith Busch

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=b12ff66f8c224e4199ff1b90ed6bc393@AUSX13MPC105.AMER.DELL.COM \
    --to=mario.limonciello@dell.com \
    --cc=hch@lst.de \
    --cc=kai.heng.feng@canonical.com \
    --cc=keith.busch@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=rafael@kernel.org \
    --cc=sagi@grimberg.me \
    --subject='RE: [PATCH] nvme/pci: Use host managed power state for suspend' \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).