All of lore.kernel.org
 help / color / mirror / Atom feed
From: Will Deacon <will.deacon@arm.com>
To: Robert Richter <robert.richter@cavium.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	"linux-arm-kernel@lists.infradead.org" 
	<linux-arm-kernel@lists.infradead.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Hanjun Guo <hanjun.guo@linaro.org>,
	Yisheng Xie <xieyisheng1@huawei.com>,
	James Morse <james.morse@arm.com>
Subject: Re: [PATCH 2/2] arm64: mm: enable CONFIG_HOLES_IN_ZONE for NUMA
Date: Thu, 5 Jan 2017 12:08:20 +0000	[thread overview]
Message-ID: <20170105120819.GH679@arm.com> (raw)
In-Reply-To: <20170105112407.GU4930@rric.localdomain>

On Thu, Jan 05, 2017 at 12:24:07PM +0100, Robert Richter wrote:
> On 04.01.17 14:02:23, Will Deacon wrote:
> > Using early_pfn_valid feels like a bodge to me, since having pfn_valid
> > return false for something that early_pfn_valid says is valid (and is
> > therefore initialised in the memmap) makes the NOMAP semantics even more
> > confusing.
> 
> The concern I have had with HOLES_IN_ZONE is that it enables
> pfn_valid_within() for arm64. This means that each pfn of a section is
> checked which is done only once for the section otherwise. With up to
> 2^18 pages per section we traverse the memblock list by that factor
> more often. There could be a performance regression.

There could be, but we're trying to fix a bug here. I wouldn't have
thought that walking over pfns like that is done very often.

> I haven't numbers yet, since the fix causes another kernel crash. And,
> this is the next problem I have. The crash doesn't happen otherwise. So,
> either it uncovers another bug or the fix is incomplete. Though the
> changes look like it should work. This needs more investigation.

I really can't see how the fix causes a crash, and I couldn't reproduce
it on any of my boards, nor could any of the Linaro folk afaik. Are you
definitely running mainline with just these two patches from Ard?

Will

WARNING: multiple messages have this Message-ID (diff)
From: Will Deacon <will.deacon@arm.com>
To: Robert Richter <robert.richter@cavium.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	"linux-arm-kernel@lists.infradead.org"
	<linux-arm-kernel@lists.infradead.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Hanjun Guo <hanjun.guo@linaro.org>,
	Yisheng Xie <xieyisheng1@huawei.com>,
	James Morse <james.morse@arm.com>
Subject: Re: [PATCH 2/2] arm64: mm: enable CONFIG_HOLES_IN_ZONE for NUMA
Date: Thu, 5 Jan 2017 12:08:20 +0000	[thread overview]
Message-ID: <20170105120819.GH679@arm.com> (raw)
In-Reply-To: <20170105112407.GU4930@rric.localdomain>

On Thu, Jan 05, 2017 at 12:24:07PM +0100, Robert Richter wrote:
> On 04.01.17 14:02:23, Will Deacon wrote:
> > Using early_pfn_valid feels like a bodge to me, since having pfn_valid
> > return false for something that early_pfn_valid says is valid (and is
> > therefore initialised in the memmap) makes the NOMAP semantics even more
> > confusing.
> 
> The concern I have had with HOLES_IN_ZONE is that it enables
> pfn_valid_within() for arm64. This means that each pfn of a section is
> checked which is done only once for the section otherwise. With up to
> 2^18 pages per section we traverse the memblock list by that factor
> more often. There could be a performance regression.

There could be, but we're trying to fix a bug here. I wouldn't have
thought that walking over pfns like that is done very often.

> I haven't numbers yet, since the fix causes another kernel crash. And,
> this is the next problem I have. The crash doesn't happen otherwise. So,
> either it uncovers another bug or the fix is incomplete. Though the
> changes look like it should work. This needs more investigation.

I really can't see how the fix causes a crash, and I couldn't reproduce
it on any of my boards, nor could any of the Linaro folk afaik. Are you
definitely running mainline with just these two patches from Ard?

Will

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: will.deacon@arm.com (Will Deacon)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 2/2] arm64: mm: enable CONFIG_HOLES_IN_ZONE for NUMA
Date: Thu, 5 Jan 2017 12:08:20 +0000	[thread overview]
Message-ID: <20170105120819.GH679@arm.com> (raw)
In-Reply-To: <20170105112407.GU4930@rric.localdomain>

On Thu, Jan 05, 2017 at 12:24:07PM +0100, Robert Richter wrote:
> On 04.01.17 14:02:23, Will Deacon wrote:
> > Using early_pfn_valid feels like a bodge to me, since having pfn_valid
> > return false for something that early_pfn_valid says is valid (and is
> > therefore initialised in the memmap) makes the NOMAP semantics even more
> > confusing.
> 
> The concern I have had with HOLES_IN_ZONE is that it enables
> pfn_valid_within() for arm64. This means that each pfn of a section is
> checked which is done only once for the section otherwise. With up to
> 2^18 pages per section we traverse the memblock list by that factor
> more often. There could be a performance regression.

There could be, but we're trying to fix a bug here. I wouldn't have
thought that walking over pfns like that is done very often.

> I haven't numbers yet, since the fix causes another kernel crash. And,
> this is the next problem I have. The crash doesn't happen otherwise. So,
> either it uncovers another bug or the fix is incomplete. Though the
> changes look like it should work. This needs more investigation.

I really can't see how the fix causes a crash, and I couldn't reproduce
it on any of my boards, nor could any of the Linaro folk afaik. Are you
definitely running mainline with just these two patches from Ard?

Will

  reply	other threads:[~2017-01-05 12:08 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-12-14  9:11 [PATCH 0/2] arm64: numa: fix spurious BUG() on NOMAP regions Ard Biesheuvel
2016-12-14  9:11 ` Ard Biesheuvel
2016-12-14  9:11 ` Ard Biesheuvel
2016-12-14  9:11 ` [PATCH 1/2] mm: don't dereference struct page fields of invalid pages Ard Biesheuvel
2016-12-14  9:11   ` Ard Biesheuvel
2016-12-14  9:11   ` Ard Biesheuvel
2017-01-04 12:16   ` Will Deacon
2017-01-04 12:16     ` Will Deacon
2017-01-04 12:16     ` Will Deacon
2016-12-14  9:11 ` [PATCH 2/2] arm64: mm: enable CONFIG_HOLES_IN_ZONE for NUMA Ard Biesheuvel
2016-12-14  9:11   ` Ard Biesheuvel
2016-12-14  9:11   ` Ard Biesheuvel
2016-12-15 15:39   ` Robert Richter
2016-12-15 15:39     ` Robert Richter
2016-12-15 15:39     ` Robert Richter
2016-12-15 16:07     ` Ard Biesheuvel
2016-12-15 16:07       ` Ard Biesheuvel
2016-12-15 16:07       ` Ard Biesheuvel
2016-12-16 17:10       ` Robert Richter
2016-12-16 17:10         ` Robert Richter
2016-12-16 17:10         ` Robert Richter
2016-12-16  1:57     ` Hanjun Guo
2016-12-16  1:57       ` Hanjun Guo
2016-12-16  1:57       ` Hanjun Guo
2016-12-16 17:14       ` Robert Richter
2016-12-16 17:14         ` Robert Richter
2016-12-16 17:14         ` Robert Richter
2017-01-04 13:28   ` Will Deacon
2017-01-04 13:28     ` Will Deacon
2017-01-04 13:28     ` Will Deacon
2017-01-04 13:50     ` Ard Biesheuvel
2017-01-04 13:50       ` Ard Biesheuvel
2017-01-04 13:50       ` Ard Biesheuvel
2017-01-04 14:02       ` Will Deacon
2017-01-04 14:02         ` Will Deacon
2017-01-04 14:02         ` Will Deacon
2017-01-05 11:24         ` Robert Richter
2017-01-05 11:24           ` Robert Richter
2017-01-05 11:24           ` Robert Richter
2017-01-05 12:08           ` Will Deacon [this message]
2017-01-05 12:08             ` Will Deacon
2017-01-05 12:08             ` Will Deacon
2017-01-05 12:22             ` Robert Richter
2017-01-05 12:22               ` Robert Richter
2017-01-05 12:22               ` Robert Richter
2017-01-05 19:49               ` Robert Richter
2017-01-05 19:49                 ` Robert Richter
2017-01-05 19:49                 ` Robert Richter
2017-01-06 12:03                 ` Will Deacon
2017-01-06 12:03                   ` Will Deacon
2017-01-06 12:03                   ` Will Deacon
2017-01-06 12:22                   ` Ard Biesheuvel
2017-01-06 12:22                     ` Ard Biesheuvel
2017-01-06 12:22                     ` Ard Biesheuvel
2017-02-06 13:36   ` Robert Richter
2017-02-06 13:36     ` Robert Richter
2017-02-06 13:36     ` Robert Richter

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=20170105120819.GH679@arm.com \
    --to=will.deacon@arm.com \
    --cc=akpm@linux-foundation.org \
    --cc=ard.biesheuvel@linaro.org \
    --cc=catalin.marinas@arm.com \
    --cc=hanjun.guo@linaro.org \
    --cc=james.morse@arm.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=robert.richter@cavium.com \
    --cc=xieyisheng1@huawei.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.