All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: akpm@linux-foundation.org, npiggin@gmail.com, mpe@ellerman.id.au,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linuxppc-dev@lists.ozlabs.org
Subject: Re: [RFC PATCH 2/2] mm/mmu_gather: Avoid multiple page walk cache flush
Date: Tue, 17 Dec 2019 13:34:16 +0100	[thread overview]
Message-ID: <20191217123416.GH2827@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <32404765-ad4f-6612-d1a9-43f9acdc8a62@linux.ibm.com>

On Tue, Dec 17, 2019 at 03:45:36PM +0530, Aneesh Kumar K.V wrote:
> On 12/17/19 2:28 PM, Peter Zijlstra wrote:
> > On Tue, Dec 17, 2019 at 12:47:13PM +0530, Aneesh Kumar K.V wrote:
> > > On tlb_finish_mmu() kernel does a tlb flush before  mmu gather table invalidate.
> > > The mmu gather table invalidate depending on kernel config also does another
> > > TLBI. Avoid the later on tlb_finish_mmu().
> > 
> > That is already avoided, if you look at tlb_flush_mmu_tlbonly() it does
> > __tlb_range_reset(), which results in ->end = 0, which then triggers the
> > early exit on the next invocation:
> > 
> > 	if (!tlb->end)
> > 		return;
> > 
> 
> Is that true for tlb->fulmm flush?

Hmm, no, but I'm thinking you patch is broken, even for that case. We
must issue the TLBI before call_rcu().

Perhaps if we replace !tlb->end with something like:

  !tlb->freed_tables && !tlb->cleared_p*

(which GCC should be able to do with a single load and mask)

I've not really thought too hard about it yet, I need to run some
errands, but I'll look at it more closely when I get back.

WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: linux-kernel@vger.kernel.org, npiggin@gmail.com,
	linux-mm@kvack.org, akpm@linux-foundation.org,
	linuxppc-dev@lists.ozlabs.org
Subject: Re: [RFC PATCH 2/2] mm/mmu_gather: Avoid multiple page walk cache flush
Date: Tue, 17 Dec 2019 13:34:16 +0100	[thread overview]
Message-ID: <20191217123416.GH2827@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <32404765-ad4f-6612-d1a9-43f9acdc8a62@linux.ibm.com>

On Tue, Dec 17, 2019 at 03:45:36PM +0530, Aneesh Kumar K.V wrote:
> On 12/17/19 2:28 PM, Peter Zijlstra wrote:
> > On Tue, Dec 17, 2019 at 12:47:13PM +0530, Aneesh Kumar K.V wrote:
> > > On tlb_finish_mmu() kernel does a tlb flush before  mmu gather table invalidate.
> > > The mmu gather table invalidate depending on kernel config also does another
> > > TLBI. Avoid the later on tlb_finish_mmu().
> > 
> > That is already avoided, if you look at tlb_flush_mmu_tlbonly() it does
> > __tlb_range_reset(), which results in ->end = 0, which then triggers the
> > early exit on the next invocation:
> > 
> > 	if (!tlb->end)
> > 		return;
> > 
> 
> Is that true for tlb->fulmm flush?

Hmm, no, but I'm thinking you patch is broken, even for that case. We
must issue the TLBI before call_rcu().

Perhaps if we replace !tlb->end with something like:

  !tlb->freed_tables && !tlb->cleared_p*

(which GCC should be able to do with a single load and mask)

I've not really thought too hard about it yet, I need to run some
errands, but I'll look at it more closely when I get back.

  reply	other threads:[~2019-12-17 12:34 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-17  7:17 [RFC PATCH 1/2] mm/mmu_gather: Invalidate TLB correctly on batch allocation failure and flush Aneesh Kumar K.V
2019-12-17  7:17 ` Aneesh Kumar K.V
2019-12-17  7:17 ` [RFC PATCH 2/2] mm/mmu_gather: Avoid multiple page walk cache flush Aneesh Kumar K.V
2019-12-17  7:17   ` Aneesh Kumar K.V
2019-12-17  8:58   ` Peter Zijlstra
2019-12-17  8:58     ` Peter Zijlstra
2019-12-17 10:15     ` Aneesh Kumar K.V
2019-12-17 10:15       ` Aneesh Kumar K.V
2019-12-17 12:34       ` Peter Zijlstra [this message]
2019-12-17 12:34         ` Peter Zijlstra
2019-12-17 20:12         ` [PATCH] asm-generic/tlb: Avoid potential double flush Peter Zijlstra
2019-12-17 20:12           ` Peter Zijlstra
2019-12-17  9:09 ` [RFC PATCH 1/2] mm/mmu_gather: Invalidate TLB correctly on batch allocation failure and flush Peter Zijlstra
2019-12-17  9:09   ` Peter Zijlstra
2019-12-17 10:48   ` Aneesh Kumar K.V
2019-12-17 10:48     ` Aneesh Kumar K.V
2019-12-17 12:35     ` Peter Zijlstra
2019-12-17 12:35       ` Peter Zijlstra
2019-12-18  5:22       ` Aneesh Kumar K.V
2019-12-18  5:22         ` Aneesh Kumar K.V
2019-12-18  9:01         ` Peter Zijlstra
2019-12-18  9:01           ` Peter Zijlstra
  -- strict thread matches above, loose matches on Subject: below --
2019-12-17  7:16 Aneesh Kumar K.V
2019-12-17  7:16 ` [RFC PATCH 2/2] mm/mmu_gather: Avoid multiple page walk cache flush Aneesh Kumar K.V
2019-12-17  7:16   ` Aneesh Kumar K.V

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=20191217123416.GH2827@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.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.