public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Will Deacon <will@kernel.org>
Cc: Michal Simek <michal.simek@xilinx.com>,
	linux-kernel@vger.kernel.org, monstr@monstr.eu, git@xilinx.com,
	arnd@arndb.de,
	Stefan Asserhall load and store  <stefan.asserhall@xilinx.com>,
	Boqun Feng <boqun.feng@gmail.com>,
	paulmck@kernel.org
Subject: Re: [PATCH 7/7] microblaze: Do atomic operations by using exclusive ops
Date: Thu, 13 Feb 2020 11:15:38 +0100	[thread overview]
Message-ID: <20200213101538.GN14897@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20200213100403.GA1405@willie-the-truck>

On Thu, Feb 13, 2020 at 10:04:03AM +0000, Will Deacon wrote:
> On Thu, Feb 13, 2020 at 10:16:51AM +0100, Peter Zijlstra wrote:
> > On Thu, Feb 13, 2020 at 09:58:49AM +0100, Peter Zijlstra wrote:
> > 
> > > The thing is, your bog standard LL/SC _SHOULD_ fail the SC if someone
> > > else does a regular store to the same variable. See the example in
> > > Documentation/atomic_t.txt.
> > > 
> > > That is, a competing SW/SWI should result in the interconnect responding
> > > with something other than EXOKAY, the SWX should fail and MSR[C] <- 1.
> > 
> > The thing is; we have code that relies on this behaviour. There are a
> > few crusty SMP archs that sorta-kinda limp along (mostly by disabling
> > some of the code and praying the rest doesn't trigger too often), but we
> > really should not allow more broken SMP archs.
> 
> I did find this in the linked pdf:
> 
>   | If the store [swx] is successful, the sequence of instructions from
>   | the semaphore load to the semaphore store appear to be executed
>   | atomically - no other device modified the semaphore location between
>   | the read and the update.
> 
> which sounds like we're ok, although it could be better worded.
> 
> One part I haven't figured out is what happens if you take an interrupt
> between the lwx and the swx and whether you can end up succeeding thanks
> to somebody else's reservation. Also, the manual is silent about the
> interaction with TLB invalidation and just refers to "address" when
> talking about the reservation. What happens if a user thread triggers
> CoW while another is in the middle of a lwx/swx?

Page 79, Table 2-40 has the note:

"All of these events will clear the reservation bit, used together with
the LWX and SWX instructions to implement mutual exclusion,..."



  parent reply	other threads:[~2020-02-13 10:15 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-12 15:42 [PATCH 0/7] microblaze: Define SMP safe operations Michal Simek
2020-02-12 15:42 ` [PATCH 1/7] microblaze: timer: Don't use cpu timer setting Michal Simek
2020-02-12 15:42 ` [PATCH 2/7] microblaze: Make cpuinfo structure SMP aware Michal Simek
2020-02-12 20:42   ` Arnd Bergmann
2020-02-12 15:42 ` [PATCH 3/7] microblaze: Define SMP safe bit operations Michal Simek
2020-02-12 15:53   ` Peter Zijlstra
2020-02-13  8:42     ` Michal Simek
2020-02-13  9:01       ` Stefan Asserhall
2020-02-13  9:11         ` Peter Zijlstra
2020-02-13  9:24           ` Stefan Asserhall
2020-02-12 15:42 ` [PATCH 4/7] microblaze: Add SMP implementation of xchg and cmpxchg Michal Simek
2020-02-12 15:42 ` [PATCH 5/7] microblaze: Remove disabling IRQ while pte_update() run Michal Simek
2020-02-12 15:42 ` [PATCH 6/7] microblaze: Implement architecture spinlock Michal Simek
2020-02-12 15:47   ` Peter Zijlstra
2020-02-13  7:51     ` Michal Simek
2020-02-13  8:00       ` Peter Zijlstra
2020-02-12 15:42 ` [PATCH 7/7] microblaze: Do atomic operations by using exclusive ops Michal Simek
2020-02-12 15:55   ` Peter Zijlstra
2020-02-13  8:06     ` Michal Simek
2020-02-13  8:58       ` Peter Zijlstra
2020-02-13  9:16         ` Peter Zijlstra
2020-02-13 10:04           ` Will Deacon
2020-02-13 10:14             ` Stefan Asserhall
2020-02-13 10:20               ` Will Deacon
2020-02-13 10:15             ` Peter Zijlstra [this message]
2020-02-13 11:34         ` Boqun Feng
2020-02-13 11:38           ` Boqun Feng
2020-02-13 13:51             ` Andrea Parri
2020-02-13 14:01               ` Andrea Parri
2020-02-12 16:08 ` [PATCH 0/7] microblaze: Define SMP safe operations Peter Zijlstra
2020-02-12 16:38   ` Peter Zijlstra
2020-02-13  7:49   ` Michal Simek
2020-02-13  8:11     ` Peter Zijlstra
2020-02-13  8:12       ` Michal Simek

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=20200213101538.GN14897@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=arnd@arndb.de \
    --cc=boqun.feng@gmail.com \
    --cc=git@xilinx.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=michal.simek@xilinx.com \
    --cc=monstr@monstr.eu \
    --cc=paulmck@kernel.org \
    --cc=stefan.asserhall@xilinx.com \
    --cc=will@kernel.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox