Re: Excessive TLB flush ranges

From: "Russell King (Oracle)" <linux@armlinux.org.uk>
To: Baoquan He <bhe@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>,
	Uladzislau Rezki <urezki@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, Christoph Hellwig <hch@lst.de>,
	Lorenzo Stoakes <lstoakes@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	John Ogness <jogness@linutronix.de>,
	linux-arm-kernel@lists.infradead.org,
	Mark Rutland <mark.rutland@arm.com>,
	Marc Zyngier <maz@kernel.org>
Subject: Re: Excessive TLB flush ranges
Date: Tue, 16 May 2023 09:45:08 +0100	[thread overview]
Message-ID: <ZGNClHgIFnqLvzhW@shell.armlinux.org.uk> (raw)
In-Reply-To: <ZGM5ta1HK7pMix4B@bhe.users.ipa.redhat.com>

On Tue, May 16, 2023 at 04:07:17PM +0800, Baoquan He wrote:
> On 05/16/23 at 08:40am, Thomas Gleixner wrote:
> > On Tue, May 16 2023 at 10:26, Baoquan He wrote:
> > > On 05/15/23 at 08:17pm, Uladzislau Rezki wrote:
> > >> For systems which lack a full TLB flush and to flush a long range is
> > >> a problem(it takes time), probably we can flush VA one by one. Because
> > >> currently we calculate a flush range [min:max] and that range includes
> > >> the space that might not be mapped at all. Like below:
> > >
> > > It's fine if we only calculate a flush range of [min:max] with VA. In
> > > vm_reset_perms(), it calculates the flush range with the impacted direct
> > > mapping range, then merge it with VA's range. That looks really strange
> > > and surprising. If the vm->pages[] are got from a lower part of physical
> > > memory, the final merged flush will span tremendous range. Wondering why
> > > we need merge the direct map range with VA range, then do flush. Not
> > > sure if I misunderstand it.
> > 
> > So what happens on this BPF teardown is:
> > 
> > The vfree(8k) ends up flushing 3 entries. The actual vmalloc part (2) and
> > one extra which is in the direct map. I haven't verified that yet, but I
> > assume it's the alias of one of the vmalloc'ed pages.
> 
> It looks like the reason. As Uladzislau pointed out, ARCH-es may
> have full TLB flush, so won't get trouble from the merged flush
> in the calculated [min:max] way, e.g arm64 and x86's flush_tlb_kernel_range().
> However, arm32 seems lacking the ability of full TLB flash. If agreed, I
> can make a draft patch to do the flush for direct map and VA seperately,
> see if it works.

The question IMHO is not so much whether there's a full-TLB flush
available, but whether it is appropriate to use it. If we're only
wanting to flush a small number of TLB entries but over a sparse
range (which seems to be Thomas' situation), does it make any sense
to flush all TLB entries? I don't think it does, but it depends
how often this occurs. If we're doing it on a regular basis because
of some workload, then that workload suffers. If it's a rare event
then maybe that's okay to do.

-- 
RMK's Patch system: https://www.armlinux.org.uk/developer/patches/
FTTP is here! 80Mbps down 10Mbps up. Decent connectivity at last!

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel