linux-kernel - Re: [PATCH v2 11/11] powerpc/mm/book3s64/pgtable: Uses counting method to skip serializing

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Date:   Mon, 23 Sep 2019 16:40:39 -0300
From:   Leonardo Bras <leonardo@...ux.ibm.com>
To:     John Hubbard <jhubbard@...dia.com>, linuxppc-dev@...ts.ozlabs.org,
        linux-kernel@...r.kernel.org, Linux-MM <linux-mm@...ck.org>
Cc:     Arnd Bergmann <arnd@...db.de>,
        Richard Fontana <rfontana@...hat.com>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        YueHaibing <yuehaibing@...wei.com>,
        Nicholas Piggin <npiggin@...il.com>,
        Mike Rapoport <rppt@...ux.ibm.com>,
        Keith Busch <keith.busch@...el.com>,
        Jason Gunthorpe <jgg@...pe.ca>,
        Paul Mackerras <paulus@...ba.org>,
        "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
        Allison Randal <allison@...utok.net>,
        Mahesh Salgaonkar <mahesh@...ux.vnet.ibm.com>,
        Ganesh Goudar <ganeshgr@...ux.ibm.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ira Weiny <ira.weiny@...el.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Dan Williams <dan.j.williams@...el.com>
Subject: Re: [PATCH v2 11/11] powerpc/mm/book3s64/pgtable: Uses counting
 method to skip serializing

On Mon, 2019-09-23 at 11:14 -0700, John Hubbard wrote:
> On 9/23/19 10:25 AM, Leonardo Bras wrote:
> [...]
> That part is all fine, but there are no run-time memory barriers in the 
> atomic_inc() and atomic_dec() additions, which means that this is not
> safe, because memory operations on CPU 1 can be reordered. It's safe
> as shown *if* there are memory barriers to keep the order as shown:
> 
> CPU 0                            CPU 1
> ------                         --------------
>                                atomic_inc(val) (no run-time memory barrier!)
> pmd_clear(pte)
> if (val)
>     run_on_all_cpus(): IPI
>                                local_irq_disable() (also not a mem barrier)
> 
>                                READ(pte)
>                                if(pte)
>                                   walk page tables
> 
>                                local_irq_enable() (still not a barrier)
>                                atomic_dec(val)
> 
> free(pte)
> 
> thanks,

This is serialize:

void serialize_against_pte_lookup(struct mm_struct *mm)
{
	smp_mb();
	if (running_lockless_pgtbl_walk(mm))
		smp_call_function_many(mm_cpumask(mm), do_nothing,
NULL, 1);
}

That would mean:

CPU 0                            CPU 1
------                         --------------
                               atomic_inc(val) 
pmd_clear(pte)
smp_mb()
if (val)
    run_on_all_cpus(): IPI
                               local_irq_disable() 

                               READ(pte)
                               if(pte)
                                  walk page tables

                               local_irq_enable() (still not a barrier)
                               atomic_dec(val)

By https://www.kernel.org/doc/Documentation/memory-barriers.txt :
'If you need all the CPUs to see a given store at the same time, use
smp_mb().'

Is it not enough? 
Do you suggest adding 'smp_mb()' after atomic_{inc,dec} ?

Download attachment "signature.asc" of type "application/pgp-signature" (834 bytes)