linux-kernel - Re: [RFC PATCH V2 00/22] Intel(R) Resource Director Technology Cache Pseudo-Locking enabling

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

Date:   Thu, 15 Feb 2018 12:39:55 -0800
From:   Reinette Chatre <reinette.chatre@...el.com>
To:     Mike Kravetz <mike.kravetz@...cle.com>, tglx@...utronix.de,
        fenghua.yu@...el.com, tony.luck@...el.com
Cc:     gavin.hindman@...el.com, vikas.shivappa@...ux.intel.com,
        dave.hansen@...el.com, mingo@...hat.com, hpa@...or.com,
        x86@...nel.org, linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        Andrew Morton <akpm@...ux-foundation.org>,
        Michal Hocko <mhocko@...e.com>,
        Vlastimil Babka <vbabka@...e.cz>
Subject: Re: [RFC PATCH V2 00/22] Intel(R) Resource Director Technology Cache
 Pseudo-Locking enabling

On 2/14/2018 10:31 AM, Reinette Chatre wrote:
> On 2/14/2018 10:12 AM, Mike Kravetz wrote:
>> On 02/13/2018 07:46 AM, Reinette Chatre wrote:
>>> Adding MM maintainers to v2 to share the new MM change (patch 21/22) that
>>> enables large contiguous regions that was created to support large Cache
>>> Pseudo-Locked regions (patch 22/22). This week MM team received another
>>> proposal to support large contiguous allocations ("[RFC PATCH 0/3]
>>> Interface for higher order contiguous allocations" at
>>> http://lkml.kernel.org/r/20180212222056.9735-1-mike.kravetz@oracle.com).
>>> I have not yet tested with this new proposal but it does seem appropriate
>>> and I should be able to rework patch 22 from this series on top of that if
>>> it is accepted instead of what I have in patch 21 of this series.
>>>
>>
>> Well, I certainly would prefer the adoption and use of a more general
>> purpose interface rather than exposing alloc_gigantic_page().
>>
>> Both the interface I suggested and alloc_gigantic_page end up calling
>> alloc_contig_range().  I have not looked at your entire patch series, but
>> do be aware that in its present form alloc_contig_range will run into
>> issues if called by two threads simultaneously for the same page range.
>> Calling alloc_gigantic_page without some form of synchronization will
>> expose this issue.  Currently this is handled by hugetlb_lock for all
>> users of alloc_gigantic_page.  If you simply expose alloc_gigantic_page
>> without any type of synchronization, you may run into issues.  The first
>> patch in my RFC "mm: make start_isolate_page_range() fail if already
>> isolated" should handle this situation IF we decide to expose
>> alloc_gigantic_page (which I do not suggest).
> 
> My work depends on the ability to create large contiguous regions,
> creating these large regions is not the goal in itself. Certainly I
> would want to use the most appropriate mechanism and I would gladly
> modify my work to do so.
> 
> I do not insist on using alloc_gigantic_page(). Now that I am aware of
> your RFC I started the process to convert to the new
> find_alloc_contig_pages(). I did not do so earlier because it was not
> available when I prepared this work for submission. I plan to respond to
> your RFC when my testing is complete but please give me a few days to do
> so. Could you please also cc me if you do send out any new versions?

Testing with the new find_alloc_contig_pages() introduced in
"[RFC PATCH 0/3] Interface for higher order contiguous allocations" at
http://lkml.kernel.org/r/20180212222056.9735-1-mike.kravetz@oracle.com
was successful. If this new interface is merged then Cache
Pseudo-Locking can easily be ported to use that instead of what I have
in patch 21/22 (exposing alloc_gigantic_page()) with the following
change to patch 22/22:


diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 99918943a98a..b5e4ae379352 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -228,9 +228,10 @@ static int contig_mem_alloc(struct
pseudo_lock_region *plr)
        }

        if (plr->size > KMALLOC_MAX_SIZE) {
-               plr->kmem = alloc_gigantic_page(cpu_to_node(plr->cpu),
-                                               get_order(plr->size),
-                                               GFP_KERNEL | __GFP_ZERO);
+               plr->kmem = find_alloc_contig_pages(get_order(plr->size),
+                                                   GFP_KERNEL | __GFP_ZERO,
+                                                   cpu_to_node(plr->cpu),
+                                                   NULL);
                if (!plr->kmem) {
                        rdt_last_cmd_puts("unable to allocate gigantic
page\n");
                        return -ENOMEM;
@@ -255,7 +256,7 @@ static int contig_mem_alloc(struct
pseudo_lock_region *plr)
 static void contig_mem_free(struct pseudo_lock_region *plr)
 {
        if (plr->size > KMALLOC_MAX_SIZE)
-               free_gigantic_page(plr->kmem, get_order(plr->size));
+               free_contig_pages(plr->kmem, 1 << get_order(plr->size));
        else
                kfree(page_to_virt(plr->kmem));
 }


It does seem as though there will be a new API for large contiguous
allocations, eliminating the need for patch 21 of this series. How large
contiguous regions are allocated are independent of Cache Pseudo-Locking
though and the patch series as submitted still stands. I can include the
above snippet in a new version of the series but I am not sure if it is
preferred at this time. Please do let me know, I'd be happy to.

Reinette