linux-kernel - Re: slow boot with 7fef431be9c9 ("mm/page_alloc: place pages to tail in __free_pages

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:   Tue, 16 Mar 2021 08:50:28 +0200
From:   Mike Rapoport <rppt@...ux.ibm.com>
To:     "Liang, Liang (Leo)" <Liang.Liang@....com>
Cc:     David Hildenbrand <david@...hat.com>,
        "Deucher, Alexander" <Alexander.Deucher@....com>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        amd-gfx list <amd-gfx@...ts.freedesktop.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        "Huang, Ray" <Ray.Huang@....com>,
        "Koenig, Christian" <Christian.Koenig@....com>,
        "Rafael J. Wysocki" <rafael@...nel.org>,
        George Kennedy <george.kennedy@...cle.com>
Subject: Re: slow boot with 7fef431be9c9 ("mm/page_alloc: place pages to tail
 in __free_pages_core()")

Hi Leo,

On Tue, Mar 16, 2021 at 12:36:29AM +0000, Liang, Liang (Leo) wrote:
> 
> Hi David,
> 
> Sorry for late. If revert 7fef431be9c9 (without 7fef431be9c9), the dmesg attached. And looks the exception as below:
> [  +0.027833] [0x0000000078000000 - 0x00000000783fffff] 20925 MB/s / 25405 MB/s
> [  +1.363596] [0x0000000100000000 - 0x00000001003fffff] 222 MB/s / 222 MB/s
> [  +1.562192] [0x0000000100400000 - 0x00000001007fffff] 222 MB/s / 222 MB/s
> [  +1.881332] [0x0000000100800000 - 0x0000000100bfffff] 195 MB/s / 159 MB/s
> [  +1.383388] [0x0000000100c00000 - 0x0000000100ffffff] 219 MB/s / 221 MB/s
> [  +0.029342] [0x0000000101000000 - 0x00000001013fffff] 19807 MB/s / 24125 MB/s
> 
> What is the problem here? Do you want to check the acpi tables?

As it seems the first 16M at 0x0000000100000000 are two orders of magnitude
slower than the rest of the memory as if there is a different memory device
there.

This would explain why with 7fef431be9c9 everything gets slower as we
allocate the first (and probably quite critical) data from those 16M.

No idea how this could be related to ACPI and why ACPI initialization
causes the huge slowdown on its own.

Can you please try booting with 7fef431be9c9 still applied and with this
patch (not even compile tested):

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d883176ef2ce..780f11ca14c9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -778,6 +778,7 @@ void __init setup_arch(char **cmdline_p)
 	 * L1TF its contents can be leaked to user processes.
 	 */
 	memblock_reserve(0, PAGE_SIZE);
+	memblock_reserve(0x0000000100000000, SZ_16M);
 
 	early_reserve_initrd();
 
 
> BRs,
> Leo
> -----Original Message-----
> From: David Hildenbrand <david@...hat.com> 
> Sent: Monday, March 15, 2021 9:04 PM
> To: Mike Rapoport <rppt@...ux.ibm.com>
> Cc: Liang, Liang (Leo) <Liang.Liang@....com>; Deucher, Alexander <Alexander.Deucher@....com>; linux-kernel@...r.kernel.org; amd-gfx list <amd-gfx@...ts.freedesktop.org>; Andrew Morton <akpm@...ux-foundation.org>; Huang, Ray <Ray.Huang@....com>; Koenig, Christian <Christian.Koenig@....com>; Rafael J. Wysocki <rafael@...nel.org>; George Kennedy <george.kennedy@...cle.com>
> Subject: Re: slow boot with 7fef431be9c9 ("mm/page_alloc: place pages to tail in __free_pages_core()")
> 
> On 13.03.21 14:48, Mike Rapoport wrote:
> > Hi,
> > 
> > On Sat, Mar 13, 2021 at 10:05:23AM +0100, David Hildenbrand wrote:
> >>> Am 13.03.2021 um 05:04 schrieb Liang, Liang (Leo) <Liang.Liang@....com>:
> >>>
> >>> Hi David,
> >>>
> >>> Which benchmark tool you prefer? Memtest86+ or else?
> >>
> >> Hi Leo,
> >>
> >> I think you want something that runs under Linux natively.
> >>
> >> I'm planning on coding up a kernel module to walk all 4MB pages in 
> >> the freelists and perform a stream benchmark individually. Then we 
> >> might be able to identify the problematic range - if there is a 
> >> problematic range :)
> > 
> > My wild guess would be that the pages that are now at the head of free 
> > lists have wrong caching enabled. Might be worth checking in your test 
> > module.
> 
> I hacked something up real quick:
> 
> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fdavidhildenbrand%2Fkstream&amp;data=04%7C01%7Cliang.liang%40amd.com%7C61fb103eeb7647f5228408d8e7b2d7d3%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637514102622932303%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&amp;sdata=ufUYQRtdSHvEkR61LiJZtsVdYZbtdGbKlzZHOQdct78%3D&amp;reserved=0
> 
> Only briefly tested inside a VM. The output looks something like
> 
> [...]
> [ 8396.432225] [0x0000000045800000 - 0x0000000045bfffff] 25322 MB/s /
> 38948 MB/s
> [ 8396.448749] [0x0000000045c00000 - 0x0000000045ffffff] 24481 MB/s /
> 38946 MB/s
> [ 8396.465197] [0x0000000046000000 - 0x00000000463fffff] 24892 MB/s /
> 39170 MB/s
> [ 8396.481552] [0x0000000046400000 - 0x00000000467fffff] 25222 MB/s /
> 39156 MB/s
> [ 8396.498012] [0x0000000046800000 - 0x0000000046bfffff] 24416 MB/s /
> 39159 MB/s
> [ 8396.514397] [0x0000000046c00000 - 0x0000000046ffffff] 25469 MB/s /
> 38940 MB/s
> [ 8396.530849] [0x0000000047000000 - 0x00000000473fffff] 24885 MB/s /
> 38734 MB/s
> [ 8396.547195] [0x0000000047400000 - 0x00000000477fffff] 25458 MB/s /
> 38941 MB/s
> [...]
> 
> The benchmark allocates one 4 MiB chunk at a time and runs a simplified STREAM benchmark a) without flushing caches b) flushing caches before every memory access.
> 
> It would be great if you could run that with the *old behavior* kernel (IOW, without 7fef431be9c9), so we might still be lucky to catch the problematic area in the freelist.
> 
> Let's see if that will indicate anything.
> 
> --
> Thanks,
> 
> David / dhildenb



-- 
Sincerely yours,
Mike.