qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Xiaoyao Li <xiaoyao.li@intel.com>
To: "Philippe Mathieu-Daudé" <philmd@linaro.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>
Cc: qemu-devel@nongnu.org, Chenyi Qiang <chenyi.qiang@intel.com>
Subject: Re: [PATCH] multiboot: Fix the split lock
Date: Fri, 12 Sep 2025 13:49:12 +0800	[thread overview]
Message-ID: <589b6c9b-9d83-4137-a9b0-16a7516cdb0a@intel.com> (raw)
In-Reply-To: <d480bd1f-535c-4001-b489-4a0d8b62a80b@linaro.org>

On 8/8/2025 6:54 PM, Philippe Mathieu-Daudé wrote:
> On 8/8/25 05:50, Xiaoyao Li wrote:
>> While running the kvm-unit-tests on Intel platforms with "split lock
>> disable" feature, every test triggers a kernel warning of
>>
>>    x86/split lock detection: #AC: qemu-system-x86_64/373232 took a 
>> split_lock trap at address: 0x1e3
>>
>> Hack KVM by exiting to QEMU on split lock #AC, we get
>>
>> KVM: exception 17 exit (error code 0x0)
>> EAX=00000001 EBX=00000000 ECX=00000014 EDX=0001fb80
>> ESI=00000000 EDI=000000a8 EBP=00000000 ESP=00006f10
>> EIP=000001e3 EFL=00010002 [-------] CPL=0 II=0 A20=1 SMM=0 HLT=0
>> ES =0900 00009000 0000ffff 00009300 DPL=0 DS16 [-WA]
>> CS =c000 000c0000 0000ffff 00009b00 DPL=0 CS16 [-RA]
>> SS =0000 00000000 0000ffff 00009300 DPL=0 DS16 [-WA]
>> DS =c000 000c0000 0000ffff 00009300 DPL=0 DS16 [-WA]
>> FS =0950 00009500 0000ffff 00009300 DPL=0 DS16 [-WA]
>> GS =06f2 00006f20 0000ffff 00009300 DPL=0 DS16 [-WA]
>> LDT=0000 00000000 0000ffff 00008200 DPL=0 LDT
>> TR =0000 00000000 0000ffff 00008b00 DPL=0 TSS32-busy
>> GDT=     000c02b4 00000027
>> IDT=     00000000 000003ff
>> CR0=00000011 CR2=00000000 CR3=00000000 CR4=00000000
>> DR0=0000000000000000 DR1=0000000000000000 DR2=0000000000000000 
>> DR3=0000000000000000
>> DR6=00000000ffff0ff0 DR7=0000000000000400
>> EFER=0000000000000000
>> Code=89 16 08 00 65 66 0f 01 16 06 00 66 b8 01 00 00 00 0f 22 c0 <65> 
>> 66 ff 2e 00 00 b8 10 00 00 00 8e d0 8e d8 8e c0 8e e0 8e e8 66 b8 08 
>> 00 66 ba 10 05 66
>>
>> And it matches with what disassembled from multiboo_dma.bin:
>>
>>   #objdump -b binary -m i386 -D pc-bios/multiboot_dma.bin
>>
>>    1d1:   08 00                   or     %al,(%eax)
>>    1d3:   65 66 0f 01 16          lgdtw  %gs:(%esi)
>>    1d8:   06                      push   %es
>>    1d9:   00 66 b8                add    %ah,-0x48(%esi)
>>    1dc:   01 00                   add    %eax,(%eax)
>>    1de:   00 00                   add    %al,(%eax)
>>    1e0:   0f 22 c0                mov    %eax,%cr0
>>> 1e3:   65 66 ff 2e             ljmpw  *%gs:(%esi)
>>    1e7:   00 00                   add    %al,(%eax)
>>    1e9:   b8 10 00 00 00          mov    $0x10,%eax
>>    1ee:   8e d0                   mov    %eax,%ss
>>    1f0:   8e d8                   mov    %eax,%ds
>>    1f2:   8e c0                   mov    %eax,%es
>>    1f4:   8e e0                   mov    %eax,%fs
>>    1f6:   8e e8                   mov    %eax,%gs
>>    1f8:   66 b8 08 00             mov    $0x8,%ax
>>    1fc:   66 ba 10 05             mov    $0x510,%dx
>>
>> We can see that the instruction at 0x1e3 is a far jmp through the GDT.
>> However, the GDT is not 8 byte aligned, the base is 0xc02b4.
>>
>> Intel processors follow the LOCK semantics to set the accessed flag of 
>> the
>> segment descriptor when loading a segment descriptor. If the the segment
>> descriptor crosses two cache line, it causes split lock.
>>
>> Fix it by aligning the GDT on 8 bytes, so that segment descriptor cannot
>> span two cache lines.
>>
> 
> Cc: qemu-stable@nongnu.org
> Fixes: f16408dfb0e ("Multiboot support")
> 
>> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
>> ---
>>   pc-bios/multiboot_dma.bin     | Bin 1024 -> 1024 bytes
>>   pc-bios/optionrom/multiboot.S |   2 +-
>>   2 files changed, 1 insertion(+), 1 deletion(-)
> 
> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
> 

Ping on this.

Paolo, will you take it or leave it to someone else?



  reply	other threads:[~2025-09-12  5:49 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-08  3:50 [PATCH] multiboot: Fix the split lock Xiaoyao Li
2025-08-08 10:54 ` Philippe Mathieu-Daudé
2025-09-12  5:49   ` Xiaoyao Li [this message]
2025-09-13  4:32 ` Paolo Bonzini

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=589b6c9b-9d83-4137-a9b0-16a7516cdb0a@intel.com \
    --to=xiaoyao.li@intel.com \
    --cc=chenyi.qiang@intel.com \
    --cc=pbonzini@redhat.com \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.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;
as well as URLs for NNTP newsgroup(s).