From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:45391)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <paolo.bonzini@gmail.com>) id 1Uz9KW-0001mR-1X
	for qemu-devel@nongnu.org; Tue, 16 Jul 2013 13:46:29 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <paolo.bonzini@gmail.com>) id 1Uz9KU-0004gw-Rd
	for qemu-devel@nongnu.org; Tue, 16 Jul 2013 13:46:27 -0400
Sender: Paolo Bonzini <paolo.bonzini@gmail.com>
Message-ID: <51E586E6.1060001@redhat.com>
Date: Tue, 16 Jul 2013 19:46:14 +0200
From: Paolo Bonzini <pbonzini@redhat.com>
MIME-Version: 1.0
References: <1373995321-2470-1-git-send-email-aarcange@redhat.com>
	<20130716173844.GC19826@otherpad.lan.raisama.net>
In-Reply-To: <20130716173844.GC19826@otherpad.lan.raisama.net>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCH] fix guest physical bits to match host,
 to go beyond 1TB guests
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Eduardo Habkost <ehabkost@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>, qemu-devel@nongnu.org, Gleb Natapov <gleb@redhat.com>, qemu-stable@nongnu.org

Il 16/07/2013 19:38, Eduardo Habkost ha scritto:
> On Tue, Jul 16, 2013 at 07:22:01PM +0200, Andrea Arcangeli wrote:
>> Without this patch the guest physical bits are advertised as 40, not
>> 44 or more depending on the hardware capability of the host.
>>
>> That leads to guest kernel crashes with injection of page faults 9
>> (see oops: 0009) as bits above 40 in the guest pagetables are
>> considered reserved.
>>
>> exregion-0206 [324572448] [17] ex_system_memory_space: System-Memory (width 32) R/W 0 Address=00000000FED00000
>> BUG: unable to handle kernel paging request at ffffc9006030e000
>> IP: [<ffffffff812fbb6f>] acpi_ex_system_memory_space_handler+0x23e/0x2cb
>> PGD e01f875067 PUD 1001f075067 PMD e0178d8067 PTE 80000000fed00173
>> Oops: 0009 [#1] SMP
>>
>> (see PUD with bit >=40 set)
> 
> I am not sure I understand what caused this: if we are advertising 40
> physical bits to the guest, why are we ending up with a PUD with
> bit >= 40 set?

Because we create a guest that has bigger memory than what we advertise
in CPUID.

>>
>> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
>> Reported-by: Chegu Vinod <chegu_vinod@hp.com>
>> ---
>>  target-i386/cpu.c | 6 ++++++
>>  1 file changed, 6 insertions(+)
>>
>> diff --git a/target-i386/cpu.c b/target-i386/cpu.c
>> index e3f75a8..0e65673 100644
>> --- a/target-i386/cpu.c
>> +++ b/target-i386/cpu.c
>> @@ -2108,6 +2108,12 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
>>              /* 64 bit processor */
>>  /* XXX: The physical address space is limited to 42 bits in exec.c. */
>>              *eax = 0x00003028; /* 48 bits virtual, 40 bits physical */
>> +            if (kvm_enabled()) {
>> +                uint32_t _eax;
>> +                host_cpuid(0x80000000, 0, &_eax, NULL, NULL, NULL);
>> +                if (_eax >= 0x80000008)
>> +                    host_cpuid(0x80000008, 0, eax, NULL, NULL, NULL);
>> +            }
> 
> We can't expose a different virtual machine depending on host
> capabilities. What if we live-migrate between hosts with different
> physical address bit sizes?

Same as for vPMU or leaf 0xD: who knows.  In practice, this has an
effect only for guests with 1T or more memory, otherwise the physical
memory is smaller than 40 bits.

Paolo

>>          } else {
>>              if (env->features[FEAT_1_EDX] & CPUID_PSE36) {
>>                  *eax = 0x00000024; /* 36 bits physical */
>>
>