[Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split lock

[Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split lock

[John E Lofgren]

REF: https://bugzilla.tianocore.org/show_bug.cgi?id=2150
V3 changes:
change to mov instruction (non locking instuction) instead
of xchg to simplify design.

V2 changes:
Add xchg 16 bit instructions to handle sgdt and sidt base
63:48 bits and 47:32 bits.
Add comment to explain why xchg 64bit isnt being used

Split lock happens when a locking instruction is used on mis-aligned data
that crosses two cachelines. If close source platform enables Alignment Check
Exception(#AC), They can hit a double fault due to split lock being in
CpuExceptionHandlerLib.

sigt and sgdt saves 10 bytes to memory, 8 bytes is base and 2 bytes is limit.
The data is mis-aligned, can cross two cacheline, and a xchg
instruction(locking instuction) is being utilize.

Signed-off-by: John E Lofgren <john.e.lofgren@intel.com>
---
 UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
index 4db1a09f28..7b7642b290 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
@@ -180,21 +180,29 @@ HasErrorCode:
     push    qword [rbp + 24]
 
 ;; UINT64  Gdtr[2], Idtr[2];
+    ; sidt and sgdt saves 10 bytes to memory, 8 bytes = base and 2 bytes = limit.
+    ; To avoid #AC split lock when separating base and limit into their
+    ; own separate 64 bit memory, we can’t use 64 bit xchg since base [63:48] bits
+    ; may cross the cache line.
     xor     rax, rax
     push    rax
     push    rax
     sidt    [rsp]
-    xchg    rax, [rsp + 2]
-    xchg    rax, [rsp]
-    xchg    rax, [rsp + 8]
+    xchg    eax, [rsp + 2]
+    xchg    eax, [rsp]
+    xchg    eax, [rsp + 8]
+    xchg     ax, [rsp + 6]
+    xchg     ax, [rsp + 4]
 
     xor     rax, rax
     push    rax
     push    rax
     sgdt    [rsp]
-    xchg    rax, [rsp + 2]
-    xchg    rax, [rsp]
-    xchg    rax, [rsp + 8]
+    xchg    eax, [rsp + 2]
+    xchg    eax, [rsp]
+    xchg    eax, [rsp + 8]
+    xchg     ax, [rsp + 6]
+    xchg     ax, [rsp + 4]
 
 ;; UINT64  Ldtr, Tr;
     xor     rax, rax
-- 
2.16.2.windows.1

Re: [edk2-devel] [Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split lock

[Laszlo Ersek]

On 09/18/19 00:49, John E Lofgren wrote:
> REF: https://bugzilla.tianocore.org/show_bug.cgi?id=2150
> V3 changes:
> change to mov instruction (non locking instuction) instead
> of xchg to simplify design.

I think something's wrong -- the v3 update described above isn't
actually implemented in the patch (it continues using XCHG, rather than
MOV).

Thanks
Laszlo

> 
> V2 changes:
> Add xchg 16 bit instructions to handle sgdt and sidt base
> 63:48 bits and 47:32 bits.
> Add comment to explain why xchg 64bit isnt being used
> 
> Split lock happens when a locking instruction is used on mis-aligned data
> that crosses two cachelines. If close source platform enables Alignment Check
> Exception(#AC), They can hit a double fault due to split lock being in
> CpuExceptionHandlerLib.
> 
> sigt and sgdt saves 10 bytes to memory, 8 bytes is base and 2 bytes is limit.
> The data is mis-aligned, can cross two cacheline, and a xchg
> instruction(locking instuction) is being utilize.
> 
> Signed-off-by: John E Lofgren <john.e.lofgren@intel.com>
> ---
>  UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm | 20 ++++++++++++++------
>  1 file changed, 14 insertions(+), 6 deletions(-)
> 
> diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
> index 4db1a09f28..7b7642b290 100644
> --- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
> +++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
> @@ -180,21 +180,29 @@ HasErrorCode:
>      push    qword [rbp + 24]
>  
>  ;; UINT64  Gdtr[2], Idtr[2];
> +    ; sidt and sgdt saves 10 bytes to memory, 8 bytes = base and 2 bytes = limit.
> +    ; To avoid #AC split lock when separating base and limit into their
> +    ; own separate 64 bit memory, we can’t use 64 bit xchg since base [63:48] bits
> +    ; may cross the cache line.
>      xor     rax, rax
>      push    rax
>      push    rax
>      sidt    [rsp]
> -    xchg    rax, [rsp + 2]
> -    xchg    rax, [rsp]
> -    xchg    rax, [rsp + 8]
> +    xchg    eax, [rsp + 2]
> +    xchg    eax, [rsp]
> +    xchg    eax, [rsp + 8]
> +    xchg     ax, [rsp + 6]
> +    xchg     ax, [rsp + 4]
>  
>      xor     rax, rax
>      push    rax
>      push    rax
>      sgdt    [rsp]
> -    xchg    rax, [rsp + 2]
> -    xchg    rax, [rsp]
> -    xchg    rax, [rsp + 8]
> +    xchg    eax, [rsp + 2]
> +    xchg    eax, [rsp]
> +    xchg    eax, [rsp + 8]
> +    xchg     ax, [rsp + 6]
> +    xchg     ax, [rsp + 4]
>  
>  ;; UINT64  Ldtr, Tr;
>      xor     rax, rax
> 

Re: [edk2-devel] [Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split lock

[John E Lofgren]

Sorry. I forgot amend it to the commit. Ill fix it.

Sorry Again,
John

>-----Original Message-----
>From: Laszlo Ersek [mailto:lersek@redhat.com]
>Sent: Wednesday, September 18, 2019 1:52 AM
>To: devel@edk2.groups.io; Lofgren, John E <john.e.lofgren@intel.com>
>Subject: Re: [edk2-devel] [Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix
>split lock
>
>On 09/18/19 00:49, John E Lofgren wrote:
>> REF: https://bugzilla.tianocore.org/show_bug.cgi?id=2150
>> V3 changes:
>> change to mov instruction (non locking instuction) instead of xchg to
>> simplify design.
>
>I think something's wrong -- the v3 update described above isn't actually
>implemented in the patch (it continues using XCHG, rather than MOV).
>
>Thanks
>Laszlo
>
>>
>> V2 changes:
>> Add xchg 16 bit instructions to handle sgdt and sidt base
>> 63:48 bits and 47:32 bits.
>> Add comment to explain why xchg 64bit isnt being used
>>
>> Split lock happens when a locking instruction is used on mis-aligned
>> data that crosses two cachelines. If close source platform enables
>> Alignment Check Exception(#AC), They can hit a double fault due to
>> split lock being in CpuExceptionHandlerLib.
>>
>> sigt and sgdt saves 10 bytes to memory, 8 bytes is base and 2 bytes is limit.
>> The data is mis-aligned, can cross two cacheline, and a xchg
>> instruction(locking instuction) is being utilize.
>>
>> Signed-off-by: John E Lofgren <john.e.lofgren@intel.com>
>> ---
>>
>>
>UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nas
>m
>> | 20 ++++++++++++++------
>>  1 file changed, 14 insertions(+), 6 deletions(-)
>>
>> diff --git
>>
>a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.na
>> sm
>>
>b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.na
>> sm
>> index 4db1a09f28..7b7642b290 100644
>> ---
>>
>a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.na
>> sm
>> +++
>b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAs
>> +++ m.nasm
>> @@ -180,21 +180,29 @@ HasErrorCode:
>>      push    qword [rbp + 24]
>>
>>  ;; UINT64  Gdtr[2], Idtr[2];
>> +    ; sidt and sgdt saves 10 bytes to memory, 8 bytes = base and 2 bytes =
>limit.
>> +    ; To avoid #AC split lock when separating base and limit into their
>> +    ; own separate 64 bit memory, we can’t use 64 bit xchg since base [63:48]
>bits
>> +    ; may cross the cache line.
>>      xor     rax, rax
>>      push    rax
>>      push    rax
>>      sidt    [rsp]
>> -    xchg    rax, [rsp + 2]
>> -    xchg    rax, [rsp]
>> -    xchg    rax, [rsp + 8]
>> +    xchg    eax, [rsp + 2]
>> +    xchg    eax, [rsp]
>> +    xchg    eax, [rsp + 8]
>> +    xchg     ax, [rsp + 6]
>> +    xchg     ax, [rsp + 4]
>>
>>      xor     rax, rax
>>      push    rax
>>      push    rax
>>      sgdt    [rsp]
>> -    xchg    rax, [rsp + 2]
>> -    xchg    rax, [rsp]
>> -    xchg    rax, [rsp + 8]
>> +    xchg    eax, [rsp + 2]
>> +    xchg    eax, [rsp]
>> +    xchg    eax, [rsp + 8]
>> +    xchg     ax, [rsp + 6]
>> +    xchg     ax, [rsp + 4]
>>
>>  ;; UINT64  Ldtr, Tr;
>>      xor     rax, rax
>>

[Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split lock

[John E Lofgren]

REF: https://bugzilla.tianocore.org/show_bug.cgi?id=2150
V3 changes:
change to mov instruction (non locking instuction) instead
of xchg to simplify design.

V2 changes:
Add xchg 16 bit instructions to handle sgdt and sidt base
63:48 bits and 47:32 bits.
Add comment to explain why xchg 64bit isnt being used

Split lock happens when a locking instruction is used on mis-aligned data
that crosses two cachelines. If close source platform enables Alignment Check
Exception(#AC), They can hit a double fault due to split lock being in
CpuExceptionHandlerLib.

sigt and sgdt saves 10 bytes to memory, 8 bytes is base and 2 bytes is limit.
The data is mis-aligned, can cross two cacheline, and a xchg
instruction(locking instuction) is being utilize.

Signed-off-by: John E Lofgren <john.e.lofgren@intel.com>
---
 UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
index 4db1a09f28..19198f2731 100644
--- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
+++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
@@ -184,17 +184,19 @@ HasErrorCode:
     push    rax
     push    rax
     sidt    [rsp]
-    xchg    rax, [rsp + 2]
-    xchg    rax, [rsp]
-    xchg    rax, [rsp + 8]
+    mov     bx, word [rsp]
+    mov     rax, qword [rsp + 2]
+    mov     qword [rsp], rax
+    mov     word [rsp + 8], bx
 
     xor     rax, rax
     push    rax
     push    rax
     sgdt    [rsp]
-    xchg    rax, [rsp + 2]
-    xchg    rax, [rsp]
-    xchg    rax, [rsp + 8]
+    mov     bx, word [rsp]
+    mov     rax, qword [rsp + 2]
+    mov     qword [rsp], rax
+    mov     word [rsp + 8], bx
 
 ;; UINT64  Ldtr, Tr;
     xor     rax, rax
-- 
2.16.2.windows.1

Re: [edk2-devel] [Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split lock

[Laszlo Ersek]

On 09/18/19 17:43, John E Lofgren wrote:
> REF: https://bugzilla.tianocore.org/show_bug.cgi?id=2150
> V3 changes:
> change to mov instruction (non locking instuction) instead
> of xchg to simplify design.

This patch should have been posted as "v4" actually -- it differs from
what you originally posted as v3. Therefore it cannot be considered v3.

The changelog in the patch would say,

v4:
The v3 posting didn't do what it promised to do, so do it now for real.

v3:
<whatever it originally said>

Anyway, not a deal breaker. More comments below.

> V2 changes:
> Add xchg 16 bit instructions to handle sgdt and sidt base
> 63:48 bits and 47:32 bits.
> Add comment to explain why xchg 64bit isnt being used
> 
> Split lock happens when a locking instruction is used on mis-aligned data
> that crosses two cachelines. If close source platform enables Alignment Check
> Exception(#AC), They can hit a double fault due to split lock being in
> CpuExceptionHandlerLib.
> 
> sigt and sgdt saves 10 bytes to memory, 8 bytes is base and 2 bytes is limit.
> The data is mis-aligned, can cross two cacheline, and a xchg
> instruction(locking instuction) is being utilize.
> 
> Signed-off-by: John E Lofgren <john.e.lofgren@intel.com>
> ---
>  UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm | 14 ++++++++------
>  1 file changed, 8 insertions(+), 6 deletions(-)
> 
> diff --git a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
> index 4db1a09f28..19198f2731 100644
> --- a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
> +++ b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
> @@ -184,17 +184,19 @@ HasErrorCode:
>      push    rax
>      push    rax
>      sidt    [rsp]
> -    xchg    rax, [rsp + 2]
> -    xchg    rax, [rsp]
> -    xchg    rax, [rsp + 8]
> +    mov     bx, word [rsp]
> +    mov     rax, qword [rsp + 2]
> +    mov     qword [rsp], rax
> +    mov     word [rsp + 8], bx
>  
>      xor     rax, rax
>      push    rax
>      push    rax
>      sgdt    [rsp]
> -    xchg    rax, [rsp + 2]
> -    xchg    rax, [rsp]
> -    xchg    rax, [rsp + 8]
> +    mov     bx, word [rsp]
> +    mov     rax, qword [rsp + 2]
> +    mov     qword [rsp], rax
> +    mov     word [rsp + 8], bx
>  
>  ;; UINT64  Ldtr, Tr;
>      xor     rax, rax
> 

I think it would be nice to learn why XCHG was used in the first place.
Then again, whatever it was preferred for, it could not have been
locking, as the three XCHG instructions are not atomic as a whole (i.e.
they are not locked all together).

Another reason for XCHG could be that they wanted to use just one
register -- but I totally don't see the point of not using BX too.

So:

Reviewed-by: Laszlo Ersek <lersek@redhat.com>

Thanks,
Laszlo

Re: [edk2-devel] [Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split lock

[Dong, Eric]

Reviewed-by: Eric Dong <eric.dong@intel.com>

And pushed:
  SHA-1: f4c898f2b2db2819c519cdce05403d4ba0234979

Thanks,
Eric

> -----Original Message-----
> From: devel@edk2.groups.io [mailto:devel@edk2.groups.io] On Behalf Of John
> E Lofgren
> Sent: Wednesday, September 18, 2019 11:43 PM
> To: devel@edk2.groups.io
> Subject: [edk2-devel] [Patch V3] UefiCpuPkg/CpuExceptionHandlerLib: Fix split
> lock
> 
> REF: https://bugzilla.tianocore.org/show_bug.cgi?id=2150
> V3 changes:
> change to mov instruction (non locking instuction) instead
> of xchg to simplify design.
> 
> V2 changes:
> Add xchg 16 bit instructions to handle sgdt and sidt base
> 63:48 bits and 47:32 bits.
> Add comment to explain why xchg 64bit isnt being used
> 
> Split lock happens when a locking instruction is used on mis-aligned data
> that crosses two cachelines. If close source platform enables Alignment Check
> Exception(#AC), They can hit a double fault due to split lock being in
> CpuExceptionHandlerLib.
> 
> sigt and sgdt saves 10 bytes to memory, 8 bytes is base and 2 bytes is limit.
> The data is mis-aligned, can cross two cacheline, and a xchg
> instruction(locking instuction) is being utilize.
> 
> Signed-off-by: John E Lofgren <john.e.lofgren@intel.com>
> ---
>  UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nasm
> | 14 ++++++++------
>  1 file changed, 8 insertions(+), 6 deletions(-)
> 
> diff --git
> a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nas
> m
> b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nas
> m
> index 4db1a09f28..19198f2731 100644
> ---
> a/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nas
> m
> +++
> b/UefiCpuPkg/Library/CpuExceptionHandlerLib/X64/ExceptionHandlerAsm.nas
> m
> @@ -184,17 +184,19 @@ HasErrorCode:
>      push    rax
>      push    rax
>      sidt    [rsp]
> -    xchg    rax, [rsp + 2]
> -    xchg    rax, [rsp]
> -    xchg    rax, [rsp + 8]
> +    mov     bx, word [rsp]
> +    mov     rax, qword [rsp + 2]
> +    mov     qword [rsp], rax
> +    mov     word [rsp + 8], bx
> 
>      xor     rax, rax
>      push    rax
>      push    rax
>      sgdt    [rsp]
> -    xchg    rax, [rsp + 2]
> -    xchg    rax, [rsp]
> -    xchg    rax, [rsp + 8]
> +    mov     bx, word [rsp]
> +    mov     rax, qword [rsp + 2]
> +    mov     qword [rsp], rax
> +    mov     word [rsp + 8], bx
> 
>  ;; UINT64  Ldtr, Tr;
>      xor     rax, rax
> --
> 2.16.2.windows.1
> 
> 
>