MdePkg/BaseSynchronizationLib: fix XADD operands in GCC IA32/X64 assembly

Currently, "gcc-4.8.5-28.el7_5.1.x86_64" generates the following code for
me, from the XADD inline assembly added to "X64/GccInline.c" in commit
17634d026f96:

> 0000000000004383 <InternalSyncIncrement>:
> UINT32
> EFIAPI
> InternalSyncIncrement (
>   IN      volatile UINT32    *Value
>   )
> {
>     4383:       55                      push   %rbp
>     4384:       48 89 e5                mov    %rsp,%rbp
>     4387:       48 83 ec 10             sub    $0x10,%rsp
>     438b:       48 89 4d 10             mov    %rcx,0x10(%rbp)
>   UINT32  Result;
>
>   __asm__ __volatile__ (
>     438f:       48 8b 55 10             mov    0x10(%rbp),%rdx
>     4393:       48 8b 45 10             mov    0x10(%rbp),%rax
>     4397:       b8 01 00 00 00          mov    $0x1,%eax
>     439c:       f0 0f c1 00             lock xadd %eax,(%rax)
>     43a0:       ff c0                   inc    %eax
>     43a2:       89 45 fc                mov    %eax,-0x4(%rbp)
>     : "m"  (*Value)           // %2
>     : "memory",
>       "cc"
>     );
>
>   return Result;
>     43a5:       8b 45 fc                mov    -0x4(%rbp),%eax
> }
>     43a8:       c9                      leaveq
>     43a9:       c3                      retq
>

The MOV $0X1,%EAX instruction corrupts the address of Value in %RAX before
we reach the XADD instruction. In fact, it makes no sense for XADD to use
%EAX as source operand and (%RAX) as destination operand at the same time.

The XADD instruction's destination operand is a read-write operand. The
GCC documentation states:

> The ordinary output operands must be write-only; GCC will assume that
> the values in these operands before the instruction are dead and need
> not be generated. Extended asm supports input-output or read-write
> operands. Use the constraint character `+' to indicate such an operand
> and list it with the output operands. You should only use read-write
> operands when the constraints for the operand (or the operand in which
> only some of the bits are to be changed) allow a register.

(The above is intentionally quoted from the oldest GCC release that edk2
supports, namely gcc-4.4:
<https://gcc.gnu.org/onlinedocs/gcc-4.4.7/gcc/Extended-Asm.html>.)

Fix the operand list accordingly.

With the patch applied, I get:

> 0000000000004383 <InternalSyncIncrement>:
> UINT32
> EFIAPI
> InternalSyncIncrement (
>   IN      volatile UINT32    *Value
>   )
> {
>     4383:       55                      push   %rbp
>     4384:       48 89 e5                mov    %rsp,%rbp
>     4387:       48 83 ec 10             sub    $0x10,%rsp
>     438b:       48 89 4d 10             mov    %rcx,0x10(%rbp)
>   UINT32  Result;
>
>   __asm__ __volatile__ (
>     438f:       48 8b 55 10             mov    0x10(%rbp),%rdx
>     4393:       48 8b 45 10             mov    0x10(%rbp),%rax
>     4397:       b8 01 00 00 00          mov    $0x1,%eax
>     439c:       f0 0f c1 02             lock xadd %eax,(%rdx)
>     43a0:       ff c0                   inc    %eax
>     43a2:       89 45 fc                mov    %eax,-0x4(%rbp)
>     :                         // no inputs that aren't also outputs
>     : "memory",
>       "cc"
>     );
>
>   return Result;
>     43a5:       8b 45 fc                mov    -0x4(%rbp),%eax
> }
>     43a8:       c9                      leaveq
>     43a9:       c3                      retq

Note that some other bugs remain in
"BaseSynchronizationLib/*/GccInline.c"; those should be addressed later,
under <https://bugzilla.tianocore.org/show_bug.cgi?id=1208>.

Cc: Jiewen Yao <jiewen.yao@intel.com>
Cc: Liming Gao <liming.gao@intel.com>
Cc: Michael Kinney <michael.d.kinney@intel.com>
Cc: Ruiyu Ni <ruiyu.ni@intel.com>
Ref: https://bugzilla.tianocore.org/show_bug.cgi?id=1207
Fixes: 17634d026f968c404b039a8d8431b6389dd396ea
Contributed-under: TianoCore Contribution Agreement 1.1
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Ruiyu Ni <ruiyu.ni@intel.com>

2 files changed, 12 insertions, 12 deletions

diff --git a/MdePkg/Library/BaseSynchronizationLib/Ia32/GccInline.c b/MdePkg/Library/BaseSynchronizationLib/Ia32/GccInline.c
index d82e0205f5..fa2be7f4b3 100644
--- a/MdePkg/Library/BaseSynchronizationLib/Ia32/GccInline.c
+++ b/MdePkg/Library/BaseSynchronizationLib/Ia32/GccInline.c
@@ -38,11 +38,11 @@ InternalSyncIncrement (
   __asm__ __volatile__ (

     "movl    $1, %%eax  \n\t"

     "lock               \n\t"

-    "xadd    %%eax, %2  \n\t"

+    "xadd    %%eax, %1  \n\t"

     "inc     %%eax          "

     : "=a" (Result),          // %0

-      "=m" (*Value)           // %1

-    : "m"  (*Value)           // %2

+      "+m" (*Value)           // %1

+    :                         // no inputs that aren't also outputs

     : "memory",

       "cc"

     );

@@ -75,11 +75,11 @@ InternalSyncDecrement (
   __asm__ __volatile__ (

     "movl    $-1, %%eax  \n\t"

     "lock                \n\t"

-    "xadd    %%eax, %2   \n\t"

+    "xadd    %%eax, %1   \n\t"

     "dec     %%eax                  "

     : "=a" (Result),          // %0

-      "=m" (*Value)           // %1

-    : "m"  (*Value)           // %2

+      "+m" (*Value)           // %1

+    :                         // no inputs that aren't also outputs

     : "memory",

       "cc"

     );

diff --git a/MdePkg/Library/BaseSynchronizationLib/X64/GccInline.c b/MdePkg/Library/BaseSynchronizationLib/X64/GccInline.c
index 4c4d6e3fc7..ab7efe23c4 100644
--- a/MdePkg/Library/BaseSynchronizationLib/X64/GccInline.c
+++ b/MdePkg/Library/BaseSynchronizationLib/X64/GccInline.c
@@ -38,11 +38,11 @@ InternalSyncIncrement (
   __asm__ __volatile__ (

     "movl    $1, %%eax  \n\t"

     "lock               \n\t"

-    "xadd    %%eax, %2  \n\t"

+    "xadd    %%eax, %1  \n\t"

     "inc     %%eax          "

     : "=a" (Result),          // %0

-      "=m" (*Value)           // %1

-    : "m"  (*Value)           // %2

+      "+m" (*Value)           // %1

+    :                         // no inputs that aren't also outputs

     : "memory",

       "cc"

     );

@@ -74,11 +74,11 @@ InternalSyncDecrement (
   __asm__ __volatile__ (

     "movl    $-1, %%eax  \n\t"

     "lock                \n\t"

-    "xadd    %%eax, %2   \n\t"

+    "xadd    %%eax, %1   \n\t"

     "dec     %%eax                  "

     : "=a" (Result),          // %0

-      "=m" (*Value)           // %1

-    : "m"  (*Value)           // %2

+      "+m" (*Value)           // %1

+    :                         // no inputs that aren't also outputs

     : "memory",

       "cc"

     );