summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorHuang Ying <ying.huang@intel.com>2010-03-13 16:28:42 +0800
committerHerbert Xu <herbert@gondor.apana.org.au>2010-03-13 16:28:42 +0800
commit32cbd7dfce93382a70f155bf539871b4c55bed29 (patch)
tree30ae215018df38e5f6b29eec73ad9a00d693ccc9
parent18bcc9194da3c97e8f458fb1b06ac5b9b35fb23f (diff)
crypto: aesni-intel - Fix CTR optimization build failure with gas 2.16.1
Andrew Morton reported that AES-NI CTR optimization failed to compile with gas 2.16.1, the error message is as follow: arch/x86/crypto/aesni-intel_asm.S: Assembler messages: arch/x86/crypto/aesni-intel_asm.S:752: Error: suffix or operands invalid for `movq' arch/x86/crypto/aesni-intel_asm.S:753: Error: suffix or operands invalid for `movq' To fix this, a gas macro is defined to assemble movq with 64bit general purpose registers and XMM registers. The macro will generate the raw .byte sequence for needed instructions. Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S4
-rw-r--r--arch/x86/include/asm/inst.h96
2 files changed, 95 insertions, 5 deletions
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 822846a9eba..ff16756a51c 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -749,8 +749,8 @@ _aesni_inc_init:
movaps IV, CTR
PSHUFB_XMM BSWAP_MASK CTR
mov $1, TCTR_LOW
- movq TCTR_LOW, INC
- movq CTR, TCTR_LOW
+ MOVQ_R64_XMM TCTR_LOW INC
+ MOVQ_R64_XMM CTR TCTR_LOW
ret
/*
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index 14cf526091f..840a399701b 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -7,7 +7,66 @@
#ifdef __ASSEMBLY__
+#define REG_NUM_INVALID 100
+
+#define REG_TYPE_R64 0
+#define REG_TYPE_XMM 1
+#define REG_TYPE_INVALID 100
+
+ .macro R64_NUM opd r64
+ \opd = REG_NUM_INVALID
+ .ifc \r64,%rax
+ \opd = 0
+ .endif
+ .ifc \r64,%rcx
+ \opd = 1
+ .endif
+ .ifc \r64,%rdx
+ \opd = 2
+ .endif
+ .ifc \r64,%rbx
+ \opd = 3
+ .endif
+ .ifc \r64,%rsp
+ \opd = 4
+ .endif
+ .ifc \r64,%rbp
+ \opd = 5
+ .endif
+ .ifc \r64,%rsi
+ \opd = 6
+ .endif
+ .ifc \r64,%rdi
+ \opd = 7
+ .endif
+ .ifc \r64,%r8
+ \opd = 8
+ .endif
+ .ifc \r64,%r9
+ \opd = 9
+ .endif
+ .ifc \r64,%r10
+ \opd = 10
+ .endif
+ .ifc \r64,%r11
+ \opd = 11
+ .endif
+ .ifc \r64,%r12
+ \opd = 12
+ .endif
+ .ifc \r64,%r13
+ \opd = 13
+ .endif
+ .ifc \r64,%r14
+ \opd = 14
+ .endif
+ .ifc \r64,%r15
+ \opd = 15
+ .endif
+ .endm
+
.macro XMM_NUM opd xmm
+ \opd = REG_NUM_INVALID
.ifc \xmm,%xmm0
\opd = 0
.endif
@@ -58,13 +117,25 @@
.endif
.endm
+ .macro REG_TYPE type reg
+ R64_NUM reg_type_r64 \reg
+ XMM_NUM reg_type_xmm \reg
+ .if reg_type_r64 != REG_NUM_INVALID
+ \type = REG_TYPE_R64
+ .elseif reg_type_xmm != REG_NUM_INVALID
+ \type = REG_TYPE_XMM
+ .else
+ \type = REG_TYPE_INVALID
+ .endif
+ .endm
+
.macro PFX_OPD_SIZE
.byte 0x66
.endm
- .macro PFX_REX opd1 opd2
- .if (\opd1 | \opd2) & 8
- .byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1)
+ .macro PFX_REX opd1 opd2 W=0
+ .if ((\opd1 | \opd2) & 8) || \W
+ .byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1) | (\W << 3)
.endif
.endm
@@ -145,6 +216,25 @@
.byte 0x0f, 0x38, 0xdf
MODRM 0xc0 aesdeclast_opd1 aesdeclast_opd2
.endm
+
+ .macro MOVQ_R64_XMM opd1 opd2
+ REG_TYPE movq_r64_xmm_opd1_type \opd1
+ .if movq_r64_xmm_opd1_type == REG_TYPE_XMM
+ XMM_NUM movq_r64_xmm_opd1 \opd1
+ R64_NUM movq_r64_xmm_opd2 \opd2
+ .else
+ R64_NUM movq_r64_xmm_opd1 \opd1
+ XMM_NUM movq_r64_xmm_opd2 \opd2
+ .endif
+ PFX_OPD_SIZE
+ PFX_REX movq_r64_xmm_opd1 movq_r64_xmm_opd2 1
+ .if movq_r64_xmm_opd1_type == REG_TYPE_XMM
+ .byte 0x0f, 0x7e
+ .else
+ .byte 0x0f, 0x6e
+ .endif
+ MODRM 0xc0 movq_r64_xmm_opd1 movq_r64_xmm_opd2
+ .endm
#endif
#endif