( $xlate="${dir}perlasm/x86_64-xlate.pl" and -f $xlate) or
die "can't locate x86_64-xlate.pl";
-open STDOUT,"| $^X $xlate $flavour $output";
+open OUT,"| \"$^X\" $xlate $flavour $output";
+*STDOUT=*OUT;
($arg1,$arg2,$arg3,$arg4)=$win64?("%rcx","%rdx","%r8", "%r9") : # Win64 order
("%rdi","%rsi","%rdx","%rcx"); # Unix order
call OPENSSL_cpuid_setup
.hidden OPENSSL_ia32cap_P
-.comm OPENSSL_ia32cap_P,8
+.comm OPENSSL_ia32cap_P,16,4
.text
.size OPENSSL_rdtsc,.-OPENSSL_rdtsc
.globl OPENSSL_ia32_cpuid
-.type OPENSSL_ia32_cpuid,\@abi-omnipotent
+.type OPENSSL_ia32_cpuid,\@function,1
.align 16
OPENSSL_ia32_cpuid:
mov %rbx,%r8 # save %rbx
xor %eax,%eax
+ mov %eax,8(%rdi) # clear extended feature flags
cpuid
mov %eax,%r11d # max value for standard query level
or \$0x40000000,%edx # set reserved bit#30 on Intel CPUs
and \$15,%ah
cmp \$15,%ah # examine Family ID
- jne .Lnotintel
+ jne .LnotP4
or \$0x00100000,%edx # set reserved bit#20 to engage RC4_CHAR
+.LnotP4:
+ cmp \$6,%ah
+ jne .Lnotintel
+ and \$0x0fff0ff0,%eax
+ cmp \$0x00050670,%eax # Knights Landing
+ je .Lknights
+ cmp \$0x00080650,%eax # Knights Mill (according to sde)
+ jne .Lnotintel
+.Lknights:
+ and \$0xfbffffff,%ecx # clear XSAVE flag to mimic Silvermont
+
.Lnotintel:
bt \$28,%edx # test hyper-threading bit
jnc .Lgeneric
or %ecx,%r9d # merge AMD XOP flag
mov %edx,%r10d # %r9d:%r10d is copy of %ecx:%edx
+
+ cmp \$7,%r11d
+ jb .Lno_extended_info
+ mov \$7,%eax
+ xor %ecx,%ecx
+ cpuid
+ bt \$26,%r9d # check XSAVE bit, cleared on Knights
+ jc .Lnotknights
+ and \$0xfff7ffff,%ebx # clear ADCX/ADOX flag
+.Lnotknights:
+ mov %ebx,8(%rdi) # save extended feature flags
+.Lno_extended_info:
+
bt \$27,%r9d # check OSXSAVE bit
jnc .Lclear_avx
xor %ecx,%ecx # XCR0
.Lclear_avx:
mov \$0xefffe7ff,%eax # ~(1<<28|1<<12|1<<11)
and %eax,%r9d # clear AVX, FMA and AMD XOP bits
+ andl \$0xffffffdf,8(%rdi) # clear AVX2, ~(1<<5)
.Ldone:
shl \$32,%r9
mov %r10d,%eax
.size OPENSSL_wipe_cpu,.-OPENSSL_wipe_cpu
___
+print<<___;
+.globl OPENSSL_ia32_rdrand
+.type OPENSSL_ia32_rdrand,\@abi-omnipotent
+.align 16
+OPENSSL_ia32_rdrand:
+ mov \$8,%ecx
+.Loop_rdrand:
+ rdrand %rax
+ jc .Lbreak_rdrand
+ loop .Loop_rdrand
+.Lbreak_rdrand:
+ cmp \$0,%rax
+ cmove %rcx,%rax
+ ret
+.size OPENSSL_ia32_rdrand,.-OPENSSL_ia32_rdrand
+
+.globl OPENSSL_ia32_rdseed
+.type OPENSSL_ia32_rdseed,\@abi-omnipotent
+.align 16
+OPENSSL_ia32_rdseed:
+ mov \$8,%ecx
+.Loop_rdseed:
+ rdseed %rax
+ jc .Lbreak_rdseed
+ loop .Loop_rdseed
+.Lbreak_rdseed:
+ cmp \$0,%rax
+ cmove %rcx,%rax
+ ret
+.size OPENSSL_ia32_rdseed,.-OPENSSL_ia32_rdseed
+___
+
close STDOUT; # flush