[T106][ZXW-22]7520V3SCV2.01.01.02P42U09_VEC_V0.8_AP_VEC origin source commit
Change-Id: Ic6e05d89ecd62fc34f82b23dcf306c93764aec4b
diff --git a/ap/lib/libssl/openssl-1.1.1o/crypto/ia64cpuid.S b/ap/lib/libssl/openssl-1.1.1o/crypto/ia64cpuid.S
new file mode 100644
index 0000000..92c5512
--- /dev/null
+++ b/ap/lib/libssl/openssl-1.1.1o/crypto/ia64cpuid.S
@@ -0,0 +1,297 @@
+// Copyright 2004-2017 The OpenSSL Project Authors. All Rights Reserved.
+//
+// Licensed under the OpenSSL license (the "License"). You may not use
+// this file except in compliance with the License. You can obtain a copy
+// in the file LICENSE in the source distribution or at
+// https://www.openssl.org/source/license.html
+// Works on all IA-64 platforms: Linux, HP-UX, Win64i...
+// On Win64i compile with ias.exe.
+.text
+
+#if defined(_HPUX_SOURCE) && !defined(_LP64)
+#define ADDP addp4
+#else
+#define ADDP add
+#endif
+
+.global OPENSSL_cpuid_setup#
+.proc OPENSSL_cpuid_setup#
+OPENSSL_cpuid_setup:
+{ .mib; br.ret.sptk.many b0 };;
+.endp OPENSSL_cpuid_setup#
+
+.global OPENSSL_rdtsc#
+.proc OPENSSL_rdtsc#
+OPENSSL_rdtsc:
+{ .mib; mov r8=ar.itc
+ br.ret.sptk.many b0 };;
+.endp OPENSSL_rdtsc#
+
+.global OPENSSL_atomic_add#
+.proc OPENSSL_atomic_add#
+.align 32
+OPENSSL_atomic_add:
+{ .mii; ld4 r2=[r32]
+ nop.i 0
+ nop.i 0 };;
+.Lspin:
+{ .mii; mov ar.ccv=r2
+ add r8=r2,r33
+ mov r3=r2 };;
+{ .mmi; mf;;
+ cmpxchg4.acq r2=[r32],r8,ar.ccv
+ nop.i 0 };;
+{ .mib; cmp.ne p6,p0=r2,r3
+ nop.i 0
+(p6) br.dpnt .Lspin };;
+{ .mib; nop.m 0
+ sxt4 r8=r8
+ br.ret.sptk.many b0 };;
+.endp OPENSSL_atomic_add#
+
+// Returns a structure comprising pointer to the top of stack of
+// the caller and pointer beyond backing storage for the current
+// register frame. The latter is required, because it might be
+// insufficient to wipe backing storage for the current frame
+// (as this procedure does), one might have to go further, toward
+// higher addresses to reach for whole "retroactively" saved
+// context...
+.global OPENSSL_wipe_cpu#
+.proc OPENSSL_wipe_cpu#
+.align 32
+OPENSSL_wipe_cpu:
+ .prologue
+ .fframe 0
+ .save ar.pfs,r2
+ .save ar.lc,r3
+{ .mib; alloc r2=ar.pfs,0,96,0,96
+ mov r3=ar.lc
+ brp.loop.imp .L_wipe_top,.L_wipe_end-16
+ };;
+{ .mii; mov r9=ar.bsp
+ mov r8=pr
+ mov ar.lc=96 };;
+ .body
+{ .mii; add r9=96*8-8,r9
+ mov ar.ec=1 };;
+
+// One can sweep double as fast, but then we can't guarantee
+// that backing storage is wiped...
+.L_wipe_top:
+{ .mfi; st8 [r9]=r0,-8
+ mov f127=f0
+ mov r127=r0 }
+{ .mfb; nop.m 0
+ nop.f 0
+ br.ctop.sptk .L_wipe_top };;
+.L_wipe_end:
+
+{ .mfi; mov r11=r0
+ mov f6=f0
+ mov r14=r0 }
+{ .mfi; mov r15=r0
+ mov f7=f0
+ mov r16=r0 }
+{ .mfi; mov r17=r0
+ mov f8=f0
+ mov r18=r0 }
+{ .mfi; mov r19=r0
+ mov f9=f0
+ mov r20=r0 }
+{ .mfi; mov r21=r0
+ mov f10=f0
+ mov r22=r0 }
+{ .mfi; mov r23=r0
+ mov f11=f0
+ mov r24=r0 }
+{ .mfi; mov r25=r0
+ mov f12=f0
+ mov r26=r0 }
+{ .mfi; mov r27=r0
+ mov f13=f0
+ mov r28=r0 }
+{ .mfi; mov r29=r0
+ mov f14=f0
+ mov r30=r0 }
+{ .mfi; mov r31=r0
+ mov f15=f0
+ nop.i 0 }
+{ .mfi; mov f16=f0 }
+{ .mfi; mov f17=f0 }
+{ .mfi; mov f18=f0 }
+{ .mfi; mov f19=f0 }
+{ .mfi; mov f20=f0 }
+{ .mfi; mov f21=f0 }
+{ .mfi; mov f22=f0 }
+{ .mfi; mov f23=f0 }
+{ .mfi; mov f24=f0 }
+{ .mfi; mov f25=f0 }
+{ .mfi; mov f26=f0 }
+{ .mfi; mov f27=f0 }
+{ .mfi; mov f28=f0 }
+{ .mfi; mov f29=f0 }
+{ .mfi; mov f30=f0 }
+{ .mfi; add r9=96*8+8,r9
+ mov f31=f0
+ mov pr=r8,0x1ffff }
+{ .mib; mov r8=sp
+ mov ar.lc=r3
+ br.ret.sptk b0 };;
+.endp OPENSSL_wipe_cpu#
+
+.global OPENSSL_cleanse#
+.proc OPENSSL_cleanse#
+OPENSSL_cleanse:
+{ .mib; cmp.eq p6,p0=0,r33 // len==0
+ ADDP r32=0,r32
+(p6) br.ret.spnt b0 };;
+{ .mib; and r2=7,r32
+ cmp.leu p6,p0=15,r33 // len>=15
+(p6) br.cond.dptk .Lot };;
+
+.Little:
+{ .mib; st1 [r32]=r0,1
+ cmp.ltu p6,p7=1,r33 } // len>1
+{ .mbb; add r33=-1,r33 // len--
+(p6) br.cond.dptk .Little
+(p7) br.ret.sptk.many b0 };;
+
+.Lot:
+{ .mib; cmp.eq p6,p0=0,r2
+(p6) br.cond.dptk .Laligned };;
+{ .mmi; st1 [r32]=r0,1;;
+ and r2=7,r32 }
+{ .mib; add r33=-1,r33
+ br .Lot };;
+
+.Laligned:
+{ .mmi; st8 [r32]=r0,8
+ and r2=-8,r33 // len&~7
+ add r33=-8,r33 };; // len-=8
+{ .mib; cmp.ltu p6,p0=8,r2 // ((len+8)&~7)>8
+(p6) br.cond.dptk .Laligned };;
+
+{ .mbb; cmp.eq p6,p7=r0,r33
+(p7) br.cond.dpnt .Little
+(p6) br.ret.sptk.many b0 };;
+.endp OPENSSL_cleanse#
+
+.global CRYPTO_memcmp#
+.proc CRYPTO_memcmp#
+.align 32
+.skip 16
+CRYPTO_memcmp:
+ .prologue
+{ .mib; mov r8=0
+ cmp.eq p6,p0=0,r34 // len==0?
+(p6) br.ret.spnt b0 };;
+ .save ar.pfs,r2
+{ .mib; alloc r2=ar.pfs,3,5,0,8
+ .save ar.lc,r3
+ mov r3=ar.lc
+ brp.loop.imp .Loop_cmp_ctop,.Loop_cmp_cend-16
+ }
+{ .mib; sub r10=r34,r0,1
+ .save pr,r9
+ mov r9=pr };;
+{ .mii; ADDP r16=0,r32
+ mov ar.lc=r10
+ mov ar.ec=4 }
+{ .mib; ADDP r17=0,r33
+ mov pr.rot=1<<16 };;
+
+.Loop_cmp_ctop:
+{ .mib; (p16) ld1 r32=[r16],1
+ (p18) xor r34=r34,r38 }
+{ .mib; (p16) ld1 r36=[r17],1
+ (p19) or r8=r8,r35
+ br.ctop.sptk .Loop_cmp_ctop };;
+.Loop_cmp_cend:
+
+{ .mib; cmp.ne p6,p0=0,r8
+ mov ar.lc=r3 };;
+{ .mib;
+(p6) mov r8=1
+ mov pr=r9,0x1ffff
+ br.ret.sptk.many b0 };;
+.endp CRYPTO_memcmp#
+
+.global OPENSSL_instrument_bus#
+.proc OPENSSL_instrument_bus#
+OPENSSL_instrument_bus:
+{ .mmi; mov r2=r33
+ ADDP r32=0,r32 }
+{ .mmi; mov r8=ar.itc;;
+ mov r10=r0
+ mov r9=r8 };;
+
+{ .mmi; fc r32;;
+ ld4 r8=[r32] };;
+{ .mmi; mf
+ mov ar.ccv=r8
+ add r8=r8,r10 };;
+{ .mmi; cmpxchg4.acq r3=[r32],r8,ar.ccv
+ };;
+.Loop:
+{ .mmi; mov r8=ar.itc;;
+ sub r10=r8,r9 // diff=tick-lasttick
+ mov r9=r8 };; // lasttick=tick
+{ .mmi; fc r32;;
+ ld4 r8=[r32] };;
+{ .mmi; mf
+ mov ar.ccv=r8
+ add r8=r8,r10 };;
+{ .mmi; cmpxchg4.acq r3=[r32],r8,ar.ccv
+ add r33=-1,r33
+ add r32=4,r32 };;
+{ .mib; cmp4.ne p6,p0=0,r33
+(p6) br.cond.dptk .Loop };;
+
+{ .mib; sub r8=r2,r33
+ br.ret.sptk.many b0 };;
+.endp OPENSSL_instrument_bus#
+
+.global OPENSSL_instrument_bus2#
+.proc OPENSSL_instrument_bus2#
+OPENSSL_instrument_bus2:
+{ .mmi; mov r2=r33 // put aside cnt
+ ADDP r32=0,r32 }
+{ .mmi; mov r8=ar.itc;;
+ mov r10=r0
+ mov r9=r8 };;
+
+{ .mmi; fc r32;;
+ ld4 r8=[r32] };;
+{ .mmi; mf
+ mov ar.ccv=r8
+ add r8=r8,r10 };;
+{ .mmi; cmpxchg4.acq r3=[r32],r8,ar.ccv
+ };;
+
+{ .mmi; mov r8=ar.itc;;
+ sub r10=r8,r9
+ mov r9=r8 };;
+.Loop2:
+{ .mmi; mov r11=r10 // lastdiff=diff
+ add r34=-1,r34 };; // --max
+{ .mmi; fc r32;;
+ ld4 r8=[r32]
+ cmp4.eq p6,p0=0,r34 };;
+{ .mmi; mf
+ mov ar.ccv=r8
+ add r8=r8,r10 };;
+{ .mmb; cmpxchg4.acq r3=[r32],r8,ar.ccv
+(p6) br.cond.spnt .Ldone2 };;
+
+{ .mmi; mov r8=ar.itc;;
+ sub r10=r8,r9 // diff=tick-lasttick
+ mov r9=r8 };; // lasttick=tick
+{ .mmi; cmp.ne p6,p0=r10,r11;; // diff!=lastdiff
+(p6) add r33=-1,r33 };; // conditional --cnt
+{ .mib; cmp4.ne p7,p0=0,r33
+(p6) add r32=4,r32 // conditional ++out
+(p7) br.cond.dptk .Loop2 };;
+.Ldone2:
+{ .mib; sub r8=r2,r33
+ br.ret.sptk.many b0 };;
+.endp OPENSSL_instrument_bus2#