[PATCH v3 23/23] i386: AVX+AES helpers prep

[Paolo Bonzini <pbonzini@redhat.com>]

From: Paul Brook <paul@nowt.org>

Make the AES vector helpers AVX ready

No functional changes to existing helpers

Signed-off-by: Paul Brook <paul@nowt.org>
Message-Id: <20220424220204.2493824-22-paul@nowt.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/ops_sse.h | 41 ++++++++++++++++++++++-------------------
 1 file changed, 22 insertions(+), 19 deletions(-)

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 4135623ad8..f208253161 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -2256,11 +2256,12 @@ void glue(helper_aesdec, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg st = *d;
     Reg rk = *s;
 
-    for (i = 0 ; i < 4 ; i++) {
-        d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(AES_ishifts[4*i+0])] ^
-                                    AES_Td1[st.B(AES_ishifts[4*i+1])] ^
-                                    AES_Td2[st.B(AES_ishifts[4*i+2])] ^
-                                    AES_Td3[st.B(AES_ishifts[4*i+3])]);
+    for (i = 0 ; i < 2 << SHIFT ; i++) {
+        int j = i & 3;
+        d->L(i) = rk.L(i) ^ bswap32(AES_Td0[st.B(AES_ishifts[4 * j + 0])] ^
+                                    AES_Td1[st.B(AES_ishifts[4 * j + 1])] ^
+                                    AES_Td2[st.B(AES_ishifts[4 * j + 2])] ^
+                                    AES_Td3[st.B(AES_ishifts[4 * j + 3])]);
     }
 }
 
@@ -2270,8 +2271,8 @@ void glue(helper_aesdeclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg st = *d;
     Reg rk = *s;
 
-    for (i = 0; i < 16; i++) {
-        d->B(i) = rk.B(i) ^ (AES_isbox[st.B(AES_ishifts[i])]);
+    for (i = 0; i < 8 << SHIFT; i++) {
+        d->B(i) = rk.B(i) ^ (AES_isbox[st.B(AES_ishifts[i & 15] + (i & ~15))]);
     }
 }
 
@@ -2281,11 +2282,12 @@ void glue(helper_aesenc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg st = *d;
     Reg rk = *s;
 
-    for (i = 0 ; i < 4 ; i++) {
-        d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(AES_shifts[4*i+0])] ^
-                                    AES_Te1[st.B(AES_shifts[4*i+1])] ^
-                                    AES_Te2[st.B(AES_shifts[4*i+2])] ^
-                                    AES_Te3[st.B(AES_shifts[4*i+3])]);
+    for (i = 0 ; i < 2 << SHIFT ; i++) {
+        int j = i & 3;
+        d->L(i) = rk.L(i) ^ bswap32(AES_Te0[st.B(AES_shifts[4 * j + 0])] ^
+                                    AES_Te1[st.B(AES_shifts[4 * j + 1])] ^
+                                    AES_Te2[st.B(AES_shifts[4 * j + 2])] ^
+                                    AES_Te3[st.B(AES_shifts[4 * j + 3])]);
     }
 }
 
@@ -2295,22 +2297,22 @@ void glue(helper_aesenclast, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
     Reg st = *d;
     Reg rk = *s;
 
-    for (i = 0; i < 16; i++) {
-        d->B(i) = rk.B(i) ^ (AES_sbox[st.B(AES_shifts[i])]);
+    for (i = 0; i < 8 << SHIFT; i++) {
+        d->B(i) = rk.B(i) ^ (AES_sbox[st.B(AES_shifts[i & 15] + (i & ~15))]);
     }
-
 }
 
+#if SHIFT == 1
 void glue(helper_aesimc, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
     int i;
     Reg tmp = *s;
 
     for (i = 0 ; i < 4 ; i++) {
-        d->L(i) = bswap32(AES_imc[tmp.B(4*i+0)][0] ^
-                          AES_imc[tmp.B(4*i+1)][1] ^
-                          AES_imc[tmp.B(4*i+2)][2] ^
-                          AES_imc[tmp.B(4*i+3)][3]);
+        d->L(i) = bswap32(AES_imc[tmp.B(4 * i + 0)][0] ^
+                          AES_imc[tmp.B(4 * i + 1)][1] ^
+                          AES_imc[tmp.B(4 * i + 2)][2] ^
+                          AES_imc[tmp.B(4 * i + 3)][3]);
     }
 }
 
@@ -2328,6 +2330,7 @@ void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
     d->L(3) = (d->L(2) << 24 | d->L(2) >> 8) ^ ctrl;
 }
 #endif
+#endif
 
 #undef SSE_HELPER_S
 
-- 
2.37.1