Fix syntax error for the armv4 assembler

The error was from the alignment syntax of the code.
More details:
https://stackoverflow.com/questions/57316823/arm-assembly-syntax-in-vst-vld-commands?noredirect=1#comment101133590_57316823

CLA: trivial

Fixes: #9518
Reviewed-by: Paul Dale <paul.dale@oracle.com>
Reviewed-by: Bernd Edlinger <bernd.edlinger@hotmail.de>
(Merged from https://github.com/openssl/openssl/pull/9518)

diff --git a/crypto/sha/asm/keccak1600-armv4.pl b/crypto/sha/asm/keccak1600-armv4.pl
index be411ed74b00df2a5510ed83b64551f23b6ec9a7..0bfee48f84bf7bc6639f7ba32c6294b6b509d356 100755 (executable)
--- a/crypto/sha/asm/keccak1600-armv4.pl
+++ b/crypto/sha/asm/keccak1600-armv4.pl
@@ -1132,9 +1132,9 @@ KeccakF1600_neon:
 .align 4
 .Loop_neon:
        @ Theta
-       vst1.64         {q4},  [r0:64]          @ offload A[0..1][4]
+       vst1.64         {q4},  [r0,:64]         @ offload A[0..1][4]
        veor            q13, q0,  q5            @ A[0..1][0]^A[2..3][0]
-       vst1.64         {d18}, [r1:64]          @ offload A[2][4]
+       vst1.64         {d18}, [r1,:64]         @ offload A[2][4]
        veor            q14, q1,  q6            @ A[0..1][1]^A[2..3][1]
        veor            q15, q2,  q7            @ A[0..1][2]^A[2..3][2]
        veor            d26, d26, d27           @ C[0]=A[0][0]^A[1][0]^A[2][0]^A[3][0]
@@ -1177,10 +1177,10 @@ KeccakF1600_neon:
        veor            d16, d16, d28           @ A[2][3] ^= C[2]
        veor            d17, d17, d28           @ A[3][3] ^= C[2]
        veor            d23, d23, d28           @ A[4][3] ^= C[2]
-       vld1.64         {q4},  [r0:64]          @ restore A[0..1][4]
+       vld1.64         {q4},  [r0,:64]         @ restore A[0..1][4]
        vmov            d28, d29
 
-       vld1.64         {d18}, [r1:64]          @ restore A[2][4]
+       vld1.64         {d18}, [r1,:64]         @ restore A[2][4]
        veor            q2,  q2,  q13           @ A[0..1][2] ^= D[2]
        veor            q7,  q7,  q13           @ A[2..3][2] ^= D[2]
        veor            d22, d22, d27           @ A[4][2]    ^= D[2]
@@ -1255,7 +1255,7 @@ KeccakF1600_neon:
        veor            q13, q13, q0            @ A[0..1][0] ^ (~A[0..1][1] & A[0..1][2])
        veor            q14, q14, q1            @ A[0..1][1] ^ (~A[0..1][2] & A[0..1][3])
        veor            q2,  q2,  q15           @ A[0..1][2] ^= (~A[0..1][3] & A[0..1][4])
-       vst1.64         {q13}, [r0:64]          @ offload A[0..1][0]
+       vst1.64         {q13}, [r0,:64]         @ offload A[0..1][0]
        vbic            q13, q0,  q4
        vbic            q15, q1,  q0
        vmov            q1,  q14                @ A[0..1][1]
@@ -1276,10 +1276,10 @@ KeccakF1600_neon:
        vmov            q14, q10                @ A[4][0..1]
        veor            q9,  q9,  q13           @ A[2..3][4] ^= (~A[2..3][0] & A[2..3][1])
 
-       vld1.64         d25, [r2:64]!           @ Iota[i++]
+       vld1.64         d25, [r2,:64]!          @ Iota[i++]
        vbic            d26, d22, d21
        vbic            d27, d23, d22
-       vld1.64         {q0}, [r0:64]           @ restore A[0..1][0]
+       vld1.64         {q0}, [r0,:64]          @ restore A[0..1][0]
        veor            d20, d20, d26           @ A[4][0] ^= (~A[4][1] & A[4][2])
        vbic            d26, d24, d23
        veor            d21, d21, d27           @ A[4][1] ^= (~A[4][2] & A[4][3])
@@ -1307,32 +1307,32 @@ SHA3_absorb_neon:
        mov     r5, r2                  @ len
        mov     r6, r3                  @ bsz
 
-       vld1.32 {d0}, [r0:64]!          @ A[0][0]
-       vld1.32 {d2}, [r0:64]!          @ A[0][1]
-       vld1.32 {d4}, [r0:64]!          @ A[0][2]
-       vld1.32 {d6}, [r0:64]!          @ A[0][3]
-       vld1.32 {d8}, [r0:64]!          @ A[0][4]
-
-       vld1.32 {d1}, [r0:64]!          @ A[1][0]
-       vld1.32 {d3}, [r0:64]!          @ A[1][1]
-       vld1.32 {d5}, [r0:64]!          @ A[1][2]
-       vld1.32 {d7}, [r0:64]!          @ A[1][3]
-       vld1.32 {d9}, [r0:64]!          @ A[1][4]
-
-       vld1.32 {d10}, [r0:64]!         @ A[2][0]
-       vld1.32 {d12}, [r0:64]!         @ A[2][1]
-       vld1.32 {d14}, [r0:64]!         @ A[2][2]
-       vld1.32 {d16}, [r0:64]!         @ A[2][3]
-       vld1.32 {d18}, [r0:64]!         @ A[2][4]
-
-       vld1.32 {d11}, [r0:64]!         @ A[3][0]
-       vld1.32 {d13}, [r0:64]!         @ A[3][1]
-       vld1.32 {d15}, [r0:64]!         @ A[3][2]
-       vld1.32 {d17}, [r0:64]!         @ A[3][3]
-       vld1.32 {d19}, [r0:64]!         @ A[3][4]
-
-       vld1.32 {d20-d23}, [r0:64]!     @ A[4][0..3]
-       vld1.32 {d24}, [r0:64]          @ A[4][4]
+       vld1.32 {d0}, [r0,:64]!         @ A[0][0]
+       vld1.32 {d2}, [r0,:64]!         @ A[0][1]
+       vld1.32 {d4}, [r0,:64]!         @ A[0][2]
+       vld1.32 {d6}, [r0,:64]!         @ A[0][3]
+       vld1.32 {d8}, [r0,:64]!         @ A[0][4]
+
+       vld1.32 {d1}, [r0,:64]!         @ A[1][0]
+       vld1.32 {d3}, [r0,:64]!         @ A[1][1]
+       vld1.32 {d5}, [r0,:64]!         @ A[1][2]
+       vld1.32 {d7}, [r0,:64]!         @ A[1][3]
+       vld1.32 {d9}, [r0,:64]!         @ A[1][4]
+
+       vld1.32 {d10}, [r0,:64]!                @ A[2][0]
+       vld1.32 {d12}, [r0,:64]!                @ A[2][1]
+       vld1.32 {d14}, [r0,:64]!                @ A[2][2]
+       vld1.32 {d16}, [r0,:64]!                @ A[2][3]
+       vld1.32 {d18}, [r0,:64]!                @ A[2][4]
+
+       vld1.32 {d11}, [r0,:64]!                @ A[3][0]
+       vld1.32 {d13}, [r0,:64]!                @ A[3][1]
+       vld1.32 {d15}, [r0,:64]!                @ A[3][2]
+       vld1.32 {d17}, [r0,:64]!                @ A[3][3]
+       vld1.32 {d19}, [r0,:64]!                @ A[3][4]
+
+       vld1.32 {d20-d23}, [r0,:64]!    @ A[4][0..3]
+       vld1.32 {d24}, [r0,:64]         @ A[4][4]
        sub     r0, r0, #24*8           @ rewind
        b       .Loop_absorb_neon
 
@@ -1439,32 +1439,32 @@ SHA3_absorb_neon:
 
 .align 4
 .Labsorbed_neon:
-       vst1.32 {d0}, [r0:64]!          @ A[0][0..4]
-       vst1.32 {d2}, [r0:64]!
-       vst1.32 {d4}, [r0:64]!
-       vst1.32 {d6}, [r0:64]!
-       vst1.32 {d8}, [r0:64]!
-
-       vst1.32 {d1}, [r0:64]!          @ A[1][0..4]
-       vst1.32 {d3}, [r0:64]!
-       vst1.32 {d5}, [r0:64]!
-       vst1.32 {d7}, [r0:64]!
-       vst1.32 {d9}, [r0:64]!
-
-       vst1.32 {d10}, [r0:64]!         @ A[2][0..4]
-       vst1.32 {d12}, [r0:64]!
-       vst1.32 {d14}, [r0:64]!
-       vst1.32 {d16}, [r0:64]!
-       vst1.32 {d18}, [r0:64]!
-
-       vst1.32 {d11}, [r0:64]!         @ A[3][0..4]
-       vst1.32 {d13}, [r0:64]!
-       vst1.32 {d15}, [r0:64]!
-       vst1.32 {d17}, [r0:64]!
-       vst1.32 {d19}, [r0:64]!
-
-       vst1.32 {d20-d23}, [r0:64]!     @ A[4][0..4]
-       vst1.32 {d24}, [r0:64]
+       vst1.32 {d0}, [r0,:64]!         @ A[0][0..4]
+       vst1.32 {d2}, [r0,:64]!
+       vst1.32 {d4}, [r0,:64]!
+       vst1.32 {d6}, [r0,:64]!
+       vst1.32 {d8}, [r0,:64]!
+
+       vst1.32 {d1}, [r0,:64]!         @ A[1][0..4]
+       vst1.32 {d3}, [r0,:64]!
+       vst1.32 {d5}, [r0,:64]!
+       vst1.32 {d7}, [r0,:64]!
+       vst1.32 {d9}, [r0,:64]!
+
+       vst1.32 {d10}, [r0,:64]!                @ A[2][0..4]
+       vst1.32 {d12}, [r0,:64]!
+       vst1.32 {d14}, [r0,:64]!
+       vst1.32 {d16}, [r0,:64]!
+       vst1.32 {d18}, [r0,:64]!
+
+       vst1.32 {d11}, [r0,:64]!                @ A[3][0..4]
+       vst1.32 {d13}, [r0,:64]!
+       vst1.32 {d15}, [r0,:64]!
+       vst1.32 {d17}, [r0,:64]!
+       vst1.32 {d19}, [r0,:64]!
+
+       vst1.32 {d20-d23}, [r0,:64]!    @ A[4][0..4]
+       vst1.32 {d24}, [r0,:64]
 
        mov     r0, r5                  @ return value
        vldmia  sp!, {d8-d15}
@@ -1499,64 +1499,64 @@ SHA3_squeeze_neon:
 
        vstmdb  sp!,  {d8-d15}
 
-       vld1.32 {d0}, [r0:64]!          @ A[0][0..4]
-       vld1.32 {d2}, [r0:64]!
-       vld1.32 {d4}, [r0:64]!
-       vld1.32 {d6}, [r0:64]!
-       vld1.32 {d8}, [r0:64]!
-
-       vld1.32 {d1}, [r0:64]!          @ A[1][0..4]
-       vld1.32 {d3}, [r0:64]!
-       vld1.32 {d5}, [r0:64]!
-       vld1.32 {d7}, [r0:64]!
-       vld1.32 {d9}, [r0:64]!
-
-       vld1.32 {d10}, [r0:64]!         @ A[2][0..4]
-       vld1.32 {d12}, [r0:64]!
-       vld1.32 {d14}, [r0:64]!
-       vld1.32 {d16}, [r0:64]!
-       vld1.32 {d18}, [r0:64]!
-
-       vld1.32 {d11}, [r0:64]!         @ A[3][0..4]
-       vld1.32 {d13}, [r0:64]!
-       vld1.32 {d15}, [r0:64]!
-       vld1.32 {d17}, [r0:64]!
-       vld1.32 {d19}, [r0:64]!
-
-       vld1.32 {d20-d23}, [r0:64]!     @ A[4][0..4]
-       vld1.32 {d24}, [r0:64]
+       vld1.32 {d0}, [r0,:64]!         @ A[0][0..4]
+       vld1.32 {d2}, [r0,:64]!
+       vld1.32 {d4}, [r0,:64]!
+       vld1.32 {d6}, [r0,:64]!
+       vld1.32 {d8}, [r0,:64]!
+
+       vld1.32 {d1}, [r0,:64]!         @ A[1][0..4]
+       vld1.32 {d3}, [r0,:64]!
+       vld1.32 {d5}, [r0,:64]!
+       vld1.32 {d7}, [r0,:64]!
+       vld1.32 {d9}, [r0,:64]!
+
+       vld1.32 {d10}, [r0,:64]!                @ A[2][0..4]
+       vld1.32 {d12}, [r0,:64]!
+       vld1.32 {d14}, [r0,:64]!
+       vld1.32 {d16}, [r0,:64]!
+       vld1.32 {d18}, [r0,:64]!
+
+       vld1.32 {d11}, [r0,:64]!                @ A[3][0..4]
+       vld1.32 {d13}, [r0,:64]!
+       vld1.32 {d15}, [r0,:64]!
+       vld1.32 {d17}, [r0,:64]!
+       vld1.32 {d19}, [r0,:64]!
+
+       vld1.32 {d20-d23}, [r0,:64]!    @ A[4][0..4]
+       vld1.32 {d24}, [r0,:64]
        sub     r0, r0, #24*8           @ rewind
 
        bl      KeccakF1600_neon
 
        mov     r12, r0                 @ A_flat
-       vst1.32 {d0}, [r0:64]!          @ A[0][0..4]
-       vst1.32 {d2}, [r0:64]!
-       vst1.32 {d4}, [r0:64]!
-       vst1.32 {d6}, [r0:64]!
-       vst1.32 {d8}, [r0:64]!
-
-       vst1.32 {d1}, [r0:64]!          @ A[1][0..4]
-       vst1.32 {d3}, [r0:64]!
-       vst1.32 {d5}, [r0:64]!
-       vst1.32 {d7}, [r0:64]!
-       vst1.32 {d9}, [r0:64]!
-
-       vst1.32 {d10}, [r0:64]!         @ A[2][0..4]
-       vst1.32 {d12}, [r0:64]!
-       vst1.32 {d14}, [r0:64]!
-       vst1.32 {d16}, [r0:64]!
-       vst1.32 {d18}, [r0:64]!
-
-       vst1.32 {d11}, [r0:64]!         @ A[3][0..4]
-       vst1.32 {d13}, [r0:64]!
-       vst1.32 {d15}, [r0:64]!
-       vst1.32 {d17}, [r0:64]!
-       vst1.32 {d19}, [r0:64]!
-
-       vst1.32 {d20-d23}, [r0:64]!     @ A[4][0..4]
+       vst1.32 {d0}, [r0,:64]!         @ A[0][0..4]
+       vst1.32 {d2}, [r0,:64]!
+       vst1.32 {d4}, [r0,:64]!
+       vst1.32 {d6}, [r0,:64]!
+       vst1.32 {d8}, [r0,:64]!
+
+       vst1.32 {d1}, [r0,:64]!         @ A[1][0..4]
+       vst1.32 {d3}, [r0,:64]!
+       vst1.32 {d5}, [r0,:64]!
+       vst1.32 {d7}, [r0,:64]!
+       vst1.32 {d9}, [r0,:64]!
+
+       vst1.32 {d10}, [r0,:64]!                @ A[2][0..4]
+       vst1.32 {d12}, [r0,:64]!
+       vst1.32 {d14}, [r0,:64]!
+       vst1.32 {d16}, [r0,:64]!
+       vst1.32 {d18}, [r0,:64]!
+
+       vst1.32 {d11}, [r0,:64]!                @ A[3][0..4]
+       vst1.32 {d13}, [r0,:64]!
+       vst1.32 {d15}, [r0,:64]!
+       vst1.32 {d17}, [r0,:64]!
+       vst1.32 {d19}, [r0,:64]!
+
+       vst1.32 {d20-d23}, [r0,:64]!    @ A[4][0..4]
        mov     r14, r6                 @ bsz
-       vst1.32 {d24}, [r0:64]
+       vst1.32 {d24}, [r0,:64]
        mov     r0,  r12                @ rewind
 
        vldmia  sp!, {d8-d15}