arm: Fix memxor for non-armv6+ big-endian systems

ARM assembly adjustments for big-endian systems contained armv6+-only
instructions (rev) in generic arm memxor code. Replace those with an
actual conversion of the leftover byte store routines for big-endian
systems. This also provides a slight optimisation by removing the
additional instruction as well as increased symmetry between little- and
big-endian implementations.

Signed-off-by: Michael Weiser <michael.weiser@gmx.de>

diff --git a/arm/memxor.asm b/arm/memxor.asm
index 239a40342eed80464d64e449a0169998a9e06e17..e4619629dc490a8c7231339064ca49f8c461a370 100644 (file)
--- a/arm/memxor.asm
+++ b/arm/memxor.asm
@@ -138,24 +138,25 @@ PROLOGUE(nettle_memxor)
        adds    N, #8
        beq     .Lmemxor_odd_done
 
-       C We have TNC/8 left-over bytes in r4, high end
+       C We have TNC/8 left-over bytes in r4, high end on LE and low end on
+       C BE, excess bits to be discarded by alignment adjustment at the other
        S0ADJ   r4, CNT
+       C now byte-aligned at low end on LE and high end on BE
        ldr     r3, [DST]
        eor     r3, r4
 
-       C memxor_leftover does an LSB store
-       C so we need to reverse if actually BE
-IF_BE(<        rev     r3, r3>)
-
        pop     {r4,r5,r6}
 
        C Store bytes, one by one.
 .Lmemxor_leftover:
+       C bring uppermost byte down for saving while preserving lower ones
+IF_BE(<        ror     r3, #24>)
        strb    r3, [DST], #+1
        subs    N, #1
        beq     .Lmemxor_done
        subs    TNC, #8
-       lsr     r3, #8
+       C bring down next byte, no need to preserve
+IF_LE(<        lsr     r3, #8>)
        bne     .Lmemxor_leftover
        b       .Lmemxor_bytes
 .Lmemxor_odd_done:

diff --git a/arm/memxor3.asm b/arm/memxor3.asm
index 69598e1caa5c24534557ea53ce261e74385a3b28..b6c6da4919d472f4a392cd86c38b92b0bf0b6bf8 100644 (file)
--- a/arm/memxor3.asm
+++ b/arm/memxor3.asm
@@ -159,21 +159,23 @@ PROLOGUE(nettle_memxor3)
        adds    N, #8
        beq     .Lmemxor3_done
 
-       C Leftover bytes in r4, low end
+       C Leftover bytes in r4, low end on LE and high end on BE before
+       C preparatory alignment correction
        ldr     r5, [AP, #-4]
        eor     r4, r5, r4, S1ADJ ATNC
-
-       C leftover does an LSB store
-       C so we need to reverse if actually BE
-IF_BE(<        rev     r4, r4>)
+       C now byte-aligned in high end on LE and low end on BE because we're
+       C working downwards in saving the very first bytes of the buffer
 
 .Lmemxor3_au_leftover:
        C Store a byte at a time
-       ror     r4, #24
+       C bring uppermost byte down for saving while preserving lower ones
+IF_LE(<        ror     r4, #24>)
        strb    r4, [DST, #-1]!
        subs    N, #1
        beq     .Lmemxor3_done
        subs    ACNT, #8
+       C bring down next byte, no need to preserve
+IF_BE(<        lsr     r4, #8>)
        sub     AP, #1
        bne     .Lmemxor3_au_leftover
        b       .Lmemxor3_bytes
@@ -273,18 +275,21 @@ IF_BE(<   rev     r4, r4>)
        adds    N, #8
        beq     .Lmemxor3_done
 
-       C leftover does an LSB store
-       C so we need to reverse if actually BE
-IF_BE(<        rev     r4, r4>)
-
-       C Leftover bytes in a4, low end
-       ror     r4, ACNT
+       C Leftover bytes in r4, low end on LE and high end on BE before
+       C preparatory alignment correction
+IF_LE(<        ror     r4, ACNT>)
+IF_BE(<        ror     r4, ATNC>)
+       C now byte-aligned in high end on LE and low end on BE because we're
+       C working downwards in saving the very first bytes of the buffer
 .Lmemxor3_uu_leftover:
-       ror     r4, #24
+       C bring uppermost byte down for saving while preserving lower ones
+IF_LE(<        ror     r4, #24>)
        strb    r4, [DST, #-1]!
        subs    N, #1
        beq     .Lmemxor3_done
        subs    ACNT, #8
+       C bring down next byte, no need to preserve
+IF_BE(<        lsr     r4, #8>)
        bne     .Lmemxor3_uu_leftover
        b       .Lmemxor3_bytes