@@ -8,6 +8,7 @@
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
// Registers used to hold message words temporarily. There aren't
// enough ARM registers to hold the whole message block, so we have to
@@ -38,6 +39,23 @@
#endif
.endm
+.macro _le32_bswap a, tmp
+#ifdef __ARMEB__
+ rev_l \a, \tmp
+#endif
+.endm
+
+.macro _le32_bswap_8x a, b, c, d, e, f, g, h, tmp
+ _le32_bswap \a, \tmp
+ _le32_bswap \b, \tmp
+ _le32_bswap \c, \tmp
+ _le32_bswap \d, \tmp
+ _le32_bswap \e, \tmp
+ _le32_bswap \f, \tmp
+ _le32_bswap \g, \tmp
+ _le32_bswap \h, \tmp
+.endm
+
// Execute a quarter-round of BLAKE2s by mixing two columns or two diagonals.
// (a0, b0, c0, d0) and (a1, b1, c1, d1) give the registers containing the two
// columns/diagonals. s0-s1 are the word offsets to the message words the first
@@ -180,8 +198,10 @@ ENTRY(blake2s_compress_arch)
tst r1, #3
bne .Lcopy_block_misaligned
ldmia r1!, {r2-r9}
+ _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14
stmia r12!, {r2-r9}
ldmia r1!, {r2-r9}
+ _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14
stmia r12, {r2-r9}
.Lcopy_block_done:
str r1, [sp, #68] // Update message pointer
@@ -268,6 +288,7 @@ ENTRY(blake2s_compress_arch)
1:
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
ldr r3, [r1], #4
+ _le32_bswap r3, r4
#else
ldrb r3, [r1, #0]
ldrb r4, [r1, #1]