1 files changed, 38 insertions, 34 deletions

diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 8d7784122c14..6b876ca299ee 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -39,12 +39,14 @@
 #ifdef USE_DOUBLE
 
 #define LOAD   ld
+#define LOAD32 lwu
 #define ADD    daddu
 #define NBYTES 8
 
 #else
 
 #define LOAD   lw
+#define LOAD32 lw
 #define ADD    addu
 #define NBYTES 4
 
@@ -53,12 +55,14 @@
 #define UNIT(unit)  ((unit)*NBYTES)
 
 #define ADDC(sum,reg)                                           \
-        .set    push;                                           \
-        .set    noat;                                           \
         ADD     sum, reg;                                       \
         sltu    v1, sum, reg;                                   \
         ADD     sum, v1;                                        \
-        .set    pop
+
+#define ADDC32(sum,reg)                                         \
+        addu    sum, reg;                                       \
+        sltu    v1, sum, reg;                                   \
+        addu    sum, v1;                                        \
 
 #define CSUM_BIGCHUNK1(src, offset, sum, _t0, _t1, _t2, _t3)    \
         LOAD    _t0, (offset + UNIT(0))(src);                   \
@@ -132,7 +136,7 @@ LEAF(csum_partial)
         beqz    t8, .Lqword_align
          andi   t8, src, 0x8
 
-        lw      t0, 0x00(src)
+        LOAD32  t0, 0x00(src)
         LONG_SUBU       a1, a1, 0x4
         ADDC(sum, t0)
         PTR_ADDU        src, src, 0x4
@@ -211,7 +215,7 @@ LEAF(csum_partial)
         LONG_SRL        t8, t8, 0x2
 
 .Lend_words:
-        lw      t0, (src)
+        LOAD32  t0, (src)
         LONG_SUBU       t8, t8, 0x1
         ADDC(sum, t0)
         .set    reorder                         /* DADDI_WAR */
@@ -230,6 +234,9 @@ LEAF(csum_partial)
         /* Still a full word to go  */
         ulw     t1, (src)
         PTR_ADDIU       src, 4
+#ifdef USE_DOUBLE
+        dsll    t1, t1, 32                      /* clear lower 32bit */
+#endif
         ADDC(sum, t1)
 
 1:      move    t1, zero
@@ -254,8 +261,6 @@ LEAF(csum_partial)
 1:      ADDC(sum, t1)
 
         /* fold checksum */
-        .set    push
-        .set    noat
 #ifdef USE_DOUBLE
         dsll32  v1, sum, 0
         daddu   sum, v1
@@ -263,24 +268,25 @@ LEAF(csum_partial)
         dsra32  sum, sum, 0
         addu    sum, v1
 #endif
-        sll     v1, sum, 16
-        addu    sum, v1
-        sltu    v1, sum, v1
-        srl     sum, sum, 16
-        addu    sum, v1
 
         /* odd buffer alignment? */
-        beqz    t7, 1f
-         nop
-        sll     v1, sum, 8
+#ifdef CPU_MIPSR2
+        wsbh    v1, sum
+        movn    sum, v1, t7
+#else
+        beqz    t7, 1f                  /* odd buffer alignment? */
+         lui    v1, 0x00ff
+        addu    v1, 0x00ff
+        and     t0, sum, v1
+        sll     t0, t0, 8
         srl     sum, sum, 8
-        or      sum, v1
-        andi    sum, 0xffff
-        .set    pop
+        and     sum, sum, v1
+        or      sum, sum, t0
 1:
+#endif
         .set    reorder
         /* Add the passed partial csum.  */
-        ADDC(sum, a2)
+        ADDC32(sum, a2)
         jr      ra
         .set    noreorder
         END(csum_partial)
@@ -656,8 +662,6 @@ EXC(	sb	t0, NBYTES-2(dst), .Ls_exc)
         ADDC(sum, t2)
 .Ldone:
         /* fold checksum */
-        .set    push
-        .set    noat
 #ifdef USE_DOUBLE
         dsll32  v1, sum, 0
         daddu   sum, v1
@@ -665,23 +669,23 @@ EXC(	sb	t0, NBYTES-2(dst), .Ls_exc)
         dsra32  sum, sum, 0
         addu    sum, v1
 #endif
-        sll     v1, sum, 16
-        addu    sum, v1
-        sltu    v1, sum, v1
-        srl     sum, sum, 16
-        addu    sum, v1
 
-        /* odd buffer alignment? */
-        beqz    odd, 1f
-         nop
-        sll     v1, sum, 8
+#ifdef CPU_MIPSR2
+        wsbh    v1, sum
+        movn    sum, v1, odd
+#else
+        beqz    odd, 1f                 /* odd buffer alignment? */
+         lui    v1, 0x00ff
+        addu    v1, 0x00ff
+        and     t0, sum, v1
+        sll     t0, t0, 8
         srl     sum, sum, 8
-        or      sum, v1
-        andi    sum, 0xffff
-        .set    pop
+        and     sum, sum, v1
+        or      sum, sum, t0
 1:
+#endif
         .set reorder
-        ADDC(sum, psum)
+        ADDC32(sum, psum)
         jr      ra
         .set noreorder