These changes are the raw update to linux-4.4.6-rt14. Kernel sources

[kvmfornfv.git] / kernel / lib / raid6 / neon.uc

diff --git a/kernel/lib/raid6/neon.uc b/kernel/lib/raid6/neon.uc
index 1b9ed79..4fa51b7 100644 (file)
--- a/kernel/lib/raid6/neon.uc
+++ b/kernel/lib/raid6/neon.uc
@@ -3,6 +3,7 @@
  *   neon.uc - RAID-6 syndrome calculation using ARM NEON instructions
  *
  *   Copyright (C) 2012 Rob Herring
+ *   Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  *   Based on altivec.uc:
  *     Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
@@ -78,3 +79,48 @@ void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
                vst1q_u8(&q[d+NSIZE*$$], wq$$);
        }
 }
+
+void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
+                                   unsigned long bytes, void **ptrs)
+{
+       uint8_t **dptr = (uint8_t **)ptrs;
+       uint8_t *p, *q;
+       int d, z, z0;
+
+       register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
+       const unative_t x1d = NBYTES(0x1d);
+
+       z0 = stop;              /* P/Q right side optimization */
+       p = dptr[disks-2];      /* XOR parity */
+       q = dptr[disks-1];      /* RS syndrome */
+
+       for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+               wq$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
+               wp$$ = veorq_u8(vld1q_u8(&p[d+$$*NSIZE]), wq$$);
+
+               /* P/Q data pages */
+               for ( z = z0-1 ; z >= start ; z-- ) {
+                       wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
+                       wp$$ = veorq_u8(wp$$, wd$$);
+                       w2$$ = MASK(wq$$);
+                       w1$$ = SHLBYTE(wq$$);
+
+                       w2$$ = vandq_u8(w2$$, x1d);
+                       w1$$ = veorq_u8(w1$$, w2$$);
+                       wq$$ = veorq_u8(w1$$, wd$$);
+               }
+               /* P/Q left side optimization */
+               for ( z = start-1 ; z >= 0 ; z-- ) {
+                       w2$$ = MASK(wq$$);
+                       w1$$ = SHLBYTE(wq$$);
+
+                       w2$$ = vandq_u8(w2$$, x1d);
+                       wq$$ = veorq_u8(w1$$, w2$$);
+               }
+               w1$$ = vld1q_u8(&q[d+NSIZE*$$]);
+               wq$$ = veorq_u8(wq$$, w1$$);
+
+               vst1q_u8(&p[d+NSIZE*$$], wp$$);
+               vst1q_u8(&q[d+NSIZE*$$], wq$$);
+       }
+}