Merge branch 'perf/urgent' into perf/core

Conflicts:
	tools/perf/builtin-record.c
	tools/perf/builtin-top.c
	tools/perf/perf.h
	tools/perf/util/top.h

Merge reason: resolve these cherry-picking conflicts.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 37 insertions, 46 deletions

diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 88f160b77b1f..107f6f7be5e1 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -31,11 +31,6 @@ static inline u64 Maj(u64 x, u64 y, u64 z)
         return (x & y) | (z & (x | y));
 }
 
-static inline u64 RORu64(u64 x, u64 y)
-{
-        return (x >> y) | (x << (64 - y));
-}
-
 static const u64 sha512_K[80] = {
         0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL,
         0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
@@ -66,10 +61,10 @@ static const u64 sha512_K[80] = {
         0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL,
 };
 
-#define e0(x)       (RORu64(x,28) ^ RORu64(x,34) ^ RORu64(x,39))
-#define e1(x)       (RORu64(x,14) ^ RORu64(x,18) ^ RORu64(x,41))
-#define s0(x)       (RORu64(x, 1) ^ RORu64(x, 8) ^ (x >> 7))
-#define s1(x)       (RORu64(x,19) ^ RORu64(x,61) ^ (x >> 6))
+#define e0(x)       (ror64(x,28) ^ ror64(x,34) ^ ror64(x,39))
+#define e1(x)       (ror64(x,14) ^ ror64(x,18) ^ ror64(x,41))
+#define s0(x)       (ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7))
+#define s1(x)       (ror64(x,19) ^ ror64(x,61) ^ (x >> 6))
 
 static inline void LOAD_OP(int I, u64 *W, const u8 *input)
 {
@@ -78,7 +73,7 @@ static inline void LOAD_OP(int I, u64 *W, const u8 *input)
 
 static inline void BLEND_OP(int I, u64 *W)
 {
-        W[I % 16] += s1(W[(I-2) % 16]) + W[(I-7) % 16] + s0(W[(I-15) % 16]);
+        W[I & 15] += s1(W[(I-2) & 15]) + W[(I-7) & 15] + s0(W[(I-15) & 15]);
 }
 
 static void
@@ -89,46 +84,42 @@ sha512_transform(u64 *state, const u8 *input)
         int i;
         u64 W[16];
 
-        /* load the input */
-        for (i = 0; i < 16; i++)
-                LOAD_OP(i, W, input);
-
         /* load the state into our registers */
         a=state[0];   b=state[1];   c=state[2];   d=state[3];
         e=state[4];   f=state[5];   g=state[6];   h=state[7];
 
-#define SHA512_0_15(i, a, b, c, d, e, f, g, h)                  \
-        t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[i];      \
-        t2 = e0(a) + Maj(a, b, c);                              \
-        d += t1;                                                \
-        h = t1 + t2
-
-#define SHA512_16_79(i, a, b, c, d, e, f, g, h)                 \
-        BLEND_OP(i, W);                                         \
-        t1 = h + e1(e) + Ch(e, f, g) + sha512_K[i] + W[(i)%16]; \
-        t2 = e0(a) + Maj(a, b, c);                              \
-        d += t1;                                                \
-        h = t1 + t2
-
-        for (i = 0; i < 16; i += 8) {
-                SHA512_0_15(i, a, b, c, d, e, f, g, h);
-                SHA512_0_15(i + 1, h, a, b, c, d, e, f, g);
-                SHA512_0_15(i + 2, g, h, a, b, c, d, e, f);
-                SHA512_0_15(i + 3, f, g, h, a, b, c, d, e);
-                SHA512_0_15(i + 4, e, f, g, h, a, b, c, d);
-                SHA512_0_15(i + 5, d, e, f, g, h, a, b, c);
-                SHA512_0_15(i + 6, c, d, e, f, g, h, a, b);
-                SHA512_0_15(i + 7, b, c, d, e, f, g, h, a);
-        }
-        for (i = 16; i < 80; i += 8) {
-                SHA512_16_79(i, a, b, c, d, e, f, g, h);
-                SHA512_16_79(i + 1, h, a, b, c, d, e, f, g);
-                SHA512_16_79(i + 2, g, h, a, b, c, d, e, f);
-                SHA512_16_79(i + 3, f, g, h, a, b, c, d, e);
-                SHA512_16_79(i + 4, e, f, g, h, a, b, c, d);
-                SHA512_16_79(i + 5, d, e, f, g, h, a, b, c);
-                SHA512_16_79(i + 6, c, d, e, f, g, h, a, b);
-                SHA512_16_79(i + 7, b, c, d, e, f, g, h, a);
+        /* now iterate */
+        for (i=0; i<80; i+=8) {
+                if (!(i & 8)) {
+                        int j;
+
+                        if (i < 16) {
+                                /* load the input */
+                                for (j = 0; j < 16; j++)
+                                        LOAD_OP(i + j, W, input);
+                        } else {
+                                for (j = 0; j < 16; j++) {
+                                        BLEND_OP(i + j, W);
+                                }
+                        }
+                }
+
+                t1 = h + e1(e) + Ch(e,f,g) + sha512_K[i  ] + W[(i & 15)];
+                t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
+                t1 = g + e1(d) + Ch(d,e,f) + sha512_K[i+1] + W[(i & 15) + 1];
+                t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
+                t1 = f + e1(c) + Ch(c,d,e) + sha512_K[i+2] + W[(i & 15) + 2];
+                t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
+                t1 = e + e1(b) + Ch(b,c,d) + sha512_K[i+3] + W[(i & 15) + 3];
+                t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
+                t1 = d + e1(a) + Ch(a,b,c) + sha512_K[i+4] + W[(i & 15) + 4];
+                t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
+                t1 = c + e1(h) + Ch(h,a,b) + sha512_K[i+5] + W[(i & 15) + 5];
+                t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
+                t1 = b + e1(g) + Ch(g,h,a) + sha512_K[i+6] + W[(i & 15) + 6];
+                t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
+                t1 = a + e1(f) + Ch(f,g,h) + sha512_K[i+7] + W[(i & 15) + 7];
+                t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;
         }
 
         state[0] += a; state[1] += b; state[2] += c; state[3] += d;