[PATCH v2 4/5] rslib: Improve the performance of encode_rs.c

[Zhang Boyang <zhangboyang.id@gmail.com>]

This patch enhances the performance of RS encoder by following points:

1) Avoid memmove(). The shifting operation done by memmove() can be
   merged into the calculation loop above.

2) Introduce rs_modnn_fast(). The original rs_modnn() contains a loop
   which may be slow. Since (fb + genpoly[...]) is always strictly less
   than (2 * rs->nn), we can use a ternary operator to do the same
   calculation. The new faster function is named rs_modnn_fast(). The
   new rs_modnn_fast(x) requires 0 <= x < 2*nn, in contrast, original
   rs_modnn(x) only requires x >= 0. To make things clear, the
   documentation of original rs_modnn() is also updated.

Signed-off-by: Zhang Boyang <zhangboyang.id@gmail.com>
---
 include/linux/rslib.h        | 14 +++++++++++++-
 lib/reed_solomon/encode_rs.c | 21 ++++++++++-----------
 2 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/include/linux/rslib.h b/include/linux/rslib.h
index cd0b5a7a5698..44ec7c6f24b2 100644
--- a/include/linux/rslib.h
+++ b/include/linux/rslib.h
@@ -110,7 +110,7 @@ void free_rs(struct rs_control *rs);
 /** modulo replacement for galois field arithmetics
  *
  *  @rs:	Pointer to the RS codec
- *  @x:		the value to reduce
+ *  @x:		x >= 0 ; the value to reduce
  *
  *  where
  *  rs->mm = number of bits per symbol
@@ -127,4 +127,16 @@ static inline int rs_modnn(struct rs_codec *rs, int x)
 	return x;
 }
 
+/** modulo replacement for galois field arithmetics
+ *
+ *  @rs:	Pointer to the RS codec
+ *  @x:		0 <= x < 2*nn ; the value to reduce
+ *
+ *  Same as rs_modnn(x), but faster, at the cost of limited value range of @x
+*/
+static inline int rs_modnn_fast(struct rs_codec *rs, int x)
+{
+	return x - rs->nn < 0 ? x : x - rs->nn;
+}
+
 #endif
diff --git a/lib/reed_solomon/encode_rs.c b/lib/reed_solomon/encode_rs.c
index 9112d46e869e..6e3847b17ad4 100644
--- a/lib/reed_solomon/encode_rs.c
+++ b/lib/reed_solomon/encode_rs.c
@@ -27,19 +27,18 @@
 
 	for (i = 0; i < len; i++) {
 		fb = index_of[((((uint16_t) data[i])^invmsk) & msk) ^ par[0]];
-		/* feedback term is non-zero */
 		if (fb != nn) {
-			for (j = 1; j < nroots; j++) {
-				par[j] ^= alpha_to[rs_modnn(rs, fb +
-							 genpoly[nroots - j])];
-			}
-		}
-		/* Shift */
-		memmove(&par[0], &par[1], sizeof(uint16_t) * (nroots - 1));
-		if (fb != nn) {
-			par[nroots - 1] = alpha_to[rs_modnn(rs,
-							    fb + genpoly[0])];
+			/* feedback term is non-zero */
+			for (j = 1; j < nroots; j++)
+				par[j - 1] = par[j] ^ alpha_to[rs_modnn_fast(rs,
+						      fb +
+						      genpoly[nroots - j])];
+			par[nroots - 1] = alpha_to[rs_modnn_fast(rs,
+					  fb +
+					  genpoly[0])];
 		} else {
+			for (j = 1; j < nroots; j++)
+				par[j - 1] = par[j];
 			par[nroots - 1] = 0;
 		}
 	}
-- 
2.30.2