[PATCH] ext4: improve str2hashbuf by processing 4-byte chunks

[Guan-Chun Wu]

The original byte-by-byte implementation with modulo checks is less
efficient. Refactor str2hashbuf_unsigned() and str2hashbuf_signed()
to process input in explicit 4-byte chunks instead of using a
modulus-based loop to emit words byte by byte.

This change removes per-byte modulo checks and reduces loop iterations,
improving efficiency.

Performance test (x86_64, Intel Core i7-10700 @ 2.90GHz, average over 10000
runs, using kernel module for testing):

    len | orig_s | new_s | orig_u | new_u
    ----+--------+-------+--------+-------
      1 |   70   |   71  |   63   |   63
      8 |   68   |   64  |   64   |   62
     32 |   75   |   70  |   75   |   63
     64 |   96   |   71  |  100   |   68
    255 |  192   |  108  |  187   |   84

Signed-off-by: Guan-Chun Wu <409411716@xxxxxxxxxxxxxx>
---
 fs/ext4/hash.c | 48 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 16 deletions(-)

diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 33cd5b6b02d5..75105828e8b4 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -141,21 +141,29 @@ static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num)
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
 
-	val = pad;
 	if (len > num*4)
 		len = num * 4;
-	for (i = 0; i < len; i++) {
-		val = ((int) scp[i]) + (val << 8);
-		if ((i % 4) == 3) {
-			*buf++ = val;
-			val = pad;
-			num--;
-		}
+
+	while (len >= 4) {
+		val = ((int)scp[0] << 24) + ((int)scp[1] << 16) +
+				((int)scp[2] << 8) + (int)scp[3];
+		*buf++ = val;
+		scp += 4;
+		len -= 4;
+		num--;
 	}
+
+	val = pad;
+
+	for (i = 0; i < len; i++)
+		val = (int)scp[i] + (val << 8);
+
 	if (--num >= 0)
 		*buf++ = val;
+
 	while (--num >= 0)
 		*buf++ = pad;
+
 }
 
 static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
@@ -167,21 +175,29 @@ static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num)
 	pad = (__u32)len | ((__u32)len << 8);
 	pad |= pad << 16;
 
-	val = pad;
 	if (len > num*4)
 		len = num * 4;
-	for (i = 0; i < len; i++) {
-		val = ((int) ucp[i]) + (val << 8);
-		if ((i % 4) == 3) {
-			*buf++ = val;
-			val = pad;
-			num--;
-		}
+
+	while (len >= 4) {
+		val = ((int)ucp[0] << 24) | ((int)ucp[1] << 16) |
+				((int)ucp[2] << 8) | (int)ucp[3];
+		*buf++ = val;
+		ucp += 4;
+		len -= 4;
+		num--;
 	}
+
+	val = pad;
+
+	for (i = 0; i < len; i++)
+		val = (int)ucp[i] + (val << 8);
+
 	if (--num >= 0)
 		*buf++ = val;
+
 	while (--num >= 0)
 		*buf++ = pad;
+
 }
 
 /*
-- 
2.34.1