[PATCH v3] net: fix checksum with unaligned buffer

[Morten Brørup]

With this patch, the checksum can be calculated on an unligned buffer.
I.e. the buf parameter is no longer required to be 16 bit aligned.

The checksum is still calculated using a 16 bit aligned pointer, so the
compiler can auto-vectorize the function's inner loop.

When the buffer is unaligned, the first byte of the buffer is handled
separately. Furthermore, the calculated checksum of the buffer is byte
shifted before being added to the initial checksum, to compensate for the
checksum having been calculated on the buffer shifted by one byte.

v3:
* Remove braces from single statement block.
* Fix typo in commit message.
v2:
* Do not assume that the buffer is part of an aligned packet buffer.

Bugzilla ID: 1035
Cc: stable at dpdk.org

Signed-off-by: Morten Brørup <mb at smartsharesystems.com>
---
 lib/net/rte_ip.h | 30 +++++++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 5 deletions(-)

diff --git a/lib/net/rte_ip.h b/lib/net/rte_ip.h
index b502481670..3fad448085 100644
--- a/lib/net/rte_ip.h
+++ b/lib/net/rte_ip.h
@@ -162,20 +162,40 @@ __rte_raw_cksum(const void *buf, size_t len, uint32_t sum)
 {
 	/* extend strict-aliasing rules */
 	typedef uint16_t __attribute__((__may_alias__)) u16_p;
-	const u16_p *u16_buf = (const u16_p *)buf;
-	const u16_p *end = u16_buf + len / sizeof(*u16_buf);
+	const u16_p *u16_buf;
+	const u16_p *end;
+	uint32_t bsum = 0;
+	const bool unaligned = (uintptr_t)buf & 1;
+
+	/* if buffer is unaligned, keeping it byte order independent */
+	if (unlikely(unaligned)) {
+		uint16_t first = 0;
+		if (unlikely(len == 0))
+			return 0;
+		((unsigned char *)&first)[1] = *(const unsigned char *)buf;
+		bsum += first;
+		buf = (const void *)((uintptr_t)buf + 1);
+		len--;
+	}
 
+	/* aligned access for compiler auto-vectorization */
+	u16_buf = (const u16_p *)buf;
+	end = u16_buf + len / sizeof(*u16_buf);
 	for (; u16_buf != end; ++u16_buf)
-		sum += *u16_buf;
+		bsum += *u16_buf;
 
 	/* if length is odd, keeping it byte order independent */
 	if (unlikely(len % 2)) {
 		uint16_t left = 0;
 		*(unsigned char *)&left = *(const unsigned char *)end;
-		sum += left;
+		bsum += left;
 	}
 
-	return sum;
+	/* if buffer is unaligned, swap the checksum bytes */
+	if (unlikely(unaligned))
+		bsum = (bsum & 0xFF00FF00) >> 8 | (bsum & 0x00FF00FF) << 8;
+
+	return sum + bsum;
 }
 
 /**
-- 
2.17.1