[PATCH v3 4/9] checksum: add csum_iov()

[Laurent Vivier <lvivier@redhat.com>]

Introduce the function csum_unfolded() that computes the unfolded
32-bit checksum of a data buffer, and call it from csum() that returns
the folded value.

Introduce csum_iov() that computes the checksum using csum_folded() on
all vectors of the iovec array and returns the folded result.

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---

Notes:
    v3:
      - update comments
      - use size_t for the IO vectors length
      - include checksum.h in checksum.c
      - export csum_unfolded() (for later)
    
    v2:
      - fix typo and superfluous space
      - update comments

 checksum.c | 56 ++++++++++++++++++++++++++++++++++++++++++------------
 checksum.h |  2 ++
 2 files changed, 46 insertions(+), 12 deletions(-)

diff --git a/checksum.c b/checksum.c
index 65486b4625ba..74e3742bc6f6 100644
--- a/checksum.c
+++ b/checksum.c
@@ -57,6 +57,7 @@
 #include <linux/icmpv6.h>
 
 #include "util.h"
+#include "checksum.h"
 
 /* Checksums are optional for UDP over IPv4, so we usually just set
  * them to 0.  Change this to 1 to calculate real UDP over IPv4
@@ -385,16 +386,16 @@ less_than_128_bytes:
 }
 
 /**
- * csum() - Compute TCP/IP-style checksum
- * @buf:	Input buffer
- * @len:	Input length
- * @init:	Initial 32-bit checksum, 0 for no pre-computed checksum
+ * csum_unfolded - Calculate the unfolded checksum of a data buffer.
  *
- * Return: 16-bit folded, complemented checksum
+ * @buf:   Input buffer
+ * @len:   Input length
+ * @init:  Initial 32-bit checksum, 0 for no pre-computed checksum
+ *
+ * Return: 32-bit unfolded
  */
-/* NOLINTNEXTLINE(clang-diagnostic-unknown-attributes) */
 __attribute__((optimize("-fno-strict-aliasing")))	/* See csum_16b() */
-uint16_t csum(const void *buf, size_t len, uint32_t init)
+uint32_t csum_unfolded(const void *buf, size_t len, uint32_t init)
 {
 	intptr_t align = ROUND_UP((intptr_t)buf, sizeof(__m256i));
 	unsigned int pad = align - (intptr_t)buf;
@@ -408,16 +409,30 @@ uint16_t csum(const void *buf, size_t len, uint32_t init)
 	if (len > pad)
 		init = csum_avx2((void *)align, len - pad, init);
 
-	return (uint16_t)~csum_fold(init);
+	return init;
 }
-
 #else /* __AVX2__ */
+/**
+ * csum_unfolded - Calculate the unfolded checksum of a data buffer.
+ *
+ * @buf:   Input buffer
+ * @len:   Input length
+ * @init:  Initial 32-bit checksum, 0 for no pre-computed checksum
+ *
+ * Return: 32-bit unfolded checksum
+ */
+__attribute__((optimize("-fno-strict-aliasing")))	/* See csum_16b() */
+uint32_t csum_unfolded(const void *buf, size_t len, uint32_t init)
+{
+	return sum_16b(buf, len) + init;
+}
+#endif /* !__AVX2__ */
 
 /**
  * csum() - Compute TCP/IP-style checksum
  * @buf:	Input buffer
  * @len:	Input length
- * @sum:	Initial 32-bit checksum, 0 for no pre-computed checksum
+ * @init:	Initial 32-bit checksum, 0 for no pre-computed checksum
  *
  * Return: 16-bit folded, complemented checksum
  */
@@ -425,7 +440,24 @@ uint16_t csum(const void *buf, size_t len, uint32_t init)
 __attribute__((optimize("-fno-strict-aliasing")))	/* See csum_16b() */
 uint16_t csum(const void *buf, size_t len, uint32_t init)
 {
-	return (uint16_t)~csum_fold(sum_16b(buf, len) + init);
+	return (uint16_t)~csum_fold(csum_unfolded(buf, len, init));
 }
 
-#endif /* !__AVX2__ */
+/**
+ * csum_iov() - Calculates the unfolded checksum over an array of IO vectors
+ *
+ * @iov		Pointer to the array of IO vectors
+ * @n		Length of the array
+ * @init	Initial 32-bit checksum, 0 for no pre-computed checksum
+ *
+ * Return: 16-bit folded, complemented checksum
+ */
+uint16_t csum_iov(struct iovec *iov, size_t n, uint32_t init)
+{
+	unsigned int i;
+
+	for (i = 0; i < n; i++)
+		init = csum_unfolded(iov[i].iov_base, iov[i].iov_len, init);
+
+	return (uint16_t)~csum_fold(init);
+}
diff --git a/checksum.h b/checksum.h
index 21c0310d3804..dfa705a04a24 100644
--- a/checksum.h
+++ b/checksum.h
@@ -24,6 +24,8 @@ void csum_udp6(struct udphdr *udp6hr,
 void csum_icmp6(struct icmp6hdr *icmp6hr,
 		const struct in6_addr *saddr, const struct in6_addr *daddr,
 		const void *payload, size_t len);
+uint32_t csum_unfolded(const void *buf, size_t len, uint32_t init);
 uint16_t csum(const void *buf, size_t len, uint32_t init);
+uint16_t csum_iov(struct iovec *iov, size_t n, uint32_t init);
 
 #endif /* CHECKSUM_H */
-- 
@@ -24,6 +24,8 @@ void csum_udp6(struct udphdr *udp6hr,
 void csum_icmp6(struct icmp6hdr *icmp6hr,
 		const struct in6_addr *saddr, const struct in6_addr *daddr,
 		const void *payload, size_t len);
+uint32_t csum_unfolded(const void *buf, size_t len, uint32_t init);
 uint16_t csum(const void *buf, size_t len, uint32_t init);
+uint16_t csum_iov(struct iovec *iov, size_t n, uint32_t init);
 
 #endif /* CHECKSUM_H */
-- 
2.42.0