[PATCH v3 07/39] net: use C11 alignas

[Tyler Retzlaff <roretzla@linux.microsoft.com>]

* Move __rte_aligned from the end of {struct,union} definitions to
  be between {struct,union} and tag.

  The placement between {struct,union} and the tag allows the desired
  alignment to be imparted on the type regardless of the toolchain being
  used for all of GCC, LLVM, MSVC compilers building both C and C++.

* Replace use of __rte_aligned(a) on variables/fields with alignas(a).

Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
 lib/net/net_crc_avx512.c | 14 ++++++++------
 lib/net/net_crc_neon.c   | 11 ++++++-----
 lib/net/net_crc_sse.c    | 17 +++++++++--------
 lib/net/rte_arp.h        |  8 ++++----
 lib/net/rte_ether.h      |  8 ++++----
 5 files changed, 31 insertions(+), 27 deletions(-)

diff --git a/lib/net/net_crc_avx512.c b/lib/net/net_crc_avx512.c
index f6a3ce9..0f48ca0 100644
--- a/lib/net/net_crc_avx512.c
+++ b/lib/net/net_crc_avx512.c
@@ -3,6 +3,8 @@
  */
 
 
+#include <stdalign.h>
+
 #include <rte_common.h>
 
 #include "net_crc.h"
@@ -20,8 +22,8 @@ struct crc_vpclmulqdq_ctx {
 	__m128i fold_1x128b;
 };
 
-static struct crc_vpclmulqdq_ctx crc32_eth __rte_aligned(64);
-static struct crc_vpclmulqdq_ctx crc16_ccitt __rte_aligned(64);
+static alignas(64) struct crc_vpclmulqdq_ctx crc32_eth;
+static alignas(64) struct crc_vpclmulqdq_ctx crc16_ccitt;
 
 static uint16_t byte_len_to_mask_table[] = {
 	0x0000, 0x0001, 0x0003, 0x0007,
@@ -30,18 +32,18 @@ struct crc_vpclmulqdq_ctx {
 	0x0fff, 0x1fff, 0x3fff, 0x7fff,
 	0xffff};
 
-static const uint8_t shf_table[32] __rte_aligned(16) = {
+static const alignas(16) uint8_t shf_table[32] = {
 	0x00, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
 	0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
 	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
 	0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
 };
 
-static const uint32_t mask[4] __rte_aligned(16) = {
+static const alignas(16) uint32_t mask[4] = {
 	0xffffffff, 0xffffffff, 0x00000000, 0x00000000
 };
 
-static const uint32_t mask2[4] __rte_aligned(16) = {
+static const alignas(16) uint32_t mask2[4] = {
 	0x00000000, 0xffffffff, 0xffffffff, 0xffffffff
 };
 
@@ -93,7 +95,7 @@ struct crc_vpclmulqdq_ctx {
 	uint32_t offset;
 	__m128i res2, res3, res4, pshufb_shf;
 
-	const uint32_t mask3[4] __rte_aligned(16) = {
+	const alignas(16) uint32_t mask3[4] = {
 		   0x80808080, 0x80808080, 0x80808080, 0x80808080
 	};
 
diff --git a/lib/net/net_crc_neon.c b/lib/net/net_crc_neon.c
index f61d75a..cee75dd 100644
--- a/lib/net/net_crc_neon.c
+++ b/lib/net/net_crc_neon.c
@@ -2,6 +2,7 @@
  * Copyright(c) 2017 Cavium, Inc
  */
 
+#include <stdalign.h>
 #include <string.h>
 
 #include <rte_common.h>
@@ -19,8 +20,8 @@ struct crc_pmull_ctx {
 	uint64x2_t rk7_rk8;
 };
 
-struct crc_pmull_ctx crc32_eth_pmull __rte_aligned(16);
-struct crc_pmull_ctx crc16_ccitt_pmull __rte_aligned(16);
+alignas(16) struct crc_pmull_ctx crc32_eth_pmull;
+alignas(16) struct crc_pmull_ctx crc16_ccitt_pmull;
 
 /**
  * @brief Performs one folding round
@@ -96,10 +97,10 @@ struct crc_pmull_ctx {
 crcr32_reduce_64_to_32(uint64x2_t data64,
 	uint64x2_t precomp)
 {
-	static uint32_t mask1[4] __rte_aligned(16) = {
+	static alignas(16) uint32_t mask1[4] = {
 		0xffffffff, 0xffffffff, 0x00000000, 0x00000000
 	};
-	static uint32_t mask2[4] __rte_aligned(16) = {
+	static alignas(16) uint32_t mask2[4] = {
 		0x00000000, 0xffffffff, 0xffffffff, 0xffffffff
 	};
 	uint64x2_t tmp0, tmp1, tmp2;
@@ -148,7 +149,7 @@ struct crc_pmull_ctx {
 
 		if (unlikely(data_len < 16)) {
 			/* 0 to 15 bytes */
-			uint8_t buffer[16] __rte_aligned(16);
+			alignas(16) uint8_t buffer[16];
 
 			memset(buffer, 0, sizeof(buffer));
 			memcpy(buffer, data, data_len);
diff --git a/lib/net/net_crc_sse.c b/lib/net/net_crc_sse.c
index dd75845..d673ae3 100644
--- a/lib/net/net_crc_sse.c
+++ b/lib/net/net_crc_sse.c
@@ -2,6 +2,7 @@
  * Copyright(c) 2017-2020 Intel Corporation
  */
 
+#include <stdalign.h>
 #include <string.h>
 
 #include <rte_common.h>
@@ -18,8 +19,8 @@ struct crc_pclmulqdq_ctx {
 	__m128i rk7_rk8;
 };
 
-static struct crc_pclmulqdq_ctx crc32_eth_pclmulqdq __rte_aligned(16);
-static struct crc_pclmulqdq_ctx crc16_ccitt_pclmulqdq __rte_aligned(16);
+static alignas(16) struct crc_pclmulqdq_ctx crc32_eth_pclmulqdq;
+static alignas(16) struct crc_pclmulqdq_ctx crc16_ccitt_pclmulqdq;
 /**
  * @brief Performs one folding round
  *
@@ -96,11 +97,11 @@ struct crc_pclmulqdq_ctx {
 static __rte_always_inline uint32_t
 crcr32_reduce_64_to_32(__m128i data64, __m128i precomp)
 {
-	static const uint32_t mask1[4] __rte_aligned(16) = {
+	static const alignas(16) uint32_t mask1[4] = {
 		0xffffffff, 0xffffffff, 0x00000000, 0x00000000
 	};
 
-	static const uint32_t mask2[4] __rte_aligned(16) = {
+	static const alignas(16) uint32_t mask2[4] = {
 		0x00000000, 0xffffffff, 0xffffffff, 0xffffffff
 	};
 	__m128i tmp0, tmp1, tmp2;
@@ -118,7 +119,7 @@ struct crc_pclmulqdq_ctx {
 	return _mm_extract_epi32(tmp2, 2);
 }
 
-static const uint8_t crc_xmm_shift_tab[48] __rte_aligned(16) = {
+static const alignas(16) uint8_t crc_xmm_shift_tab[48] = {
 	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
 	0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff,
 	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
@@ -175,7 +176,7 @@ struct crc_pclmulqdq_ctx {
 
 		if (unlikely(data_len < 16)) {
 			/* 0 to 15 bytes */
-			uint8_t buffer[16] __rte_aligned(16);
+			alignas(16) uint8_t buffer[16];
 
 			memset(buffer, 0, sizeof(buffer));
 			memcpy(buffer, data, data_len);
@@ -212,11 +213,11 @@ struct crc_pclmulqdq_ctx {
 partial_bytes:
 	if (likely(n < data_len)) {
 
-		const uint32_t mask3[4] __rte_aligned(16) = {
+		const alignas(16) uint32_t mask3[4] = {
 			0x80808080, 0x80808080, 0x80808080, 0x80808080
 		};
 
-		const uint8_t shf_table[32] __rte_aligned(16) = {
+		const alignas(16) uint8_t shf_table[32] = {
 			0x00, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
 			0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
 			0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
diff --git a/lib/net/rte_arp.h b/lib/net/rte_arp.h
index c3cd0af..668cea1 100644
--- a/lib/net/rte_arp.h
+++ b/lib/net/rte_arp.h
@@ -21,17 +21,17 @@
 /**
  * ARP header IPv4 payload.
  */
-struct rte_arp_ipv4 {
+struct __rte_aligned(2) rte_arp_ipv4 {
 	struct rte_ether_addr arp_sha;  /**< sender hardware address */
 	rte_be32_t            arp_sip;  /**< sender IP address */
 	struct rte_ether_addr arp_tha;  /**< target hardware address */
 	rte_be32_t            arp_tip;  /**< target IP address */
-} __rte_packed __rte_aligned(2);
+} __rte_packed;
 
 /**
  * ARP header.
  */
-struct rte_arp_hdr {
+struct __rte_aligned(2) rte_arp_hdr {
 	rte_be16_t arp_hardware; /**< format of hardware address */
 #define RTE_ARP_HRD_ETHER     1  /**< ARP Ethernet address format */
 
@@ -47,7 +47,7 @@ struct rte_arp_hdr {
 #define	RTE_ARP_OP_INVREPLY   9  /**< response identifying peer */
 
 	struct rte_arp_ipv4 arp_data;
-} __rte_packed __rte_aligned(2);
+} __rte_packed;
 
 /**
  * Make a RARP packet based on MAC addr.
diff --git a/lib/net/rte_ether.h b/lib/net/rte_ether.h
index ce073ea..f4c5af4 100644
--- a/lib/net/rte_ether.h
+++ b/lib/net/rte_ether.h
@@ -57,9 +57,9 @@
  * administrator and does not contain OUIs.
  * See http://standards.ieee.org/regauth/groupmac/tutorial.html
  */
-struct rte_ether_addr {
+struct __rte_aligned(2) rte_ether_addr {
 	uint8_t addr_bytes[RTE_ETHER_ADDR_LEN]; /**< Addr bytes in tx order */
-} __rte_aligned(2);
+};
 
 #define RTE_ETHER_LOCAL_ADMIN_ADDR 0x02 /**< Locally assigned Eth. address. */
 #define RTE_ETHER_GROUP_ADDR  0x01 /**< Multicast or broadcast Eth. address. */
@@ -276,11 +276,11 @@ static inline int rte_is_valid_assigned_ether_addr(const struct rte_ether_addr *
  * Ethernet header: Contains the destination address, source address
  * and frame type.
  */
-struct rte_ether_hdr {
+struct __rte_aligned(2) rte_ether_hdr {
 	struct rte_ether_addr dst_addr; /**< Destination address. */
 	struct rte_ether_addr src_addr; /**< Source address. */
 	rte_be16_t ether_type; /**< Frame type. */
-} __rte_aligned(2);
+};
 
 /**
  * Ethernet VLAN Header.
-- 
1.8.3.1