[PATCH v7 38/39] graph: use C11 alignas

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

The current location used for __rte_aligned(a) for alignment of types
and variables is not compatible with MSVC. There is only a single
location accepted by both toolchains.

For variables standard C11 offers alignas(a) supported by conformant
compilers i.e. both MSVC and GCC.

For types the standard offers no alignment facility that compatibly
interoperates with C and C++ but may be achieved by relocating the
placement of __rte_aligned(a) to the aforementioned location accepted
by all currently supported toolchains.

To allow alignment for both compilers do the following:

* 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>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
---
 lib/graph/graph_private.h           |  4 ++--
 lib/graph/graph_stats.c             |  4 ++--
 lib/graph/rte_graph.h               |  4 ++--
 lib/graph/rte_graph_worker_common.h | 17 ++++++++++-------
 4 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/lib/graph/graph_private.h b/lib/graph/graph_private.h
index 04538ea..d557d55 100644
--- a/lib/graph/graph_private.h
+++ b/lib/graph/graph_private.h
@@ -70,11 +70,11 @@ struct node {
  * Structure that holds the graph scheduling workqueue node stream.
  * Used for mcore dispatch model.
  */
-struct graph_mcore_dispatch_wq_node {
+struct __rte_cache_aligned graph_mcore_dispatch_wq_node {
 	rte_graph_off_t node_off;
 	uint16_t nb_objs;
 	void *objs[RTE_GRAPH_BURST_SIZE];
-} __rte_cache_aligned;
+};
 
 /**
  * @internal
diff --git a/lib/graph/graph_stats.c b/lib/graph/graph_stats.c
index cc32245..2fb808b 100644
--- a/lib/graph/graph_stats.c
+++ b/lib/graph/graph_stats.c
@@ -28,7 +28,7 @@ struct cluster_node {
 	struct rte_node *nodes[];
 };
 
-struct rte_graph_cluster_stats {
+struct __rte_cache_aligned rte_graph_cluster_stats {
 	/* Header */
 	rte_graph_cluster_stats_cb_t fn;
 	uint32_t cluster_node_size; /* Size of struct cluster_node */
@@ -38,7 +38,7 @@ struct rte_graph_cluster_stats {
 	size_t sz;
 
 	struct cluster_node clusters[];
-} __rte_cache_aligned;
+};
 
 #define boarder_model_dispatch()                                                              \
 	fprintf(f, "+-------------------------------+---------------+--------" \
diff --git a/lib/graph/rte_graph.h b/lib/graph/rte_graph.h
index 2d37d5e..ecfec20 100644
--- a/lib/graph/rte_graph.h
+++ b/lib/graph/rte_graph.h
@@ -200,7 +200,7 @@ struct rte_graph_cluster_stats_param {
  *
  * @see struct rte_graph_cluster_stats_param::fn
  */
-struct rte_graph_cluster_node_stats {
+struct __rte_cache_aligned rte_graph_cluster_node_stats {
 	uint64_t ts;	    /**< Current timestamp. */
 	uint64_t calls;	    /**< Current number of calls made. */
 	uint64_t objs;      /**< Current number of objs processed. */
@@ -225,7 +225,7 @@ struct rte_graph_cluster_node_stats {
 	rte_node_t id;	/**< Node identifier of stats. */
 	uint64_t hz;	/**< Cycles per seconds. */
 	char name[RTE_NODE_NAMESIZE];	/**< Name of the node. */
-} __rte_cache_aligned;
+};
 
 /**
  * Create Graph.
diff --git a/lib/graph/rte_graph_worker_common.h b/lib/graph/rte_graph_worker_common.h
index 4045a7a..36d864e 100644
--- a/lib/graph/rte_graph_worker_common.h
+++ b/lib/graph/rte_graph_worker_common.h
@@ -12,6 +12,8 @@
  * process, enqueue and move streams of objects to the next nodes.
  */
 
+#include <stdalign.h>
+
 #include <rte_common.h>
 #include <rte_cycles.h>
 #include <rte_prefetch.h>
@@ -43,7 +45,7 @@
  *
  * Data structure to hold graph data.
  */
-struct rte_graph {
+struct __rte_cache_aligned rte_graph {
 	/* Fast path area. */
 	uint32_t tail;		     /**< Tail of circular buffer. */
 	uint32_t head;		     /**< Head of circular buffer. */
@@ -57,7 +59,8 @@ struct rte_graph {
 	union {
 		/* Fast schedule area for mcore dispatch model */
 		struct {
-			struct rte_graph_rq_head *rq __rte_cache_aligned; /* The run-queue */
+			alignas(RTE_CACHE_LINE_SIZE) struct rte_graph_rq_head *rq;
+				/* The run-queue */
 			struct rte_graph_rq_head rq_head; /* The head for run-queue list */
 
 			unsigned int lcore_id;  /**< The graph running Lcore. */
@@ -77,14 +80,14 @@ struct rte_graph {
 	uint64_t nb_pkt_to_capture;
 	char pcap_filename[RTE_GRAPH_PCAP_FILE_SZ];  /**< Pcap filename. */
 	uint64_t fence;			/**< Fence. */
-} __rte_cache_aligned;
+};
 
 /**
  * @internal
  *
  * Data structure to hold node data.
  */
-struct rte_node {
+struct __rte_cache_aligned rte_node {
 	/* Slow path area  */
 	uint64_t fence;		/**< Fence. */
 	rte_graph_off_t next;	/**< Index to next node. */
@@ -109,7 +112,7 @@ struct rte_node {
 	};
 	/* Fast path area  */
 #define RTE_NODE_CTX_SZ 16
-	uint8_t ctx[RTE_NODE_CTX_SZ] __rte_cache_aligned; /**< Node Context. */
+	alignas(RTE_CACHE_LINE_SIZE) uint8_t ctx[RTE_NODE_CTX_SZ]; /**< Node Context. */
 	uint16_t size;		/**< Total number of objects available. */
 	uint16_t idx;		/**< Number of objects used. */
 	rte_graph_off_t off;	/**< Offset of node in the graph reel. */
@@ -124,8 +127,8 @@ struct rte_node {
 			rte_node_process_t process; /**< Process function. */
 			uint64_t process_u64;
 		};
-	struct rte_node *nodes[] __rte_cache_min_aligned; /**< Next nodes. */
-} __rte_cache_aligned;
+	alignas(RTE_CACHE_LINE_MIN_SIZE) struct rte_node *nodes[]; /**< Next nodes. */
+};
 
 /**
  * @internal
-- 
1.8.3.1