RE: [EXTERNAL] [PATCH v6] graph: expose node context as pointers

[Kiran Kumar Kokkilagadda <kirankumark@marvell.com>]

> -----Original Message-----
> From: Robin Jarry <rjarry@redhat.com>
> Sent: Friday, July 5, 2024 8:23 PM
> To: dev@dpdk.org; Jerin Jacob <jerinj@marvell.com>; Kiran Kumar
> Kokkilagadda <kirankumark@marvell.com>; Nithin Kumar Dabilpuram
> <ndabilpuram@marvell.com>; Zhirun Yan <yanzhirun_163@163.com>
> Subject: [EXTERNAL] [PATCH v6] graph: expose node context as pointers
> 
> In some cases, the node context data is used to store two pointers because
> the data is larger than the reserved 16 bytes. Having to define intermediate
> structures just to be able to cast is tedious. And without intermediate
> structures, casting 
> In some cases, the node context data is used to store two pointers because
> the data is larger than the reserved 16 bytes. Having to define intermediate
> structures just to be able to cast is tedious. And without intermediate
> structures, casting to opaque pointers is hard without violating strict aliasing
> rules.
> 
> Add an unnamed union to allow storing opaque pointers in the node
> context. Unfortunately, aligning an unnamed union that contains an array
> produces inconsistent results between C and C++. To preserve ABI/API
> compatibility in both C and C++, move all fast-path area fields into an
> unnamed struct which is itself cache aligned. Use __rte_cache_aligned to
> preserve existing alignment on architectures where cache lines are 128 bytes.
> 
> Add a static assert to ensure that the fast path area does not grow beyond a
> 64 bytes cache line.
> 
> Signed-off-by: Robin Jarry <rjarry@redhat.com>
> ---

Acked-by: Kiran Kumar Kokkilagadda <kirankumark@marvell.com>

> 
> Notes:
>     v6:
> 
>     * Fix ABI breakage on arm64 (and all platforms that have
> RTE_CACHE_LINE_SIZE=128).
>     * This patch will cause CI failures without libabigail 2.5. See this commit
>       https://urldefense.proofpoint.com/v2/url?u=https-
> 3A__sourceware.org_git_-3Fp-3Dlibabigail.git-3Ba-3Dcommitdiff-3Bh-
> 3Df821c2be3fff2047ef8fc436f6f02301812d166f&d=DwIDAg&c=nKjWec2b6R0m
> OyPaz7xtfQ&r=owEKckYY4FTmil1Z6oBURwkTThyuRbLAY9LdfiaT6HA&m=p2InA
> hlxVf3SXbWbwMoGbsA2ylexBEm_WKDY6mf88Lgp6hbAD5UNuKGkFiO0F8vV&
> s=mtRUGLkylM_33OiTJTBoxFQNDQh6p7xIyNwmDu9GgTk&e=
>       for more details.
> 
>     v5:
> 
>     * Helper functions to hide casting proved to be harder than expected.
>       Naive casting may even be impossible without breaking strict aliasing
>       rules. The only other option would be to use explicit memcpy calls.
>     * Unnamed union tentative again. As suggested by Tyler (thank you!),
>       using an intermediate unnamed struct to carry the alignment produces
>       consistent ABI in C and C++.
>     * Also, Tyler (thank you!) suggested that the fast path area alignment
>       size may be incorrect for architectures where the cache line is not 64
>       bytes. There will be a 64 bytes hole in the structure at the end of
>       the unnamed struct before the zero length next nodes array. Use
>       __rte_cache_min_aligned to preserve existing alignment.
> 
>     v4:
> 
>     * Replaced the unnamed union with helper inline functions.
> 
>     v3:
> 
>     * Added __extension__ to the unnamed struct inside the union.
>     * Fixed C++ header checks.
>     * Replaced alignas() with an explicit static_assert.
> 
>  lib/graph/rte_graph_worker_common.h | 29 +++++++++++++++++++++--------
>  1 file changed, 21 insertions(+), 8 deletions(-)
> 
> diff --git a/lib/graph/rte_graph_worker_common.h
> b/lib/graph/rte_graph_worker_common.h
> index 36d864e2c14e..8d8956fdddda 100644
> --- a/lib/graph/rte_graph_worker_common.h
> +++ b/lib/graph/rte_graph_worker_common.h
> @@ -12,7 +12,9 @@
>   * process, enqueue and move streams of objects to the next nodes.
>   */
> 
> +#include <assert.h>
>  #include <stdalign.h>
> +#include <stddef.h>
> 
>  #include <rte_common.h>
>  #include <rte_cycles.h>
> @@ -111,14 +113,21 @@ struct __rte_cache_aligned rte_node {
>  		} dispatch;
>  	};
>  	/* Fast path area  */
> +	__extension__ struct __rte_cache_aligned {
>  #define RTE_NODE_CTX_SZ 16
> -	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. */
> -	uint64_t total_cycles;	/**< Cycles spent in this node. */
> -	uint64_t total_calls;	/**< Calls done to this node. */
> -	uint64_t total_objs;	/**< Objects processed by this node. */
> +		union {
> +			uint8_t ctx[RTE_NODE_CTX_SZ];
> +			__extension__ struct {
> +				void *ctx_ptr;
> +				void *ctx_ptr2;
> +			};
> +		}; /**< 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.
> */
> +		uint64_t total_cycles;	/**< Cycles spent in this node. */
> +		uint64_t total_calls;	/**< Calls done to this node. */
> +		uint64_t total_objs;	/**< Objects processed by this node.
> */
>  		union {
>  			void **objs;	   /**< Array of object pointers. */
>  			uint64_t objs_u64;
> @@ -127,9 +136,13 @@ struct __rte_cache_aligned rte_node {
>  			rte_node_process_t process; /**< Process function.
> */
>  			uint64_t process_u64;
>  		};
> -	alignas(RTE_CACHE_LINE_MIN_SIZE) struct rte_node *nodes[]; /**<
> Next nodes. */
> +		alignas(RTE_CACHE_LINE_MIN_SIZE) struct rte_node
> *nodes[]; /**< Next nodes. */
> +	};
>  };
> 
> +static_assert(offsetof(struct rte_node, nodes) - offsetof(struct rte_node, ctx)
> +	== RTE_CACHE_LINE_MIN_SIZE, "rte_node fast path area must fit in
> 64
> +bytes");
> +
>  /**
>   * @internal
>   *
> --
> 2.45.2