[PATCH] ring: compilation fix with GCC-12

[Honnappa Nagarahalli]

<snip>

> 
> GCC 12 raises the following warning:
> 
> In function '__rte_ring_dequeue_elems_128',
>     inlined from '__rte_ring_dequeue_elems' at
> 		../lib/ring/rte_ring_elem_pvt.h:262:3,
>     inlined from '__rte_ring_do_hts_dequeue_elem' at
> 		../lib/ring/rte_ring_hts_elem_pvt.h:237:3,
>     inlined from 'rte_ring_mc_hts_dequeue_bulk_elem' at
> 		../lib/ring/rte_ring_hts.h:83:9,
>     inlined from 'rte_ring_dequeue_bulk_elem' at
> 		../lib/ring/rte_ring_elem.h:391:10,
>     inlined from 'rte_ring_dequeue_elem' at
> 		../lib/ring/rte_ring_elem.h:476:9,
>     inlined from 'rte_ring_dequeue' at
> 		../lib/ring/rte_ring.h:463:9,
>     inlined from 'rxa_intr_ring_dequeue' at
> 		../lib/eventdev/rte_event_eth_rx_adapter.c:1196:10:
> ../lib/ring/rte_ring_elem_pvt.h:234:25: error: 'memcpy' writing
> 	32 bytes into a region of size 8 overflows the destination
> 	[-Werror=stringop-overflow=]
>   234 |    memcpy((void *)(obj + i), (void *)(ring + idx), 32);
>       |    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> 
> Replacing memcpy with rte_memcpy fixes the GCC-12 compilation issue.
Any reason why this replacement fixes the problem?
Do you have any performance numbers with this change?

> Also it would be better to change to rte_memcpy as the function is called in
> fastpath.
On Arm platforms, memcpy in the later versions has the best performance.

> 
> Bugzilla ID: 1062
> Fixes: 1fc73390bcf5 ("ring: refactor exported headers")
> Cc: stable at dpdk.org
> 
> Signed-off-by: Amit Prakash Shukla <amitprakashs at marvell.com>
> ---
>  lib/ring/rte_ring_elem_pvt.h | 18 ++++++++++--------
>  1 file changed, 10 insertions(+), 8 deletions(-)
> 
> diff --git a/lib/ring/rte_ring_elem_pvt.h b/lib/ring/rte_ring_elem_pvt.h index
> 83788c56e6..3d85b13333 100644
> --- a/lib/ring/rte_ring_elem_pvt.h
> +++ b/lib/ring/rte_ring_elem_pvt.h
> @@ -10,6 +10,8 @@
>  #ifndef _RTE_RING_ELEM_PVT_H_
>  #define _RTE_RING_ELEM_PVT_H_
> 
> +#include <rte_memcpy.h>
> +
>  static __rte_always_inline void
>  __rte_ring_enqueue_elems_32(struct rte_ring *r, const uint32_t size,
>  		uint32_t idx, const void *obj_table, uint32_t n) @@ -97,20
> +99,20 @@ __rte_ring_enqueue_elems_128(struct rte_ring *r, uint32_t
> prod_head,
>  	const rte_int128_t *obj = (const rte_int128_t *)obj_table;
>  	if (likely(idx + n <= size)) {
>  		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> -			memcpy((void *)(ring + idx),
> +			rte_memcpy((void *)(ring + idx),
>  				(const void *)(obj + i), 32);
>  		switch (n & 0x1) {
>  		case 1:
> -			memcpy((void *)(ring + idx),
> +			rte_memcpy((void *)(ring + idx),
>  				(const void *)(obj + i), 16);
>  		}
>  	} else {
>  		for (i = 0; idx < size; i++, idx++)
> -			memcpy((void *)(ring + idx),
> +			rte_memcpy((void *)(ring + idx),
>  				(const void *)(obj + i), 16);
>  		/* Start at the beginning */
>  		for (idx = 0; i < n; i++, idx++)
> -			memcpy((void *)(ring + idx),
> +			rte_memcpy((void *)(ring + idx),
>  				(const void *)(obj + i), 16);
>  	}
>  }
> @@ -231,17 +233,17 @@ __rte_ring_dequeue_elems_128(struct rte_ring *r,
> uint32_t prod_head,
>  	rte_int128_t *obj = (rte_int128_t *)obj_table;
>  	if (likely(idx + n <= size)) {
>  		for (i = 0; i < (n & ~0x1); i += 2, idx += 2)
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 32);
> +			rte_memcpy((void *)(obj + i), (void *)(ring + idx), 32);
>  		switch (n & 0x1) {
>  		case 1:
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> +			rte_memcpy((void *)(obj + i), (void *)(ring + idx), 16);
>  		}
>  	} else {
>  		for (i = 0; idx < size; i++, idx++)
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> +			rte_memcpy((void *)(obj + i), (void *)(ring + idx), 16);
>  		/* Start at the beginning */
>  		for (idx = 0; i < n; i++, idx++)
> -			memcpy((void *)(obj + i), (void *)(ring + idx), 16);
> +			rte_memcpy((void *)(obj + i), (void *)(ring + idx), 16);
>  	}
>  }
> 
> --
> 2.25.1