Re: [dpdk-dev] [PATCH] acl: fix build issue with some arm64 compiler

[Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>]

> Subject: [dpdk-dev] [PATCH] acl: fix build issue with some arm64 compiler
> 
> From: Jerin Jacob <jerinj@marvell.com>
> 
> Some compilers reporting the following error, though the existing code
> doesn't have any uninitialized variable case.
> Just to make compiler happy, initialize the int32x4_t variable one shot in C
> language.
> 
> ../lib/librte_acl/acl_run_neon.h: In function 'search_neon_4'
> ../lib/librte_acl/acl_run_neon.h:230:12: error: 'input' may be used
> uninitialized in this function [-Werror=maybe-uninitialized]
>   int32x4_t input;
> 
> Fixes: 34fa6c27c156 ("acl: add NEON optimization for ARMv8")
> Cc: stable@dpdk.org
> 
> Signed-off-by: Jerin Jacob <jerinj@marvell.com>
> ---
>  lib/librte_acl/acl_run_neon.h | 29 ++++++++++++-----------------
>  1 file changed, 12 insertions(+), 17 deletions(-)
> 
> diff --git a/lib/librte_acl/acl_run_neon.h b/lib/librte_acl/acl_run_neon.h
> index 01b9766d8..dc9e9efe9 100644
> --- a/lib/librte_acl/acl_run_neon.h
> +++ b/lib/librte_acl/acl_run_neon.h
> @@ -165,7 +165,6 @@ search_neon_8(const struct rte_acl_ctx *ctx, const
> uint8_t **data,
>  	uint64_t index_array[8];
>  	struct completion cmplt[8];
>  	struct parms parms[8];
> -	int32x4_t input0, input1;
> 
>  	acl_set_flow(&flows, cmplt, RTE_DIM(cmplt), data, results,
>  		     total_packets, categories, ctx->trans_table); @@ -181,17
> +180,14 @@ search_neon_8(const struct rte_acl_ctx *ctx, const uint8_t
> **data,
> 
>  	while (flows.started > 0) {
>  		/* Gather 4 bytes of input data for each stream. */
> -		input0 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 0),
> input0, 0);
> -		input1 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 4),
> input1, 0);
> -
> -		input0 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 1),
> input0, 1);
> -		input1 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 5),
> input1, 1);
> -
> -		input0 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 2),
> input0, 2);
> -		input1 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 6),
> input1, 2);
> -
> -		input0 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 3),
> input0, 3);
> -		input1 = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 7),
> input1, 3);
> +		int32x4_t input0 = {GET_NEXT_4BYTES(parms, 0),
> +				    GET_NEXT_4BYTES(parms, 1),
> +				    GET_NEXT_4BYTES(parms, 2),
> +				    GET_NEXT_4BYTES(parms, 3)};
> +		int32x4_t input1 = {GET_NEXT_4BYTES(parms, 4),
> +				    GET_NEXT_4BYTES(parms, 5),
> +				    GET_NEXT_4BYTES(parms, 6),
> +				    GET_NEXT_4BYTES(parms, 7)};
> 
This mixes the use of NEON intrinsics with GCC vector extensions. ACLE (Arm C Language Extensions) specifically recommends not to mix the two methods in section 12.2.6. IMO, Aaron's suggestion of using a temp vector should be good.

>  		/* Process the 4 bytes of input on each stream. */
> 
> @@ -227,7 +223,6 @@ search_neon_4(const struct rte_acl_ctx *ctx, const
> uint8_t **data,
>  	uint64_t index_array[4];
>  	struct completion cmplt[4];
>  	struct parms parms[4];
> -	int32x4_t input;
> 
>  	acl_set_flow(&flows, cmplt, RTE_DIM(cmplt), data, results,
>  		     total_packets, categories, ctx->trans_table); @@ -242,10
> +237,10 @@ search_neon_4(const struct rte_acl_ctx *ctx, const uint8_t
> **data,
> 
>  	while (flows.started > 0) {
>  		/* Gather 4 bytes of input data for each stream. */
> -		input = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 0), input,
> 0);
> -		input = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 1), input,
> 1);
> -		input = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 2), input,
> 2);
> -		input = vsetq_lane_s32(GET_NEXT_4BYTES(parms, 3), input,
> 3);
> +		int32x4_t input = {GET_NEXT_4BYTES(parms, 0),
> +				   GET_NEXT_4BYTES(parms, 1),
> +				   GET_NEXT_4BYTES(parms, 2),
> +				   GET_NEXT_4BYTES(parms, 3)};
> 
>  		/* Process the 4 bytes of input on each stream. */
>  		input = transition4(input, flows.trans, index_array);
> --
> 2.21.0