RE: [PATCH] eal/x86: cache queried CPU flags

[Konstantin Ananyev <konstantin.ananyev@huawei.com>]

> Rather than re-querying the HW each time a CPU flag is requested, we can
> just save the return value in the flags array. This should speed up
> repeated querying of CPU flags, and provides a workaround for a reported
> issue where errors are seen with constant querying of the AVX-512 CPU
> flag from a non-AVX VM.
> 
> Bugzilla Id: 1501
> 
> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
> ---
>  lib/eal/x86/rte_cpuflags.c | 20 +++++++++++++++-----
>  1 file changed, 15 insertions(+), 5 deletions(-)
> 
> diff --git a/lib/eal/x86/rte_cpuflags.c b/lib/eal/x86/rte_cpuflags.c
> index 26163ab746..62e782fb4b 100644
> --- a/lib/eal/x86/rte_cpuflags.c
> +++ b/lib/eal/x86/rte_cpuflags.c
> @@ -8,6 +8,7 @@
>  #include <errno.h>
>  #include <stdint.h>
>  #include <string.h>
> +#include <stdbool.h>
> 
>  #include "rte_cpuid.h"
> 
> @@ -21,12 +22,14 @@ struct feature_entry {
>  	uint32_t bit;				/**< cpuid register bit */
>  #define CPU_FLAG_NAME_MAX_LEN 64
>  	char name[CPU_FLAG_NAME_MAX_LEN];       /**< String for printing */
> +	bool has_value;
> +	bool value;
>  };
> 
>  #define FEAT_DEF(name, leaf, subleaf, reg, bit) \
>  	[RTE_CPUFLAG_##name] = {leaf, subleaf, reg, bit, #name },
> 
> -const struct feature_entry rte_cpu_feature_table[] = {
> +struct feature_entry rte_cpu_feature_table[] = {
>  	FEAT_DEF(SSE3, 0x00000001, 0, RTE_REG_ECX,  0)
>  	FEAT_DEF(PCLMULQDQ, 0x00000001, 0, RTE_REG_ECX,  1)
>  	FEAT_DEF(DTES64, 0x00000001, 0, RTE_REG_ECX,  2)
> @@ -147,7 +150,7 @@ const struct feature_entry rte_cpu_feature_table[] = {
>  int
>  rte_cpu_get_flag_enabled(enum rte_cpu_flag_t feature)
>  {
> -	const struct feature_entry *feat;
> +	struct feature_entry *feat;
>  	cpuid_registers_t regs;
>  	unsigned int maxleaf;
> 
> @@ -156,6 +159,8 @@ rte_cpu_get_flag_enabled(enum rte_cpu_flag_t feature)
>  		return -ENOENT;
> 
>  	feat = &rte_cpu_feature_table[feature];
> +	if (feat->has_value)
> +		return feat->value;
> 
>  	if (!feat->leaf)
>  		/* This entry in the table wasn't filled out! */
> @@ -163,8 +168,10 @@ rte_cpu_get_flag_enabled(enum rte_cpu_flag_t feature)
> 
>  	maxleaf = __get_cpuid_max(feat->leaf & 0x80000000, NULL);
> 
> -	if (maxleaf < feat->leaf)
> -		return 0;
> +	if (maxleaf < feat->leaf) {
> +		feat->value = 0;
> +		goto out;
> +	}
> 
>  #ifdef RTE_TOOLCHAIN_MSVC
>  	__cpuidex(regs, feat->leaf, feat->subleaf);
> @@ -175,7 +182,10 @@ rte_cpu_get_flag_enabled(enum rte_cpu_flag_t feature)
>  #endif
> 
>  	/* check if the feature is enabled */
> -	return (regs[feat->reg] >> feat->bit) & 1;
> +	feat->value = (regs[feat->reg] >> feat->bit) & 1;
> +out:
> +	feat->has_value = true;
> +	return feat->value;

If that function can be called by 2 (or more) threads simultaneously,
then In theory  'feat->has_value = true;' can be reordered with 
' feat->value = (regs[feat->reg] >> feat->bit) & 1;'  (by cpu or complier)
and some thread(s) can get wrong feat->value.
The probability of such collision is really low, but still seems not impossible. 

>  }
> 
>  const char *
> --
> 2.43.0