Re: [PATCH v2 8/8] perf record: Directly bail out for compat case

[Adrian Hunter]

On 2/06/21 1:30 pm, Leo Yan wrote:
> Since the 64-bit atomicity is not promised in 32-bit perf, directly
> report the error and bail out for this case.
> 
> Now only applies on x86_64 and Arm64 platforms.
> 
> Suggested-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>

Maybe we can do better for the compat case.

We can assume the upper 32-bits change very seldom,
and always increase. So for the 'read' case:

	u64 first, second, last;
	u64 mask = (u64)((u32)-1) << 32;

	do {
		first = READ_ONCE(pc->aux_head);
		rmb();
		second = READ_ONCE(pc->aux_head);
		rmb();
		last = READ_ONCE(pc->aux_head);
	} while ((first & mask) != (last & mask));
	return second;

For the write case, we can cause a fatal error only if the new
tail has non-zero upper 32-bits.  That gives up to 4GiB of data
before aborting:

	if (tail & mask)
		return -1;
	smp_mb();
	WRITE_ONCE(pc->aux_tail, tail);

> Signed-off-by: Leo Yan <leo.yan@xxxxxxxxxx>
> ---
>  tools/perf/builtin-record.c | 17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
> 
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index 3337b5f93336..f47e298281f7 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -74,6 +74,7 @@
>  #include <linux/zalloc.h>
>  #include <linux/bitmap.h>
>  #include <sys/time.h>
> +#include <sys/utsname.h>
>  
>  struct switch_output {
>  	bool		 enabled;
> @@ -848,6 +849,22 @@ static int record__mmap_evlist(struct record *rec,
>  				  opts->auxtrace_sample_mode;
>  	char msg[512];
>  
> +#ifndef __LP64__
> +	struct utsname uts;
> +	int ret;
> +
> +	ret = uname(&uts);
> +	if (ret < 0)
> +		return ret;
> +
> +	if (!strncmp(uts.machine, "x86_64", 6) || !strncmp(uts.machine, "aarch64", 7) ||
> +	    !strncmp(uts.machine, "arm64", 5)) {
> +		pr_err("Error, 32-bit perf cannot record from a 64-bit kernel.\n"
> +		       "Please use a 64-bit version of perf instead.\n");
> +		return -ENOTSUP;
> +	}
> +#endif
> +
>  	if (opts->affinity != PERF_AFFINITY_SYS)
>  		cpu__setup_cpunode_map();
>  
>