Re: [PATCH v3 4/8] perf amd ibs: Suppress bogus TlbRefillLat and DCPhysAd on Zen4+

[sashiko-bot@kernel.org]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] The patch uses a value-based heuristic to suppress the output of IbsDCPhysAd if it is zero, which incorrectly hides valid memory accesses to physical address 0x0.
--

commit a0f442c06429e0cbb710a06da2ee24b2a327f365
Author: Ravi Bangoria <ravi.bangoria@amd.com>

perf amd ibs: Suppress bogus TlbRefillLat and DCPhysAd on Zen4+

This commit updates the decoding of IBS MSRs on Zen4+ to add validity
checks for TlbRefillLat and DCPhysAd. It also attempts to avoid printing
zeroed physical addresses that the kernel sanitizes for unprivileged users.

> diff --git a/tools/perf/util/amd-sample-raw.c b/tools/perf/util/amd-sample-raw.c
> index b084dee76b1a7..385308c55f347 100644
> --- a/tools/perf/util/amd-sample-raw.c
> +++ b/tools/perf/util/amd-sample-raw.c

[ ... ]

> @@ -253,8 +260,12 @@ static void amd_dump_ibs_op(struct perf_sample *sample)
>  	pr_ibs_op_data3(*op_data3);
>  	if (op_data3->dc_lin_addr_valid)
>  		printf("IbsDCLinAd:\t%016llx\n", *(rip + 4));
> -	if (op_data3->dc_phy_addr_valid)
> +
> +	/* Use !zen4_ibs_extensions as a proxy for Zen3 and earlier */
> +	if (op_data3->dc_phy_addr_valid && *(rip + 5) &&
> +	    (!zen4_ibs_extensions || op_data3->dc_lin_addr_valid)) {
>  		printf("IbsDCPhysAd:\t%016llx\n", *(rip + 5));
> +	}

Does checking *(rip + 5) here suppress valid memory accesses to physical
address 0x0?

While this successfully hides kernel-zeroed addresses for unprivileged users,
it seems like it cannot distinguish between software-zeroed values and actual
0x0 addresses. Could this silently discard valid diagnostic data during
privileged profiling sessions if an actual hardware access to physical page 0
occurs?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260508060004.2575-1-ravi.bangoria@amd.com?part=4