Linux Perf Users
 help / color / mirror / Atom feed
From: sashiko-bot@kernel.org
To: "Dapeng Mi" <dapeng1.mi@linux.intel.com>
Cc: linux-perf-users@vger.kernel.org
Subject: Re: [RESEND Patch v10 06/23] x86/fpu/xstate: Add xsaves_nmi() helper
Date: Mon, 24 Aug 2026 08:54:07 +0000	[thread overview]
Message-ID: <20260824085408.595F21F000E9@smtp.kernel.org> (raw)
In-Reply-To: <20260824082731.1013973-7-dapeng1.mi@linux.intel.com>

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Critical] xsaves_nmi() uses the XSAVES instruction which employs hardware 'modified optimization', causing catastrophic data corruption for the interrupted task.
--

--- Patch [6]: [RESEND Patch v10 06/23] x86/fpu/xstate: Add xsaves_nmi() helper ---
commit 2691ef22b25df7392d6766bb1de8a6d97a6ee37c
Author: Kan Liang <kan.liang@linux.intel.com>

    x86/fpu/xstate: Add xsaves_nmi() helper

This commit introduces the xsaves_nmi() helper function to allow the perf
subsystem to save supported xsave states within an NMI handler. It is intended
to snapshot SIMD and APX eGPR registers at the exact moment an NMI occurs.

> diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
> index a7b6524a9dea2..d39c01546dee7 100644
> --- a/arch/x86/kernel/fpu/xstate.c
> +++ b/arch/x86/kernel/fpu/xstate.c
[ ... ]
> @@ -1474,6 +1474,29 @@ void xrstors(struct xregs_state *xstate, u64 mask)
[ ... ]
> +void xsaves_nmi(struct xregs_state *xstate, u64 mask)
> +{
> +	int err;
> +
> +	if (!in_nmi())
> +		return;
> +
> +	XSTATE_OP(XSAVES, xstate, (u32)mask, (u32)(mask >> 32), err);

[Severity: Critical]
Does executing the xsaves instruction in this context corrupt the FPU state of
the interrupted task?

According to the Intel SDM, the xsaves instruction employs a modified
optimization that unconditionally resets the CPU internal state-component
tracking, marking all components as unmodified.

If a task is interrupted by an NMI (such as a perf PMI) and this instruction
executes, won't the subsequent context switch out of the task also see the
state as unmodified? It seems the normal context-switch xsaves would silently
skip saving the state to the task FPU buffer, losing any SIMD modifications
made prior to the NMI.

Additionally, since xsaves skips writing components it considers unmodified,
could this leak stale SIMD state from previously interrupted tasks into the
current perf sample buffer?

> +	WARN_ON_ONCE(err);
> +}

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260824082731.1013973-1-dapeng1.mi@linux.intel.com?part=6

  reply	other threads:[~2026-08-24  8:54 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-24  8:27 [RESEND Patch v10 00/23] Support SIMD/eGPRs/SSP registers sampling for perf Dapeng Mi
2026-08-24  8:27 ` [RESEND Patch v10 01/23] perf/x86: Move hybrid PMU initialization before x86_pmu_starting_cpu() Dapeng Mi
2026-08-24  8:44   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 02/23] perf/x86/intel: Enable large PEBS sampling for XMMs Dapeng Mi
2026-08-24  8:52   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 03/23] perf/x86/intel: Convert x86_perf_regs to per-cpu variables Dapeng Mi
2026-08-24  8:46   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 04/23] perf: Eliminate duplicate arch-specific function definitions Dapeng Mi
2026-08-24  8:44   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 05/23] perf/x86: Use x86_perf_regs in NMI handlers Dapeng Mi
2026-08-24  8:54   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 06/23] x86/fpu/xstate: Add xsaves_nmi() helper Dapeng Mi
2026-08-24  8:54   ` sashiko-bot [this message]
2026-08-25  1:03     ` Mi, Dapeng
2026-08-24  8:27 ` [RESEND Patch v10 07/23] x86/fpu: Add update_fpu_state_and_flag() helper Dapeng Mi
2026-08-24  8:47   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 08/23] perf: Move and enhance has_extended_regs() for arch-specific use Dapeng Mi
2026-08-24  8:47   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 09/23] perf/x86/intel: Centralize PERF_PMU_CAP_EXTENDED_REGS updates Dapeng Mi
2026-08-24  8:46   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 10/23] perf/x86: Enable XMM register sampling for non-PEBS events Dapeng Mi
2026-08-24  8:53   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 11/23] perf/x86: Enable XMM register sampling for REGS_USER case Dapeng Mi
2026-08-24 10:16   ` sashiko-bot
2026-08-25  1:13     ` Mi, Dapeng
2026-08-24  8:27 ` [RESEND Patch v10 12/23] perf: Add sampling support for SIMD registers Dapeng Mi
2026-08-24  8:54   ` sashiko-bot
2026-08-25  1:19     ` Mi, Dapeng
2026-08-24  8:27 ` [RESEND Patch v10 13/23] perf/x86: Support XMM sampling using sample_simd_vec_reg_* fields Dapeng Mi
2026-08-24  9:12   ` sashiko-bot
2026-08-25  1:28     ` Mi, Dapeng
2026-08-24  8:27 ` [RESEND Patch v10 14/23] perf/x86: Support YMM " Dapeng Mi
2026-08-24  8:55   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 15/23] perf/x86: Support ZMM " Dapeng Mi
2026-08-24  8:58   ` sashiko-bot
2026-08-25  1:30     ` Mi, Dapeng
2026-08-24  8:27 ` [RESEND Patch v10 16/23] perf/x86: Support OPMASK sampling using sample_simd_pred_reg_* fields Dapeng Mi
2026-08-24  8:54   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 17/23] perf: Enhance perf_reg_validate() with simd_enabled argument Dapeng Mi
2026-08-24  8:56   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 18/23] perf/x86: Support eGPRs sampling using sample_regs_* fields Dapeng Mi
2026-08-24  8:59   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 19/23] perf/x86: Support SSP " Dapeng Mi
2026-08-24  9:39   ` sashiko-bot
2026-08-25  1:34     ` Mi, Dapeng
2026-08-24  8:27 ` [RESEND Patch v10 20/23] perf/x86/intel: Support arch-PEBS based SIMD/eGPRs sampling Dapeng Mi
2026-08-24  9:09   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 21/23] perf/x86/intel: Advertise PERF_PMU_CAP_SIMD_REGS capability Dapeng Mi
2026-08-24  9:25   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 22/23] perf/x86: Activate back-to-back NMI detection for arch-PEBS induced NMIs Dapeng Mi
2026-08-24  9:06   ` sashiko-bot
2026-08-24  8:27 ` [RESEND Patch v10 23/23] perf/x86/intel: Add sanity check for PEBS record/fragment size Dapeng Mi
2026-08-24  9:08   ` sashiko-bot
2026-08-25  1:39     ` Mi, Dapeng
2026-09-01  8:55 ` [RESEND Patch v10 00/23] Support SIMD/eGPRs/SSP registers sampling for perf Mi, Dapeng
2026-09-02 11:56   ` Peter Zijlstra
2026-09-02 12:13     ` Mi, Dapeng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260824085408.595F21F000E9@smtp.kernel.org \
    --to=sashiko-bot@kernel.org \
    --cc=dapeng1.mi@linux.intel.com \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=sashiko-reviews@lists.linux.dev \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox