public inbox for linux-perf-users@vger.kernel.org
 help / color / mirror / Atom feed
From: "Mi, Dapeng" <dapeng1.mi@linux.intel.com>
To: Ravi Bangoria <ravi.bangoria@amd.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	James Clark <james.clark@linaro.org>,
	x86@kernel.org, linux-perf-users@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	Manali Shukla <manali.shukla@amd.com>,
	Santosh Shukla <santosh.shukla@amd.com>,
	Ananth Narayan <ananth.narayan@amd.com>,
	Sandipan Das <sandipan.das@amd.com>
Subject: Re: [PATCH 07/11] perf/amd/ibs: Support IBS_{FETCH|OP}_CTL2[Dis] to eliminate RMW race
Date: Mon, 19 Jan 2026 15:48:45 +0800	[thread overview]
Message-ID: <82e836e7-c0cc-4226-91cf-4b2275d99e73@linux.intel.com> (raw)
In-Reply-To: <20260116033450.965-8-ravi.bangoria@amd.com>


On 1/16/2026 11:34 AM, Ravi Bangoria wrote:
> The existing IBS_{FETCH|OP}_CTL MSRs combine control and status bits
> which leads to RMW race between HW and SW:
>
>   HW                               SW
>   ------------------------         ------------------------------
>                                    config = rdmsr(IBS_OP_CTL);
>                                    config &= ~EN;
>   Set IBS_OP_CTL[Val] to 1
>   trigger NMI
>                                    wrmsr(IBS_OP_CTL, config);
>                                    // Val is accidentally cleared
>
> Future hardware adds a control-only MSR, IBS_{FETCH|OP}_CTL2, which
> provides a second-level "disable" bit (Dis). IBS is now:
>
>   Enabled:  IBS_{FETCH|OP}_CTL[En] = 1 && IBS_{FETCH|OP}_CTL2[Dis] = 0
>   Disabled: IBS_{FETCH|OP}_CTL[En] = 0 || IBS_{FETCH|OP}_CTL2[Dis] = 1
>
> The separate "Dis" bit lets software disable IBS without touching any
> status fields, eliminating the hardware/software race.
>
> Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
> ---
>  arch/x86/events/amd/ibs.c | 45 +++++++++++++++++++++++++++++++++++++++
>  1 file changed, 45 insertions(+)
>
> diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
> index 02e7bffe1208..d8216048be84 100644
> --- a/arch/x86/events/amd/ibs.c
> +++ b/arch/x86/events/amd/ibs.c
> @@ -86,9 +86,11 @@ struct cpu_perf_ibs {
>  struct perf_ibs {
>  	struct pmu			pmu;
>  	unsigned int			msr;
> +	unsigned int			msr2;
>  	u64				config_mask;
>  	u64				cnt_mask;
>  	u64				enable_mask;
> +	u64				disable_mask;
>  	u64				valid_mask;
>  	u16				min_period;
>  	u64				max_period;
> @@ -292,6 +294,8 @@ static int perf_ibs_init(struct perf_event *event)
>  		return -ENOENT;
>  
>  	config = event->attr.config;
> +	hwc->extra_reg.config = 0;
> +	hwc->extra_reg.reg = 0;
>  
>  	if (event->pmu != &perf_ibs->pmu)
>  		return -ENOENT;
> @@ -316,6 +320,11 @@ static int perf_ibs_init(struct perf_event *event)
>  	if (ret)
>  		return ret;
>  
> +	if (ibs_caps & IBS_CAPS_DIS) {
> +		hwc->extra_reg.config &= ~perf_ibs->disable_mask;
> +		hwc->extra_reg.reg = perf_ibs->msr2;
> +	}
> +
>  	if (hwc->sample_period) {
>  		if (config & perf_ibs->cnt_mask)
>  			/* raw max_cnt may not be set */
> @@ -445,6 +454,9 @@ static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs,
>  		wrmsrq(hwc->config_base, tmp & ~perf_ibs->enable_mask);
>  
>  	wrmsrq(hwc->config_base, tmp | perf_ibs->enable_mask);
> +
> +	if (hwc->extra_reg.reg)
> +		wrmsrq(hwc->extra_reg.reg, hwc->extra_reg.config);
>  }
>  
>  /*
> @@ -457,6 +469,11 @@ static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs,
>  static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
>  					  struct hw_perf_event *hwc, u64 config)
>  {
> +	if (ibs_caps & IBS_CAPS_DIS) {
> +		wrmsrq(hwc->extra_reg.reg, perf_ibs->disable_mask);
> +		return;
> +	}
> +
>  	config &= ~perf_ibs->cnt_mask;
>  	if (boot_cpu_data.x86 == 0x10)
>  		wrmsrq(hwc->config_base, config);
> @@ -809,6 +826,7 @@ static struct perf_ibs perf_ibs_fetch = {
>  		.check_period	= perf_ibs_check_period,
>  	},
>  	.msr			= MSR_AMD64_IBSFETCHCTL,
> +	.msr2			= MSR_AMD64_IBSFETCHCTL2,
>  	.config_mask		= IBS_FETCH_MAX_CNT | IBS_FETCH_RAND_EN,
>  	.cnt_mask		= IBS_FETCH_MAX_CNT,
>  	.enable_mask		= IBS_FETCH_ENABLE,
> @@ -834,6 +852,7 @@ static struct perf_ibs perf_ibs_op = {
>  		.check_period	= perf_ibs_check_period,
>  	},
>  	.msr			= MSR_AMD64_IBSOPCTL,
> +	.msr2			= MSR_AMD64_IBSOPCTL2,
>  	.config_mask		= IBS_OP_MAX_CNT,
>  	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
>  				  IBS_OP_CUR_CNT_RAND,
> @@ -1389,6 +1408,9 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
>  
>  out:
>  	if (!throttle) {
> +		if (ibs_caps & IBS_CAPS_DIS)
> +			wrmsrq(hwc->extra_reg.reg, perf_ibs->disable_mask);
> +
>  		if (perf_ibs == &perf_ibs_op) {
>  			if (ibs_caps & IBS_CAPS_OPCNTEXT) {
>  				new_config = period & IBS_OP_MAX_CNT_EXT_MASK;
> @@ -1460,6 +1482,9 @@ static __init int perf_ibs_fetch_init(void)
>  	if (ibs_caps & IBS_CAPS_ZEN4)
>  		perf_ibs_fetch.config_mask |= IBS_FETCH_L3MISSONLY;
>  
> +	if (ibs_caps & IBS_CAPS_DIS)
> +		perf_ibs_fetch.disable_mask = IBS_FETCH_2_DIS;
> +
>  	perf_ibs_fetch.pmu.attr_groups = fetch_attr_groups;
>  	perf_ibs_fetch.pmu.attr_update = fetch_attr_update;
>  
> @@ -1481,6 +1506,9 @@ static __init int perf_ibs_op_init(void)
>  	if (ibs_caps & IBS_CAPS_ZEN4)
>  		perf_ibs_op.config_mask |= IBS_OP_L3MISSONLY;
>  
> +	if (ibs_caps & IBS_CAPS_DIS)
> +		perf_ibs_op.disable_mask = IBS_OP_2_DIS;
> +
>  	perf_ibs_op.pmu.attr_groups = op_attr_groups;
>  	perf_ibs_op.pmu.attr_update = op_attr_update;
>  
> @@ -1727,6 +1755,23 @@ static void clear_APIC_ibs(void)
>  static int x86_pmu_amd_ibs_starting_cpu(unsigned int cpu)
>  {
>  	setup_APIC_ibs();
> +
> +	if (ibs_caps & IBS_CAPS_DIS) {
> +		/*
> +		 * IBS enable sequence:
> +		 *   CTL[En] = 1;
> +		 *   CTL2[Dis] = 0;
> +		 *
> +		 * IBS disable sequence:
> +		 *   CTL2[Dis] = 1;
> +		 *
> +		 * Set CTL2[Dis] when CPU comes up. This is needed to make
> +		 * enable sequence effective.
> +		 */
> +		wrmsrq(MSR_AMD64_IBSFETCHCTL2, 1);
> +		wrmsrq(MSR_AMD64_IBSOPCTL2, 1);

What does the BIT 0 of these 2 MSRs mean? Disable? Better define a macro
instead of using the magic number "1". 


> +	}
> +
>  	return 0;
>  }
>  

  reply	other threads:[~2026-01-19  7:48 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-01-16  3:34 [PATCH 00/11] perf/amd/ibs: Fixes + future enhancements Ravi Bangoria
2026-01-16  3:34 ` [PATCH 01/11] perf/amd/ibs: Throttle interrupts with filtered ldlat samples Ravi Bangoria
2026-01-19  7:31   ` Mi, Dapeng
2026-01-19 12:56     ` Ravi Bangoria
2026-01-16  3:34 ` [PATCH 02/11] perf/amd/ibs: Limit ldlat->l3missonly dependency to Zen5 Ravi Bangoria
2026-01-16  3:34 ` [PATCH 03/11] perf/amd/ibs: Preserve PhyAddrVal bit when clearing PhyAddr MSR Ravi Bangoria
2026-01-16  3:34 ` [PATCH 04/11] perf/amd/ibs: Avoid race between event add and NMI Ravi Bangoria
2026-01-16  3:34 ` [PATCH 05/11] perf/amd/ibs: Define macro for ldlat mask Ravi Bangoria
2026-01-19  7:38   ` Mi, Dapeng
2026-01-16  3:34 ` [PATCH 06/11] perf/amd/ibs: Add new MSRs and CPUID bits definitions Ravi Bangoria
2026-01-19  7:39   ` Mi, Dapeng
2026-01-16  3:34 ` [PATCH 07/11] perf/amd/ibs: Support IBS_{FETCH|OP}_CTL2[Dis] to eliminate RMW race Ravi Bangoria
2026-01-19  7:48   ` Mi, Dapeng [this message]
2026-01-19 13:00     ` Ravi Bangoria
2026-01-16  3:34 ` [PATCH 08/11] perf/amd/ibs: Enable fetch latency filtering Ravi Bangoria
2026-01-16  3:34 ` [PATCH 09/11] perf/amd/ibs: Enable RIP bit63 hardware filtering Ravi Bangoria
2026-01-16  3:34 ` [PATCH 10/11] perf/amd/ibs: Enable streaming store filter Ravi Bangoria
2026-01-19  7:57   ` Mi, Dapeng
2026-01-19 13:02     ` Ravi Bangoria
2026-01-16  3:34 ` [PATCH 11/11] perf/amd/ibs: Advertise remote socket capability Ravi Bangoria

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=82e836e7-c0cc-4226-91cf-4b2275d99e73@linux.intel.com \
    --to=dapeng1.mi@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=ananth.narayan@amd.com \
    --cc=irogers@google.com \
    --cc=james.clark@linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=manali.shukla@amd.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=ravi.bangoria@amd.com \
    --cc=sandipan.das@amd.com \
    --cc=santosh.shukla@amd.com \
    --cc=x86@kernel.org \
    /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