lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240620073426.GR31592@noisy.programming.kicks-ass.net>
Date: Thu, 20 Jun 2024 09:34:26 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: kan.liang@...ux.intel.com
Cc: mingo@...nel.org, acme@...nel.org, namhyung@...nel.org,
	irogers@...gle.com, adrian.hunter@...el.com,
	alexander.shishkin@...ux.intel.com, linux-kernel@...r.kernel.org,
	ak@...ux.intel.com, eranian@...gle.com
Subject: Re: [RESEND PATCH 04/12] perf/x86/intel: Support new data source for
 Lunar Lake

On Tue, Jun 18, 2024 at 08:10:36AM -0700, kan.liang@...ux.intel.com wrote:

> @@ -77,7 +86,7 @@ union intel_x86_pebs_dse {
>  #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
>  
>  /* Version for Sandy Bridge and later */
> -static u64 pebs_data_source[] = {
> +static u64 pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = {
>  	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
>  	OP_LH | P(LVL, L1)  | LEVEL(L1) | P(SNOOP, NONE),  /* 0x01: L1 local */
>  	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
> @@ -173,6 +182,40 @@ void __init intel_pmu_pebs_data_source_cmt(void)
>  	__intel_pmu_pebs_data_source_cmt(pebs_data_source);
>  }
>  
> +/* Version for Lunar Lake p-core and later */
> +static u64 lnc_pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = {

Comment and naming are inconsistent, please lion-cove and lnc

> +	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),	/* 0x00: ukn L3 */
> +	OP_LH | P(LVL, L1)  | LEVEL(L1) | P(SNOOP, NONE),	/* 0x01: L1 hit */
> +	OP_LH | P(LVL, L1)  | LEVEL(L1) | P(SNOOP, NONE),	/* 0x02: L1 hit */
> +	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE),	/* 0x03: LFB/L1 Miss Handling Buffer hit */
> +	0,							/* 0x04: Reserved */
> +	OP_LH | P(LVL, L2)  | LEVEL(L2) | P(SNOOP, NONE),	/* 0x05: L2 Hit */
> +	OP_LH | LEVEL(L2_MHB) | P(SNOOP, NONE),			/* 0x06: L2 Miss Handling Buffer Hit */
> +	0,							/* 0x07: Reserved */
> +	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, NONE),	/* 0x08: L3 Hit */
> +	0,							/* 0x09: Reserved */
> +	0,							/* 0x0a: Reserved */
> +	0,							/* 0x0b: Reserved */
> +	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOPX, FWD),	/* 0x0c: L3 Hit Snoop Fwd */
> +	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, HITM),	/* 0x0d: L3 Hit Snoop HitM */
> +	0,							/* 0x0e: Reserved */
> +	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, HITM),	/* 0x0f: L3 Miss Snoop HitM */
> +	OP_LH | LEVEL(MSC) | P(SNOOP, NONE),			/* 0x10: Memory-side Cache Hit */
> +	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, NONE), /* 0x11: Local Memory Hit */
> +};
> +
> +void __init intel_pmu_pebs_data_source_lnl(void)
> +{
> +	u64 *data_source;
> +
> +	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source;
> +	memcpy(data_source, lnc_pebs_data_source, sizeof(lnc_pebs_data_source));
> +
> +	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
> +	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
> +	__intel_pmu_pebs_data_source_cmt(data_source);
> +}
> +
>  static u64 precise_store_data(u64 status)
>  {
>  	union intel_x86_pebs_dse dse;
> @@ -264,7 +307,7 @@ static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
>  
>  	WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big);
>  
> -	dse &= PERF_PEBS_DATA_SOURCE_MASK;
> +	dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
>  	val = hybrid_var(event->pmu, pebs_data_source)[dse];
>  
>  	pebs_set_tlb_lock(&val, tlb, lock);
> @@ -300,6 +343,45 @@ u64 mtl_latency_data_small(struct perf_event *event, u64 status)
>  					dse.mtl_fwd_blk);
>  }
>  
> +u64 lnl_latency_data(struct perf_event *event, u64 status)
> +{
> +	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
> +	union intel_x86_pebs_dse dse;
> +	union perf_mem_data_src src;
> +	u64 val;
> +
> +	if (pmu->pmu_type == hybrid_small)
> +		return mtl_latency_data_small(event, status);

argh,.. can you please go and rename this mtl_small nonsense to .. /me
googles.. crestmont / crm ?

Oh gawd, and the adl_small things to gracemont / gcm ?

> +
	return lnc_latency_data();
}


u64 lnc_latency_data()
{
> +	dse.val = status;
> +
> +	/* LNC core latency data */
> +	val = hybrid_var(event->pmu, pebs_data_source)[status & PERF_PEBS_DATA_SOURCE_MASK];
> +	if (!val)
> +		val = P(OP, LOAD) | LEVEL(NA) | P(SNOOP, NA);
> +
> +	if (dse.lnc_stlb_miss)
> +		val |= P(TLB, MISS) | P(TLB, L2);
> +	else
> +		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
> +
> +	if (dse.lnc_locked)
> +		val |= P(LOCK, LOCKED);
> +
> +	if (dse.lnc_data_blk)
> +		val |= P(BLK, DATA);
> +	if (dse.lnc_addr_blk)
> +		val |= P(BLK, ADDR);
> +	if (!dse.lnc_data_blk && !dse.lnc_addr_blk)
> +		val |= P(BLK, NA);
> +
> +	src.val = val;
> +	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
> +		src.mem_op = P(OP, STORE);
> +
> +	return src.val;
> +}


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ