linux-kernel - [PATCH v4 02/12] perf: arm_spe: Support FEAT

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: <20250721-james-perf-feat_spe_eft-v4-2-0a527410f8fd@linaro.org>
Date: Mon, 21 Jul 2025 13:53:33 +0100
From: James Clark <james.clark@...aro.org>
To: Catalin Marinas <catalin.marinas@....com>, 
 Will Deacon <will@...nel.org>, Mark Rutland <mark.rutland@....com>, 
 Jonathan Corbet <corbet@....net>, Marc Zyngier <maz@...nel.org>, 
 Oliver Upton <oliver.upton@...ux.dev>, Joey Gouly <joey.gouly@....com>, 
 Suzuki K Poulose <suzuki.poulose@....com>, 
 Zenghui Yu <yuzenghui@...wei.com>, Peter Zijlstra <peterz@...radead.org>, 
 Ingo Molnar <mingo@...hat.com>, Arnaldo Carvalho de Melo <acme@...nel.org>, 
 Namhyung Kim <namhyung@...nel.org>, 
 Alexander Shishkin <alexander.shishkin@...ux.intel.com>, 
 Jiri Olsa <jolsa@...nel.org>, Ian Rogers <irogers@...gle.com>, 
 Adrian Hunter <adrian.hunter@...el.com>
Cc: linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org, 
 linux-perf-users@...r.kernel.org, linux-doc@...r.kernel.org, 
 kvmarm@...ts.linux.dev, James Clark <james.clark@...aro.org>
Subject: [PATCH v4 02/12] perf: arm_spe: Support FEAT_SPEv1p4 filters

FEAT_SPEv1p4 (optional from Armv8.8) adds some new filter bits and also
makes some previously available bits unavailable again e.g:

  E[30], bit [30]
  When FEAT_SPEv1p4 is _not_ implemented ...

Continuing to hard code the valid filter bits for each version isn't
scalable, and it also doesn't work for filter bits that aren't related
to SPE version. For example most bits have a further condition:

  E[15], bit [15]
  When ... and filtering on event 15 is supported:

Whether "filtering on event 15" is implemented or not is only
discoverable from the TRM of that specific CPU or by probing
PMSEVFR_EL1.

Instead of hard coding them, write all 1s to the PMSEVFR_EL1 register
and read it back to discover the RES0 bits. Unsupported bits are RAZ/WI
so should read as 0s.

For any hardware that doesn't strictly follow RAZ/WI for unsupported
filters: Any bits that should have been supported in a specific SPE
version but now incorrectly appear to be RES0 wouldn't have worked
anyway, so it's better to fail to open events that request them rather
than behaving unexpectedly. Bits that aren't implemented but also aren't
RAZ/WI will be incorrectly reported as supported, but allowing them to
be used is harmless.

Testing on N1SDP shows the probed RES0 bits to be the same as the hard
coded ones. The FVP with SPEv1p4 shows only additional new RES0 bits,
i.e. no previously hard coded RES0 bits are missing.

Signed-off-by: James Clark <james.clark@...aro.org>
---
 arch/arm64/include/asm/sysreg.h |  9 ---------
 drivers/perf/arm_spe_pmu.c      | 23 +++++++----------------
 2 files changed, 7 insertions(+), 25 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index f1bb0d10c39a..e80207572786 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -350,15 +350,6 @@
 #define SYS_PAR_EL1_ATTR		GENMASK_ULL(63, 56)
 #define SYS_PAR_EL1_F0_RES0		(GENMASK_ULL(6, 1) | GENMASK_ULL(55, 52))
 
-/*** Statistical Profiling Extension ***/
-#define PMSEVFR_EL1_RES0_IMP	\
-	(GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\
-	 BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0))
-#define PMSEVFR_EL1_RES0_V1P1	\
-	(PMSEVFR_EL1_RES0_IMP & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11)))
-#define PMSEVFR_EL1_RES0_V1P2	\
-	(PMSEVFR_EL1_RES0_V1P1 & ~BIT_ULL(6))
-
 /* Buffer error reporting */
 #define PMBSR_EL1_FAULT_FSC_SHIFT	PMBSR_EL1_MSS_SHIFT
 #define PMBSR_EL1_FAULT_FSC_MASK	PMBSR_EL1_MSS_MASK
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 3efed8839a4e..051ec885318d 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -89,6 +89,7 @@ struct arm_spe_pmu {
 #define SPE_PMU_FEAT_DEV_PROBED			(1UL << 63)
 	u64					features;
 
+	u64					pmsevfr_res0;
 	u16					max_record_sz;
 	u16					align;
 	struct perf_output_handle __percpu	*handle;
@@ -693,20 +694,6 @@ static irqreturn_t arm_spe_pmu_irq_handler(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static u64 arm_spe_pmsevfr_res0(u16 pmsver)
-{
-	switch (pmsver) {
-	case ID_AA64DFR0_EL1_PMSVer_IMP:
-		return PMSEVFR_EL1_RES0_IMP;
-	case ID_AA64DFR0_EL1_PMSVer_V1P1:
-		return PMSEVFR_EL1_RES0_V1P1;
-	case ID_AA64DFR0_EL1_PMSVer_V1P2:
-	/* Return the highest version we support in default */
-	default:
-		return PMSEVFR_EL1_RES0_V1P2;
-	}
-}
-
 /* Perf callbacks */
 static int arm_spe_pmu_event_init(struct perf_event *event)
 {
@@ -722,10 +709,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 	    !cpumask_test_cpu(event->cpu, &spe_pmu->supported_cpus))
 		return -ENOENT;
 
-	if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
+	if (arm_spe_event_to_pmsevfr(event) & spe_pmu->pmsevfr_res0)
 		return -EOPNOTSUPP;
 
-	if (arm_spe_event_to_pmsnevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver))
+	if (arm_spe_event_to_pmsnevfr(event) & spe_pmu->pmsevfr_res0)
 		return -EOPNOTSUPP;
 
 	if (attr->exclude_idle)
@@ -1103,6 +1090,10 @@ static void __arm_spe_pmu_dev_probe(void *info)
 		spe_pmu->counter_sz = 16;
 	}
 
+	/* Write all 1s and then read back. Unsupported filter bits are RAZ/WI. */
+	write_sysreg_s(U64_MAX, SYS_PMSEVFR_EL1);
+	spe_pmu->pmsevfr_res0 = ~read_sysreg_s(SYS_PMSEVFR_EL1);
+
 	dev_info(dev,
 		 "probed SPEv1.%d for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n",
 		 spe_pmu->pmsver - 1, cpumask_pr_args(&spe_pmu->supported_cpus),

-- 
2.34.1