[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aFPu4SorUGlFt-2p@arm.com>
Date: Thu, 19 Jun 2025 12:05:05 +0100
From: Catalin Marinas <catalin.marinas@....com>
To: Mikołaj Lenczewski <miko.lenczewski@....com>
Cc: ryan.roberts@....com, yang@...amperecomputing.com, will@...nel.org,
jean-philippe@...aro.org, robin.murphy@....com, joro@...tes.org,
maz@...nel.org, oliver.upton@...ux.dev, joey.gouly@....com,
james.morse@....com, broonie@...nel.org, ardb@...nel.org,
baohua@...nel.org, suzuki.poulose@....com, david@...hat.com,
jgg@...pe.ca, nicolinc@...dia.com, jsnitsel@...hat.com,
mshavit@...gle.com, kevin.tian@...el.com,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
iommu@...ts.linux.dev
Subject: Re: [PATCH v7 2/4] arm64: Add BBM Level 2 cpu feature
On Tue, Jun 17, 2025 at 09:51:02AM +0000, Mikołaj Lenczewski wrote:
> diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
> index f9c947166322..2e80ff237b96 100644
> --- a/arch/arm64/kernel/cpufeature.c
> +++ b/arch/arm64/kernel/cpufeature.c
> @@ -2213,6 +2213,41 @@ static bool hvhe_possible(const struct arm64_cpu_capabilities *entry,
> return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_HVHE);
> }
>
> +static bool has_bbml2_noabort(const struct arm64_cpu_capabilities *caps, int scope)
> +{
> + /*
> + * We want to allow usage of BBML2 in as wide a range of kernel contexts
> + * as possible. This list is therefore an allow-list of known-good
> + * implementations that both support BBML2 and additionally, fulfill the
> + * extra constraint of never generating TLB conflict aborts when using
> + * the relaxed BBML2 semantics (such aborts make use of BBML2 in certain
> + * kernel contexts difficult to prove safe against recursive aborts).
> + *
> + * Note that implementations can only be considered "known-good" if their
> + * implementors attest to the fact that the implementation never raises
> + * TLBI conflict aborts for BBML2 mapping granularity changes.
s/TLBI/TLB/
> + */
> + static const struct midr_range supports_bbml2_noabort_list[] = {
> + MIDR_REV_RANGE(MIDR_CORTEX_X4, 0, 3, 0xf),
> + MIDR_REV_RANGE(MIDR_NEOVERSE_V3, 0, 2, 0xf),
> + {}
> + };
> +
> + /* Does our cpu guarantee to never raise TLB conflict aborts? */
> + if (!is_midr_in_range_list(supports_bbml2_noabort_list))
> + return false;
> +
> + /*
> + * We currently ignore the AA64_ID_MMFR2 register, and only care about
s/AA64_ID_MMFR2/ID_AA64MMFR2_EL1/
> + * whether the MIDR check passes. This is because we specifically
> + * care only about a stricter form of BBML2 (one guaranteeing noabort),
> + * and so the MMFR2 check is pointless (all implementations passing the
> + * MIDR check should also pass the MMFR2 check).
I think there's at least one implementation that behaves as
BBML2-noabort but does not have the ID field advertising BBML2.
> + */
> +
> + return true;
> +}
> +
> #ifdef CONFIG_ARM64_PAN
> static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
> {
> @@ -2980,6 +3015,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
> .matches = has_cpuid_feature,
> ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP)
> },
> + {
> + .capability = ARM64_HAS_BBML2_NOABORT,
> + .type = ARM64_CPUCAP_EARLY_LOCAL_CPU_FEATURE,
> + .matches = has_bbml2_noabort,
> + },
> {
> .desc = "52-bit Virtual Addressing for KVM (LPA2)",
> .capability = ARM64_HAS_LPA2,
> diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
> index 10effd4cff6b..2bd2bfaeddcd 100644
> --- a/arch/arm64/tools/cpucaps
> +++ b/arch/arm64/tools/cpucaps
> @@ -45,6 +45,7 @@ HAS_LPA2
> HAS_LSE_ATOMICS
> HAS_MOPS
> HAS_NESTED_VIRT
> +HAS_BBML2_NOABORT
> HAS_PAN
> HAS_PMUV3
> HAS_S1PIE
Otherwise it looks fine.
Reviewed-by: Catalin Marinas <catalin.marinas@....com>
Powered by blists - more mailing lists