RE: [PATCH 2/4] arm64: tlb: Add tlbi workaround for FUJITSU-MONAKA Erratum E#030001

From: Tomohiro Misono (Fujitsu)

Date: Tue Oct 06 2026 - 05:51:19 EST

Hi Mark,

> Subject: Re: [PATCH 2/4] arm64: tlb: Add tlbi workaround for FUJITSU-MONAKA Erratum E#030001
>
> On Fri, Oct 02, 2026 at 07:26:50PM +0900, Tomohiro Misono wrote:
> > FUJITSU-MONAKA Erratum E#030001 affects FUJITSU-MONAKA CPU
> > when using 64k page size.
> >
> > On affected FUJITSU-MONAKA CPUs, range-based TLBI operations
> > targeting a VA or IPA may fail to invalidate TLB entries when
> > addr[34:29] == all 1 && addr[28:0] == 0 for 512MB mappings.
> > The affected instructions are:
> > RVA[L]E{1,2,3}*, RVAA[L]E1*, and RIPAS2[L]E1*.
>
> How does this work when all of the following are true:
>
> * The S1 translation granule is 4K.
> * The S2 translation granule is 64K.
> * S1 has a 1G block translating VA x to IPA y.
> * S2 has a 512M block translating IPA y to PA z.
>
> In that case, can a "512MB mapping" exist for VA x? I would expect so.
>
> Assuming that is the case, the S1 translation granule doesn't matter,
> and the S1 workaround cannot depend on PAGE_SIZE_64KB.

Your expectation is correct. I confirmed that this erratum could occur in
that case as well (S1 1G block & S2 512M block). This is also affected by
GPT size. Therefore, the PAGE_SIZE condition needs to be removed.

> > Work around the erratum by issuing additional non-range
> > TLBI instructions corresponding to the affected VA or IPA
> > range-based TLBI operations.
> >
> > Signed-off-by: Tomohiro Misono <misono.tomohiro@xxxxxxxxxxx>
> > ---
> > Documentation/arch/arm64/silicon-errata.rst | 2 ++
> > arch/arm64/Kconfig | 19 +++++++++++++++++
> > arch/arm64/include/asm/cpucaps.h | 2 ++
> > arch/arm64/include/asm/tlbflush.h | 33 +++++++++++++++++++++++++++++
> > arch/arm64/kernel/cpu_errata.c | 10 +++++++++
> > arch/arm64/tools/cpucaps | 1 +
> > 6 files changed, 67 insertions(+)
> >
> > diff --git a/Documentation/arch/arm64/silicon-errata.rst
> b/Documentation/arch/arm64/silicon-errata.rst
> > index ac3248b9f2f3..8ab6284e3d10 100644
> > --- a/Documentation/arch/arm64/silicon-errata.rst
> > +++ b/Documentation/arch/arm64/silicon-errata.rst
> > @@ -373,6 +373,8 @@ stable kernels.
> > +----------------+-----------------+-----------------+-----------------------------+
> > | Fujitsu | A64FX | E#010001 | FUJITSU_ERRATUM_010001 |
> > +----------------+-----------------+-----------------+-----------------------------+
> > +| Fujitsu | MONAKA | E#030001 | FUJITSU_ERRATUM_030001 |
> > ++----------------+-----------------+-----------------+-----------------------------+
> > +----------------+-----------------+-----------------+-----------------------------+
> > | ASR | ASR8601 | #8601001 | N/A |
> > +----------------+-----------------+-----------------+-----------------------------+
> > diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
> > index b5a51b0ef944..38248a31d5f1 100644
> > --- a/arch/arm64/Kconfig
> > +++ b/arch/arm64/Kconfig
> > @@ -1312,6 +1312,25 @@ config FUJITSU_ERRATUM_010001
> >
> > If unsure, say Y.
> >
> > +config FUJITSU_ERRATUM_030001
> > + bool "FUJITSU-MONAKA erratum E#030001: Range TLBI may fail to invalidate some entries"
> > + depends on PAGE_SIZE_64KB
>
> As above, I strongly suspect this depends on the conbiation of S1 and S2
> sizes, and could happen regardless of whether S1 uses 64K.
>
> > + default y
> > + help
> > + This option adds a workaround for FUJITSU-MONAKA erratum E#030001.
> > + On affected FUJITSU-MONAKA CPUs, range-based TLBI operation
> > + targeting a VA or IPA may fail to invalidate some TLB entries
> > + for 512MB mappings. The affected instructions are RVA[L]E{1,2,3}*,
> > + RVAA[L]E1*, and RIPAS2[L]E1*.
> > +
> > + Work around the erratum by issuing additional non-range TLBI
> > + instructions corresponding to the affected VA or IPA range-based
> > + TLBI operations.
> > +
> > + The erratum only affects the FUJITSU-MONAKA on 64k pagesize.
> > +
> > + If unsure, say Y.
> > +
> > config HISILICON_ERRATUM_161600802
> > bool "Hip07 161600802: Erroneous redistributor VLPI base"
> > default y
> > diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
> > index 76350b38f0d7..9220b917ec20 100644
> > --- a/arch/arm64/include/asm/cpucaps.h
> > +++ b/arch/arm64/include/asm/cpucaps.h
> > @@ -66,6 +66,8 @@ cpucap_is_possible(const unsigned int cap)
> > return IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386);
> > case ARM64_WORKAROUND_4193714:
> > return IS_ENABLED(CONFIG_ARM64_ERRATUM_4193714);
> > + case ARM64_WORKAROUND_FUJITSU_030001:
> > + return IS_ENABLED(CONFIG_FUJITSU_ERRATUM_030001);
> > case ARM64_MPAM:
> > /*
> > * KVM MPAM support doesn't rely on the host kernel supporting MPAM.
> > diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
> > index 14a78ac0f800..0487daec1652 100644
> > --- a/arch/arm64/include/asm/tlbflush.h
> > +++ b/arch/arm64/include/asm/tlbflush.h
> > @@ -487,6 +487,37 @@ static __always_inline void __tlbi_range(tlbi_op op, u64 addr,
> > op(arg);
> > }
> >
> > +#ifdef CONFIG_FUJITSU_ERRATUM_030001
> > +static inline void fujitsu_erratum_wa(tlbi_op lop, u64 start, u64 end, u16 asid)
> > +{
> > + u64 addr;
> > +
> > + if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_FUJITSU_030001))
> > + return;
> > +
> > + /*
> > + * The erratum fails to invalidate TLBI entries in the range when
> > + * addr[34:29] == all 1 && addr[28:0] == all 0 for 512M hugepage.
> > + * However, since it cannot be determined reliably if the target
> > + * entry is hugepage or not here, always assume hugepage is used.
> > + * The workaround is to issue extra non-range TLBI ops corresponding
> > + * to the affected VA or IPA range-based ops in the range.
> > + */
> > + addr = (start & GENMASK_ULL(63, 35)) | GENMASK_ULL(34, 29);
> > + while (addr < end) {
> > + __tlbi_level_asid(lop, addr, TLBI_TTL_UNKNOWN, asid);
> > + if (addr + BIT_ULL(35) < addr)
> > + /* overflow */
> > + break;
> > + addr += BIT_ULL(35);
> > + }
> > +}
> > +#else
> > +static inline void fujitsu_erratum_wa(tlbi_op lop, u64 start, u64 end, u16 asid)
> > +{
> > +}
> > +#endif /* CONFIG_FUJITSU_ERRATUM_030001 */
> > +
> > static __always_inline void __flush_tlb_range_op(tlbi_op lop, tlbi_op rop,
> > u64 start, size_t pages,
> > u64 stride, u16 asid,
> > @@ -518,6 +549,8 @@ static __always_inline void __flush_tlb_range_op(tlbi_op lop, tlbi_op rop,
> > __tlbi_level_asid(lop, addr, level, asid);
> > addr += stride;
> > }
> > +
> > + fujitsu_erratum_wa(lop, start, end, asid);
> > }
>
> It would be much simpler to say range invalidation doesn't work on this
> part.

Disabling range operations on MONAKA CPUs would be another solution.
We'd like to select the option that minimizes the performance impact.
Since the PAGE_SIZE condition has changed, I will check the performance
impact of this erratum (including on a 4k kernel).

>
> >
> > #define __flush_s1_tlb_range_op(op, start, pages, stride, asid, tlb_level) \
> > diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
> > index 8ec47d89b45b..5b9dea3c761d 100644
> > --- a/arch/arm64/kernel/cpu_errata.c
> > +++ b/arch/arm64/kernel/cpu_errata.c
> > @@ -1027,6 +1027,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
> > .matches = has_impdef_pmuv3,
> > .cpu_enable = cpu_enable_impdef_pmuv3_traps,
> > },
> > +#ifdef CONFIG_FUJITSU_ERRATUM_030001
> > + {
> > + .desc = "FUJITSU-MONAKA Erratum E#030001",
> > + .capability = ARM64_WORKAROUND_FUJITSU_030001,
> > + ERRATA_MIDR_RANGE_LIST(((const struct midr_range[]) {
> > + MIDR_ALL_VERSIONS(MIDR_FUJITSU_MONAKA),
> > + {}
> > + })),
> > + },
>
> Are you expecting to add other parts here?
>
> Is there a (future?) revision of MONAKA with this fixed?

There is currently no plan of fix for this part.

Thanks for the review.
Best Regards,
Tomohiro Misono

>
> Mark.
>
> > +#endif
> > {
> > .desc = "Known broken GICv3 SEIS implementation",
> > .capability = ARM64_WORKAROUND_GICv3_BROKEN_SEIS,
> > diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
> > index 2775ba3359cf..50a9aa0e2bf0 100644
> > --- a/arch/arm64/tools/cpucaps
> > +++ b/arch/arm64/tools/cpucaps
> > @@ -132,3 +132,4 @@ WORKAROUND_REPEAT_TLBI_SYNC
> > WORKAROUND_SPECULATIVE_AT
> > WORKAROUND_SPECULATIVE_SSBS
> > WORKAROUND_SPECULATIVE_UNPRIV_LOAD
> > +WORKAROUND_FUJITSU_030001
> >
> > --
> > 2.43.0
> >