Commit d1777e68 authored by Will Deacon's avatar Will Deacon

arm64: erratum: Work around Falkor erratum #E1003 in trampoline code

We rely on an atomic swizzling of TTBR1 when transitioning from the entry
trampoline to the kernel proper on an exception. We can't rely on this
atomicity in the face of Falkor erratum #E1003, so on affected cores we
can issue a TLB invalidation to invalidate the walk cache prior to
jumping into the kernel. There is still the possibility of a TLB conflict
here due to conflicting walk cache entries prior to the invalidation, but
this doesn't appear to be the case on these CPUs in practice.
Reviewed-by: default avatarMark Rutland <mark.rutland@arm.com>
Tested-by: default avatarLaura Abbott <labbott@redhat.com>
Tested-by: default avatarShanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: default avatarWill Deacon <will.deacon@arm.com>
parent 4bf3286d
...@@ -522,20 +522,13 @@ config CAVIUM_ERRATUM_30115 ...@@ -522,20 +522,13 @@ config CAVIUM_ERRATUM_30115
config QCOM_FALKOR_ERRATUM_1003 config QCOM_FALKOR_ERRATUM_1003
bool "Falkor E1003: Incorrect translation due to ASID change" bool "Falkor E1003: Incorrect translation due to ASID change"
default y default y
select ARM64_PAN if ARM64_SW_TTBR0_PAN
help help
On Falkor v1, an incorrect ASID may be cached in the TLB when ASID On Falkor v1, an incorrect ASID may be cached in the TLB when ASID
and BADDR are changed together in TTBRx_EL1. The workaround for this and BADDR are changed together in TTBRx_EL1. Since we keep the ASID
issue is to use a reserved ASID in cpu_do_switch_mm() before in TTBR1_EL1, this situation only occurs in the entry trampoline and
switching to the new ASID. Saying Y here selects ARM64_PAN if then only for entries in the walk cache, since the leaf translation
ARM64_SW_TTBR0_PAN is selected. This is done because implementing and is unchanged. Work around the erratum by invalidating the walk cache
maintaining the E1003 workaround in the software PAN emulation code entries for the trampoline before entering the kernel proper.
would be an unnecessary complication. The affected Falkor v1 CPU
implements ARMv8.1 hardware PAN support and using hardware PAN
support versus software PAN emulation is mutually exclusive at
runtime.
If unsure, say Y.
config QCOM_FALKOR_ERRATUM_1009 config QCOM_FALKOR_ERRATUM_1009
bool "Falkor E1009: Prematurely complete a DSB after a TLBI" bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
......
...@@ -989,6 +989,18 @@ __ni_sys_trace: ...@@ -989,6 +989,18 @@ __ni_sys_trace:
sub \tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE) sub \tmp, \tmp, #(SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
bic \tmp, \tmp, #USER_ASID_FLAG bic \tmp, \tmp, #USER_ASID_FLAG
msr ttbr1_el1, \tmp msr ttbr1_el1, \tmp
#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003
alternative_if ARM64_WORKAROUND_QCOM_FALKOR_E1003
/* ASID already in \tmp[63:48] */
movk \tmp, #:abs_g2_nc:(TRAMP_VALIAS >> 12)
movk \tmp, #:abs_g1_nc:(TRAMP_VALIAS >> 12)
/* 2MB boundary containing the vectors, so we nobble the walk cache */
movk \tmp, #:abs_g0_nc:((TRAMP_VALIAS & ~(SZ_2M - 1)) >> 12)
isb
tlbi vae1, \tmp
dsb nsh
alternative_else_nop_endif
#endif /* CONFIG_QCOM_FALKOR_ERRATUM_1003 */
.endm .endm
.macro tramp_unmap_kernel, tmp .macro tramp_unmap_kernel, tmp
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment