FEAT_FPMR defines a new EL0 accessible register FPMR use to configure the
FP8 related features added to the architecture at the same time. Detect
support for this register and context switch it for EL0 when present.
Due to the sharing of responsibility for saving floating point state
between the host kernel and KVM FP8 support is not yet implemented in KVM
and a stub similar to that used for SVCR is provided for FPMR in order to
avoid bisection issues. To make it easier to share host state with the
hypervisor we store FPMR as a hardened usercopy field in uw (along with
some padding).
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20240306-arm64-2023-dpisa-v5-3-c568edc8ed7f@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
return system_supports_sme();
}
+static __always_inline bool system_supports_fpmr(void)
+{
+ return alternative_has_cap_unlikely(ARM64_HAS_FPMR);
+}
+
static __always_inline bool system_supports_cnp(void)
{
return alternative_has_cap_unlikely(ARM64_HAS_CNP);
void *sve_state;
void *sme_state;
u64 *svcr;
+ u64 *fpmr;
unsigned int sve_vl;
unsigned int sme_vl;
enum fp_type *fp_type;
extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused);
extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused);
extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused);
+extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused);
extern u64 read_smcr_features(void);
enum fp_type fp_type;
unsigned int sve_max_vl;
u64 svcr;
+ u64 fpmr;
/* Stage 2 paging state used by the hardware on next switch */
struct kvm_s2_mmu *hw_mmu;
struct {
unsigned long tp_value; /* TLS register */
unsigned long tp2_value;
+ u64 fpmr;
+ unsigned long pad;
struct user_fpsimd_state fpsimd_state;
} uw;
BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) !=
sizeof_field(struct thread_struct, uw.tp_value) +
sizeof_field(struct thread_struct, uw.tp2_value) +
+ sizeof_field(struct thread_struct, uw.fpmr) +
+ sizeof_field(struct thread_struct, uw.pad) +
sizeof_field(struct thread_struct, uw.fpsimd_state));
*offset = offsetof(struct thread_struct, uw);
};
static const struct arm64_ftr_bits ftr_id_aa64pfr2[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR2_EL1_FPMR_SHIFT, 4, 0),
ARM64_FTR_END,
};
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_lpa2,
},
+ {
+ .desc = "FPMR",
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_HAS_FPMR,
+ .matches = has_cpuid_feature,
+ .cpu_enable = cpu_enable_fpmr,
+ ARM64_CPUID_FIELDS(ID_AA64PFR2_EL1, FPMR, IMP)
+ },
{},
};
WARN_ON(preemptible());
WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE));
+ if (system_supports_fpmr())
+ write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
+
if (system_supports_sve() || system_supports_sme()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
if (test_thread_flag(TIF_FOREIGN_FPSTATE))
return;
+ if (system_supports_fpmr())
+ *(last->fpmr) = read_sysreg_s(SYS_FPMR);
+
/*
* If a task is in a syscall the ABI allows us to only
* preserve the state shared with FPSIMD so don't bother
}
}
+void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p)
+{
+ write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK,
+ SYS_SCTLR_EL1);
+}
+
#ifdef CONFIG_ARM64_SVE
/*
* Call __sve_free() directly only if you know task can't be scheduled
last->sve_vl = task_get_sve_vl(current);
last->sme_vl = task_get_sme_vl(current);
last->svcr = ¤t->thread.svcr;
+ last->fpmr = ¤t->thread.uw.fpmr;
last->fp_type = ¤t->thread.fp_type;
last->to_save = FP_STATE_CURRENT;
current->thread.fpsimd_cpu = smp_processor_id();
fp_state.sve_vl = vcpu->arch.sve_max_vl;
fp_state.sme_state = NULL;
fp_state.svcr = &vcpu->arch.svcr;
+ fp_state.fpmr = &vcpu->arch.fpmr;
fp_state.fp_type = &vcpu->arch.fp_type;
if (vcpu_has_sve(vcpu))
HAS_ECV_CNTPOFF
HAS_EPAN
HAS_EVT
+HAS_FPMR
HAS_FGT
HAS_FPSIMD
HAS_GENERIC_AUTH