| Message ID | 20240531231358.1000039-4-oliver.upton@linux.dev (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | KVM: arm64: nv: FPSIMD/SVE support | expand |
On Sat, 01 Jun 2024 00:13:50 +0100, Oliver Upton <oliver.upton@linux.dev> wrote: > > Round out the ZCR_EL2 gymnastics by loading SVE state in the fast path > when the guest hypervisor tries to access SVE state. > > Signed-off-by: Oliver Upton <oliver.upton@linux.dev> > --- > arch/arm64/kvm/hyp/include/hyp/switch.h | 23 +++++++++++++++++++++++ > 1 file changed, 23 insertions(+) > > diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h > index 428ee15dd6ae..5872eaafc7f0 100644 > --- a/arch/arm64/kvm/hyp/include/hyp/switch.h > +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h > @@ -345,6 +345,10 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) > if (guest_hyp_fpsimd_traps_enabled(vcpu)) > return false; > break; > + case ESR_ELx_EC_SYS64: > + if (WARN_ON_ONCE(!is_hyp_ctxt(vcpu))) > + return false; > + fallthrough; > case ESR_ELx_EC_SVE: > if (!sve_guest) > return false; > @@ -520,6 +524,22 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) > return true; > } > > +static bool kvm_hyp_handle_zcr(struct kvm_vcpu *vcpu, u64 *exit_code) > +{ > + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); > + > + if (!vcpu_has_nv(vcpu)) > + return false; > + > + if (sysreg != SYS_ZCR_EL2) > + return false; > + > + if (guest_owns_fp_regs()) > + return false; > + > + return kvm_hyp_handle_fpsimd(vcpu, exit_code); For my own understanding of the flow: let's say the L1 guest accesses ZCR_EL2 while the host own the FP regs: - ZCR_EL2 traps - we restore the guest's state, enable SVE - ZCR_EL2 traps again - emulate the access on the slow path In contrast, the same thing using ZCR_EL1 in L1 results in: - ZCR_EL1 traps - we restore the guest's state, enable SVE and we're done. Is that correct? If so, a comment would help... ;-) > +} > + > static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) > { > if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && > @@ -537,6 +557,9 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) > if (kvm_hyp_handle_cntpct(vcpu)) > return true; > > + if (kvm_hyp_handle_zcr(vcpu, exit_code)) > + return true; > + > return false; > } > Thanks, M.
On Sat, Jun 01, 2024 at 10:47:47AM +0100, Marc Zyngier wrote: > On Sat, 01 Jun 2024 00:13:50 +0100, Oliver Upton <oliver.upton@linux.dev> wrote: > > +static bool kvm_hyp_handle_zcr(struct kvm_vcpu *vcpu, u64 *exit_code) > > +{ > > + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); > > + > > + if (!vcpu_has_nv(vcpu)) > > + return false; > > + > > + if (sysreg != SYS_ZCR_EL2) > > + return false; > > + > > + if (guest_owns_fp_regs()) > > + return false; > > + > > + return kvm_hyp_handle_fpsimd(vcpu, exit_code); > > For my own understanding of the flow: let's say the L1 guest accesses > ZCR_EL2 while the host own the FP regs: > > - ZCR_EL2 traps > - we restore the guest's state, enable SVE > - ZCR_EL2 traps again > - emulate the access on the slow path > > In contrast, the same thing using ZCR_EL1 in L1 results in: > > - ZCR_EL1 traps > - we restore the guest's state, enable SVE > > and we're done. > > Is that correct? If so, a comment would help... ;-) Yeah, and I agree having a comment for this would be a good idea. Now that I'm looking at this code again, I had wanted to avoid the second trap on ZCR_EL2, so I'll probably fold in a change to bounce out to the slow path after loading SVE state.
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 428ee15dd6ae..5872eaafc7f0 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -345,6 +345,10 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) if (guest_hyp_fpsimd_traps_enabled(vcpu)) return false; break; + case ESR_ELx_EC_SYS64: + if (WARN_ON_ONCE(!is_hyp_ctxt(vcpu))) + return false; + fallthrough; case ESR_ELx_EC_SVE: if (!sve_guest) return false; @@ -520,6 +524,22 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) return true; } +static bool kvm_hyp_handle_zcr(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + + if (!vcpu_has_nv(vcpu)) + return false; + + if (sysreg != SYS_ZCR_EL2) + return false; + + if (guest_owns_fp_regs()) + return false; + + return kvm_hyp_handle_fpsimd(vcpu, exit_code); +} + static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) { if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && @@ -537,6 +557,9 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) if (kvm_hyp_handle_cntpct(vcpu)) return true; + if (kvm_hyp_handle_zcr(vcpu, exit_code)) + return true; + return false; }
Round out the ZCR_EL2 gymnastics by loading SVE state in the fast path when the guest hypervisor tries to access SVE state. Signed-off-by: Oliver Upton <oliver.upton@linux.dev> --- arch/arm64/kvm/hyp/include/hyp/switch.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+)