SME has optional support for configuring the relative priorities of PEs in systems where they share a single SME hardware block, known as a SMCU. Currently we do not have any support for this in Linux and will also hide it from KVM guests, pending experience with practical implementations. The interface for configuring priority support is via two new system registers, these registers are always defined when SME is available.

The register SMPRI_EL1 allows control of SME execution priorities. Since we disable SME priority support for guests this register is RES0, define it as such and enable fine grained traps for SMPRI_EL1 to ensure that guests can't write to it even if the hardware supports priorites. Since the register should be readable with fixed contents we only trap writes, not reads. Since there is no host support for using priorities the register currently left with a value of 0 by the host so we do not need to update the value for guests.

There is also an EL2 register SMPRIMAP_EL2 for virtualisation of priorities, this is RES0 when priority configuration is not supported but has no specific traps available. When saving state from a nested guest we overwite any value the guest stored.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 1 + arch/arm64/include/asm/vncr_mapping.h | 1 + arch/arm64/kvm/config.c | 3 +++ arch/arm64/kvm/hyp/vhe/sysreg-sr.c | 7 +++++++ arch/arm64/kvm/sys_regs.c | 30 +++++++++++++++++++++++++++++- 5 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index fead6988f47c..44595a789a97 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -546,6 +546,7 @@ enum vcpu_sysreg { VNCR(CPACR_EL1),/* Coprocessor Access Control */ VNCR(ZCR_EL1), /* SVE Control */ VNCR(SMCR_EL1), /* SME Control */ + VNCR(SMPRIMAP_EL2), /* Streaming Mode Priority Mapping Register */ VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */ VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */ VNCR(TCR_EL1), /* Translation Control Register */ diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h index 44b12565321b..a2a84af6585b 100644 --- a/arch/arm64/include/asm/vncr_mapping.h +++ b/arch/arm64/include/asm/vncr_mapping.h @@ -45,6 +45,7 @@ #define VNCR_ZCR_EL1 0x1E0 #define VNCR_HAFGRTR_EL2 0x1E8 #define VNCR_SMCR_EL1 0x1F0 +#define VNCR_SMPRIMAP_EL2 0x1F0 #define VNCR_TTBR0_EL1 0x200 #define VNCR_TTBR1_EL1 0x210 #define VNCR_FAR_EL1 0x220 diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c index 7e26991b2df1..0088635a95bd 100644 --- a/arch/arm64/kvm/config.c +++ b/arch/arm64/kvm/config.c @@ -1481,6 +1481,9 @@ static void __compute_hfgwtr(struct kvm_vcpu *vcpu)

if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38)) *vcpu_fgt(vcpu, HFGWTR_EL2) |= HFGWTR_EL2_TCR_EL1; + + if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SME, IMP)) + *vcpu_fgt(vcpu, HFGWTR_EL2) |= HFGWTR_EL2_nSMPRI_EL1; }

static void __compute_hdfgwtr(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c index f28c6cf4fe1b..07aa4378c58a 100644 --- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -80,6 +80,13 @@ static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)

if (ctxt_has_sctlr2(&vcpu->arch.ctxt)) __vcpu_assign_sys_reg(vcpu, SCTLR2_EL2, read_sysreg_el1(SYS_SCTLR2)); + + /* + * We block SME priorities so SMPRIMAP_EL2 is RES0, however we + * do not have traps to block access so the guest might have + * updated the state, overwrite anything there. + */ + __vcpu_assign_sys_reg(vcpu, SMPRIMAP_EL2, 0); }

static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index a7ab02822023..51f175bbe8d1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -691,6 +691,15 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, return read_zero(vcpu, p); }

+static int set_res0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + u64 val) +{ + if (val) + return -EINVAL; + + return 0; +} + /* * ARMv8.1 mandates at least a trivial LORegion implementation, where all the * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 @@ -1979,6 +1988,15 @@ static unsigned int fp8_visibility(const struct kvm_vcpu *vcpu, return REG_HIDDEN; }

+static unsigned int sme_raz_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + if (vcpu_has_sme(vcpu)) + return REG_RAZ; + + return REG_HIDDEN; +} + static u64 sanitise_id_aa64pfr0_el1(const struct kvm_vcpu *vcpu, u64 val) { if (!vcpu_has_sve(vcpu)) @@ -3349,7 +3367,14 @@ static const struct sys_reg_desc sys_reg_descs[] = {

{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TRFCR_EL1), undef_access }, - { SYS_DESC(SYS_SMPRI_EL1), undef_access }, + + /* + * SMPRI_EL1 is UNDEF when SME is disabled, the UNDEF is + * handled via FGU which is handled without consulting this + * table. + */ + { SYS_DESC(SYS_SMPRI_EL1), trap_raz_wi, .visibility = sme_raz_visibility }, + { SYS_DESC(SYS_SMCR_EL1), NULL, reset_val, SMCR_EL1, 0, .visibility = sme_visibility }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 }, @@ -3719,6 +3744,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {

EL2_REG_VNCR(HCRX_EL2, reset_val, 0),

+ { SYS_DESC(SYS_SMPRIMAP_EL2), .reg = SMPRIMAP_EL2, + .access = trap_raz_wi, .set_user = set_res0, .reset = reset_val, + .val = 0, .visibility = sme_el2_visibility }, EL2_REG_FILTERED(SMCR_EL2, access_smcr_el2, reset_val, 0, sme_el2_visibility),

The primary register for identifying SME is ID_AA64PFR1_EL1.SME. This is hidden from guests unless SME is enabled by the VMM. When it is visible it is writable and can be used to control the availability of SME2.

There is also a new register ID_AA64SMFR0_EL1 which we make writable, forcing it to all bits 0 if SME is disabled. This includes the field SMEver giving the SME version, userspace is responsible for ensuring the value is consistent with ID_AA64PFR1_EL1.SME. It also includes FA64, a separately enableable extension which provides the full FPSIMD and SVE instruction set including FFR in streaming mode. Userspace can control the availability of FA64 by writing to this field. The other features enumerated there only add new instructions, there are no architectural controls for these.

There is a further identification register SMIDR_EL1 which provides a basic description of the SME microarchitecture, in a manner similar to MIDR_EL1 for the PE. It also describes support for priority management and a basic affinity description for shared SME units, plus some RES0 space. We do not support priority management for guests so this is hidden from guests, along with any new fields.

As for MIDR_EL1 and REVIDR_EL1 we expose the implementer and revision information to guests with the raw value from the CPU we are running on, this may present issues for asymmetric systems or for migration as it does for the existing registers.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 3 +++ arch/arm64/kvm/config.c | 8 +----- arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 11 ++++++++ arch/arm64/kvm/hyp/nvhe/pkvm.c | 4 ++- arch/arm64/kvm/sys_regs.c | 40 +++++++++++++++++++++++++++--- 5 files changed, 54 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 825b74f752d6..fead6988f47c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -400,6 +400,7 @@ struct kvm_arch { u64 revidr_el1; u64 aidr_el1; u64 ctr_el0; + u64 smidr_el1;

/* Masks for VNCR-backed and general EL2 sysregs */ struct kvm_sysreg_masks *sysreg_masks; @@ -1543,6 +1544,8 @@ static inline u64 *__vm_id_reg(struct kvm_arch *ka, u32 reg) return &ka->revidr_el1; case SYS_AIDR_EL1: return &ka->aidr_el1; + case SYS_SMIDR_EL1: + return &ka->smidr_el1; default: WARN_ON_ONCE(1); return NULL; diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c index 24bb3f36e9d5..7e26991b2df1 100644 --- a/arch/arm64/kvm/config.c +++ b/arch/arm64/kvm/config.c @@ -274,14 +274,8 @@ static bool feat_anerr(struct kvm *kvm)

static bool feat_sme_smps(struct kvm *kvm) { - /* - * Revists this if KVM ever supports SME -- this really should - * look at the guest's view of SMIDR_EL1. Funnily enough, this - * is not captured in the JSON file, but only as a note in the - * ARM ARM. - */ return (kvm_has_feat(kvm, FEAT_SME) && - (read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS)); + (kvm_read_vm_id_reg(kvm, SYS_SMIDR_EL1) & SMIDR_EL1_SMPS)); }

static bool feat_spe_fds(struct kvm *kvm) diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h index 8c3b3d6df99f..d921db152119 100644 --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -125,6 +125,17 @@ static inline u64 ctxt_midr_el1(struct kvm_cpu_context *ctxt) return kvm_read_vm_id_reg(kvm, SYS_MIDR_EL1); }

+static inline u64 ctxt_smidr_el1(struct kvm_cpu_context *ctxt) +{ + struct kvm *kvm = kern_hyp_va(ctxt_to_vcpu(ctxt)->kvm); + + if (!(ctxt_is_guest(ctxt) && + test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags))) + return read_sysreg_s(SYS_SMIDR_EL1); + + return kvm_read_vm_id_reg(kvm, SYS_SMIDR_EL1); +} + static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { *ctxt_mdscr_el1(ctxt) = read_sysreg(mdscr_el1); diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index f4ec6695a6a5..b656449dff69 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -351,8 +351,10 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc host_kvm->arch.vcpu_features, KVM_VCPU_MAX_FEATURES);

- if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &host_arch_flags)) + if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &host_arch_flags)) { hyp_vm->kvm.arch.midr_el1 = host_kvm->arch.midr_el1; + hyp_vm->kvm.arch.smidr_el1 = host_kvm->arch.smidr_el1; + }

return; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 7e550f045f4d..a7ab02822023 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1893,6 +1893,10 @@ static unsigned int id_visibility(const struct kvm_vcpu *vcpu, if (!vcpu_has_sve(vcpu)) return REG_RAZ; break; + case SYS_ID_AA64SMFR0_EL1: + if (!vcpu_has_sme(vcpu)) + return REG_RAZ; + break; }

return 0; @@ -1920,10 +1924,25 @@ static unsigned int raz_visibility(const struct kvm_vcpu *vcpu,

/* cpufeature ID register access trap handlers */

+static bool hidden_id_reg(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + switch (reg_to_encoding(r)) { + case SYS_SMIDR_EL1: + return !vcpu_has_sme(vcpu); + default: + return false; + } +} + static bool access_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { + if (hidden_id_reg(vcpu, p, r)) + return bad_trap(vcpu, p, r, "write to hidden ID register"); + if (p->is_write) return write_to_read_only(vcpu, p, r);

@@ -2012,7 +2031,9 @@ static u64 sanitise_id_aa64pfr1_el1(const struct kvm_vcpu *vcpu, u64 val) SYS_FIELD_GET(ID_AA64PFR0_EL1, RAS, pfr0) == ID_AA64PFR0_EL1_RAS_IMP)) val &= ~ID_AA64PFR1_EL1_RAS_frac;

- val &= ~ID_AA64PFR1_EL1_SME; + if (!kvm_has_sme(vcpu->kvm)) + val &= ~ID_AA64PFR1_EL1_SME; + val &= ~ID_AA64PFR1_EL1_RNDR_trap; val &= ~ID_AA64PFR1_EL1_NMI; val &= ~ID_AA64PFR1_EL1_GCS; @@ -3038,6 +3059,9 @@ static bool access_imp_id_reg(struct kvm_vcpu *vcpu, case SYS_AIDR_EL1: p->regval = read_sysreg(aidr_el1); break; + case SYS_SMIDR_EL1: + p->regval = read_sysreg_s(SYS_SMIDR_EL1); + break; default: WARN_ON_ONCE(1); } @@ -3048,12 +3072,15 @@ static bool access_imp_id_reg(struct kvm_vcpu *vcpu, static u64 __ro_after_init boot_cpu_midr_val; static u64 __ro_after_init boot_cpu_revidr_val; static u64 __ro_after_init boot_cpu_aidr_val; +static u64 __ro_after_init boot_cpu_smidr_val;

static void init_imp_id_regs(void) { boot_cpu_midr_val = read_sysreg(midr_el1); boot_cpu_revidr_val = read_sysreg(revidr_el1); boot_cpu_aidr_val = read_sysreg(aidr_el1); + if (system_supports_sme()) + boot_cpu_smidr_val = read_sysreg_s(SYS_SMIDR_EL1); }

static u64 reset_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) @@ -3065,6 +3092,8 @@ static u64 reset_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) return boot_cpu_revidr_val; case SYS_AIDR_EL1: return boot_cpu_aidr_val; + case SYS_SMIDR_EL1: + return boot_cpu_smidr_val; default: KVM_BUG_ON(1, vcpu->kvm); return 0; @@ -3229,7 +3258,6 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64PFR1_EL1_MTE_frac | ID_AA64PFR1_EL1_NMI | ID_AA64PFR1_EL1_RNDR_trap | - ID_AA64PFR1_EL1_SME | ID_AA64PFR1_EL1_RES0 | ID_AA64PFR1_EL1_MPAM_frac | ID_AA64PFR1_EL1_MTE)), @@ -3239,7 +3267,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64PFR2_EL1_MTESTOREONLY), ID_UNALLOCATED(4,3), ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0), - ID_HIDDEN(ID_AA64SMFR0_EL1), + ID_WRITABLE(ID_AA64SMFR0_EL1, ~ID_AA64SMFR0_EL1_RES0), ID_UNALLOCATED(4,6), ID_WRITABLE(ID_AA64FPFR0_EL1, ~ID_AA64FPFR0_EL1_RES0),

@@ -3446,7 +3474,11 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CLIDR_EL1), access_clidr, reset_clidr, CLIDR_EL1, .set_user = set_clidr, .val = ~CLIDR_EL1_RES0 }, { SYS_DESC(SYS_CCSIDR2_EL1), undef_access }, - { SYS_DESC(SYS_SMIDR_EL1), undef_access }, + IMPLEMENTATION_ID(SMIDR_EL1, (SMIDR_EL1_NSMC | SMIDR_EL1_HIP | + SMIDR_EL1_AFFINITY2 | + SMIDR_EL1_IMPLEMENTER | + SMIDR_EL1_REVISION | SMIDR_EL1_SH | + SMIDR_EL1_AFFINITY)), IMPLEMENTATION_ID(AIDR_EL1, GENMASK_ULL(63, 0)), { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, ID_FILTERED(CTR_EL0, ctr_el0,

If the guest has SME state we need to context switch that state, provide support for that for normal guests.

SME has three sets of registers, ZA, ZT (only present for SME2) and also streaming SVE which replaces the standard floating point registers when active. The first two are fairly straightforward, they are accessible only when PSTATE.ZA is set and we can reuse the assembly from the host to save and load them from a single contiguous buffer. When PSTATE.ZA is not set then these registers are inaccessible, when the guest enables PSTATE.ZA all bits will be set to 0 by that and nothing is required on restore.

Streaming mode is slightly more complicated, when enabled via PSTATE.SM it provides a version of the SVE registers using the SME vector length and may optionally omit the FFR register. SME may also be present without SVE. The register state is stored in sve_state as for non-streaming SVE mode, we make an initial selection of registers to update based on the guest SVE support and then override this when loading SVCR if streaming mode is enabled.

A further complication is that when the hardware is in streaming mode guest operations that are invalid in in streaming mode will generate SME exceptions. There are also subfeature exceptions for SME2 controlled via SMCR which generate distinct exception codes. In many situations these exceptions are routed directly to the lower ELs with no opportunity for the hypervisor to intercept. So that guests do not see unexpected exception types due to the actual hardware configuration not being what the guest configured we update the SMCRs and SVCR even if the guest does not own the registers.

Since in order to avoid duplication with SME we now restore the register state outside of the SVE specific restore function we need to move the restore of the effective VL for nested guests to a separate restore function run after loading the floating point register state, along with the similar handling required for SME.

The selection of which vector length to use is handled by vcpu_sve_pffr().

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/fpsimd.h | 10 +++ arch/arm64/include/asm/kvm_emulate.h | 6 ++ arch/arm64/include/asm/kvm_host.h | 4 + arch/arm64/kvm/fpsimd.c | 25 ++++-- arch/arm64/kvm/hyp/include/hyp/switch.h | 151 ++++++++++++++++++++++++++++++-- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 80 +++++++++++++++-- 6 files changed, 255 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 8b0840bd7e14..8642efbdcb2b 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -442,6 +442,15 @@ static inline size_t sme_state_size(struct task_struct const *task) write_sysreg_s(__new, (reg)); \ } while (0)

+#define sme_cond_update_smcr_vq(val, reg) \ + do { \ + u64 __smcr = read_sysreg_s((reg)); \ + u64 __new = __smcr & ~SMCR_ELx_LEN_MASK; \ + __new |= (val) & SMCR_ELx_LEN_MASK; \ + if (__smcr != __new) \ + write_sysreg_s(__new, (reg)); \ + } while (0) + #else

static inline void sme_user_disable(void) { BUILD_BUG(); } @@ -471,6 +480,7 @@ static inline size_t sme_state_size(struct task_struct const *task) }

#define sme_cond_update_smcr(val, fa64, zt0, reg) do { } while (0) +#define sme_cond_update_smcr_vq(val, reg) do { } while (0)

#endif /* ! CONFIG_ARM64_SME */

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index c9eab316398e..1b0ebe480e19 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -696,4 +696,10 @@ static inline void vcpu_set_hcrx(struct kvm_vcpu *vcpu) vcpu->arch.hcrx_el2 |= HCRX_EL2_SCTLR2En; } } + +static inline bool guest_hyp_sme_traps_enabled(const struct kvm_vcpu *vcpu) +{ + return __guest_hyp_cptr_xen_trap_enabled(vcpu, SMEN); +} + #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bd7a9a4efbc3..bceaf0608d75 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -736,6 +736,7 @@ struct kvm_host_data {

/* Used by pKVM only. */ u64 fpmr; + u64 smcr_el1;

/* Ownership of the FP regs */ enum { @@ -1131,6 +1132,9 @@ struct kvm_vcpu_arch { #define vcpu_sve_zcr_elx(vcpu) \ (unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1)

+#define vcpu_sme_smcr_elx(vcpu) \ + (unlikely(is_hyp_ctxt(vcpu)) ? SMCR_EL2 : SMCR_EL1) + #define sve_state_size_from_vl(sve_max_vl) ({ \ size_t __size_ret; \ unsigned int __vq; \ diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 1f4fcc8b5554..8fb8c55e50b3 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -69,19 +69,25 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!irqs_disabled());

if (guest_owns_fp_regs()) { - /* - * Currently we do not support SME guests so SVCR is - * always 0 and we just need a variable to point to. - */ fp_state.st = &vcpu->arch.ctxt.fp_regs; fp_state.sve_state = vcpu->arch.sve_state; fp_state.sve_vl = vcpu->arch.max_vl[ARM64_VEC_SVE]; - fp_state.sme_state = NULL; + fp_state.sme_state = vcpu->arch.sme_state; + fp_state.sme_vl = vcpu->arch.max_vl[ARM64_VEC_SME]; fp_state.svcr = __ctxt_sys_reg(&vcpu->arch.ctxt, SVCR); fp_state.fpmr = __ctxt_sys_reg(&vcpu->arch.ctxt, FPMR); fp_state.fp_type = &vcpu->arch.fp_type; + fp_state.sme_features = 0; + if (kvm_has_fa64(vcpu->kvm)) + fp_state.sme_features |= SMCR_ELx_FA64; + if (kvm_has_sme2(vcpu->kvm)) + fp_state.sme_features |= SMCR_ELx_EZT0;

+ /* + * For SME only hosts fpsimd_save() will override the + * state selection if we are in streaming mode. + */ if (vcpu_has_sve(vcpu)) fp_state.to_save = FP_STATE_SVE; else @@ -90,6 +96,15 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) fpsimd_bind_state_to_cpu(&fp_state);

clear_thread_flag(TIF_FOREIGN_FPSTATE); + } else { + /* + * We might have enabled SME to configure traps but + * insist the host doesn't run the hypervisor with SME + * enabled, ensure it's disabled again. + */ + if (system_supports_sme()) { + sme_smstop(); + } } }

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 9ce53524d664..5bcc72ae48ff 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -431,6 +431,22 @@ static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) return true; }

+static inline void __hyp_sme_restore_guest(struct kvm_vcpu *vcpu, + bool *restore_sve, + bool *restore_ffr) +{ + bool has_fa64 = vcpu_has_fa64(vcpu); + bool has_sme2 = vcpu_has_sme2(vcpu); + + if (vcpu_in_streaming_mode(vcpu)) { + *restore_sve = true; + *restore_ffr = has_fa64; + } + + if (vcpu_za_enabled(vcpu)) + __sme_restore_state(vcpu_sme_state(vcpu), has_sme2); +} + static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) { /* @@ -438,19 +454,25 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) * vCPU. Start off with the max VL so we can load the SVE state. */ sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); - __sve_restore_state(vcpu_sve_pffr(vcpu), - &vcpu->arch.ctxt.fp_regs.fpsr, - true);

+ write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR); +} + +static inline void __hyp_nv_restore_guest_vls(struct kvm_vcpu *vcpu) +{ /* * The effective VL for a VM could differ from the max VL when running a * nested guest, as the guest hypervisor could select a smaller VL. Slap * that into hardware before wrapping up. */ - if (is_nested_ctxt(vcpu)) + if (!is_nested_ctxt(vcpu)) + return; + + if (vcpu_has_sve(vcpu)) sve_cond_update_zcr_vq(__vcpu_sys_reg(vcpu, ZCR_EL2), SYS_ZCR_EL2);

- write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR); + if (vcpu_has_sme(vcpu)) + sme_cond_update_smcr_vq(__vcpu_sys_reg(vcpu, SMCR_EL2), SYS_SMCR_EL2); }

static inline void __hyp_sve_save_host(void) @@ -464,10 +486,46 @@ static inline void __hyp_sve_save_host(void) true); }

+static inline void kvm_sme_configure_traps(struct kvm_vcpu *vcpu) +{ + u64 smcr_el1, smcr_el2; + u64 svcr; + + if (!vcpu_has_sme(vcpu)) + return; + + /* A guest hypervisor may restrict the effective max VL. */ + if (is_nested_ctxt(vcpu)) + smcr_el2 = __vcpu_sys_reg(vcpu, SMCR_EL2); + else + smcr_el2 = vcpu_sme_max_vq(vcpu) - 1; + + if (vcpu_has_fa64(vcpu)) + smcr_el2 |= SMCR_ELx_FA64; + if (vcpu_has_sme2(vcpu)) + smcr_el2 |= SMCR_ELx_EZT0; + + write_sysreg_el2(smcr_el2, SYS_SMCR); + + smcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sme_smcr_elx(vcpu)); + write_sysreg_el1(smcr_el1, SYS_SMCR); + + svcr = __vcpu_sys_reg(vcpu, SVCR); + write_sysreg_s(svcr, SYS_SVCR); +} + static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu) { u64 zcr_el1, zcr_el2;

+ /* + * We always load the SME control registers that affect traps + * since if they are not configured as expected by the guest + * then it may have exceptions that it does not expect + * directly delivered. + */ + kvm_sme_configure_traps(vcpu); + if (!guest_owns_fp_regs()) return;

@@ -487,8 +545,51 @@ static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu)

static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu) { + u64 smcr_el1, smcr_el2; u64 zcr_el1, zcr_el2;

+ /* + * We always load the control registers for the guest so we + * always restore state for the host. + */ + if (vcpu_has_sme(vcpu)) { + /* + * __deactivate_cptr_traps() disabled traps, but there + * hasn't necessarily been a context synchronization + * event yet. + */ + isb(); + + smcr_el1 = read_sysreg_el1(SYS_SMCR); + __vcpu_assign_sys_reg(vcpu, vcpu_sme_smcr_elx(vcpu), smcr_el1); + + smcr_el2 = 0; + if (system_supports_fa64()) + smcr_el2 |= SMCR_ELx_FA64; + if (system_supports_sme2()) + smcr_el2 |= SMCR_ELx_EZT0; + + /* + * The guest's state is always saved using the guest's max VL. + * Ensure that the host has the guest's max VL active such that + * the host can save the guest's state lazily, but don't + * artificially restrict the host to the guest's max VL. + */ + if (has_vhe()) { + smcr_el2 |= vcpu_sme_max_vq(vcpu) - 1; + write_sysreg_el2(smcr_el2, SYS_SMCR); + } else { + smcr_el1 = smcr_el2; + smcr_el2 |= sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SME]) - 1; + write_sysreg_el2(smcr_el2, SYS_SMCR); + + smcr_el1 |= vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el1(smcr_el1, SYS_SMCR); + } + + __vcpu_assign_sys_reg(vcpu, SVCR, read_sysreg_s(SYS_SVCR)); + } + if (!guest_owns_fp_regs()) return;

@@ -525,6 +626,16 @@ static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)

static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) { + /* + * The hypervisor refuses to run if streaming mode or ZA is + * enabled, we only need to save SMCR_EL1 for SME. For pKVM + * we will restore this, reset SMCR_EL2 to a fixed value and + * disable streaming mode and ZA to avoid any state being + * leaked. + */ + if (system_supports_sme()) + *host_data_ptr(smcr_el1) = read_sysreg_el1(SYS_SMCR); + /* * Non-protected kvm relies on the host restoring its sve state. * Protected kvm restores the host's sve state as not to reveal that @@ -549,14 +660,17 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) */ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { - bool sve_guest; - u8 esr_ec; + bool restore_sve, restore_ffr; + bool sve_guest, sme_guest; + u8 esr_ec, esr_iss_smtc;

if (!system_supports_fpsimd()) return false;

sve_guest = vcpu_has_sve(vcpu); + sme_guest = vcpu_has_sme(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); + esr_iss_smtc = ESR_ELx_SME_ISS_SMTC((kvm_vcpu_get_esr(vcpu)));

/* Only handle traps the vCPU can support here: */ switch (esr_ec) { @@ -575,6 +689,15 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) if (guest_hyp_sve_traps_enabled(vcpu)) return false; break; + case ESR_ELx_EC_SME: + if (!sme_guest) + return false; + if (guest_hyp_sme_traps_enabled(vcpu)) + return false; + if (!kvm_has_sme2(vcpu->kvm) && + (esr_iss_smtc == ESR_ELx_SME_ISS_SMTC_ZT_DISABLED)) + return false; + break; default: return false; } @@ -590,8 +713,20 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_hyp_save_fpsimd_host(vcpu);

/* Restore the guest state */ + + /* These may be overridden for a SME guest */ + restore_sve = sve_guest; + restore_ffr = sve_guest; + if (sve_guest) __hyp_sve_restore_guest(vcpu); + if (sme_guest) + __hyp_sme_restore_guest(vcpu, &restore_sve, &restore_ffr); + + if (restore_sve) + __sve_restore_state(vcpu_sve_pffr(vcpu), + &vcpu->arch.ctxt.fp_regs.fpsr, + restore_ffr); else __fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs);

@@ -602,6 +737,8 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) if (!(read_sysreg(hcr_el2) & HCR_RW)) write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2);

+ __hyp_nv_restore_guest_vls(vcpu); + *host_data_ptr(fp_owner) = FP_STATE_GUEST_OWNED;

/* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 208e9042aca4..bd48e149764c 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -26,14 +26,17 @@ void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);

static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu) { + bool save_ffr = !vcpu_in_streaming_mode(vcpu) || vcpu_has_fa64(vcpu); + __vcpu_assign_sys_reg(vcpu, ZCR_EL1, read_sysreg_el1(SYS_ZCR)); + /* * On saving/restoring guest sve state, always use the maximum VL for * the guest. The layout of the data when saving the sve state depends * on the VL, so use a consistent (i.e., the maximum) guest VL. */ sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); - __sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true); + __sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, save_ffr); write_sysreg_s(sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SVE]) - 1, SYS_ZCR_EL2); }

@@ -57,9 +60,63 @@ static void __hyp_sve_restore_host(void) write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR); }

-static void fpsimd_sve_flush(void) +static void __hyp_sme_save_guest(struct kvm_vcpu *vcpu) { - *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; + __vcpu_assign_sys_reg(vcpu, SMCR_EL1, read_sysreg_el1(SYS_SMCR)); + __vcpu_assign_sys_reg(vcpu, SVCR, read_sysreg_s(SYS_SVCR)); + + /* + * On saving/restoring guest sve state, always use the maximum VL for + * the guest. The layout of the data when saving the sve state depends + * on the VL, so use a consistent (i.e., the maximum) guest VL. + * + * We restore the FA64 and SME2 enables for the host since we + * will always restore the host configuration so if host and + * guest VLs are the same we might suppress an update. + */ + sme_cond_update_smcr(vcpu_sme_max_vq(vcpu) - 1, system_supports_fa64(), + system_supports_sme2(), SYS_SMCR_EL2); + + if (vcpu_za_enabled(vcpu)) + __sme_save_state(vcpu_sme_state(vcpu), vcpu_has_sme2(vcpu)); +} + +static void __hyp_sme_restore_host(void) +{ + /* + * The hypervisor refuses to run if we are in streaming mode + * or have ZA enabled so there is no SME specific state to + * restore other than the system registers. + * + * Note that this constrains the PE to the maximum shared VL + * that was discovered, if we wish to use larger VLs this will + * need to be revisited. + */ + sme_cond_update_smcr(sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SME]) - 1, + cpus_have_final_cap(ARM64_SME_FA64), + cpus_have_final_cap(ARM64_SME2), SYS_SMCR_EL2); + + write_sysreg_el1(*host_data_ptr(smcr_el1), SYS_SMCR); + + sme_smstop(); +} + +static void fpsimd_sve_flush(struct kvm_vcpu *vcpu) +{ + /* + * If the guest has SME then we need to restore the trap + * controls in SMCR and mode in SVCR in order to ensure that + * traps generated directly to EL1 have the correct types, + * otherwise we can defer until we load the guest state. + */ + if (vcpu_has_sme(vcpu)) { + kvm_hyp_save_fpsimd_host(vcpu); + kvm_sme_configure_traps(vcpu); + + *host_data_ptr(fp_owner) = FP_STATE_FREE; + } else { + *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; + } }

static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) @@ -75,7 +132,10 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) */ isb();

- if (vcpu_has_sve(vcpu)) + if (vcpu_has_sme(vcpu)) + __hyp_sme_save_guest(vcpu); + + if (vcpu_has_sve(vcpu) || vcpu_in_streaming_mode(vcpu)) __hyp_sve_save_guest(vcpu); else __fpsimd_save_state(&vcpu->arch.ctxt.fp_regs); @@ -84,6 +144,9 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (has_fpmr) __vcpu_assign_sys_reg(vcpu, FPMR, read_sysreg_s(SYS_FPMR));

+ if (system_supports_sme()) + __hyp_sme_restore_host(); + if (system_supports_sve()) __hyp_sve_restore_host(); else @@ -121,7 +184,7 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) { struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;

- fpsimd_sve_flush(); + fpsimd_sve_flush(host_vcpu); flush_debug_state(hyp_vcpu);

hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt; @@ -204,10 +267,9 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu();

/* - * KVM (and pKVM) doesn't support SME guests for now, and - * ensures that SME features aren't enabled in pstate when - * loading a vcpu. Therefore, if SME features enabled the host - * is misbehaving. + * KVM (and pKVM) refuses to run if PSTATE.{SM,ZA} are + * enabled. Therefore, if SME features enabled the + * host is misbehaving. */ if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) { ret = -EINVAL;

SME adds a second vector length configured in a very similar way to the SVE vector length, in order to facilitate future code sharing for SME refactor our storage of vector lengths to use an array like the host does. We do not yet take much advantage of this so the intermediate code is not as clean as might be.

No functional change.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 17 +++++++++++------ arch/arm64/include/asm/kvm_hyp.h | 2 +- arch/arm64/include/asm/kvm_pkvm.h | 2 +- arch/arm64/kvm/fpsimd.c | 2 +- arch/arm64/kvm/guest.c | 6 +++--- arch/arm64/kvm/hyp/include/hyp/switch.h | 6 +++--- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 6 +++--- arch/arm64/kvm/hyp/nvhe/pkvm.c | 7 ++++--- arch/arm64/kvm/reset.c | 22 +++++++++++----------- 9 files changed, 38 insertions(+), 32 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0816180dc551..3a3330b2a6a9 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -77,8 +77,10 @@ enum kvm_mode kvm_get_mode(void); static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; #endif

-extern unsigned int __ro_after_init kvm_sve_max_vl; -extern unsigned int __ro_after_init kvm_host_sve_max_vl; +extern unsigned int __ro_after_init kvm_max_vl[ARM64_VEC_MAX]; +extern unsigned int __ro_after_init kvm_host_max_vl[ARM64_VEC_MAX]; +DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); + int __init kvm_arm_init_sve(void);

u32 __attribute_const__ kvm_target_cpu(void); @@ -811,7 +813,7 @@ struct kvm_vcpu_arch { */ void *sve_state; enum fp_type fp_type; - unsigned int sve_max_vl; + unsigned int max_vl[ARM64_VEC_MAX];

/* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; @@ -1098,9 +1100,12 @@ struct kvm_vcpu_arch {

/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) + \ - sve_ffr_offset((vcpu)->arch.sve_max_vl)) + sve_ffr_offset((vcpu)->arch.max_vl[ARM64_VEC_SVE])) + +#define vcpu_vec_max_vq(vcpu, type) sve_vq_from_vl((vcpu)->arch.max_vl[type]) + +#define vcpu_sve_max_vq(vcpu) vcpu_vec_max_vq(vcpu, ARM64_VEC_SVE)

-#define vcpu_sve_max_vq(vcpu) sve_vq_from_vl((vcpu)->arch.sve_max_vl)

#define vcpu_sve_zcr_elx(vcpu) \ (unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1) @@ -1119,7 +1124,7 @@ struct kvm_vcpu_arch { __size_ret; \ })

-#define vcpu_sve_state_size(vcpu) sve_state_size_from_vl((vcpu)->arch.sve_max_vl) +#define vcpu_sve_state_size(vcpu) sve_state_size_from_vl((vcpu)->arch.max_vl[ARM64_VEC_SVE])

/* * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 76ce2b94bd97..0317790dd3b7 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -146,6 +146,6 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val);

extern unsigned long kvm_nvhe_sym(__icache_flags); extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits); -extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl); +extern unsigned int kvm_nvhe_sym(kvm_host_max_vl[ARM64_VEC_MAX]);

#endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h index 0aecd4ac5f45..0697c88f2210 100644 --- a/arch/arm64/include/asm/kvm_pkvm.h +++ b/arch/arm64/include/asm/kvm_pkvm.h @@ -167,7 +167,7 @@ static inline size_t pkvm_host_sve_state_size(void) return 0;

return size_add(sizeof(struct cpu_sve_state), - SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl))); + SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SVE]))); }

struct pkvm_mapping { diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 9158353d8be3..1f4fcc8b5554 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -75,7 +75,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) */ fp_state.st = &vcpu->arch.ctxt.fp_regs; fp_state.sve_state = vcpu->arch.sve_state; - fp_state.sve_vl = vcpu->arch.sve_max_vl; + fp_state.sve_vl = vcpu->arch.max_vl[ARM64_VEC_SVE]; fp_state.sme_state = NULL; fp_state.svcr = __ctxt_sys_reg(&vcpu->arch.ctxt, SVCR); fp_state.fpmr = __ctxt_sys_reg(&vcpu->arch.ctxt, FPMR); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 8c3405b5d7b1..456ef61b6ed5 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -318,7 +318,7 @@ static int get_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (!vcpu_has_sve(vcpu)) return -ENOENT;

- if (WARN_ON(!sve_vl_valid(vcpu->arch.sve_max_vl))) + if (WARN_ON(!sve_vl_valid(vcpu->arch.max_vl[ARM64_VEC_SVE]))) return -EINVAL;

memset(vqs, 0, sizeof(vqs)); @@ -356,7 +356,7 @@ static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (vq_present(vqs, vq)) max_vq = vq;

- if (max_vq > sve_vq_from_vl(kvm_sve_max_vl)) + if (max_vq > sve_vq_from_vl(kvm_max_vl[ARM64_VEC_SVE])) return -EINVAL;

/* @@ -375,7 +375,7 @@ static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) return -EINVAL;

/* vcpu->arch.sve_state will be alloc'd by kvm_vcpu_finalize_sve() */ - vcpu->arch.sve_max_vl = sve_vl_from_vq(max_vq); + vcpu->arch.max_vl[ARM64_VEC_SVE] = sve_vl_from_vq(max_vq);

return 0; } diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index c5d5e5b86eaf..9ce53524d664 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -458,8 +458,8 @@ static inline void __hyp_sve_save_host(void) struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);

sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR); - write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); - __sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl), + write_sysreg_s(sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SVE]) - 1, SYS_ZCR_EL2); + __sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_max_vl[ARM64_VEC_SVE]), &sve_state->fpsr, true); } @@ -514,7 +514,7 @@ static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu) zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; write_sysreg_el2(zcr_el2, SYS_ZCR); } else { - zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1; + zcr_el2 = sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SVE]) - 1; write_sysreg_el2(zcr_el2, SYS_ZCR);

zcr_el1 = vcpu_sve_max_vq(vcpu) - 1; diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index a7c689152f68..208e9042aca4 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -34,7 +34,7 @@ static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu) */ sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); __sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true); - write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); + write_sysreg_s(sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SVE]) - 1, SYS_ZCR_EL2); }

static void __hyp_sve_restore_host(void) @@ -50,8 +50,8 @@ static void __hyp_sve_restore_host(void) * that was discovered, if we wish to use larger VLs this will * need to be revisited. */ - write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); - __sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl), + write_sysreg_s(sve_vq_from_vl(kvm_host_max_vl[ARM64_VEC_SVE]) - 1, SYS_ZCR_EL2); + __sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_max_vl[ARM64_VEC_SVE]), &sve_state->fpsr, true); write_sysreg_el1(sve_state->zcr_el1, SYS_ZCR); diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index b402dcb7691e..f4ec6695a6a5 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -20,7 +20,7 @@ unsigned long __icache_flags; /* Used by kvm_get_vttbr(). */ unsigned int kvm_arm_vmid_bits;

-unsigned int kvm_host_sve_max_vl; +unsigned int kvm_host_max_vl[ARM64_VEC_MAX];

/* * The currently loaded hyp vCPU for each physical CPU. Used in protected mode @@ -450,7 +450,8 @@ static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *h }

/* Limit guest vector length to the maximum supported by the host. */ - sve_max_vl = min(READ_ONCE(host_vcpu->arch.sve_max_vl), kvm_host_sve_max_vl); + sve_max_vl = min(READ_ONCE(host_vcpu->arch.max_vl[ARM64_VEC_SVE]), + kvm_host_max_vl[ARM64_VEC_SVE]); sve_state_size = sve_state_size_from_vl(sve_max_vl); sve_state = kern_hyp_va(READ_ONCE(host_vcpu->arch.sve_state));

@@ -464,7 +465,7 @@ static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *h goto err;

vcpu->arch.sve_state = sve_state; - vcpu->arch.sve_max_vl = sve_max_vl; + vcpu->arch.max_vl[ARM64_VEC_SVE] = sve_max_vl;

return 0; err: diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index f7c63e145d54..a8684a1346ec 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -32,7 +32,7 @@

/* Maximum phys_shift supported for any VM on this host */ static u32 __ro_after_init kvm_ipa_limit; -unsigned int __ro_after_init kvm_host_sve_max_vl; +unsigned int __ro_after_init kvm_host_max_vl[ARM64_VEC_MAX];

/* * ARMv8 Reset Values @@ -46,14 +46,14 @@ unsigned int __ro_after_init kvm_host_sve_max_vl; #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT)

-unsigned int __ro_after_init kvm_sve_max_vl; +unsigned int __ro_after_init kvm_max_vl[ARM64_VEC_MAX];

int __init kvm_arm_init_sve(void) { if (system_supports_sve()) { - kvm_sve_max_vl = sve_max_virtualisable_vl(); - kvm_host_sve_max_vl = sve_max_vl(); - kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl; + kvm_max_vl[ARM64_VEC_SVE] = sve_max_virtualisable_vl(); + kvm_host_max_vl[ARM64_VEC_SVE] = sve_max_vl(); + kvm_nvhe_sym(kvm_host_max_vl[ARM64_VEC_SVE]) = kvm_host_max_vl[ARM64_VEC_SVE];

/* * The get_sve_reg()/set_sve_reg() ioctl interface will need @@ -61,16 +61,16 @@ int __init kvm_arm_init_sve(void) * order to support vector lengths greater than * VL_ARCH_MAX: */ - if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX)) - kvm_sve_max_vl = VL_ARCH_MAX; + if (WARN_ON(kvm_max_vl[ARM64_VEC_SVE] > VL_ARCH_MAX)) + kvm_max_vl[ARM64_VEC_SVE] = VL_ARCH_MAX;

/* * Don't even try to make use of vector lengths that * aren't available on all CPUs, for now: */ - if (kvm_sve_max_vl < sve_max_vl()) + if (kvm_max_vl[ARM64_VEC_SVE] < sve_max_vl()) pr_warn("KVM: SVE vector length for guests limited to %u bytes\n", - kvm_sve_max_vl); + kvm_max_vl[ARM64_VEC_SVE]); }

return 0; @@ -78,7 +78,7 @@ int __init kvm_arm_init_sve(void)

static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) { - vcpu->arch.sve_max_vl = kvm_sve_max_vl; + vcpu->arch.max_vl[ARM64_VEC_SVE] = kvm_max_vl[ARM64_VEC_SVE];

/* * Userspace can still customize the vector lengths by writing @@ -99,7 +99,7 @@ static int kvm_vcpu_finalize_vec(struct kvm_vcpu *vcpu) size_t reg_sz; int ret;

- vl = vcpu->arch.sve_max_vl; + vl = vcpu->arch.max_vl[ARM64_VEC_SVE];

/* * Responsibility for these properties is shared between

Writes to the physical SVCR.SM and SVCR.ZA change the state of PSTATE.SM and PSTATE.ZA, causing other floating point state to reset. Emulate this behaviour for writes done via the KVM userspace ABI.

Setting PSTATE.ZA to 1 causes ZA and ZT0 to be reset to 0, these are stored in sme_state. Setting PSTATE.ZA to 0 causes ZA and ZT0 to become inaccesible so no reset is needed.

Any change in PSTATE.SM causes the V, Z, P, FFR and FPMR registers to be reset to 0 and FPSR to be reset to 0x800009f.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 24 ++++++++++++++++++++++++ arch/arm64/kvm/sys_regs.c | 29 ++++++++++++++++++++++++++++- 2 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 44595a789a97..bd7a9a4efbc3 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1147,6 +1147,30 @@ struct kvm_vcpu_arch {

#define vcpu_sve_state_size(vcpu) sve_state_size_from_vl((vcpu)->arch.max_vl[ARM64_VEC_SVE])

+#define vcpu_sme_state(vcpu) (kern_hyp_va((vcpu)->arch.sme_state)) + +#define sme_state_size_from_vl(vl, sme2) ({ \ + size_t __size_ret; \ + unsigned int __vq; \ + \ + if (WARN_ON(!sve_vl_valid(vl))) { \ + __size_ret = 0; \ + } else { \ + __vq = sve_vq_from_vl(vl); \ + __size_ret = ZA_SIG_REGS_SIZE(__vq); \ + if (sme2) \ + __size_ret += ZT_SIG_REG_SIZE; \ + } \ + \ + __size_ret; \ +}) + +#define vcpu_sme_state_size(vcpu) ({ \ + unsigned long __vl; \ + __vl = (vcpu)->arch.max_vl[ARM64_VEC_SME]; \ + sme_state_size_from_vl(__vl, vcpu_has_sme2(vcpu)); \ +}) + /* * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the * memory backed version of a register, and not the one most recently diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 51f175bbe8d1..4ecfcb0af24c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -927,6 +927,33 @@ static unsigned int hidden_visibility(const struct kvm_vcpu *vcpu, return REG_HIDDEN; }

+static int set_svcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + u64 val) +{ + u64 old = __vcpu_sys_reg(vcpu, rd->reg); + + if (val & SVCR_RES0) + return -EINVAL; + + if ((val & SVCR_ZA) && !(old & SVCR_ZA) && vcpu->arch.sme_state) + memset(vcpu->arch.sme_state, 0, vcpu_sme_state_size(vcpu)); + + if ((val & SVCR_SM) != (old & SVCR_SM)) { + memset(vcpu->arch.ctxt.fp_regs.vregs, 0, + sizeof(vcpu->arch.ctxt.fp_regs.vregs)); + + if (vcpu->arch.sve_state) + memset(vcpu->arch.sve_state, 0, + vcpu_sve_state_size(vcpu)); + + __vcpu_assign_sys_reg(vcpu, FPMR, 0); + vcpu->arch.ctxt.fp_regs.fpsr = 0x800009f; + } + + __vcpu_assign_sys_reg(vcpu, rd->reg, val); + return 0; +} + static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { @@ -3512,7 +3539,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { CTR_EL0_DminLine_MASK | CTR_EL0_L1Ip_MASK | CTR_EL0_IminLine_MASK), - { SYS_DESC(SYS_SVCR), undef_access, reset_val, SVCR, 0, .visibility = sme_visibility }, + { SYS_DESC(SYS_SVCR), undef_access, reset_val, SVCR, 0, .visibility = sme_visibility, .set_user = set_svcr }, { SYS_DESC(SYS_FPMR), undef_access, reset_val, FPMR, 0, .visibility = fp8_visibility },

{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr,

SME adds a number of new system registers, update get-reg-list to check for them based on the visibility of SME.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/kvm/arm64/get-reg-list.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/arm64/get-reg-list.c b/tools/testing/selftests/kvm/arm64/get-reg-list.c index 0a3a94c4cca1..876c4719e2e2 100644 --- a/tools/testing/selftests/kvm/arm64/get-reg-list.c +++ b/tools/testing/selftests/kvm/arm64/get-reg-list.c @@ -61,7 +61,13 @@ static struct feature_id_reg feat_id_regs[] = { REG_FEAT(HFGITR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), REG_FEAT(HDFGRTR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), REG_FEAT(HDFGWTR2_EL2, ID_AA64MMFR0_EL1, FGT, FGT2), - REG_FEAT(ZCR_EL2, ID_AA64PFR0_EL1, SVE, IMP), + REG_FEAT(SMCR_EL1, ID_AA64PFR1_EL1, SME, IMP), + REG_FEAT(SMCR_EL2, ID_AA64PFR1_EL1, SME, IMP), + REG_FEAT(SMIDR_EL1, ID_AA64PFR1_EL1, SME, IMP), + REG_FEAT(SMPRI_EL1, ID_AA64PFR1_EL1, SME, IMP), + REG_FEAT(SMPRIMAP_EL2, ID_AA64PFR1_EL1, SME, IMP), + REG_FEAT(TPIDR2_EL0, ID_AA64PFR1_EL1, SME, IMP), + REG_FEAT(SVCR, ID_AA64PFR1_EL1, SME, IMP), REG_FEAT(SCTLR2_EL1, ID_AA64MMFR3_EL1, SCTLRX, IMP), REG_FEAT(SCTLR2_EL2, ID_AA64MMFR3_EL1, SCTLRX, IMP), REG_FEAT(VDISR_EL2, ID_AA64PFR0_EL1, RAS, IMP), @@ -367,6 +373,7 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */ ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */ ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 6), /* SMIDR_EL1 */ ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */ ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */ ARM64_SYS_REG(2, 0, 0, 0, 4), @@ -498,6 +505,8 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */ ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */ KVM_ARM64_SYS_REG(SYS_SCTLR2_EL1), + ARM64_SYS_REG(3, 0, 1, 2, 4), /* SMPRI_EL1 */ + ARM64_SYS_REG(3, 0, 1, 2, 6), /* SMCR_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ @@ -518,9 +527,11 @@ static __u64 base_regs[] = { ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */ ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */ ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ + ARM64_SYS_REG(3, 3, 4, 2, 2), /* SVCR */ ARM64_SYS_REG(3, 3, 10, 2, 4), /* POR_EL0 */ ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 5), /* TPIDR2_EL0 */ ARM64_SYS_REG(3, 3, 14, 0, 1), /* CNTPCT_EL0 */ ARM64_SYS_REG(3, 3, 14, 2, 1), /* CNTP_CTL_EL0 */ ARM64_SYS_REG(3, 3, 14, 2, 2), /* CNTP_CVAL_EL0 */ @@ -730,6 +741,8 @@ static __u64 el2_regs[] = { SYS_REG(HFGITR_EL2), SYS_REG(HACR_EL2), SYS_REG(ZCR_EL2), + SYS_REG(SMPRIMAP_EL2), + SYS_REG(SMCR_EL2), SYS_REG(HCRX_EL2), SYS_REG(TTBR0_EL2), SYS_REG(TTBR1_EL2),

The set_id_regs test currently assumes that there will always be invalid values available in bitfields for it to generate but this may not be the case if the architecture has defined meanings for every possible value for the bitfield. An assert added in commit bf09ee918053e ("KVM: arm64: selftests: Remove ARM64_FEATURE_FIELD_BITS and its last user") refuses to run for single bit fields which will show the issue most readily but there is no reason wider ones can't show the same issue.

Rework the tests for invalid value to check if an invalid value can be generated and skip the test if not, removing the assert.

Signed-off-by: Mark Brown broonie@kernel.org --- tools/testing/selftests/kvm/arm64/set_id_regs.c | 58 ++++++++++++++++++++----- 1 file changed, 46 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 322cd13b9352..641194c5005a 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -318,11 +318,12 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) }

/* Return an invalid value to a given ftr_bits an ftr value */ -uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) +uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr, + bool *skip) { uint64_t ftr_max = ftr_bits->mask >> ftr_bits->shift;

- TEST_ASSERT(ftr_max > 1, "This test doesn't support single bit features"); + *skip = false;

if (ftr_bits->sign == FTR_UNSIGNED) { switch (ftr_bits->type) { @@ -330,42 +331,72 @@ uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr) ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1); break; case FTR_LOWER_SAFE: + if (ftr == ftr_max) + *skip = true; ftr++; break; case FTR_HIGHER_SAFE: + if (ftr == 0) + *skip = true; ftr--; break; case FTR_HIGHER_OR_ZERO_SAFE: - if (ftr == 0) + switch (ftr) { + case 0: ftr = ftr_max; - else + break; + case 1: + *skip = true; + break; + default: ftr--; - break; + break; + } default: + *skip = true; break; } } else if (ftr != ftr_max) { switch (ftr_bits->type) { case FTR_EXACT: ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1); + if (ftr > ftr_max) + *skip = true; break; case FTR_LOWER_SAFE: - ftr++; + if (ftr == ftr_max) + *skip = true; + else + ftr++; break; case FTR_HIGHER_SAFE: - ftr--; - break; - case FTR_HIGHER_OR_ZERO_SAFE: if (ftr == 0) - ftr = ftr_max - 1; + *skip = true; else ftr--; break; + case FTR_HIGHER_OR_ZERO_SAFE: + switch (ftr) { + case 0: + if (ftr_max > 1) + ftr = ftr_max - 1; + else + *skip = true; + break; + case 1: + *skip = true; + break; + default: + ftr--; + break; + break; + } default: + *skip = true; break; } } else { - ftr = 0; + *skip = true; }

return ftr; @@ -400,12 +431,15 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, uint8_t shift = ftr_bits->shift; uint64_t mask = ftr_bits->mask; uint64_t val, old_val, ftr; + bool skip; int r;

val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift;

- ftr = get_invalid_value(ftr_bits, ftr); + ftr = get_invalid_value(ftr_bits, ftr, &skip); + if (skip) + return;

old_val = val; ftr <<= shift;

Since SME requires configuration of a vector length in order to know the size of both the streaming mode SVE state and ZA array we implement a capability for it and require that it be enabled and finalized before the SME specific state can be accessed, similarly to SVE.

Due to the overlap with sizing the SVE state we finalise both SVE and SME with a single finalization, preventing any further changes to the SVE and SME configuration once KVM_ARM_VCPU_VEC (an alias for _VCPU_SVE) has been finalised. This is not a thing of great elegance but it ensures that we never have a state where one of SVE or SME is finalised and the other not, avoiding complexity.

SME is supported for normal and protected guests.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 12 +++- arch/arm64/include/uapi/asm/kvm.h | 1 + arch/arm64/kvm/arm.c | 10 ++++ arch/arm64/kvm/hyp/nvhe/pkvm.c | 76 +++++++++++++++++++----- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 6 ++ arch/arm64/kvm/reset.c | 116 +++++++++++++++++++++++++++++++------ include/uapi/linux/kvm.h | 1 + 7 files changed, 189 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index bceaf0608d75..011debfc1afd 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -39,7 +39,7 @@

#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS

-#define KVM_VCPU_MAX_FEATURES 9 +#define KVM_VCPU_MAX_FEATURES 10 #define KVM_VCPU_VALID_FEATURES (BIT(KVM_VCPU_MAX_FEATURES) - 1)

#define KVM_REQ_SLEEP \ @@ -82,6 +82,7 @@ extern unsigned int __ro_after_init kvm_host_max_vl[ARM64_VEC_MAX]; DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);

int __init kvm_arm_init_sve(void); +int __init kvm_arm_init_sme(void);

u32 __attribute_const__ kvm_target_cpu(void); void kvm_reset_vcpu(struct kvm_vcpu *vcpu); @@ -1149,7 +1150,14 @@ struct kvm_vcpu_arch { __size_ret; \ })

-#define vcpu_sve_state_size(vcpu) sve_state_size_from_vl((vcpu)->arch.max_vl[ARM64_VEC_SVE]) +#define vcpu_sve_state_size(vcpu) ({ \ + unsigned int __max_vl; \ + \ + __max_vl = max((vcpu)->arch.max_vl[ARM64_VEC_SVE], \ + (vcpu)->arch.max_vl[ARM64_VEC_SME]); \ + \ + sve_state_size_from_vl(__max_vl); \ +})

#define vcpu_sme_state(vcpu) (kern_hyp_va((vcpu)->arch.sme_state))

diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 9a19cc58d227..b4be424e4230 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -106,6 +106,7 @@ struct kvm_regs { #define KVM_ARM_VCPU_PTRAUTH_GENERIC 6 /* VCPU uses generic authentication */ #define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */ #define KVM_ARM_VCPU_HAS_EL2_E2H0 8 /* Limit NV support to E2H RES0 */ +#define KVM_ARM_VCPU_SME 9 /* enable SME for this CPU */

/* * An alias for _SVE since we finalize VL configuration for both SVE and SME diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 4f80da0c0d1d..7de7b497f74f 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -402,6 +402,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_SVE: r = system_supports_sve(); break; + case KVM_CAP_ARM_SME: + r = system_supports_sme(); + break; case KVM_CAP_ARM_PTRAUTH_ADDRESS: case KVM_CAP_ARM_PTRAUTH_GENERIC: r = kvm_has_full_ptr_auth(); @@ -1456,6 +1459,9 @@ static unsigned long system_supported_vcpu_features(void) if (!system_supports_sve()) clear_bit(KVM_ARM_VCPU_SVE, &features);

+ if (!system_supports_sme()) + clear_bit(KVM_ARM_VCPU_SME, &features); + if (!kvm_has_full_ptr_auth()) { clear_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features); clear_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features); @@ -2878,6 +2884,10 @@ static __init int kvm_arm_init(void) if (err) return err;

+ err = kvm_arm_init_sme(); + if (err) + return err; + err = kvm_arm_vmid_alloc_init(); if (err) { kvm_err("Failed to initialize VMID allocator.\n"); diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index b656449dff69..30ee9f371b0d 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -148,10 +148,6 @@ static int pkvm_check_pvm_cpu_features(struct kvm_vcpu *vcpu) !kvm_has_feat(kvm, ID_AA64PFR0_EL1, AdvSIMD, IMP)) return -EINVAL;

- /* No SME support in KVM right now. Check to catch if it changes. */ - if (kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP)) - return -EINVAL; - return 0; }

@@ -377,6 +373,11 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_GUEST_HAS_SVE); }

+ if (kvm_pvm_ext_allowed(KVM_CAP_ARM_SME)) { + set_bit(KVM_ARM_VCPU_SME, allowed_features); + kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_GUEST_HAS_SME); + } + bitmap_and(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features, allowed_features, KVM_VCPU_MAX_FEATURES); } @@ -399,6 +400,18 @@ static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu) sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu)); }

+static void unpin_host_sme_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + void *sme_state; + + if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SME)) + return; + + sme_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sme_state); + hyp_unpin_shared_mem(sme_state, + sme_state + vcpu_sme_state_size(&hyp_vcpu->vcpu)); +} + static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[], unsigned int nr_vcpus) { @@ -412,6 +425,7 @@ static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[],

unpin_host_vcpu(hyp_vcpu->host_vcpu); unpin_host_sve_state(hyp_vcpu); + unpin_host_sme_state(hyp_vcpu); } }

@@ -438,23 +452,35 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm, mmu->pgt = &hyp_vm->pgt; }

-static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu) +static int pkvm_vcpu_init_vec(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu) { struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu; - unsigned int sve_max_vl; - size_t sve_state_size; - void *sve_state; + unsigned int sve_max_vl, sme_max_vl; + size_t sve_state_size, sme_state_size; + void *sve_state, *sme_state; int ret = 0;

- if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { + if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE) && + !vcpu_has_feature(vcpu, KVM_ARM_VCPU_SME)) { vcpu_clear_flag(vcpu, VCPU_VEC_FINALIZED); return 0; }

/* Limit guest vector length to the maximum supported by the host. */ - sve_max_vl = min(READ_ONCE(host_vcpu->arch.max_vl[ARM64_VEC_SVE]), - kvm_host_max_vl[ARM64_VEC_SVE]); - sve_state_size = sve_state_size_from_vl(sve_max_vl); + if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) + sve_max_vl = min(READ_ONCE(host_vcpu->arch.max_vl[ARM64_VEC_SVE]), + kvm_host_max_vl[ARM64_VEC_SVE]); + else + sve_max_vl = 0; + + if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SME)) + sme_max_vl = min(READ_ONCE(host_vcpu->arch.max_vl[ARM64_VEC_SME]), + kvm_host_max_vl[ARM64_VEC_SME]); + else + sme_max_vl = 0; + + /* We need SVE storage for the larger of normal or streaming mode */ + sve_state_size = sve_state_size_from_vl(max(sve_max_vl, sme_max_vl)); sve_state = kern_hyp_va(READ_ONCE(host_vcpu->arch.sve_state));

if (!sve_state || !sve_state_size) { @@ -466,12 +492,36 @@ static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *h if (ret) goto err;

+ if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SME)) { + sme_state_size = sme_state_size_from_vl(sme_max_vl, + vcpu_has_sme2(vcpu)); + sme_state = kern_hyp_va(READ_ONCE(host_vcpu->arch.sme_state)); + + if (!sme_state || !sme_state_size) { + ret = -EINVAL; + goto err_sve_mapped; + } + + ret = hyp_pin_shared_mem(sme_state, sme_state + sme_state_size); + if (ret) + goto err_sve_mapped; + } else { + sme_state = 0; + } + vcpu->arch.sve_state = sve_state; vcpu->arch.max_vl[ARM64_VEC_SVE] = sve_max_vl;

+ vcpu->arch.sme_state = sme_state; + vcpu->arch.max_vl[ARM64_VEC_SME] = sme_max_vl; + return 0; + +err_sve_mapped: + hyp_unpin_shared_mem(sve_state, sve_state + sve_state_size); err: clear_bit(KVM_ARM_VCPU_SVE, vcpu->kvm->arch.vcpu_features); + clear_bit(KVM_ARM_VCPU_SME, vcpu->kvm->arch.vcpu_features); return ret; }

@@ -501,7 +551,7 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, if (ret) goto done;

- ret = pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu); + ret = pkvm_vcpu_init_vec(hyp_vcpu, host_vcpu); done: if (ret) unpin_host_vcpu(host_vcpu); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 3108b5185c20..40127ba86335 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -66,6 +66,11 @@ static bool vm_has_ptrauth(const struct kvm *kvm) kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC); }

+static bool vm_has_sme(const struct kvm *kvm) +{ + return system_supports_sme() && kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_SME); +} + static bool vm_has_sve(const struct kvm *kvm) { return system_supports_sve() && kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_SVE); @@ -102,6 +107,7 @@ static const struct pvm_ftr_bits pvmid_aa64pfr0[] = { };

static const struct pvm_ftr_bits pvmid_aa64pfr1[] = { + MAX_FEAT_FUNC(ID_AA64PFR1_EL1, SME, SME2, vm_has_sme), MAX_FEAT(ID_AA64PFR1_EL1, BT, IMP), MAX_FEAT(ID_AA64PFR1_EL1, SSBS, SSBS2), MAX_FEAT_ENUM(ID_AA64PFR1_EL1, MTE_frac, NI), diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index a8684a1346ec..e6dc04267cbb 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -76,6 +76,34 @@ int __init kvm_arm_init_sve(void) return 0; }

+int __init kvm_arm_init_sme(void) +{ + if (system_supports_sme()) { + kvm_max_vl[ARM64_VEC_SME] = sme_max_virtualisable_vl(); + kvm_host_max_vl[ARM64_VEC_SME] = sme_max_vl(); + kvm_nvhe_sym(kvm_host_max_vl[ARM64_VEC_SME]) = kvm_host_max_vl[ARM64_VEC_SME]; + + /* + * The get_sve_reg()/set_sve_reg() ioctl interface will need + * to be extended with multiple register slice support in + * order to support vector lengths greater than + * VL_ARCH_MAX: + */ + if (WARN_ON(kvm_max_vl[ARM64_VEC_SME] > VL_ARCH_MAX)) + kvm_max_vl[ARM64_VEC_SME] = VL_ARCH_MAX; + + /* + * Don't even try to make use of vector lengths that + * aren't available on all CPUs, for now: + */ + if (kvm_max_vl[ARM64_VEC_SME] < sme_max_vl()) + pr_warn("KVM: SME vector length for guests limited to %u bytes\n", + kvm_max_vl[ARM64_VEC_SME]); + } + + return 0; +} + static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) { vcpu->arch.max_vl[ARM64_VEC_SVE] = kvm_max_vl[ARM64_VEC_SVE]; @@ -88,42 +116,86 @@ static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) set_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &vcpu->kvm->arch.flags); }

+static void kvm_vcpu_enable_sme(struct kvm_vcpu *vcpu) +{ + vcpu->arch.max_vl[ARM64_VEC_SME] = kvm_max_vl[ARM64_VEC_SME]; + + /* + * Userspace can still customize the vector lengths by writing + * KVM_REG_ARM64_SME_VLS. Allocation is deferred until + * kvm_arm_vcpu_finalize(), which freezes the configuration. + */ + set_bit(KVM_ARCH_FLAG_GUEST_HAS_SME, &vcpu->kvm->arch.flags); +} + /* - * Finalize vcpu's maximum SVE vector length, allocating - * vcpu->arch.sve_state as necessary. + * Finalize vcpu's maximum vector lengths, allocating + * vcpu->arch.sve_state and vcpu->arch.sme_state as necessary. */ static int kvm_vcpu_finalize_vec(struct kvm_vcpu *vcpu) { - void *buf; + void *sve_state, *sme_state; unsigned int vl; - size_t reg_sz; int ret;

- vl = vcpu->arch.max_vl[ARM64_VEC_SVE]; - /* * Responsibility for these properties is shared between * kvm_arm_init_sve(), kvm_vcpu_enable_sve() and * set_sve_vls(). Double-check here just to be sure: */ - if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() || - vl > VL_ARCH_MAX)) - return -EIO; + if (vcpu_has_sve(vcpu)) { + vl = vcpu->arch.max_vl[ARM64_VEC_SVE]; + if (WARN_ON(!sve_vl_valid(vl) || + vl > sve_max_virtualisable_vl() || + vl > VL_ARCH_MAX)) + return -EIO; + }

- reg_sz = vcpu_sve_state_size(vcpu); - buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT); - if (!buf) + /* Similarly for SME */ + if (vcpu_has_sme(vcpu)) { + vl = vcpu->arch.max_vl[ARM64_VEC_SME]; + if (WARN_ON(!sve_vl_valid(vl) || + vl > sme_max_virtualisable_vl() || + vl > VL_ARCH_MAX)) + return -EIO; + } + + sve_state = kzalloc(vcpu_sve_state_size(vcpu), GFP_KERNEL_ACCOUNT); + if (!sve_state) return -ENOMEM;

- ret = kvm_share_hyp(buf, buf + reg_sz); - if (ret) { - kfree(buf); - return ret; + ret = kvm_share_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); + if (ret) + goto err_sve_alloc; + + if (vcpu_has_sme(vcpu)) { + sme_state = kzalloc(vcpu_sme_state_size(vcpu), + GFP_KERNEL_ACCOUNT); + if (!sme_state) { + ret = -ENOMEM; + goto err_sve_map; + } + + ret = kvm_share_hyp(sme_state, + sme_state + vcpu_sme_state_size(vcpu)); + if (ret) + goto err_sme_alloc; + } else { + sme_state = NULL; } - - vcpu->arch.sve_state = buf; + + vcpu->arch.sve_state = sve_state; + vcpu->arch.sme_state = sme_state; vcpu_set_flag(vcpu, VCPU_VEC_FINALIZED); return 0; + +err_sme_alloc: + kfree(sme_state); +err_sve_map: + kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); +err_sve_alloc: + kfree(sve_state); + return ret; }

int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature) @@ -153,12 +225,16 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) { void *sve_state = vcpu->arch.sve_state; + void *sme_state = vcpu->arch.sme_state;

kvm_unshare_hyp(vcpu, vcpu + 1); if (sve_state) kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); kfree(sve_state); free_page((unsigned long)vcpu->arch.ctxt.vncr_array); + if (sme_state) + kvm_unshare_hyp(sme_state, sme_state + vcpu_sme_state_size(vcpu)); + kfree(sme_state); kfree(vcpu->arch.vncr_tlb); kfree(vcpu->arch.ccsidr); } @@ -167,6 +243,8 @@ static void kvm_vcpu_reset_vec(struct kvm_vcpu *vcpu) { if (vcpu_has_sve(vcpu)) memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu)); + if (vcpu_has_sme(vcpu)) + memset(vcpu->arch.sme_state, 0, vcpu_sme_state_size(vcpu)); }

/** @@ -206,6 +284,8 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (!kvm_arm_vcpu_vec_finalized(vcpu)) { if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) kvm_vcpu_enable_sve(vcpu); + if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SME)) + kvm_vcpu_enable_sme(vcpu); } else { kvm_vcpu_reset_vec(vcpu); } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dddb781b0507..d9e068db3b73 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -974,6 +974,7 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD_FLAGS 244 #define KVM_CAP_ARM_SEA_TO_USER 245 #define KVM_CAP_S390_USER_OPEREXEC 246 +#define KVM_CAP_ARM_SME 247

struct kvm_irq_routing_irqchip { __u32 irqchip;

SME is configured by the system registers SMCR_EL1 and SMCR_EL2, add definitions and userspace access for them. These control the SME vector length in a manner similar to that for SVE and also have feature enable bits for SME2 and FA64. A subsequent patch will add management of them for guests as part of the general floating point context switch, as is done for the equivalent SVE registers.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 2 ++ arch/arm64/include/asm/vncr_mapping.h | 1 + arch/arm64/kvm/sys_regs.c | 36 ++++++++++++++++++++++++++++++++++- 3 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b41700df3ce9..f24441244a68 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -504,6 +504,7 @@ enum vcpu_sysreg { CPTR_EL2, /* Architectural Feature Trap Register (EL2) */ HACR_EL2, /* Hypervisor Auxiliary Control Register */ ZCR_EL2, /* SVE Control Register (EL2) */ + SMCR_EL2, /* SME Control Register (EL2) */ TTBR0_EL2, /* Translation Table Base Register 0 (EL2) */ TTBR1_EL2, /* Translation Table Base Register 1 (EL2) */ TCR_EL2, /* Translation Control Register (EL2) */ @@ -542,6 +543,7 @@ enum vcpu_sysreg { VNCR(ACTLR_EL1),/* Auxiliary Control Register */ VNCR(CPACR_EL1),/* Coprocessor Access Control */ VNCR(ZCR_EL1), /* SVE Control */ + VNCR(SMCR_EL1), /* SME Control */ VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */ VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */ VNCR(TCR_EL1), /* Translation Control Register */ diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h index c2485a862e69..44b12565321b 100644 --- a/arch/arm64/include/asm/vncr_mapping.h +++ b/arch/arm64/include/asm/vncr_mapping.h @@ -44,6 +44,7 @@ #define VNCR_HDFGWTR_EL2 0x1D8 #define VNCR_ZCR_EL1 0x1E0 #define VNCR_HAFGRTR_EL2 0x1E8 +#define VNCR_SMCR_EL1 0x1F0 #define VNCR_TTBR0_EL1 0x200 #define VNCR_TTBR1_EL1 0x210 #define VNCR_FAR_EL1 0x220 diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 3576e69468db..5c912139d264 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2827,6 +2827,37 @@ static bool access_gic_elrsr(struct kvm_vcpu *vcpu, return true; }

+static unsigned int sme_el2_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + return __el2_visibility(vcpu, rd, sme_visibility); +} + +static bool access_smcr_el2(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + unsigned int vq; + u64 smcr; + + if (guest_hyp_sve_traps_enabled(vcpu)) { + kvm_inject_nested_sve_trap(vcpu); + return false; + } + + if (!p->is_write) { + p->regval = __vcpu_sys_reg(vcpu, SMCR_EL2); + return true; + } + + smcr = p->regval; + vq = SYS_FIELD_GET(SMCR_ELx, LEN, smcr) + 1; + vq = min(vq, vcpu_sme_max_vq(vcpu)); + __vcpu_assign_sys_reg(vcpu, SMCR_EL2, SYS_FIELD_PREP(SMCR_ELx, LEN, + vq - 1)); + return true; +} + static unsigned int s1poe_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { @@ -3291,7 +3322,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TRFCR_EL1), undef_access }, { SYS_DESC(SYS_SMPRI_EL1), undef_access }, - { SYS_DESC(SYS_SMCR_EL1), undef_access }, + { SYS_DESC(SYS_SMCR_EL1), NULL, reset_val, SMCR_EL1, 0, .visibility = sme_visibility }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 }, { SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 }, @@ -3655,6 +3686,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {

EL2_REG_VNCR(HCRX_EL2, reset_val, 0),

+ EL2_REG_FILTERED(SMCR_EL2, access_smcr_el2, reset_val, 0, + sme_el2_visibility), + EL2_REG(TTBR0_EL2, access_rw, reset_val, 0), EL2_REG(TTBR1_EL2, access_rw, reset_val, 0), EL2_REG(TCR_EL2, access_rw, reset_val, TCR_EL2_RES1),

In order to simplify interdependencies in the rest of the series define the feature detection for SME and it's subfeatures. Due to the need for vector length configuration we define a flag for SME like for SVE. We also have two subfeatures which add architectural state, FA64 and SME2, which are configured via the normal ID register scheme.

Also provide helpers which check if the vCPU is in streaming mode or has ZA enabled.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 35 ++++++++++++++++++++++++++++++++++- arch/arm64/kvm/sys_regs.c | 2 +- 2 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0f3d26467bf0..0816180dc551 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -353,6 +353,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS 10 /* Unhandled SEAs are taken to userspace */ #define KVM_ARCH_FLAG_EXIT_SEA 11 + /* SME exposed to guest */ +#define KVM_ARCH_FLAG_GUEST_HAS_SME 12 unsigned long flags;

/* VM-wide vCPU feature set */ @@ -1062,7 +1064,16 @@ struct kvm_vcpu_arch { #define vcpu_has_sve(vcpu) kvm_has_sve((vcpu)->kvm) #endif

-#define vcpu_has_vec(vcpu) vcpu_has_sve(vcpu) +#define kvm_has_sme(kvm) (system_supports_sme() && \ + test_bit(KVM_ARCH_FLAG_GUEST_HAS_SME, &(kvm)->arch.flags)) + +#ifdef __KVM_NVHE_HYPERVISOR__ +#define vcpu_has_sme(vcpu) kvm_has_sme(kern_hyp_va((vcpu)->kvm)) +#else +#define vcpu_has_sme(vcpu) kvm_has_sme((vcpu)->kvm) +#endif + +#define vcpu_has_vec(vcpu) (vcpu_has_sve(vcpu) || vcpu_has_sme(vcpu))

#ifdef CONFIG_ARM64_PTR_AUTH #define vcpu_has_ptrauth(vcpu) \ @@ -1602,6 +1613,28 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); #define kvm_has_sctlr2(k) \ (kvm_has_feat((k), ID_AA64MMFR3_EL1, SCTLRX, IMP))

+#define kvm_has_fa64(k) \ + (system_supports_fa64() && \ + kvm_has_feat((k), ID_AA64SMFR0_EL1, FA64, IMP)) + +#define kvm_has_sme2(k) \ + (system_supports_sme2() && \ + kvm_has_feat((k), ID_AA64PFR1_EL1, SME, SME2)) + +#ifdef __KVM_NVHE_HYPERVISOR__ +#define vcpu_has_sme2(vcpu) kvm_has_sme2(kern_hyp_va((vcpu)->kvm)) +#define vcpu_has_fa64(vcpu) kvm_has_fa64(kern_hyp_va((vcpu)->kvm)) +#else +#define vcpu_has_sme2(vcpu) kvm_has_sme2((vcpu)->kvm) +#define vcpu_has_fa64(vcpu) kvm_has_fa64((vcpu)->kvm) +#endif + +#define vcpu_in_streaming_mode(vcpu) \ + (__vcpu_sys_reg(vcpu, SVCR) & SVCR_SM_MASK) + +#define vcpu_za_enabled(vcpu) \ + (__vcpu_sys_reg(vcpu, SVCR) & SVCR_ZA_MASK) + static inline bool kvm_arch_has_irq_bypass(void) { return true; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index c8fd7c6a12a1..3576e69468db 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1945,7 +1945,7 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu, static unsigned int sme_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SME, IMP)) + if (vcpu_has_sme(vcpu)) return 0;

return REG_HIDDEN;

SME introduces a mode called streaming mode where the Z, P and optionally FFR registers can be accessed using the SVE instructions but with the SME vector length. Reflect this in the ABI for accessing the guest registers by making the vector length for the vcpu reflect the vector length that would be seen by the guest were it running, using the SME vector length when the guest is configured for streaming mode.

Since SME may be present without SVE we also update the existing checks for access to the Z, P and V registers to check for either SVE or streaming mode. When not in streaming mode the guest floating point state may be accessed via the V registers.

Any VMM that supports SME must be aware of the need to configure streaming mode prior to writing the floating point registers that this creates.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kvm/guest.c | 38 ++++++++++++++++++++++++++++++++++---- 1 file changed, 34 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 2a1fdcb0ec49..90dcacb35f01 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -73,6 +73,11 @@ static u64 core_reg_offset_from_id(u64 id) return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE); }

+static bool vcpu_has_sve_regs(const struct kvm_vcpu *vcpu) +{ + return vcpu_has_sve(vcpu) || vcpu_in_streaming_mode(vcpu); +} + static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) { int size; @@ -110,9 +115,10 @@ static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) /* * The KVM_REG_ARM64_SVE regs must be used instead of * KVM_REG_ARM_CORE for accessing the FPSIMD V-registers on - * SVE-enabled vcpus: + * SVE-enabled vcpus or when a SME enabled vcpu is in + * streaming mode: */ - if (vcpu_has_sve(vcpu) && core_reg_offset_is_vreg(off)) + if (vcpu_has_sve_regs(vcpu) && core_reg_offset_is_vreg(off)) return -EINVAL;

return size; @@ -426,6 +432,24 @@ struct vec_state_reg_region { unsigned int upad; /* extra trailing padding in user memory */ };

+/* + * We represent the Z and P registers to userspace using either the + * SVE or SME vector length, depending on which features the guest has + * and if the guest is in streaming mode. + */ +static unsigned int vcpu_sve_cur_vq(struct kvm_vcpu *vcpu) +{ + unsigned int vq = 0; + + if (vcpu_has_sve(vcpu)) + vq = vcpu_sve_max_vq(vcpu); + + if (vcpu_in_streaming_mode(vcpu)) + vq = vcpu_sme_max_vq(vcpu); + + return vq; +} + /* * Validate SVE register ID and get sanitised bounds for user/kernel SVE * register copy @@ -466,7 +490,7 @@ static int sve_reg_to_region(struct vec_state_reg_region *region, if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0) return -ENOENT;

- vq = vcpu_sve_max_vq(vcpu); + vq = vcpu_sve_cur_vq(vcpu);

reqoffset = SVE_SIG_ZREG_OFFSET(vq, reg_num) - SVE_SIG_REGS_OFFSET; @@ -476,7 +500,7 @@ static int sve_reg_to_region(struct vec_state_reg_region *region, if (!vcpu_has_sve(vcpu) || (reg->id & SVE_REG_SLICE_MASK) > 0) return -ENOENT;

- vq = vcpu_sve_max_vq(vcpu); + vq = vcpu_sve_cur_vq(vcpu);

reqoffset = SVE_SIG_PREG_OFFSET(vq, reg_num) - SVE_SIG_REGS_OFFSET; @@ -515,6 +539,9 @@ static int get_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (!kvm_arm_vcpu_vec_finalized(vcpu)) return -EPERM;

+ if (!vcpu_has_sve_regs(vcpu)) + return -EBUSY; + if (copy_to_user(uptr, vcpu->arch.sve_state + region.koffset, region.klen) || clear_user(uptr + region.klen, region.upad)) @@ -541,6 +568,9 @@ static int set_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (!kvm_arm_vcpu_vec_finalized(vcpu)) return -EPERM;

+ if (!vcpu_has_sve_regs(vcpu)) + return -EBUSY; + if (copy_from_user(vcpu->arch.sve_state + region.koffset, uptr, region.klen)) return -EFAULT;

Due to the overlap between SVE and SME vector length configuration created by streaming mode SVE we will finalize both at once. Rename the existing finalization to use _VEC (vector) for the naming to avoid confusion.

Since this includes the userspace API we create an alias KVM_ARM_VCPU_VEC for the existing KVM_ARM_VCPU_SVE capability, existing code which does not enable SME will be unaffected and any SME only code will not need to use SVE constants.

No functional change.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 8 +++++--- arch/arm64/include/uapi/asm/kvm.h | 6 ++++++ arch/arm64/kvm/guest.c | 10 +++++----- arch/arm64/kvm/hyp/nvhe/pkvm.c | 2 +- arch/arm64/kvm/reset.c | 20 ++++++++++---------- 5 files changed, 27 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index e6d25db10a6b..0f3d26467bf0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -988,8 +988,8 @@ struct kvm_vcpu_arch {

/* KVM_ARM_VCPU_INIT completed */ #define VCPU_INITIALIZED __vcpu_single_flag(cflags, BIT(0)) -/* SVE config completed */ -#define VCPU_SVE_FINALIZED __vcpu_single_flag(cflags, BIT(1)) +/* Vector config completed */ +#define VCPU_VEC_FINALIZED __vcpu_single_flag(cflags, BIT(1)) /* pKVM VCPU setup completed */ #define VCPU_PKVM_FINALIZED __vcpu_single_flag(cflags, BIT(2))

@@ -1062,6 +1062,8 @@ struct kvm_vcpu_arch { #define vcpu_has_sve(vcpu) kvm_has_sve((vcpu)->kvm) #endif

+#define vcpu_has_vec(vcpu) vcpu_has_sve(vcpu) + #ifdef CONFIG_ARM64_PTR_AUTH #define vcpu_has_ptrauth(vcpu) \ ((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || \ @@ -1458,7 +1460,7 @@ struct kvm *kvm_arch_alloc_vm(void); int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature); bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);

-#define kvm_arm_vcpu_sve_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_SVE_FINALIZED) +#define kvm_arm_vcpu_vec_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_VEC_FINALIZED)

#define kvm_has_mte(kvm) \ (system_supports_mte() && \ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index a792a599b9d6..c67564f02981 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -107,6 +107,12 @@ struct kvm_regs { #define KVM_ARM_VCPU_HAS_EL2 7 /* Support nested virtualization */ #define KVM_ARM_VCPU_HAS_EL2_E2H0 8 /* Limit NV support to E2H RES0 */

+/* + * An alias for _SVE since we finalize VL configuration for both SVE and SME + * simultaneously. + */ +#define KVM_ARM_VCPU_VEC KVM_ARM_VCPU_SVE + struct kvm_vcpu_init { __u32 target; __u32 features[7]; diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 1c87699fd886..d15aa2da1891 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -342,7 +342,7 @@ static int set_sve_vls(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (!vcpu_has_sve(vcpu)) return -ENOENT;

- if (kvm_arm_vcpu_sve_finalized(vcpu)) + if (kvm_arm_vcpu_vec_finalized(vcpu)) return -EPERM; /* too late! */

if (WARN_ON(vcpu->arch.sve_state)) @@ -497,7 +497,7 @@ static int get_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (ret) return ret;

- if (!kvm_arm_vcpu_sve_finalized(vcpu)) + if (!kvm_arm_vcpu_vec_finalized(vcpu)) return -EPERM;

if (copy_to_user(uptr, vcpu->arch.sve_state + region.koffset, @@ -523,7 +523,7 @@ static int set_sve_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if (ret) return ret;

- if (!kvm_arm_vcpu_sve_finalized(vcpu)) + if (!kvm_arm_vcpu_vec_finalized(vcpu)) return -EPERM;

if (copy_from_user(vcpu->arch.sve_state + region.koffset, uptr, @@ -599,7 +599,7 @@ static unsigned long num_sve_regs(const struct kvm_vcpu *vcpu) return 0;

/* Policed by KVM_GET_REG_LIST: */ - WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu)); + WARN_ON(!kvm_arm_vcpu_vec_finalized(vcpu));

return slices * (SVE_NUM_PREGS + SVE_NUM_ZREGS + 1 /* FFR */) + 1; /* KVM_REG_ARM64_SVE_VLS */ @@ -617,7 +617,7 @@ static int copy_sve_reg_indices(const struct kvm_vcpu *vcpu, return 0;

/* Policed by KVM_GET_REG_LIST: */ - WARN_ON(!kvm_arm_vcpu_sve_finalized(vcpu)); + WARN_ON(!kvm_arm_vcpu_vec_finalized(vcpu));

/* * Enumerate this first, so that userspace can save/restore in diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 8911338961c5..b402dcb7691e 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -445,7 +445,7 @@ static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *h int ret = 0;

if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { - vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED); + vcpu_clear_flag(vcpu, VCPU_VEC_FINALIZED); return 0; }

diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 959532422d3a..f7c63e145d54 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -92,7 +92,7 @@ static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) * Finalize vcpu's maximum SVE vector length, allocating * vcpu->arch.sve_state as necessary. */ -static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) +static int kvm_vcpu_finalize_vec(struct kvm_vcpu *vcpu) { void *buf; unsigned int vl; @@ -122,21 +122,21 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) } vcpu->arch.sve_state = buf; - vcpu_set_flag(vcpu, VCPU_SVE_FINALIZED); + vcpu_set_flag(vcpu, VCPU_VEC_FINALIZED); return 0; }

int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature) { switch (feature) { - case KVM_ARM_VCPU_SVE: - if (!vcpu_has_sve(vcpu)) + case KVM_ARM_VCPU_VEC: + if (!vcpu_has_vec(vcpu)) return -EINVAL;

- if (kvm_arm_vcpu_sve_finalized(vcpu)) + if (kvm_arm_vcpu_vec_finalized(vcpu)) return -EPERM;

- return kvm_vcpu_finalize_sve(vcpu); + return kvm_vcpu_finalize_vec(vcpu); }

return -EINVAL; @@ -144,7 +144,7 @@ int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature)

bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) { - if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu)) + if (vcpu_has_vec(vcpu) && !kvm_arm_vcpu_vec_finalized(vcpu)) return false;

return true; @@ -163,7 +163,7 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) kfree(vcpu->arch.ccsidr); }

-static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) +static void kvm_vcpu_reset_vec(struct kvm_vcpu *vcpu) { if (vcpu_has_sve(vcpu)) memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu)); @@ -203,11 +203,11 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (loaded) kvm_arch_vcpu_put(vcpu);

- if (!kvm_arm_vcpu_sve_finalized(vcpu)) { + if (!kvm_arm_vcpu_vec_finalized(vcpu)) { if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) kvm_vcpu_enable_sve(vcpu); } else { - kvm_vcpu_reset_sve(vcpu); + kvm_vcpu_reset_vec(vcpu); }

if (vcpu_el1_is_32bit(vcpu))

Some parts of the SME state are optional, enabled by additional features on top of the base FEAT_SME and controlled with enable bits in SMCR_ELx. We unconditionally enable these for the host but for KVM we will allow the feature set exposed to guests to be restricted by the VMM. These are the FFR register (FEAT_SME_FA64) and ZT0 (FEAT_SME2).

We defer saving of guest floating point state for non-protected guests to the host kernel. We also want to avoid having to reconfigure the guest floating point state if nothing used the floating point state while running the host. If the guest was running with the optional features disabled then traps will be enabled for them so the host kernel will need to skip accessing that state when saving state for the guest.

Support this by moving the decision about saving this state to the point where we bind floating point state to the CPU, adding a new variable to the cpu_fp_state which uses the enable bits in SMCR_ELx to flag which features are enabled.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/fpsimd.h | 1 + arch/arm64/kernel/fpsimd.c | 10 ++++++++-- arch/arm64/kvm/fpsimd.c | 1 + 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index ece65061dea0..146c1af55e22 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -87,6 +87,7 @@ struct cpu_fp_state { void *sme_state; u64 *svcr; u64 *fpmr; + u64 sme_features; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index be4499ff6498..887fce177c92 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -490,12 +490,12 @@ static void fpsimd_save_user_state(void)

if (*svcr & SVCR_ZA_MASK) sme_save_state(last->sme_state, - system_supports_sme2()); + last->sme_features & SMCR_ELx_EZT0);

/* If we are in streaming mode override regular SVE. */ if (*svcr & SVCR_SM_MASK) { save_sve_regs = true; - save_ffr = system_supports_fa64(); + save_ffr = last->sme_features & SMCR_ELx_FA64; vl = last->sme_vl; } } @@ -1671,6 +1671,12 @@ static void fpsimd_bind_task_to_cpu(void) last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id();

+ last->sme_features = 0; + if (system_supports_fa64()) + last->sme_features |= SMCR_ELx_FA64; + if (system_supports_sme2()) + last->sme_features |= SMCR_ELx_EZT0; + /* * Toggle SVE and SME trapping for userspace if needed, these * are serialsied by ret_to_user(). diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 15e17aca1dec..9158353d8be3 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -80,6 +80,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) fp_state.svcr = __ctxt_sys_reg(&vcpu->arch.ctxt, SVCR); fp_state.fpmr = __ctxt_sys_reg(&vcpu->arch.ctxt, FPMR); fp_state.fp_type = &vcpu->arch.fp_type; + fp_state.sme_features = 0;

if (vcpu_has_sve(vcpu)) fp_state.to_save = FP_STATE_SVE;

Currently when deciding if we need to save FFR when in streaming mode prior to EFI calls we check if FA64 is supported by the system. Since KVM guest support will mean that FA64 might be enabled and disabled at runtime switch to checking if traps for FA64 are enabled in SMCR_EL1 instead.

Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kernel/fpsimd.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 887fce177c92..f4e8cee00198 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1948,6 +1948,11 @@ static bool efi_sm_state; * either doing something wrong or you need to propose some refactoring. */

+static bool fa64_enabled(void) +{ + return read_sysreg_s(SYS_SMCR_EL1) & SMCR_ELx_FA64; +} + /* * __efi_fpsimd_begin(): prepare FPSIMD for making an EFI runtime services call */ @@ -1980,7 +1985,7 @@ void __efi_fpsimd_begin(void) * Unless we have FA64 FFR does not * exist in streaming mode. */ - if (!system_supports_fa64()) + if (!fa64_enabled()) ffr = !(svcr & SVCR_SM_MASK); }

@@ -2028,7 +2033,7 @@ void __efi_fpsimd_end(void) * Unless we have FA64 FFR does not * exist in streaming mode. */ - if (!system_supports_fa64()) + if (!fa64_enabled()) ffr = false; } }