Re: [PATCH v10 14/40] KVM: arm64: Manage GCS access and registers for guests

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Thu, 01 Aug 2024 13:06:41 +0100,
Mark Brown <broonie@xxxxxxxxxx> wrote:
> 
> GCS introduces a number of system registers for EL1 and EL0, on systems
> with GCS we need to context switch them and expose them to VMMs to allow
> guests to use GCS.
> 
> In order to allow guests to use GCS we also need to configure
> HCRX_EL2.GCSEn, if this is not set GCS instructions will be noops and
> CHKFEAT will report GCS as disabled.  Also enable fine grained traps for
> access to the GCS registers by guests which do not have the feature
> enabled.
> 
> Signed-off-by: Mark Brown <broonie@xxxxxxxxxx>
> ---
>  arch/arm64/include/asm/kvm_host.h          |  8 +++++
>  arch/arm64/include/asm/vncr_mapping.h      |  2 ++
>  arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 49 ++++++++++++++++++++++++------
>  arch/arm64/kvm/sys_regs.c                  | 12 ++++++++
>  4 files changed, 61 insertions(+), 10 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index a33f5996ca9f..5818e4a1c2d1 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -446,6 +446,10 @@ enum vcpu_sysreg {
>  	GCR_EL1,	/* Tag Control Register */
>  	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
>  
> +	/* Guarded Control Stack registers */
> +	GCSCRE0_EL1,	/* Guarded Control Stack Control (EL0) */
> +	GCSPR_EL0,	/* Guarded Control Stack Pointer (EL0) */
> +
>  	/* 32bit specific registers. */
>  	DACR32_EL2,	/* Domain Access Control Register */
>  	IFSR32_EL2,	/* Instruction Fault Status Register */
> @@ -517,6 +521,10 @@ enum vcpu_sysreg {
>  	VNCR(PIR_EL1),	 /* Permission Indirection Register 1 (EL1) */
>  	VNCR(PIRE0_EL1), /*  Permission Indirection Register 0 (EL1) */
>  
> +	/* Guarded Control Stack registers */
> +	VNCR(GCSPR_EL1),	/* Guarded Control Stack Pointer (EL1) */
> +	VNCR(GCSCR_EL1),	/* Guarded Control Stack Control (EL1) */
> +
>  	VNCR(HFGRTR_EL2),
>  	VNCR(HFGWTR_EL2),
>  	VNCR(HFGITR_EL2),
> diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h
> index df2c47c55972..5e83e6f579fd 100644
> --- a/arch/arm64/include/asm/vncr_mapping.h
> +++ b/arch/arm64/include/asm/vncr_mapping.h
> @@ -88,6 +88,8 @@
>  #define VNCR_PMSIRR_EL1         0x840
>  #define VNCR_PMSLATFR_EL1       0x848
>  #define VNCR_TRFCR_EL1          0x880
> +#define VNCR_GCSPR_EL1		0x8C0
> +#define VNCR_GCSCR_EL1		0x8D0
>  #define VNCR_MPAM1_EL1          0x900
>  #define VNCR_MPAMHCR_EL2        0x930
>  #define VNCR_MPAMVPMV_EL2       0x938
> diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
> index 4c0fdabaf8ae..ac29352e225a 100644
> --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
> +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
> @@ -16,6 +16,27 @@
>  #include <asm/kvm_hyp.h>
>  #include <asm/kvm_mmu.h>
>  
> +static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt)
> +{
> +	struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu;
> +
> +	if (!vcpu)
> +		vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
> +
> +	return vcpu;
> +}
> +
> +static inline bool ctxt_has_gcs(struct kvm_cpu_context *ctxt)
> +{
> +	struct kvm_vcpu *vcpu;
> +
> +	if (!cpus_have_final_cap(ARM64_HAS_GCS))
> +		return false;
> +
> +	vcpu = ctxt_to_vcpu(ctxt);
> +	return kvm_has_feat(kern_hyp_va(vcpu->kvm), ID_AA64PFR1_EL1, GCS, IMP);
> +}
> +
>  static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
>  {
>  	ctxt_sys_reg(ctxt, MDSCR_EL1)	= read_sysreg(mdscr_el1);
> @@ -25,16 +46,10 @@ static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
>  {
>  	ctxt_sys_reg(ctxt, TPIDR_EL0)	= read_sysreg(tpidr_el0);
>  	ctxt_sys_reg(ctxt, TPIDRRO_EL0)	= read_sysreg(tpidrro_el0);
> -}
> -
> -static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt)
> -{
> -	struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu;
> -
> -	if (!vcpu)
> -		vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
> -
> -	return vcpu;
> +	if (ctxt_has_gcs(ctxt)) {
> +		ctxt_sys_reg(ctxt, GCSPR_EL0) = read_sysreg_s(SYS_GCSPR_EL0);
> +		ctxt_sys_reg(ctxt, GCSCRE0_EL1)	= read_sysreg_s(SYS_GCSCRE0_EL1);
> +	}
>  }
>  
>  static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt)
> @@ -79,6 +94,10 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
>  		if (ctxt_has_s1pie(ctxt)) {
>  			ctxt_sys_reg(ctxt, PIR_EL1)	= read_sysreg_el1(SYS_PIR);
>  			ctxt_sys_reg(ctxt, PIRE0_EL1)	= read_sysreg_el1(SYS_PIRE0);
> +			if (ctxt_has_gcs(ctxt)) {
> +				ctxt_sys_reg(ctxt, GCSPR_EL1)	= read_sysreg_el1(SYS_GCSPR);
> +				ctxt_sys_reg(ctxt, GCSCR_EL1)	= read_sysreg_el1(SYS_GCSCR);
> +			}
>  		}
>  	}
>  	ctxt_sys_reg(ctxt, ESR_EL1)	= read_sysreg_el1(SYS_ESR);
> @@ -126,6 +145,11 @@ static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt)
>  {
>  	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL0),	tpidr_el0);
>  	write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0),	tpidrro_el0);
> +	if (ctxt_has_gcs(ctxt)) {
> +		write_sysreg_s(ctxt_sys_reg(ctxt, GCSPR_EL0), SYS_GCSPR_EL0);
> +		write_sysreg_s(ctxt_sys_reg(ctxt, GCSCRE0_EL1),
> +			       SYS_GCSCRE0_EL1);
> +	}
>  }
>  
>  static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
> @@ -157,6 +181,11 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
>  		if (ctxt_has_s1pie(ctxt)) {
>  			write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1),	SYS_PIR);
>  			write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1),	SYS_PIRE0);
> +
> +			if (ctxt_has_gcs(ctxt)) {
> +				write_sysreg_el1(ctxt_sys_reg(ctxt, GCSPR_EL1),	SYS_GCSPR);
> +				write_sysreg_el1(ctxt_sys_reg(ctxt, GCSCR_EL1),	SYS_GCSCR);
> +			}
>  		}
>  	}
>  	write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1),	SYS_ESR);
> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
> index c90324060436..ac98d3237130 100644
> --- a/arch/arm64/kvm/sys_regs.c
> +++ b/arch/arm64/kvm/sys_regs.c
> @@ -2446,6 +2446,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
>  	PTRAUTH_KEY(APDB),
>  	PTRAUTH_KEY(APGA),
>  
> +	{ SYS_DESC(SYS_GCSCR_EL1), NULL, reset_val, GCSCR_EL1, 0 },
> +	{ SYS_DESC(SYS_GCSPR_EL1), NULL, reset_unknown, GCSPR_EL1 },
> +	{ SYS_DESC(SYS_GCSCRE0_EL1), NULL, reset_val, GCSCRE0_EL1, 0 },
> +

Global visibility for these registers? Why should we expose them to
userspace if the feature is neither present nor configured?

>  	{ SYS_DESC(SYS_SPSR_EL1), access_spsr},
>  	{ SYS_DESC(SYS_ELR_EL1), access_elr},
>  
> @@ -2535,6 +2539,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
>  			     CTR_EL0_IDC_MASK |
>  			     CTR_EL0_DminLine_MASK |
>  			     CTR_EL0_IminLine_MASK),
> +	{ SYS_DESC(SYS_GCSPR_EL0), NULL, reset_unknown, GCSPR_EL0 },
>  	{ SYS_DESC(SYS_SVCR), undef_access },
>  
>  	{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr,
> @@ -4560,6 +4565,9 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
>  
>  		if (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, TCRX, IMP))
>  			vcpu->arch.hcrx_el2 |= HCRX_EL2_TCR2En;
> +
> +		if (kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
> +			vcpu->arch.hcrx_el2 |= HCRX_EL2_GCSEn;
>  	}
>  
>  	if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags))
> @@ -4604,6 +4612,10 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
>  		kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPIRE0_EL1 |
>  						HFGxTR_EL2_nPIR_EL1);
>  
> +	if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
> +		kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nGCS_EL0 |
> +						HFGxTR_EL2_nGCS_EL1);

How can this work if you don't handle ID_AA64PFR_EL1 being written to?
You are exposing GCS to all guests without giving the VMM an
opportunity to turn it off. This breaks A->B->A migration, which is
not acceptable.

	M.

-- 
Without deviation from the norm, progress is not possible.




[Index of Archives]     [Linux Wireless]     [Linux Kernel]     [ATH6KL]     [Linux Bluetooth]     [Linux Netdev]     [Kernel Newbies]     [Share Photos]     [IDE]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux ATA RAID]     [Samba]     [Device Mapper]

  Powered by Linux