Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue, 09 Mar 2021 17:27:14 +0000
Message-ID: <87h7lkxmod.wl-maz@kernel.org>
From:   Marc Zyngier <maz@kernel.org>
To:     Steven Price <steven.price@arm.com>
Cc:     Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will@kernel.org>,
        James Morse <james.morse@arm.com>,
        Julien Thierry <julien.thierry.kdev@gmail.com>,
        Suzuki K Poulose <suzuki.poulose@arm.com>,
        kvmarm@lists.cs.columbia.edu, linux-arm-kernel@lists.infradead.org,
        linux-kernel@vger.kernel.org, Dave Martin <Dave.Martin@arm.com>,
        Mark Rutland <mark.rutland@arm.com>,
        Thomas Gleixner <tglx@linutronix.de>, qemu-devel@nongnu.org,
        Juan Quintela <quintela@redhat.com>,
        "Dr. David Alan Gilbert" <dgilbert@redhat.com>,
        Richard Henderson <richard.henderson@linaro.org>,
        Peter Maydell <peter.maydell@linaro.org>,
        Haibo Xu <Haibo.Xu@arm.com>, Andrew Jones <drjones@redhat.com>
Subject: Re: [PATCH v9 3/6] arm64: kvm: Save/restore MTE registers
In-Reply-To: <20210301142315.30920-4-steven.price@arm.com>
References: <20210301142315.30920-1-steven.price@arm.com>
        <20210301142315.30920-4-steven.price@arm.com>
User-Agent: Wanderlust/2.15.9 (Almost Unreal) SEMI-EPG/1.14.7 (Harue)
 FLIM-LB/1.14.9 (=?UTF-8?B?R29qxY0=?=) APEL-LB/10.8 EasyPG/1.0.0 Emacs/27.1
 (x86_64-pc-linux-gnu) MULE/6.0 (HANACHIRUSATO)
MIME-Version: 1.0 (generated by SEMI-EPG 1.14.7 - "Harue")
Content-Type: text/plain; charset=US-ASCII
Precedence: bulk

On Mon, 01 Mar 2021 14:23:12 +0000,
Steven Price <steven.price@arm.com> wrote:
> 
> Define the new system registers that MTE introduces and context switch
> them. The MTE feature is still hidden from the ID register as it isn't
> supported in a VM yet.
> 
> Signed-off-by: Steven Price <steven.price@arm.com>
> ---
>  arch/arm64/include/asm/kvm_host.h          |  6 ++
>  arch/arm64/include/asm/kvm_mte.h           | 66 ++++++++++++++++++++++
>  arch/arm64/include/asm/sysreg.h            |  3 +-
>  arch/arm64/kernel/asm-offsets.c            |  3 +
>  arch/arm64/kvm/hyp/entry.S                 |  7 +++
>  arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h | 21 +++++++
>  arch/arm64/kvm/sys_regs.c                  | 22 ++++++--
>  7 files changed, 123 insertions(+), 5 deletions(-)
>  create mode 100644 arch/arm64/include/asm/kvm_mte.h
> 
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index 1170ee137096..d00cc3590f6e 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -208,6 +208,12 @@ enum vcpu_sysreg {
>  	CNTP_CVAL_EL0,
>  	CNTP_CTL_EL0,
>  
> +	/* Memory Tagging Extension registers */
> +	RGSR_EL1,	/* Random Allocation Tag Seed Register */
> +	GCR_EL1,	/* Tag Control Register */
> +	TFSR_EL1,	/* Tag Fault Status Register (EL1) */
> +	TFSRE0_EL1,	/* Tag Fault Status Register (EL0) */
> +
>  	/* 32bit specific registers. Keep them at the end of the range */
>  	DACR32_EL2,	/* Domain Access Control Register */
>  	IFSR32_EL2,	/* Instruction Fault Status Register */
> diff --git a/arch/arm64/include/asm/kvm_mte.h b/arch/arm64/include/asm/kvm_mte.h
> new file mode 100644
> index 000000000000..6541c7d6ce06
> --- /dev/null
> +++ b/arch/arm64/include/asm/kvm_mte.h
> @@ -0,0 +1,66 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +/*
> + * Copyright (C) 2020 ARM Ltd.
> + */
> +#ifndef __ASM_KVM_MTE_H
> +#define __ASM_KVM_MTE_H
> +
> +#ifdef __ASSEMBLY__
> +
> +#include <asm/sysreg.h>
> +
> +#ifdef CONFIG_ARM64_MTE
> +
> +.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
> +alternative_if_not ARM64_MTE
> +	b	.L__skip_switch\@
> +alternative_else_nop_endif
> +	mrs	\reg1, hcr_el2
> +	and	\reg1, \reg1, #(HCR_ATA)
> +	cbz	\reg1, .L__skip_switch\@
> +
> +	mrs_s	\reg1, SYS_RGSR_EL1
> +	str	\reg1, [\h_ctxt, #CPU_RGSR_EL1]
> +	mrs_s	\reg1, SYS_GCR_EL1
> +	str	\reg1, [\h_ctxt, #CPU_GCR_EL1]
> +
> +	ldr	\reg1, [\g_ctxt, #CPU_RGSR_EL1]
> +	msr_s	SYS_RGSR_EL1, \reg1
> +	ldr	\reg1, [\g_ctxt, #CPU_GCR_EL1]
> +	msr_s	SYS_GCR_EL1, \reg1
> +
> +.L__skip_switch\@:
> +.endm
> +
> +.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
> +alternative_if_not ARM64_MTE
> +	b	.L__skip_switch\@
> +alternative_else_nop_endif
> +	mrs	\reg1, hcr_el2
> +	and	\reg1, \reg1, #(HCR_ATA)
> +	cbz	\reg1, .L__skip_switch\@
> +
> +	mrs_s	\reg1, SYS_RGSR_EL1
> +	str	\reg1, [\g_ctxt, #CPU_RGSR_EL1]
> +	mrs_s	\reg1, SYS_GCR_EL1
> +	str	\reg1, [\g_ctxt, #CPU_GCR_EL1]
> +
> +	ldr	\reg1, [\h_ctxt, #CPU_RGSR_EL1]
> +	msr_s	SYS_RGSR_EL1, \reg1
> +	ldr	\reg1, [\h_ctxt, #CPU_GCR_EL1]
> +	msr_s	SYS_GCR_EL1, \reg1
> +
> +.L__skip_switch\@:
> +.endm
> +
> +#else /* CONFIG_ARM64_MTE */
> +
> +.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
> +.endm
> +
> +.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
> +.endm
> +
> +#endif /* CONFIG_ARM64_MTE */
> +#endif /* __ASSEMBLY__ */
> +#endif /* __ASM_KVM_MTE_H */
> diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
> index dfd4edbfe360..5424d195cf96 100644
> --- a/arch/arm64/include/asm/sysreg.h
> +++ b/arch/arm64/include/asm/sysreg.h
> @@ -580,7 +580,8 @@
>  #define SCTLR_ELx_M	(BIT(0))
>  
>  #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M  | SCTLR_ELx_A | SCTLR_ELx_C | \
> -			 SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB)
> +			 SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB | \
> +			 SCTLR_ELx_ITFSB)
>  
>  /* SCTLR_EL2 specific flags. */
>  #define SCTLR_EL2_RES1	((BIT(4))  | (BIT(5))  | (BIT(11)) | (BIT(16)) | \
> diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
> index a36e2fc330d4..944e4f1f45d9 100644
> --- a/arch/arm64/kernel/asm-offsets.c
> +++ b/arch/arm64/kernel/asm-offsets.c
> @@ -108,6 +108,9 @@ int main(void)
>    DEFINE(VCPU_WORKAROUND_FLAGS,	offsetof(struct kvm_vcpu, arch.workaround_flags));
>    DEFINE(VCPU_HCR_EL2,		offsetof(struct kvm_vcpu, arch.hcr_el2));
>    DEFINE(CPU_USER_PT_REGS,	offsetof(struct kvm_cpu_context, regs));
> +  DEFINE(CPU_RGSR_EL1,		offsetof(struct kvm_cpu_context, sys_regs[RGSR_EL1]));
> +  DEFINE(CPU_GCR_EL1,		offsetof(struct kvm_cpu_context, sys_regs[GCR_EL1]));
> +  DEFINE(CPU_TFSRE0_EL1,	offsetof(struct kvm_cpu_context, sys_regs[TFSRE0_EL1]));
>    DEFINE(CPU_APIAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
>    DEFINE(CPU_APIBKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1]));
>    DEFINE(CPU_APDAKEYLO_EL1,	offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1]));
> diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S
> index b0afad7a99c6..c67582c6dd55 100644
> --- a/arch/arm64/kvm/hyp/entry.S
> +++ b/arch/arm64/kvm/hyp/entry.S
> @@ -13,6 +13,7 @@
>  #include <asm/kvm_arm.h>
>  #include <asm/kvm_asm.h>
>  #include <asm/kvm_mmu.h>
> +#include <asm/kvm_mte.h>
>  #include <asm/kvm_ptrauth.h>
>  
>  	.text
> @@ -51,6 +52,9 @@ alternative_else_nop_endif
>  
>  	add	x29, x0, #VCPU_CONTEXT
>  
> +	// mte_switch_to_guest(g_ctxt, h_ctxt, tmp1)
> +	mte_switch_to_guest x29, x1, x2
> +
>  	// Macro ptrauth_switch_to_guest format:
>  	// 	ptrauth_switch_to_guest(guest cxt, tmp1, tmp2, tmp3)
>  	// The below macro to restore guest keys is not implemented in C code
> @@ -140,6 +144,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
>  	// when this feature is enabled for kernel code.
>  	ptrauth_switch_to_hyp x1, x2, x3, x4, x5
>  
> +	// mte_switch_to_hyp(g_ctxt, h_ctxt, reg1)
> +	mte_switch_to_hyp x1, x2, x3
> +
>  	// Restore hyp's sp_el0
>  	restore_sp_el0 x2, x3
>  
> diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
> index cce43bfe158f..de7e14c862e6 100644
> --- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
> +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
> @@ -14,6 +14,7 @@
>  #include <asm/kvm_asm.h>
>  #include <asm/kvm_emulate.h>
>  #include <asm/kvm_hyp.h>
> +#include <asm/kvm_mmu.h>
>  
>  static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
>  {
> @@ -26,6 +27,16 @@ static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
>  	ctxt_sys_reg(ctxt, TPIDRRO_EL0)	= read_sysreg(tpidrro_el0);
>  }
>  
> +static inline bool ctxt_has_mte(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 kvm_has_mte(kern_hyp_va(vcpu->kvm));
> +}
> +
>  static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
>  {
>  	ctxt_sys_reg(ctxt, CSSELR_EL1)	= read_sysreg(csselr_el1);
> @@ -46,6 +57,11 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
>  	ctxt_sys_reg(ctxt, PAR_EL1)	= read_sysreg_par();
>  	ctxt_sys_reg(ctxt, TPIDR_EL1)	= read_sysreg(tpidr_el1);
>  
> +	if (ctxt_has_mte(ctxt)) {
> +		ctxt_sys_reg(ctxt, TFSR_EL1) = read_sysreg_el1(SYS_TFSR);
> +		ctxt_sys_reg(ctxt, TFSRE0_EL1) = read_sysreg_s(SYS_TFSRE0_EL1);
> +	}

Could TFSRE0_EL1 be synchronised on vcpu_load()/vcpu_put() instead of
being done eagerly on each save/restore? Same thing for TFSR_EL1 when
running VHE?

I'd like to keep the switch as lean as possible. I'm pretty sure this
would simplify some of the "container_of()" ugliness above.

> +
>  	ctxt_sys_reg(ctxt, SP_EL1)	= read_sysreg(sp_el1);
>  	ctxt_sys_reg(ctxt, ELR_EL1)	= read_sysreg_el1(SYS_ELR);
>  	ctxt_sys_reg(ctxt, SPSR_EL1)	= read_sysreg_el1(SYS_SPSR);
> @@ -107,6 +123,11 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
>  	write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1),	par_el1);
>  	write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1),	tpidr_el1);
>  
> +	if (ctxt_has_mte(ctxt)) {
> +		write_sysreg_el1(ctxt_sys_reg(ctxt, TFSR_EL1), SYS_TFSR);
> +		write_sysreg_s(ctxt_sys_reg(ctxt, TFSRE0_EL1), SYS_TFSRE0_EL1);
> +	}
> +
>  	if (!has_vhe() &&
>  	    cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
>  	    ctxt->__hyp_running_vcpu) {
> diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
> index e09dbc00b0a2..17cb6256f205 100644
> --- a/arch/arm64/kvm/sys_regs.c
> +++ b/arch/arm64/kvm/sys_regs.c
> @@ -1301,6 +1301,20 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
>  	return true;
>  }
>  
> +static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
> +				   const struct sys_reg_desc *rd)
> +{
> +	return REG_HIDDEN;
> +}
> +
> +#define MTE_REG(name) {				\
> +	SYS_DESC(SYS_##name),			\
> +	.access = undef_access,			\
> +	.reset = reset_unknown,			\
> +	.reg = name,				\
> +	.visibility = mte_visibility,		\
> +}
> +
>  /* sys_reg_desc initialiser for known cpufeature ID registers */
>  #define ID_SANITISED(name) {			\
>  	SYS_DESC(SYS_##name),			\
> @@ -1469,8 +1483,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
>  	{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
>  	{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
>  
> -	{ SYS_DESC(SYS_RGSR_EL1), undef_access },
> -	{ SYS_DESC(SYS_GCR_EL1), undef_access },
> +	MTE_REG(RGSR_EL1),
> +	MTE_REG(GCR_EL1),
>  
>  	{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
>  	{ SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
> @@ -1496,8 +1510,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
>  	{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
>  	{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
>  
> -	{ SYS_DESC(SYS_TFSR_EL1), undef_access },
> -	{ SYS_DESC(SYS_TFSRE0_EL1), undef_access },
> +	MTE_REG(TFSR_EL1),
> +	MTE_REG(TFSRE0_EL1),
>  
>  	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
>  	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },

Thanks,

	M.

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