[RFC 1/4] arm64: kvm: add a cpu tear-down function

[takahiro.akashi@linaro.org (AKASHI Takahiro)]

Marc,

On 03/24/2015 07:00 PM, Marc Zyngier wrote:
> Hi Takahiro,
>
> On 23/03/15 11:53, AKASHI Takahiro wrote:
>> Cpu must be put back into its initial state, at least, in the
>> following cases in order to shutdown the system and/or re-initialize cpus
>> later on:
>> 1) kexec/kdump
>> 2) cpu hotplug (offline)
>> 3) removing kvm as a module
>>
>> To address those issues in later patches, this patch adds a tear-down
>> function, kvm_cpu_reset(), that disables D-cache & MMU and restore a vector
>> table to the initial stub at EL2.
>
> Thanks for having a look at this.
>
>> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
>> ---
>>   arch/arm/kvm/arm.c                |   18 ++++++++++++++++
>>   arch/arm/kvm/mmu.c                |   16 +++++++++++++++
>>   arch/arm64/include/asm/kvm_asm.h  |    3 +++
>>   arch/arm64/include/asm/kvm_host.h |   10 +++++++++
>>   arch/arm64/include/asm/kvm_mmu.h  |    3 +++
>>   arch/arm64/include/asm/virt.h     |   11 ++++++++++
>>   arch/arm64/kvm/hyp-init.S         |   41 +++++++++++++++++++++++++++++++++++++
>>   arch/arm64/kvm/hyp.S              |   29 ++++++++++++++++++++++----
>>   8 files changed, 127 insertions(+), 4 deletions(-)
>>
>> diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
>> index 5560f74..35c8bc0 100644
>> --- a/arch/arm/kvm/arm.c
>> +++ b/arch/arm/kvm/arm.c
>> @@ -897,6 +897,24 @@ static void cpu_init_hyp_mode(void *dummy)
>>   	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
>>   }
>>
>> +void kvm_cpu_reset(void *dummy)
>
> Given that the notifier introduced in patch #2 lives in the same file,
> this could be made static, couldn't it?

Yes. Will fix it.

>> +{
>> +	phys_addr_t boot_pgd_ptr;
>> +	phys_addr_t phys_idmap_start;
>> +	unsigned long reset_func;
>> +	unsigned long vector_ptr;
>> +
>> +	if (__hyp_get_vectors() == hyp_default_vectors)
>> +		return;
>> +
>> +	reset_func = kvm_reset_func_entry();
>> +	boot_pgd_ptr = kvm_mmu_get_boot_httbr();
>> +	phys_idmap_start = kvm_get_idmap_start();
>> +	vector_ptr = kvm_get_stub_vectors();
>
> Isn't that hyp_default_vectors already?

Yeah, I already use it in kvm_cpu_reset(). Will fix it.

>> +	__cpu_reset_hyp_mode(reset_func,
>> +			     boot_pgd_ptr, phys_idmap_start, vector_ptr);
>> +}
>> +
>>   static int hyp_init_cpu_notify(struct notifier_block *self,
>>   			       unsigned long action, void *cpu)
>>   {
>> diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
>> index 3e6859b..428f41c 100644
>> --- a/arch/arm/kvm/mmu.c
>> +++ b/arch/arm/kvm/mmu.c
>> @@ -1490,6 +1490,22 @@ phys_addr_t kvm_get_idmap_vector(void)
>>   	return hyp_idmap_vector;
>>   }
>>
>> +phys_addr_t kvm_get_idmap_start(void)
>> +{
>> +	return hyp_idmap_start;
>> +}
>> +
>> +phys_addr_t kvm_get_stub_vectors(void)
>> +{
>> +	return virt_to_phys(__hyp_stub_vectors);
>> +}
>
> As Geoff already mentioned, this doesn't belong in KVM. But I don't
> think you need it, as explained above.

Will remove it.

>> +
>> +unsigned long kvm_reset_func_entry(void)
>> +{
>> +	/* VA of __kvm_hyp_reset in trampline code */
>> +	return TRAMPOLINE_VA + (__kvm_hyp_reset - __hyp_idmap_text_start);
>> +}
>
> If you need to compute addresses in the trampoline page, it would be
> better to have a generic macro that takes a kernel VA, and turns it into
> a trampoline VA.

This is the only place to calculate the address. But will fix it.

>> +
>>   int kvm_mmu_init(void)
>>   {
>>   	int err;
>> diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
>> index 4f7310f..97ee2fc 100644
>> --- a/arch/arm64/include/asm/kvm_asm.h
>> +++ b/arch/arm64/include/asm/kvm_asm.h
>> @@ -116,8 +116,11 @@
>>   struct kvm;
>>   struct kvm_vcpu;
>>
>> +extern char __hyp_stub_vectors[];
>
> Not a KVM thing (for the same reason).

Will remove it.

>> +
>>   extern char __kvm_hyp_init[];
>>   extern char __kvm_hyp_init_end[];
>> +extern char __kvm_hyp_reset[];
>>
>>   extern char __kvm_hyp_vector[];
>>
>> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
>> index 8ac3c70..97f88fe 100644
>> --- a/arch/arm64/include/asm/kvm_host.h
>> +++ b/arch/arm64/include/asm/kvm_host.h
>> @@ -199,6 +199,7 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
>>   struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
>>
>>   u64 kvm_call_hyp(void *hypfn, ...);
>> +void kvm_call_reset(unsigned long reset_func, ...);
>
> You seem to have a single call signature for this function, and have
> defined all the parameters below. You can drop the variadic aspect.

As Geoff suggested, the arguments of __cpu_reset_hyp_mode() and
kvm_call_reset() will be shuffled as in this order:
     phys_addr_t boot_pgd_ptr,
     phys_addr_t phys_idmap_start,
     unsigned long stub_vector_ptr
     unsigned long reset_func.


>>   void force_vm_exit(const cpumask_t *mask);
>>   void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
>>
>> @@ -223,6 +224,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
>>   		     hyp_stack_ptr, vector_ptr);
>>   }
>>
>> +static inline void __cpu_reset_hyp_mode(unsigned long reset_func,
>> +					phys_addr_t boot_pgd_ptr,
>> +					phys_addr_t phys_idmap_start,
>> +					unsigned long stub_vector_ptr)
>> +{
>> +	kvm_call_reset(reset_func, boot_pgd_ptr,
>> +		       phys_idmap_start, stub_vector_ptr);
>> +}
>> +
>>   struct vgic_sr_vectors {
>>   	void	*save_vgic;
>>   	void	*restore_vgic;
>> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
>> index 6458b53..36be582 100644
>> --- a/arch/arm64/include/asm/kvm_mmu.h
>> +++ b/arch/arm64/include/asm/kvm_mmu.h
>> @@ -96,6 +96,9 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
>>   phys_addr_t kvm_mmu_get_httbr(void);
>>   phys_addr_t kvm_mmu_get_boot_httbr(void);
>>   phys_addr_t kvm_get_idmap_vector(void);
>> +phys_addr_t kvm_get_idmap_start(void);
>> +phys_addr_t kvm_get_stub_vectors(void);
>> +unsigned long kvm_reset_func_entry(void);
>>   int kvm_mmu_init(void);
>>   void kvm_clear_hyp_idmap(void);
>>
>> diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
>> index 3070096..7fcd087 100644
>> --- a/arch/arm64/include/asm/virt.h
>> +++ b/arch/arm64/include/asm/virt.h
>> @@ -61,6 +61,17 @@
>>   #define BOOT_CPU_MODE_EL1	(0xe11)
>>   #define BOOT_CPU_MODE_EL2	(0xe12)
>>
>> +/*
>> + * HVC_RESET - Reset cpu in EL2 to initial state.
>> + *
>> + * @x0: entry address in trampoline code in va
>> + * @x1: identical mapping page table in pa
>> + * @x2: start address of identical mapping in pa
>> + * @x3: initial stub vector in pa
>> + */
>> +
>> +#define HVC_RESET 5
>> +
>>   #ifndef __ASSEMBLY__
>>
>>   /*
>> diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
>> index c319116..ca7e6bf 100644
>> --- a/arch/arm64/kvm/hyp-init.S
>> +++ b/arch/arm64/kvm/hyp-init.S
>> @@ -115,6 +115,47 @@ target: /* We're now in the trampoline code, switch page tables */
>>   	eret
>>   ENDPROC(__kvm_hyp_init)
>>
>> +	/*
>> +	 * x0: HYP boot pgd
>> +	 * x1: HYP phys_idmap_start
>> +	 * x2: HYP stub vectors
>> +	 */
>> +ENTRY(__kvm_hyp_reset)
>> +	/* We're in trampoline code in VA */
>> +	/* Invalidate the old TLBs */
>> +	tlbi	alle2
>> +	dsb	sy
>
> Invalidating the TLBs before switching TTBR0_EL2 is unlikely to have the
> effect you want.
>
>> +	/* Switch back to boot page tables */
>> +	msr	ttbr0_el2, x0
>> +	isb
>
> This is the place where you want TLBI to occur.

Will remove tlbi above and put it here.

>> +	/* Branch into PA space */
>> +	adr	x0, 1f
>> +	bfi	x1, x0, #0, #PAGE_SHIFT
>> +	br	x1
>> +
>> +	/* We're now in idmap */
>> +1:	/* Invalidate the old TLBs again */
>> +	tlbi	alle2
>> +	dsb	sy
>
> See? This is the only TLBI that actually makes sense. Now, given that
> you are actually disabling the MMU, I'm not sure these TBLIs make much
> sense.

Probably you're right, but
otherwise, I guess, bogus TLB might remain and be used when MMU get enabled again.
(MMU setting would be the same across disabling/enabling hyp mode though.)

>> +	/* Disable MMU */
>> +	mrs	x0, sctlr_el2
>> +	and	x1, x0, #SCTLR_EL2_EE
>> +	orr	x0, x0, x1		// preserve endianness of EL2
>> +	ldr	x1, =SCTLR_EL2_FLAGS
>> +	eor	x1, x1, xzr
>> +	bic	x0, x0, x1		// Clear SCTL_M and etc
>> +	msr	sctlr_el2, x0
>> +	isb
>> +
>> +	/* Switch back to stub vectors */
>> +	msr	vbar_el2, x2
>> +
>> +	eret
>> +ENDPROC(__kvm_hyp_reset)
>> +
>>   	.ltorg
>>
>>   	.popsection
>> diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
>> index fd085ec..aee75f9 100644
>> --- a/arch/arm64/kvm/hyp.S
>> +++ b/arch/arm64/kvm/hyp.S
>> @@ -1136,6 +1136,11 @@ ENTRY(kvm_call_hyp)
>>   	ret
>>   ENDPROC(kvm_call_hyp)
>>
>> +ENTRY(kvm_call_reset)
>> +	hvc	#HVC_RESET
>> +	ret
>> +ENDPROC(kvm_call_reset)
>> +
>>   .macro invalid_vector	label, target
>>   	.align	2
>>   \label:
>> @@ -1179,10 +1184,10 @@ el1_sync:					// Guest trapped into EL2
>>   	cmp	x18, #HVC_GET_VECTORS
>>   	b.ne	1f
>>   	mrs	x0, vbar_el2
>> -	b	2f
>> -
>> -1:	/* Default to HVC_CALL_HYP. */
>> +	b	3f
>>
>> +1:	cmp	x18, #HVC_CALL_HYP
>> +	b.ne	2f
>>   	push	lr, xzr
>>
>>   	/*
>> @@ -1196,7 +1201,23 @@ el1_sync:					// Guest trapped into EL2
>>   	blr	lr
>>
>>   	pop	lr, xzr
>> -2:	eret
>> +	b	3f
>> +
>> +	/*
>> +	 * shuffle the parameters and jump into trampline code.
>> +	 */
>> +2:	cmp	x18, #HVC_RESET
>> +	b.ne	3f
>> +
>> +	mov	x18, x0
>> +	mov	x0, x1
>> +	mov	x1, x2
>> +	mov	x2, x3
>> +	mov	x3, x4
>> +	br	x18
>
> I'd rather move the shuffling of the registers before the HVC call.

See above.

Thanks,
-Takahiro AKASHI

>> +	/* not reach here */
>> +
>> +3:	eret
>>
>>   el1_trap:
>>   	/*
>>
>
> Thanks,
>
> 	M.
>