[v4,05/13] arm64: kvm: allows kvm cpu hotplug

From: AKASHI Takahiro <takahiro.akashi@linaro.org>


The current kvm implementation on arm64 does cpu-specific initialization
at system boot, and has no way to gracefully shutdown a core in terms of
kvm. This prevents kexec from rebooting the system at EL2.

This patch adds a cpu tear-down function and also puts an existing cpu-init
code into a separate function, kvm_arch_hardware_disable() and
kvm_arch_hardware_enable() respectively.
We don't need the arm64 specific cpu hotplug hook any more.

Since this patch modifies common code between arm and arm64, one stub
definition, __cpu_reset_hyp_mode(), is added on arm side to avoid
compilation errors.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>

[Moved __kvm_hyp_reset() to use kvm_call_hyp(), instead of having its own
 dedicated entry point in el1_sync. Added some comments and a tlbi.]
Signed-off-by: James Morse <james.morse@arm.com>

---
This patch is from v13 of kexec, see my [changes] above.

 arch/arm/include/asm/kvm_host.h   | 10 +++-
 arch/arm/include/asm/kvm_mmu.h    |  1 +
 arch/arm/kvm/arm.c                | 98 ++++++++++++++++++++++++---------------
 arch/arm/kvm/mmu.c                |  5 ++
 arch/arm64/include/asm/kvm_host.h |  1 -
 arch/arm64/include/asm/kvm_mmu.h  | 19 ++++++++
 arch/arm64/kvm/hyp-init.S         | 42 +++++++++++++++++
 7 files changed, 136 insertions(+), 40 deletions(-)

-- 
2.6.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

On 01/28/2016 07:42 PM, James Morse wrote:
> From: AKASHI Takahiro <takahiro.akashi@linaro.org>

>

> The current kvm implementation on arm64 does cpu-specific initialization

> at system boot, and has no way to gracefully shutdown a core in terms of

> kvm. This prevents kexec from rebooting the system at EL2.

>

> This patch adds a cpu tear-down function and also puts an existing cpu-init

> code into a separate function, kvm_arch_hardware_disable() and

> kvm_arch_hardware_enable() respectively.

> We don't need the arm64 specific cpu hotplug hook any more.

>

> Since this patch modifies common code between arm and arm64, one stub

> definition, __cpu_reset_hyp_mode(), is added on arm side to avoid

> compilation errors.

>

> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>

> [Moved __kvm_hyp_reset() to use kvm_call_hyp(), instead of having its own

>   dedicated entry point in el1_sync. Added some comments and a tlbi.]

> Signed-off-by: James Morse <james.morse@arm.com>

> ---

> This patch is from v13 of kexec, see my [changes] above.

>

>   arch/arm/include/asm/kvm_host.h   | 10 +++-

>   arch/arm/include/asm/kvm_mmu.h    |  1 +

>   arch/arm/kvm/arm.c                | 98 ++++++++++++++++++++++++---------------

>   arch/arm/kvm/mmu.c                |  5 ++

>   arch/arm64/include/asm/kvm_host.h |  1 -

>   arch/arm64/include/asm/kvm_mmu.h  | 19 ++++++++

>   arch/arm64/kvm/hyp-init.S         | 42 +++++++++++++++++

>   7 files changed, 136 insertions(+), 40 deletions(-)

>

> diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h

> index f9f27792d8ed..8af531d64771 100644

> --- a/arch/arm/include/asm/kvm_host.h

> +++ b/arch/arm/include/asm/kvm_host.h

> @@ -220,6 +220,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,

>   	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);

>   }

>

> +static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,

> +					phys_addr_t phys_idmap_start)

> +{

> +	/*

> +	 * TODO

> +	 * kvm_call_reset(boot_pgd_ptr, phys_idmap_start);

> +	 */

> +}

> +

>   static inline int kvm_arch_dev_ioctl_check_extension(long ext)

>   {

>   	return 0;

> @@ -232,7 +241,6 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);

>

>   struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

>

> -static inline void kvm_arch_hardware_disable(void) {}

>   static inline void kvm_arch_hardware_unsetup(void) {}

>   static inline void kvm_arch_sync_events(struct kvm *kvm) {}

>   static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}

> diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h

> index a520b7987a29..4fd9ddb48c0f 100644

> --- a/arch/arm/include/asm/kvm_mmu.h

> +++ b/arch/arm/include/asm/kvm_mmu.h

> @@ -66,6 +66,7 @@ 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);

>   int kvm_mmu_init(void);

>   void kvm_clear_hyp_idmap(void);

>

> diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c

> index dda1959f0dde..f060567e9c0a 100644

> --- a/arch/arm/kvm/arm.c

> +++ b/arch/arm/kvm/arm.c

> @@ -16,7 +16,6 @@

>    * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.

>    */

>

> -#include <linux/cpu.h>

>   #include <linux/cpu_pm.h>

>   #include <linux/errno.h>

>   #include <linux/err.h>

> @@ -65,6 +64,8 @@ static DEFINE_SPINLOCK(kvm_vmid_lock);

>

>   static bool vgic_present;

>

> +static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled);

> +

>   static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)

>   {

>   	BUG_ON(preemptible());

> @@ -89,11 +90,6 @@ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)

>   	return &kvm_arm_running_vcpu;

>   }

>

> -int kvm_arch_hardware_enable(void)

> -{

> -	return 0;

> -}

> -

>   int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)

>   {

>   	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;

> @@ -585,7 +581,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)

>   		/*

>   		 * Re-check atomic conditions

>   		 */

> -		if (signal_pending(current)) {

> +		if (unlikely(!__this_cpu_read(kvm_arm_hardware_enabled))) {

> +			/* cpu has been torn down */

> +			ret = 0;

> +			run->exit_reason = KVM_EXIT_FAIL_ENTRY;

> +			run->fail_entry.hardware_entry_failure_reason

> +					= (u64)-ENOEXEC;

> +		} else if (signal_pending(current)) {

>   			ret = -EINTR;

>   			run->exit_reason = KVM_EXIT_INTR;

>   		}

> @@ -967,7 +969,7 @@ long kvm_arch_vm_ioctl(struct file *filp,

>   	}

>   }

>

> -static void cpu_init_hyp_mode(void *dummy)

> +static void cpu_init_hyp_mode(void)

>   {

>   	phys_addr_t boot_pgd_ptr;

>   	phys_addr_t pgd_ptr;

> @@ -989,36 +991,61 @@ static void cpu_init_hyp_mode(void *dummy)

>   	kvm_arm_init_debug();

>   }

>

> -static int hyp_init_cpu_notify(struct notifier_block *self,

> -			       unsigned long action, void *cpu)

> +static void cpu_reset_hyp_mode(void)

>   {

> -	switch (action) {

> -	case CPU_STARTING:

> -	case CPU_STARTING_FROZEN:

> -		if (__hyp_get_vectors() == hyp_default_vectors)

> -			cpu_init_hyp_mode(NULL);

> -		break;

> +	phys_addr_t boot_pgd_ptr;

> +	phys_addr_t phys_idmap_start;

> +

> +	boot_pgd_ptr = kvm_mmu_get_boot_httbr();

> +	phys_idmap_start = kvm_get_idmap_start();

> +

> +	__cpu_reset_hyp_mode(boot_pgd_ptr, phys_idmap_start);

> +}

> +

> +int kvm_arch_hardware_enable(void)

> +{

> +	if (!__this_cpu_read(kvm_arm_hardware_enabled)) {

> +		cpu_init_hyp_mode();

> +		__this_cpu_write(kvm_arm_hardware_enabled, 1);

>   	}

>

> -	return NOTIFY_OK;

> +	return 0;

>   }

>

> -static struct notifier_block hyp_init_cpu_nb = {

> -	.notifier_call = hyp_init_cpu_notify,

> -};

> +void kvm_arch_hardware_disable(void)

> +{

> +	if (!__this_cpu_read(kvm_arm_hardware_enabled))

> +		return;

> +

> +	cpu_reset_hyp_mode();

> +	__this_cpu_write(kvm_arm_hardware_enabled, 0);

> +}

>

>   #ifdef CONFIG_CPU_PM

>   static int hyp_init_cpu_pm_notifier(struct notifier_block *self,

>   				    unsigned long cmd,

>   				    void *v)

>   {

> -	if (cmd == CPU_PM_EXIT &&

> -	    __hyp_get_vectors() == hyp_default_vectors) {

> -		cpu_init_hyp_mode(NULL);

> +	/*

> +	 * kvm_arm_hardware_enabled is left with its old value over

> +	 * PM_ENTER->PM_EXIT. It is used to indicate PM_EXIT should

> +	 * re-enable hyp.

> +	 */

> +	switch (cmd) {

> +	case CPU_PM_ENTER:

> +		if (__this_cpu_read(kvm_arm_hardware_enabled))

> +			cpu_reset_hyp_mode();

> +

> +		return NOTIFY_OK;

> +	case CPU_PM_EXIT:

> +		if (__this_cpu_read(kvm_arm_hardware_enabled))

> +			cpu_init_hyp_mode();

> +

>   		return NOTIFY_OK;

> -	}

>

> -	return NOTIFY_DONE;

> +	default:

> +		return NOTIFY_DONE;

> +	}

>   }

>

>   static struct notifier_block hyp_init_cpu_pm_nb = {

> @@ -1122,14 +1149,20 @@ static int init_hyp_mode(void)

>   	}

>

>   	/*

> -	 * Execute the init code on each CPU.

> +	 * Init this CPU temporarily to execute kvm_hyp_call()

> +	 * during kvm_vgic_hyp_init().

>   	 */

> -	on_each_cpu(cpu_init_hyp_mode, NULL, 1);

> +	preempt_disable();

> +	cpu_init_hyp_mode();

>

>   	/*

>   	 * Init HYP view of VGIC

>   	 */

>   	err = kvm_vgic_hyp_init();

> +

> +	cpu_reset_hyp_mode();

> +	preempt_enable();

> +

>   	switch (err) {

>   	case 0:

>   		vgic_present = true;

> @@ -1213,26 +1246,15 @@ int kvm_arch_init(void *opaque)

>   		}

>   	}

>

> -	cpu_notifier_register_begin();

> -

>   	err = init_hyp_mode();

>   	if (err)

>   		goto out_err;

>

> -	err = __register_cpu_notifier(&hyp_init_cpu_nb);

> -	if (err) {

> -		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);

> -		goto out_err;

> -	}

> -

> -	cpu_notifier_register_done();

> -

>   	hyp_cpu_pm_init();

>

>   	kvm_coproc_table_init();

>   	return 0;

>   out_err:

> -	cpu_notifier_register_done();

>   	return err;

>   }

>

> diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c

> index aba61fd3697a..7a3aed62499a 100644

> --- a/arch/arm/kvm/mmu.c

> +++ b/arch/arm/kvm/mmu.c

> @@ -1643,6 +1643,11 @@ phys_addr_t kvm_get_idmap_vector(void)

>   	return hyp_idmap_vector;

>   }

>

> +phys_addr_t kvm_get_idmap_start(void)

> +{

> +	return hyp_idmap_start;

> +}

> +

>   int kvm_mmu_init(void)

>   {

>   	int err;

> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h

> index 689d4c95e12f..7d6d75616fb5 100644

> --- a/arch/arm64/include/asm/kvm_host.h

> +++ b/arch/arm64/include/asm/kvm_host.h

> @@ -332,7 +332,6 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,

>   		     hyp_stack_ptr, vector_ptr);

>   }

>

> -static inline void kvm_arch_hardware_disable(void) {}

>   static inline void kvm_arch_hardware_unsetup(void) {}

>   static inline void kvm_arch_sync_events(struct kvm *kvm) {}

>   static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}

> diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h

> index 736433912a1e..1d48208a904a 100644

> --- a/arch/arm64/include/asm/kvm_mmu.h

> +++ b/arch/arm64/include/asm/kvm_mmu.h

> @@ -99,6 +99,7 @@ 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);

>   int kvm_mmu_init(void);

>   void kvm_clear_hyp_idmap(void);

>

> @@ -310,5 +311,23 @@ static inline unsigned int kvm_get_vmid_bits(void)

>   	return (cpuid_feature_extract_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;

>   }

>

> +void __kvm_hyp_reset(phys_addr_t boot_pgd_ptr, phys_addr_t phys_idmap_start);

> +

> +/*

> + * Call reset code, and switch back to stub hyp vectors. We need to execute

> + * __kvm_hyp_reset() from the trampoline page, we calculate its address here.

> + */

> +static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,

> +					phys_addr_t phys_idmap_start)

> +{

> +	unsigned long trampoline_hyp_reset;

> +

> +	trampoline_hyp_reset = TRAMPOLINE_VA +

> +			       ((unsigned long)__kvm_hyp_reset & ~PAGE_MASK);

> +

> +	kvm_call_hyp((void *)trampoline_hyp_reset,

> +		     boot_pgd_ptr, phys_idmap_start);

> +}

> +


I want to place this definition in kvm_host.h as its counterpart, __cpu_init_hyp_mode().

-Takahiro AKASHI

>   #endif /* __ASSEMBLY__ */

>   #endif /* __ARM64_KVM_MMU_H__ */

> diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S

> index dc6335a7353e..d20d86c7f9d8 100644

> --- a/arch/arm64/kvm/hyp-init.S

> +++ b/arch/arm64/kvm/hyp-init.S

> @@ -150,6 +150,48 @@ merged:

>   	eret

>   ENDPROC(__kvm_hyp_init)

>

> +	/*

> +	 * x0: HYP boot pgd

> +	 * x1: HYP phys_idmap_start

> +	 */

> +ENTRY(__kvm_hyp_reset)

> +	/*

> +	 * Retrieve lr from the stack (pushed by el1_sync()), so we can eret

> +	 * from here.

> +	 */

> +	ldp	lr, xzr, [sp], #16

> +

> +	/* We're in trampoline code in VA, switch back to boot page tables */

> +	msr	ttbr0_el2, x0

> +	isb

> +

> +	/* Ensure the PA branch doesn't find a stale tlb entry. */

> +	tlbi	alle2

> +	dsb	sy

> +

> +	/* Branch into PA space */

> +	adr	x0, 1f

> +	bfi	x1, x0, #0, #PAGE_SHIFT

> +	br	x1

> +

> +	/* We're now in idmap, disable MMU */

> +1:	mrs	x0, sctlr_el2

> +	ldr	x1, =SCTLR_ELx_FLAGS

> +	bic	x0, x0, x1		// Clear SCTL_M and etc

> +	msr	sctlr_el2, x0

> +	isb

> +

> +	/* Invalidate the old TLBs */

> +	tlbi	alle2

> +	dsb	sy

> +

> +	/* Install stub vectors */

> +	adr_l	x0, __hyp_stub_vectors

> +	msr	vbar_el2, x0

> +

> +	eret

> +ENDPROC(__kvm_hyp_reset)

> +

>   	.ltorg

>

>   	.popsection

>


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel