[v3,21/33] KVM: PPC: Book3S HV: Framework to handle HV Emulation Assist Interrupt

From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>

A HEAI (hypervisor emulation assistance interrupt) occurs when a
hypervisor resource or instruction is used in a privileged but
non-hypervisor state and the LPCR_EVIRT bit is set in LPCR.  When
this occurs bit 45 is set in HSRR1.  Detect the occurrence of this,
and if userspace has enabled the nested virtualization capability
on the VM, then call the code to handle it accordingly.

With LPCR[EVIRT] set, we also get HEAI (without bit 45 set) for
mfspr or mtspr to unimplemented SPR numbers.  For these accesses,
we emulate the EVIRT=0 behaviour, which is to make the access
a no-op for privileged software unless it is accessing SPR 0,
4, 5 or 6.  Problem-state accesses and accesses to SPR 0, 4, 5
or 6 generate an illegal-instruction type program interrupt.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
 arch/powerpc/include/asm/kvm_book3s.h |  2 +
 arch/powerpc/include/asm/reg.h        |  1 +
 arch/powerpc/kvm/book3s_hv.c          | 87 ++++++++++++++++++++++-------------
 arch/powerpc/kvm/book3s_hv_nested.c   | 55 ++++++++++++++++++++++
 4 files changed, 113 insertions(+), 32 deletions(-)

On Tue, Oct 02, 2018 at 09:31:20PM +1000, Paul Mackerras wrote:
> From: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
> 
> A HEAI (hypervisor emulation assistance interrupt) occurs when a
> hypervisor resource or instruction is used in a privileged but
> non-hypervisor state and the LPCR_EVIRT bit is set in LPCR.  When
> this occurs bit 45 is set in HSRR1.  Detect the occurrence of this,
> and if userspace has enabled the nested virtualization capability
> on the VM, then call the code to handle it accordingly.
> 
> With LPCR[EVIRT] set, we also get HEAI (without bit 45 set) for
> mfspr or mtspr to unimplemented SPR numbers.  For these accesses,
> we emulate the EVIRT=0 behaviour, which is to make the access
> a no-op for privileged software unless it is accessing SPR 0,
> 4, 5 or 6.  Problem-state accesses and accesses to SPR 0, 4, 5
> or 6 generate an illegal-instruction type program interrupt.
> 
> Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> Signed-off-by: Suraj Jitindar Singh <sjitindarsingh@gmail.com>
> Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

Do we still need this if we're moving to paravirt tlbie?

> ---
>  arch/powerpc/include/asm/kvm_book3s.h |  2 +
>  arch/powerpc/include/asm/reg.h        |  1 +
>  arch/powerpc/kvm/book3s_hv.c          | 87 ++++++++++++++++++++++-------------
>  arch/powerpc/kvm/book3s_hv_nested.c   | 55 ++++++++++++++++++++++
>  4 files changed, 113 insertions(+), 32 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
> index 093fd70..0a97446 100644
> --- a/arch/powerpc/include/asm/kvm_book3s.h
> +++ b/arch/powerpc/include/asm/kvm_book3s.h
> @@ -287,6 +287,8 @@ void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
>  void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
>  				   struct hv_guest_state *hr);
>  long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu);
> +int kvmhv_emulate_priv(struct kvm_run *run, struct kvm_vcpu *vcpu,
> +			unsigned int instr);
>  
>  void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
>  
> diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
> index 6fda746..9c42abf 100644
> --- a/arch/powerpc/include/asm/reg.h
> +++ b/arch/powerpc/include/asm/reg.h
> @@ -456,6 +456,7 @@
>  #define   LPCR_HVICE		ASM_CONST(0x0000000000000002)      /* P9: HV interrupt enable */
>  #define   LPCR_HDICE		ASM_CONST(0x0000000000000001)      /* Hyp Decr enable (HV,PR,EE) */
>  #define   LPCR_UPRT		ASM_CONST(0x0000000000400000)      /* Use Process Table (ISA 3) */
> +#define   LPCR_EVIRT		ASM_CONST(0x0000000000200000)      /* Enhanced Virtualisation */
>  #define   LPCR_HR		ASM_CONST(0x0000000000100000)
>  #ifndef SPRN_LPID
>  #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 134d7c7..b975683 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -1027,30 +1027,6 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
>  	return kvmppc_hcall_impl_hv_realmode(cmd);
>  }
>  
> -static int kvmppc_emulate_debug_inst(struct kvm_run *run,
> -					struct kvm_vcpu *vcpu)
> -{
> -	u32 last_inst;
> -
> -	if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) !=
> -					EMULATE_DONE) {
> -		/*
> -		 * Fetch failed, so return to guest and
> -		 * try executing it again.
> -		 */
> -		return RESUME_GUEST;
> -	}
> -
> -	if (last_inst == KVMPPC_INST_SW_BREAKPOINT) {
> -		run->exit_reason = KVM_EXIT_DEBUG;
> -		run->debug.arch.address = kvmppc_get_pc(vcpu);
> -		return RESUME_HOST;
> -	} else {
> -		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
> -		return RESUME_GUEST;
> -	}
> -}
> -
>  static void do_nothing(void *x)
>  {
>  }
> @@ -1144,6 +1120,23 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu)
>  	return RESUME_GUEST;
>  }
>  
> +static int kvmhv_emulate_unknown_spr(struct kvm_vcpu *vcpu, u32 instr)
> +{
> +	u32 spr = get_sprn(instr);
> +
> +	/*
> +	 * In privileged state, access to unimplemented SPRs is a no-op
> +	 * except for SPR 0, 4, 5 and 6.  All other accesses get turned
> +	 * into illegal-instruction program interrupts.
> +	 */
> +	if ((vcpu->arch.shregs.msr & MSR_PR) ||
> +	    spr == 0 || (4 <= spr && spr <= 6))
> +		return EMULATE_FAIL;
> +
> +	kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4);
> +	return RESUME_GUEST;
> +}
> +
>  static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
>  				 struct task_struct *tsk)
>  {
> @@ -1260,19 +1253,49 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
>  	 * to the guest. If guest debug is enabled, we need to check
>  	 * whether the instruction is a software breakpoint instruction.
>  	 * Accordingly return to Guest or Host.
> +	 * With LPCR[EVIRT] set, we also get these for accesses to
> +	 * unknown SPRs and for guests executing hypervisor privileged
> +	 * instructions.
>  	 */
>  	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
> -		if (vcpu->arch.emul_inst != KVM_INST_FETCH_FAILED)
> -			vcpu->arch.last_inst = kvmppc_need_byteswap(vcpu) ?
> -				swab32(vcpu->arch.emul_inst) :
> -				vcpu->arch.emul_inst;
> -		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
> -			r = kvmppc_emulate_debug_inst(run, vcpu);
> +	{
> +		u32 instr = vcpu->arch.emul_inst;
> +		unsigned long srr1_bit = SRR1_PROGILL;
> +
> +		vcpu->arch.last_inst = kvmppc_need_byteswap(vcpu) ?
> +			swab32(instr) : instr;
> +
> +		r = EMULATE_FAIL;
> +		if (vcpu->arch.shregs.msr & SRR1_PROGPRIV) {
> +			/*
> +			 * Tried to execute hypervisor privileged instruction
> +			 * or mtspr/mfspr on a hypervisor privileged SPR while
> +			 * MSR(HV | PR) == 0b00 -> Privileged but !HV state
> +			 */
> +			srr1_bit = SRR1_PROGPRIV;
> +			if (vcpu->kvm->arch.nested_enable)
> +				r = kvmhv_emulate_priv(run, vcpu, instr);
>  		} else {
> -			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
> +			/* Illegal instruction or unknown SPR access */
> +			if (instr == KVMPPC_INST_SW_BREAKPOINT &&
> +			    (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)) {
> +				run->exit_reason = KVM_EXIT_DEBUG;
> +				run->debug.arch.address = kvmppc_get_pc(vcpu);
> +				r = RESUME_HOST;
> +				break;
> +			}
> +			if ((instr & 0xfc0006fe) == PPC_INST_MFSPR)
> +				/* mfspr or mtspr to unknown SPR, may be noop */
> +				r = kvmhv_emulate_unknown_spr(vcpu, instr);
> +		}
> +		if (r == EMULATE_FAIL) {
> +			pr_debug("KVM: Couldn't emulate instruction 0x%.8x\n",
> +				 instr);
> +			kvmppc_core_queue_program(vcpu, srr1_bit);
>  			r = RESUME_GUEST;
>  		}
>  		break;
> +	}
>  	/*
>  	 * This occurs if the guest (kernel or userspace), does something that
>  	 * is prohibited by HFSCR.
> @@ -4612,7 +4635,7 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
>  	 */
>  	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
>  		lpcr &= ~LPCR_VPM0;
> -		lpcr |= LPCR_HVICE | LPCR_HEIC;
> +		lpcr |= LPCR_HVICE | LPCR_HEIC | LPCR_EVIRT;
>  
>  		/*
>  		 * If xive is enabled, we route 0x500 interrupts directly
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index 4a381b4..f8f9fab 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -15,6 +15,7 @@
>  #include <asm/mmu.h>
>  #include <asm/pgtable.h>
>  #include <asm/pgalloc.h>
> +#include <asm/disassemble.h>
>  
>  static struct patb_entry *pseries_partition_tb;
>  
> @@ -515,3 +516,57 @@ long kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
>  {
>  	return RESUME_HOST;
>  }
> +
> +static int kvmhv_emulate_priv_mtspr(struct kvm_run *run, struct kvm_vcpu *vcpu,
> +				    unsigned int instr)
> +{
> +	return EMULATE_FAIL;
> +}
> +
> +static int kvmhv_emulate_priv_mfspr(struct kvm_run *run, struct kvm_vcpu *vcpu,
> +				    unsigned int instr)
> +{
> +	return EMULATE_FAIL;
> +}
> +
> +static int kvmhv_emulate_priv_op_31(struct kvm_run *run, struct kvm_vcpu *vcpu,
> +				    unsigned int instr)
> +{
> +	return EMULATE_FAIL;
> +}
> +
> +static int kvmhv_emulate_priv_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
> +				  unsigned int instr)
> +{
> +	return EMULATE_FAIL;
> +}
> +
> +int kvmhv_emulate_priv(struct kvm_run *run, struct kvm_vcpu *vcpu,
> +			unsigned int instr)
> +{
> +	int rc = EMULATE_FAIL;
> +
> +	switch (get_op(instr)) {
> +	case 31:
> +		switch (get_xop(instr)) {
> +		case OP_31_XOP_MTSPR:
> +			rc = kvmhv_emulate_priv_mtspr(run, vcpu, instr);
> +			break;
> +		case OP_31_XOP_MFSPR:
> +			rc = kvmhv_emulate_priv_mfspr(run, vcpu, instr);
> +			break;
> +		default:
> +			rc = kvmhv_emulate_priv_op_31(run, vcpu, instr);
> +			break;
> +		}
> +
> +		if (rc == EMULATE_DONE)
> +			kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4);
> +		break;
> +	default:
> +		rc = kvmhv_emulate_priv_op(run, vcpu, instr);
> +		break;
> +	}
> +
> +	return rc;
> +}