Re: [RFC PATCH] KVM: PPC: Book3S: MMIO emulation support for little endian guests

["Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>]

Cédric Le Goater <clg@fr.ibm.com> writes:

> MMIO emulation reads the last instruction executed by the guest
> and then emulates. If the guest is running in Little Endian mode,
> the instruction needs to be byte-swapped before being emulated.
>
> This patch stores the last instruction in the endian order of the
> host, primarily doing a byte-swap if needed. The common code
> which fetches last_inst uses a helper routine kvmppc_need_byteswap().
> and the exit paths for the Book3S PV and HR guests use their own
> version in assembly.
>
> kvmppc_emulate_instruction() also uses kvmppc_need_byteswap() to
> define in which endian order the mmio needs to be done.
>
> The patch is based on Alex Graf's kvm-ppc-queue branch and it
> has been tested on Big Endian and Little Endian HV guests and
> Big Endian PR guests.
>
> Signed-off-by: Cédric Le Goater <clg@fr.ibm.com>
> ---
>
> Here are some comments/questions : 
>
>  * the host is assumed to be running in Big Endian. when Little Endian
>    hosts are supported in the future, we will use the cpu features to
>    fix kvmppc_need_byteswap()
>
>  * the 'is_bigendian' parameter of the routines kvmppc_handle_load()
>    and kvmppc_handle_store() seems redundant but the *BRX opcodes 
>    make the improvements unclear. We could eventually rename the
>    parameter to byteswap and the attribute vcpu->arch.mmio_is_bigendian
>    to vcpu->arch.mmio_need_byteswap. Anyhow, the current naming sucks
>    and I would happy to have some directions to fix it.
>
>
>
>  arch/powerpc/include/asm/kvm_book3s.h   |   15 ++++++-
>  arch/powerpc/kvm/book3s_64_mmu_hv.c     |    4 ++
>  arch/powerpc/kvm/book3s_hv_rmhandlers.S |   14 +++++-
>  arch/powerpc/kvm/book3s_segment.S       |   14 +++++-
>  arch/powerpc/kvm/emulate.c              |   71 +++++++++++++++++--------------
>  5 files changed, 83 insertions(+), 35 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
> index 0ec00f4..36c5573 100644
> --- a/arch/powerpc/include/asm/kvm_book3s.h
> +++ b/arch/powerpc/include/asm/kvm_book3s.h
> @@ -270,14 +270,22 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
>  	return vcpu->arch.pc;
>  }
>  
> +static inline bool kvmppc_need_byteswap(struct kvm_vcpu *vcpu)
> +{
> +	return vcpu->arch.shared->msr & MSR_LE;
> +}
> +

May be kvmppc_need_instbyteswap ?, because for data it also depend on
SLE bit ? Don't also need to check the host platform endianness here ?
ie, if host os __BIG_ENDIAN__ ?

>  static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
>  {
>  	ulong pc = kvmppc_get_pc(vcpu);
>  
>  	/* Load the instruction manually if it failed to do so in the
>  	 * exit path */
> -	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
> +	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) {
>  		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
> +		if (kvmppc_need_byteswap(vcpu))
> +			vcpu->arch.last_inst = swab32(vcpu->arch.last_inst);
> +	}
>  
>  	return vcpu->arch.last_inst;
>  }
> @@ -293,8 +301,11 @@ static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
>  
>  	/* Load the instruction manually if it failed to do so in the
>  	 * exit path */
> -	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
> +	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) {
>  		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
> +		if (kvmppc_need_byteswap(vcpu))
> +			vcpu->arch.last_inst = swab32(vcpu->arch.last_inst);
> +	}
>  
>  	return vcpu->arch.last_inst;
>  }
> diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
> index 3a89b85..28130c7 100644
> --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
> +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
> @@ -547,6 +547,10 @@ static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
>  		ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
>  		if (ret != EMULATE_DONE || last_inst == KVM_INST_FETCH_FAILED)
>  			return RESUME_GUEST;
> +
> +		if (kvmppc_need_byteswap(vcpu))
> +			last_inst = swab32(last_inst);
> +
>  		vcpu->arch.last_inst = last_inst;
>  	}
>  
> diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> index dd80953..1d3ee40 100644
> --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
> @@ -1393,14 +1393,26 @@ fast_interrupt_c_return:
>  	lwz	r8, 0(r10)
>  	mtmsrd	r3
>  
> +	ld	r0, VCPU_MSR(r9)
> +
> +	/* r10 = vcpu->arch.msr & MSR_LE */
> +	rldicl	r10, r0, 0, 63
> +	cmpdi	r10, 0
> +	bne	2f
> +
>  	/* Store the result */
>  	stw	r8, VCPU_LAST_INST(r9)
>  
>  	/* Unset guest mode. */
> -	li	r0, KVM_GUEST_MODE_NONE
> +1:	li	r0, KVM_GUEST_MODE_NONE
>  	stb	r0, HSTATE_IN_GUEST(r13)
>  	b	guest_exit_cont
>  
> +	/* Swap and store the result */
> +2:	addi	r11, r9, VCPU_LAST_INST
> +	stwbrx	r8, 0, r11
> +	b	1b
> +
>  /*
>   * Similarly for an HISI, reflect it to the guest as an ISI unless
>   * it is an HPTE not found fault for a page that we have paged out.
> diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
> index 1abe478..bf20b45 100644
> --- a/arch/powerpc/kvm/book3s_segment.S
> +++ b/arch/powerpc/kvm/book3s_segment.S
> @@ -287,7 +287,19 @@ ld_last_inst:
>  	sync
>  
>  #endif
> -	stw	r0, SVCPU_LAST_INST(r13)
> +	ld	r8, SVCPU_SHADOW_SRR1(r13)
> +
> +	/* r10 = vcpu->arch.msr & MSR_LE */
> +	rldicl	r10, r0, 0, 63

that should be  ?
	rldicl	r10, r8, 0, 63

-aneesh