Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
On Tue, Mar 02, 2021 at 10:28:53AM +0530, Bharata B Rao wrote:
> On Tue, Mar 02, 2021 at 12:45:18PM +1100, David Gibson wrote:
> > > diff --git a/Documentation/virt/kvm/api.rst
> > > b/Documentation/virt/kvm/api.rst
> > > index 45fd862ac128..38ce3f21b21f 100644
> > > --- a/Documentation/virt/kvm/api.rst
> > > +++ b/Documentation/virt/kvm/api.rst
> > > @@ -6225,6 +6225,24 @@ KVM_RUN_BUS_LOCK flag is used to distinguish
> > > between them.
> > > This capability can be used to check / enable 2nd DAWR feature provided
> > > by POWER10 processor.
> > >
> > > +7.23 KVM_CAP_PPC_RPT_INVALIDATE
> > > +--
> > > +
> > > +:Capability: KVM_CAP_PPC_RPT_INVALIDATE
> > > +:Architectures: ppc
> > > +:Type: vm
> > > +
> > > +This capability indicates that the kernel is capable of handling
> > > +H_RPT_INVALIDATE hcall.
> > > +
> > > +In order to enable the use of H_RPT_INVALIDATE in the guest,
> > > +user space might have to advertise it for the guest. For example,
> > > +IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
> > > +present in the "ibm,hypertas-functions" device-tree property.
> > > +
> > > +This capability is enabled for hypervisors on platforms like POWER9
> > > +that support radix MMU.
> >
> > Does this mean that KVM will handle the hypercall, even if not
> > explicitly enabled by userspace (qemu)? That's generally not what we
> > want, since we need to allow qemu to set up backwards compatible
> > guests.
>
> This capability only indicates that hypervisor supports the hcall.
>
> QEMU will check for this and conditionally enable the hcall
> (via KVM_CAP_PPC_ENABLE_HCALL ioctl). Enabling the hcall is
> conditional to cap-rpt-invalidate sPAPR machine capability being
> enabled by the user. Will post a followup QEMU patch shortly.
Ok.
> Older QEMU patch can be found here:
> https://lists.gnu.org/archive/html/qemu-devel/2021-01/msg00627.html
>
> >
> > > +
> > > 8. Other capabilities.
> > > ==
> > >
> > > diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > > b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > > index 8b33601cdb9d..a46fd37ad552 100644
> > > --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > > +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > > @@ -4,6 +4,10 @@
> > >
> > > #include
> > >
> > > +#define RIC_FLUSH_TLB 0
> > > +#define RIC_FLUSH_PWC 1
> > > +#define RIC_FLUSH_ALL 2
> > > +
> > > struct vm_area_struct;
> > > struct mm_struct;
> > > struct mmu_gather;
> > > diff --git a/arch/powerpc/include/asm/kvm_book3s.h
> > > b/arch/powerpc/include/asm/kvm_book3s.h
> > > index 2f5f919f6cd3..a1515f94400e 100644
> > > --- a/arch/powerpc/include/asm/kvm_book3s.h
> > > +++ b/arch/powerpc/include/asm/kvm_book3s.h
> > > @@ -305,6 +305,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0,
> > > u64 dw1);
> > > void kvmhv_release_all_nested(struct kvm *kvm);
> > > long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
> > > long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
> > > +long kvmhv_h_rpti_nested(struct kvm_vcpu *vcpu, unsigned long lpid,
> > > + unsigned long type, unsigned long pg_sizes,
> > > + unsigned long start, unsigned long end);
> > > int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu,
> > > u64 time_limit, unsigned long lpcr);
> > > void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state
> > > *hr);
> > > diff --git a/arch/powerpc/include/asm/mmu_context.h
> > > b/arch/powerpc/include/asm/mmu_context.h
> > > index 652ce85f9410..820caf4e01b7 100644
> > > --- a/arch/powerpc/include/asm/mmu_context.h
> > > +++ b/arch/powerpc/include/asm/mmu_context.h
> > > @@ -124,8 +124,19 @@ static inline bool need_extra_context(struct
> > > mm_struct *mm, unsigned long ea)
> > >
> > > #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) &&
> > > defined(CONFIG_PPC_RADIX_MMU)
> > > extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
> > > +void do_h_rpt_invalidate(unsigned long pid, unsigned long lpid,
> > > + unsigned long type, unsigned long page_size,
> > > + unsigned long psize, unsigned long start,
> > > + unsigned long end);
> > > #else
> > > static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) {
> > > }
> > > +static inline void do_h_rpt_invalidate(unsigned long pid,
> > > +unsigned long lpid,
> > > +unsigned long type,
> > > +unsigned long page_size,
> > > +unsigned long psize,
> > > +unsigned long start,
> > > +unsigned long end) { }
> > > #endif
> > >
> > > extern void switch_cop(struct mm_struct *next);
> > > diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> > > index 13bad6bf4c95..d8
Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
On Tue, Mar 02, 2021 at 12:45:18PM +1100, David Gibson wrote:
> > diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> > index 45fd862ac128..38ce3f21b21f 100644
> > --- a/Documentation/virt/kvm/api.rst
> > +++ b/Documentation/virt/kvm/api.rst
> > @@ -6225,6 +6225,24 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between
> > them.
> > This capability can be used to check / enable 2nd DAWR feature provided
> > by POWER10 processor.
> >
> > +7.23 KVM_CAP_PPC_RPT_INVALIDATE
> > +--
> > +
> > +:Capability: KVM_CAP_PPC_RPT_INVALIDATE
> > +:Architectures: ppc
> > +:Type: vm
> > +
> > +This capability indicates that the kernel is capable of handling
> > +H_RPT_INVALIDATE hcall.
> > +
> > +In order to enable the use of H_RPT_INVALIDATE in the guest,
> > +user space might have to advertise it for the guest. For example,
> > +IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
> > +present in the "ibm,hypertas-functions" device-tree property.
> > +
> > +This capability is enabled for hypervisors on platforms like POWER9
> > +that support radix MMU.
>
> Does this mean that KVM will handle the hypercall, even if not
> explicitly enabled by userspace (qemu)? That's generally not what we
> want, since we need to allow qemu to set up backwards compatible
> guests.
This capability only indicates that hypervisor supports the hcall.
QEMU will check for this and conditionally enable the hcall
(via KVM_CAP_PPC_ENABLE_HCALL ioctl). Enabling the hcall is
conditional to cap-rpt-invalidate sPAPR machine capability being
enabled by the user. Will post a followup QEMU patch shortly.
Older QEMU patch can be found here:
https://lists.gnu.org/archive/html/qemu-devel/2021-01/msg00627.html
>
> > +
> > 8. Other capabilities.
> > ==
> >
> > diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > index 8b33601cdb9d..a46fd37ad552 100644
> > --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> > @@ -4,6 +4,10 @@
> >
> > #include
> >
> > +#define RIC_FLUSH_TLB 0
> > +#define RIC_FLUSH_PWC 1
> > +#define RIC_FLUSH_ALL 2
> > +
> > struct vm_area_struct;
> > struct mm_struct;
> > struct mmu_gather;
> > diff --git a/arch/powerpc/include/asm/kvm_book3s.h
> > b/arch/powerpc/include/asm/kvm_book3s.h
> > index 2f5f919f6cd3..a1515f94400e 100644
> > --- a/arch/powerpc/include/asm/kvm_book3s.h
> > +++ b/arch/powerpc/include/asm/kvm_book3s.h
> > @@ -305,6 +305,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0,
> > u64 dw1);
> > void kvmhv_release_all_nested(struct kvm *kvm);
> > long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
> > long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
> > +long kvmhv_h_rpti_nested(struct kvm_vcpu *vcpu, unsigned long lpid,
> > +unsigned long type, unsigned long pg_sizes,
> > +unsigned long start, unsigned long end);
> > int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu,
> > u64 time_limit, unsigned long lpcr);
> > void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
> > diff --git a/arch/powerpc/include/asm/mmu_context.h
> > b/arch/powerpc/include/asm/mmu_context.h
> > index 652ce85f9410..820caf4e01b7 100644
> > --- a/arch/powerpc/include/asm/mmu_context.h
> > +++ b/arch/powerpc/include/asm/mmu_context.h
> > @@ -124,8 +124,19 @@ static inline bool need_extra_context(struct mm_struct
> > *mm, unsigned long ea)
> >
> > #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
> > extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
> > +void do_h_rpt_invalidate(unsigned long pid, unsigned long lpid,
> > +unsigned long type, unsigned long page_size,
> > +unsigned long psize, unsigned long start,
> > +unsigned long end);
> > #else
> > static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
> > +static inline void do_h_rpt_invalidate(unsigned long pid,
> > + unsigned long lpid,
> > + unsigned long type,
> > + unsigned long page_size,
> > + unsigned long psize,
> > + unsigned long start,
> > + unsigned long end) { }
> > #endif
> >
> > extern void switch_cop(struct mm_struct *next);
> > diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> > index 13bad6bf4c95..d83f006fc19d 100644
> > --- a/arch/powerpc/kvm/book3s_hv.c
> > +++ b/arch/powerpc/kvm/book3s_hv.c
> > @@ -921,6 +921,69 @@ static int kvmppc_get_yield_count(struct kvm_vcpu
> > *vcpu)
> > return yield_count;
> > }
> >
> > +static void do_h_rpt_invalidate_prs(unsigned long pid, un
Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
On Wed, Feb 24, 2021 at 12:58:02PM -0300, Fabiano Rosas wrote:
> > @@ -1590,6 +1662,24 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu
> > *vcpu)
> > if (!xics_on_xive())
> > kvmppc_xics_rm_complete(vcpu, 0);
> > break;
> > + case BOOK3S_INTERRUPT_SYSCALL:
> > + {
> > + unsigned long req = kvmppc_get_gpr(vcpu, 3);
> > +
> > + /*
> > +* The H_RPT_INVALIDATE hcalls issued by nested
> > +* guests for process scoped invalidations when
> > +* GTSE=0, are handled here in L0.
> > +*/
> > + if (req == H_RPT_INVALIDATE) {
> > + kvmppc_nested_rpt_invalidate(vcpu);
> > + r = RESUME_GUEST;
> > + break;
> > + }
>
> I'm inclined to say this is a bit too early. We're handling the hcall
> before kvmhv_run_single_vcpu has fully finished and we'll skip some
> code that has been running in all guest exits:
>
> if (trap) {
> if (!nested)
> r = kvmppc_handle_exit_hv(vcpu, current);
> else
> r = kvmppc_handle_nested_exit(vcpu); <--- we're here
> }
> vcpu->arch.ret = r;
>
> (...)
>
> vcpu->arch.ceded = 0;
>
> vc->vcore_state = VCORE_INACTIVE;
> trace_kvmppc_run_core(vc, 1);
>
> done:
> kvmppc_remove_runnable(vc, vcpu);
> trace_kvmppc_run_vcpu_exit(vcpu);
>
> return vcpu->arch.ret;
>
> Especially the kvmppc_remove_runnable function because it sets the
> vcpu state:
>
> vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
>
> which should be the case if we're handling a hypercall.
>
> I suggest we do similarly to the L1 exit code and defer the hcall
> handling until after kvmppc_run_single_vcpu has exited, still inside the
> is_kvmppc_resume_guest(r) loop.
>
> So we'd set:
> case BOOK3S_INTERRUPT_SYSCALL:
> vcpu->run->exit_reason = KVM_EXIT_PAPR_HCALL;
> r = RESUME_HOST;
> break;
>
> and perhaps introduce a new kvmppc_pseries_do_nested_hcall that's called
> after kvmppc_run_single_vcpu.
Yes, looks like we should, but I wasn't sure if an exit similar to L1
exit for hcall handling is needed here too, hence took this approach.
Paul, could you please clarify?
Regards,
Bharata.
Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
On Wed, Feb 24, 2021 at 01:55:09PM +0530, Bharata B Rao wrote: > Implement H_RPT_INVALIDATE hcall and add KVM capability > KVM_CAP_PPC_RPT_INVALIDATE to indicate the support for the same. > > This hcall does two types of TLB invalidations: > > 1. Process-scoped invalidations for guests with LPCR[GTSE]=0. >This is currently not used in KVM as GTSE is not usually >disabled in KVM. > 2. Partition-scoped invalidations that an L1 hypervisor does on >behalf of an L2 guest. This replaces the uses of the existing >hcall H_TLB_INVALIDATE. > > In order to handle process scoped invalidations of L2, we > intercept the nested exit handling code in L0 only to handle > H_TLB_INVALIDATE hcall. > > Process scoped tlbie invalidations from L1 and nested guests > need RS register for TLBIE instruction to contain both PID and > LPID. This patch introduces primitives that execute tlbie > instruction with both PID and LPID set in prepartion for > H_RPT_INVALIDATE hcall. > > Signed-off-by: Bharata B Rao > --- > Documentation/virt/kvm/api.rst| 18 +++ > .../include/asm/book3s/64/tlbflush-radix.h| 4 + > arch/powerpc/include/asm/kvm_book3s.h | 3 + > arch/powerpc/include/asm/mmu_context.h| 11 ++ > arch/powerpc/kvm/book3s_hv.c | 90 +++ > arch/powerpc/kvm/book3s_hv_nested.c | 77 + > arch/powerpc/kvm/powerpc.c| 3 + > arch/powerpc/mm/book3s64/radix_tlb.c | 147 +- > include/uapi/linux/kvm.h | 1 + > 9 files changed, 350 insertions(+), 4 deletions(-) > > diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst > index 45fd862ac128..38ce3f21b21f 100644 > --- a/Documentation/virt/kvm/api.rst > +++ b/Documentation/virt/kvm/api.rst > @@ -6225,6 +6225,24 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between > them. > This capability can be used to check / enable 2nd DAWR feature provided > by POWER10 processor. > > +7.23 KVM_CAP_PPC_RPT_INVALIDATE > +-- > + > +:Capability: KVM_CAP_PPC_RPT_INVALIDATE > +:Architectures: ppc > +:Type: vm > + > +This capability indicates that the kernel is capable of handling > +H_RPT_INVALIDATE hcall. > + > +In order to enable the use of H_RPT_INVALIDATE in the guest, > +user space might have to advertise it for the guest. For example, > +IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is > +present in the "ibm,hypertas-functions" device-tree property. > + > +This capability is enabled for hypervisors on platforms like POWER9 > +that support radix MMU. Does this mean that KVM will handle the hypercall, even if not explicitly enabled by userspace (qemu)? That's generally not what we want, since we need to allow qemu to set up backwards compatible guests. > + > 8. Other capabilities. > == > > diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h > b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h > index 8b33601cdb9d..a46fd37ad552 100644 > --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h > +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h > @@ -4,6 +4,10 @@ > > #include > > +#define RIC_FLUSH_TLB 0 > +#define RIC_FLUSH_PWC 1 > +#define RIC_FLUSH_ALL 2 > + > struct vm_area_struct; > struct mm_struct; > struct mmu_gather; > diff --git a/arch/powerpc/include/asm/kvm_book3s.h > b/arch/powerpc/include/asm/kvm_book3s.h > index 2f5f919f6cd3..a1515f94400e 100644 > --- a/arch/powerpc/include/asm/kvm_book3s.h > +++ b/arch/powerpc/include/asm/kvm_book3s.h > @@ -305,6 +305,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 > dw1); > void kvmhv_release_all_nested(struct kvm *kvm); > long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu); > long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu); > +long kvmhv_h_rpti_nested(struct kvm_vcpu *vcpu, unsigned long lpid, > + unsigned long type, unsigned long pg_sizes, > + unsigned long start, unsigned long end); > int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, > u64 time_limit, unsigned long lpcr); > void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr); > diff --git a/arch/powerpc/include/asm/mmu_context.h > b/arch/powerpc/include/asm/mmu_context.h > index 652ce85f9410..820caf4e01b7 100644 > --- a/arch/powerpc/include/asm/mmu_context.h > +++ b/arch/powerpc/include/asm/mmu_context.h > @@ -124,8 +124,19 @@ static inline bool need_extra_context(struct mm_struct > *mm, unsigned long ea) > > #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU) > extern void radix_kvm_prefetch_workaround(struct mm_struct *mm); > +void do_h_rpt_invalidate(unsigned long pid, unsigned long lpid, > + unsigned long type, unsigned long page_size, > + unsigned long psize, unsigned long start, > + un
Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
Bharata B Rao writes:
> Implement H_RPT_INVALIDATE hcall and add KVM capability
> KVM_CAP_PPC_RPT_INVALIDATE to indicate the support for the same.
>
> This hcall does two types of TLB invalidations:
>
> 1. Process-scoped invalidations for guests with LPCR[GTSE]=0.
>This is currently not used in KVM as GTSE is not usually
>disabled in KVM.
> 2. Partition-scoped invalidations that an L1 hypervisor does on
>behalf of an L2 guest. This replaces the uses of the existing
>hcall H_TLB_INVALIDATE.
>
> In order to handle process scoped invalidations of L2, we
> intercept the nested exit handling code in L0 only to handle
> H_TLB_INVALIDATE hcall.
>
> Process scoped tlbie invalidations from L1 and nested guests
> need RS register for TLBIE instruction to contain both PID and
> LPID. This patch introduces primitives that execute tlbie
> instruction with both PID and LPID set in prepartion for
> H_RPT_INVALIDATE hcall.
>
> Signed-off-by: Bharata B Rao
> ---
> Documentation/virt/kvm/api.rst| 18 +++
> .../include/asm/book3s/64/tlbflush-radix.h| 4 +
> arch/powerpc/include/asm/kvm_book3s.h | 3 +
> arch/powerpc/include/asm/mmu_context.h| 11 ++
> arch/powerpc/kvm/book3s_hv.c | 90 +++
> arch/powerpc/kvm/book3s_hv_nested.c | 77 +
> arch/powerpc/kvm/powerpc.c| 3 +
> arch/powerpc/mm/book3s64/radix_tlb.c | 147 +-
> include/uapi/linux/kvm.h | 1 +
> 9 files changed, 350 insertions(+), 4 deletions(-)
>
> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> index 45fd862ac128..38ce3f21b21f 100644
> --- a/Documentation/virt/kvm/api.rst
> +++ b/Documentation/virt/kvm/api.rst
> @@ -6225,6 +6225,24 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between
> them.
> This capability can be used to check / enable 2nd DAWR feature provided
> by POWER10 processor.
>
> +7.23 KVM_CAP_PPC_RPT_INVALIDATE
> +--
> +
> +:Capability: KVM_CAP_PPC_RPT_INVALIDATE
> +:Architectures: ppc
> +:Type: vm
> +
> +This capability indicates that the kernel is capable of handling
> +H_RPT_INVALIDATE hcall.
> +
> +In order to enable the use of H_RPT_INVALIDATE in the guest,
> +user space might have to advertise it for the guest. For example,
> +IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
> +present in the "ibm,hypertas-functions" device-tree property.
> +
> +This capability is enabled for hypervisors on platforms like POWER9
> +that support radix MMU.
> +
> 8. Other capabilities.
> ==
>
> diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> index 8b33601cdb9d..a46fd37ad552 100644
> --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
> @@ -4,6 +4,10 @@
>
> #include
>
> +#define RIC_FLUSH_TLB 0
> +#define RIC_FLUSH_PWC 1
> +#define RIC_FLUSH_ALL 2
> +
> struct vm_area_struct;
> struct mm_struct;
> struct mmu_gather;
> diff --git a/arch/powerpc/include/asm/kvm_book3s.h
> b/arch/powerpc/include/asm/kvm_book3s.h
> index 2f5f919f6cd3..a1515f94400e 100644
> --- a/arch/powerpc/include/asm/kvm_book3s.h
> +++ b/arch/powerpc/include/asm/kvm_book3s.h
> @@ -305,6 +305,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64
> dw1);
> void kvmhv_release_all_nested(struct kvm *kvm);
> long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
> long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
> +long kvmhv_h_rpti_nested(struct kvm_vcpu *vcpu, unsigned long lpid,
> + unsigned long type, unsigned long pg_sizes,
> + unsigned long start, unsigned long end);
> int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu,
> u64 time_limit, unsigned long lpcr);
> void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
> diff --git a/arch/powerpc/include/asm/mmu_context.h
> b/arch/powerpc/include/asm/mmu_context.h
> index 652ce85f9410..820caf4e01b7 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -124,8 +124,19 @@ static inline bool need_extra_context(struct mm_struct
> *mm, unsigned long ea)
>
> #if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
> extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
> +void do_h_rpt_invalidate(unsigned long pid, unsigned long lpid,
> + unsigned long type, unsigned long page_size,
> + unsigned long psize, unsigned long start,
> + unsigned long end);
> #else
> static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
> +static inline void do_h_rpt_invalidate(unsigned long pid,
> +unsigned long lpid,
> +
[PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
Implement H_RPT_INVALIDATE hcall and add KVM capability
KVM_CAP_PPC_RPT_INVALIDATE to indicate the support for the same.
This hcall does two types of TLB invalidations:
1. Process-scoped invalidations for guests with LPCR[GTSE]=0.
This is currently not used in KVM as GTSE is not usually
disabled in KVM.
2. Partition-scoped invalidations that an L1 hypervisor does on
behalf of an L2 guest. This replaces the uses of the existing
hcall H_TLB_INVALIDATE.
In order to handle process scoped invalidations of L2, we
intercept the nested exit handling code in L0 only to handle
H_TLB_INVALIDATE hcall.
Process scoped tlbie invalidations from L1 and nested guests
need RS register for TLBIE instruction to contain both PID and
LPID. This patch introduces primitives that execute tlbie
instruction with both PID and LPID set in prepartion for
H_RPT_INVALIDATE hcall.
Signed-off-by: Bharata B Rao
---
Documentation/virt/kvm/api.rst| 18 +++
.../include/asm/book3s/64/tlbflush-radix.h| 4 +
arch/powerpc/include/asm/kvm_book3s.h | 3 +
arch/powerpc/include/asm/mmu_context.h| 11 ++
arch/powerpc/kvm/book3s_hv.c | 90 +++
arch/powerpc/kvm/book3s_hv_nested.c | 77 +
arch/powerpc/kvm/powerpc.c| 3 +
arch/powerpc/mm/book3s64/radix_tlb.c | 147 +-
include/uapi/linux/kvm.h | 1 +
9 files changed, 350 insertions(+), 4 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 45fd862ac128..38ce3f21b21f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6225,6 +6225,24 @@ KVM_RUN_BUS_LOCK flag is used to distinguish between
them.
This capability can be used to check / enable 2nd DAWR feature provided
by POWER10 processor.
+7.23 KVM_CAP_PPC_RPT_INVALIDATE
+--
+
+:Capability: KVM_CAP_PPC_RPT_INVALIDATE
+:Architectures: ppc
+:Type: vm
+
+This capability indicates that the kernel is capable of handling
+H_RPT_INVALIDATE hcall.
+
+In order to enable the use of H_RPT_INVALIDATE in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using it if "hcall-rpt-invalidate" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+This capability is enabled for hypervisors on platforms like POWER9
+that support radix MMU.
+
8. Other capabilities.
==
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 8b33601cdb9d..a46fd37ad552 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -4,6 +4,10 @@
#include
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
struct vm_area_struct;
struct mm_struct;
struct mmu_gather;
diff --git a/arch/powerpc/include/asm/kvm_book3s.h
b/arch/powerpc/include/asm/kvm_book3s.h
index 2f5f919f6cd3..a1515f94400e 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -305,6 +305,9 @@ void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64
dw1);
void kvmhv_release_all_nested(struct kvm *kvm);
long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu);
+long kvmhv_h_rpti_nested(struct kvm_vcpu *vcpu, unsigned long lpid,
+unsigned long type, unsigned long pg_sizes,
+unsigned long start, unsigned long end);
int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu,
u64 time_limit, unsigned long lpcr);
void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
diff --git a/arch/powerpc/include/asm/mmu_context.h
b/arch/powerpc/include/asm/mmu_context.h
index 652ce85f9410..820caf4e01b7 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -124,8 +124,19 @@ static inline bool need_extra_context(struct mm_struct
*mm, unsigned long ea)
#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE) && defined(CONFIG_PPC_RADIX_MMU)
extern void radix_kvm_prefetch_workaround(struct mm_struct *mm);
+void do_h_rpt_invalidate(unsigned long pid, unsigned long lpid,
+unsigned long type, unsigned long page_size,
+unsigned long psize, unsigned long start,
+unsigned long end);
#else
static inline void radix_kvm_prefetch_workaround(struct mm_struct *mm) { }
+static inline void do_h_rpt_invalidate(unsigned long pid,
+ unsigned long lpid,
+ unsigned long type,
+ unsigned long page_size,
+ unsigned long psize,
+ unsigned long start,
+
