[PATCH v5 0/3] Support for H_RPT_INVALIDATE in PowerPC KVM

[PATCH v5 0/3] Support for H_RPT_INVALIDATE in PowerPC KVM

[Bharata B Rao]

This patchset adds support for the new hcall H_RPT_INVALIDATE
and replaces the nested tlb flush calls with this new hcall
if support for the same exists.

Changes in v5:
-------------
- Included the h_rpt_invalidate page size information within
  mmu_pszie_defs[] as per David Gibson's suggestion.
- Redid nested exit changes as per Paul Mackerras' suggestion.
- Folded the patch that added tlbie primitives into the
  hcall implementation patch.

v4: https://lore.kernel.org/linuxppc-dev/20210215063542.3642366-1-bharata@linux.ibm.com/T/#t

Bharata B Rao (3):
  powerpc/book3s64/radix: Add H_RPT_INVALIDATE pgsize encodings to
    mmu_psize_def
  KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
  KVM: PPC: Book3S HV: Use H_RPT_INVALIDATE in nested KVM

 Documentation/virt/kvm/api.rst                |  18 +++
 arch/powerpc/include/asm/book3s/64/mmu.h      |   1 +
 .../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_64_mmu_radix.c        |  27 +++-
 arch/powerpc/kvm/book3s_hv.c                  |  90 +++++++++++
 arch/powerpc/kvm/book3s_hv_nested.c           |  89 ++++++++++-
 arch/powerpc/kvm/powerpc.c                    |   3 +
 arch/powerpc/mm/book3s64/radix_pgtable.c      |   5 +
 arch/powerpc/mm/book3s64/radix_tlb.c          | 147 +++++++++++++++++-
 include/uapi/linux/kvm.h                      |   1 +
 12 files changed, 388 insertions(+), 11 deletions(-)

-- 
2.26.2

[PATCH v5 1/3] powerpc/book3s64/radix: Add H_RPT_INVALIDATE pgsize encodings to mmu_psize_def

[Bharata B Rao]

Add a field to mmu_psize_def to store the page size encodings
of H_RPT_INVALIDATE hcall. Initialize this while scanning the radix
AP encodings. This will be used when invalidating with required
page size encoding in the hcall.

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/mmu.h | 1 +
 arch/powerpc/mm/book3s64/radix_pgtable.c | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index eace8c3f7b0a..c02f42d1031e 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -19,6 +19,7 @@ struct mmu_psize_def {
 	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
 	unsigned int	tlbiel;	/* tlbiel supported for that page size */
 	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
+	unsigned long   h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */
 	union {
 		unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
 		unsigned long ap;	/* Ap encoding used by PowerISA 3.0 */
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 98f0b243c1ab..1b749899016b 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -486,6 +486,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
 		def = &mmu_psize_defs[idx];
 		def->shift = shift;
 		def->ap  = ap;
+		def->h_rpt_pgsize = psize_to_rpti_pgsize(idx);
 	}
 
 	/* needed ? */
@@ -560,9 +561,13 @@ void __init radix__early_init_devtree(void)
 		 */
 		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
 		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
+		mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize =
+			psize_to_rpti_pgsize(MMU_PAGE_4K);
 
 		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
 		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
+		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
+			psize_to_rpti_pgsize(MMU_PAGE_64K);
 	}
 
 	/*
-- 
2.26.2

Re: [PATCH v5 1/3] powerpc/book3s64/radix: Add H_RPT_INVALIDATE pgsize encodings to mmu_psize_def

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 2627 bytes --]

On Wed, Feb 24, 2021 at 01:55:08PM +0530, Bharata B Rao wrote:
> Add a field to mmu_psize_def to store the page size encodings
> of H_RPT_INVALIDATE hcall. Initialize this while scanning the radix
> AP encodings. This will be used when invalidating with required
> page size encoding in the hcall.
> 
> Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> ---
>  arch/powerpc/include/asm/book3s/64/mmu.h | 1 +
>  arch/powerpc/mm/book3s64/radix_pgtable.c | 5 +++++
>  2 files changed, 6 insertions(+)
> 
> diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
> index eace8c3f7b0a..c02f42d1031e 100644
> --- a/arch/powerpc/include/asm/book3s/64/mmu.h
> +++ b/arch/powerpc/include/asm/book3s/64/mmu.h
> @@ -19,6 +19,7 @@ struct mmu_psize_def {
>  	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
>  	unsigned int	tlbiel;	/* tlbiel supported for that page size */
>  	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
> +	unsigned long   h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */
>  	union {
>  		unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
>  		unsigned long ap;	/* Ap encoding used by PowerISA 3.0 */
> diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
> index 98f0b243c1ab..1b749899016b 100644
> --- a/arch/powerpc/mm/book3s64/radix_pgtable.c
> +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
> @@ -486,6 +486,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
>  		def = &mmu_psize_defs[idx];
>  		def->shift = shift;
>  		def->ap  = ap;
> +		def->h_rpt_pgsize = psize_to_rpti_pgsize(idx);
>  	}
>  
>  	/* needed ? */
> @@ -560,9 +561,13 @@ void __init radix__early_init_devtree(void)
>  		 */
>  		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
>  		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
> +		mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize =
> +			psize_to_rpti_pgsize(MMU_PAGE_4K);

Hm.  TBH, I was thinking of this as replacing psize_to_rpti_pgsize() -
that is, you directly put the correct codes in there, then just have
psize_to_rpti_pgsize() look them up in the table.

I guess that could be a followup change, though.

>  
>  		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
>  		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
> +		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
> +			psize_to_rpti_pgsize(MMU_PAGE_64K);
>  	}
>  
>  	/*

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v5 1/3] powerpc/book3s64/radix: Add H_RPT_INVALIDATE pgsize encodings to mmu_psize_def

[Bharata B Rao]

On Tue, Mar 02, 2021 at 12:28:34PM +1100, David Gibson wrote:
> On Wed, Feb 24, 2021 at 01:55:08PM +0530, Bharata B Rao wrote:
> > Add a field to mmu_psize_def to store the page size encodings
> > of H_RPT_INVALIDATE hcall. Initialize this while scanning the radix
> > AP encodings. This will be used when invalidating with required
> > page size encoding in the hcall.
> > 
> > Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> > ---
> >  arch/powerpc/include/asm/book3s/64/mmu.h | 1 +
> >  arch/powerpc/mm/book3s64/radix_pgtable.c | 5 +++++
> >  2 files changed, 6 insertions(+)
> > 
> > diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
> > index eace8c3f7b0a..c02f42d1031e 100644
> > --- a/arch/powerpc/include/asm/book3s/64/mmu.h
> > +++ b/arch/powerpc/include/asm/book3s/64/mmu.h
> > @@ -19,6 +19,7 @@ struct mmu_psize_def {
> >  	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
> >  	unsigned int	tlbiel;	/* tlbiel supported for that page size */
> >  	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
> > +	unsigned long   h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */
> >  	union {
> >  		unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
> >  		unsigned long ap;	/* Ap encoding used by PowerISA 3.0 */
> > diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
> > index 98f0b243c1ab..1b749899016b 100644
> > --- a/arch/powerpc/mm/book3s64/radix_pgtable.c
> > +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
> > @@ -486,6 +486,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
> >  		def = &mmu_psize_defs[idx];
> >  		def->shift = shift;
> >  		def->ap  = ap;
> > +		def->h_rpt_pgsize = psize_to_rpti_pgsize(idx);
> >  	}
> >  
> >  	/* needed ? */
> > @@ -560,9 +561,13 @@ void __init radix__early_init_devtree(void)
> >  		 */
> >  		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
> >  		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
> > +		mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize =
> > +			psize_to_rpti_pgsize(MMU_PAGE_4K);
> 
> Hm.  TBH, I was thinking of this as replacing psize_to_rpti_pgsize() -
> that is, you directly put the correct codes in there, then just have
> psize_to_rpti_pgsize() look them up in the table.
> 
> I guess that could be a followup change, though.
> 
> >  
> >  		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
> >  		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
> > +		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
> > +			psize_to_rpti_pgsize(MMU_PAGE_64K);

Hmm if you see I got rid of rpti_pgsize_to_psize() by having the
defines directly in mmu_psize_def[].

There are two cases in the above code (radix__early_init_devtree)

1. If radix pagesize encodings are present in the DT, we walk
the page sizes in the loop and populate the enconding for
H_RPT_INVALIDATE. I am not sure if we can use the direct codes
in this case.

2. If DT doesn't have the radix pagesize encodings, 4K and 64K
sizes are assumed as fallback sizes where we can use direct
encodings.

Regards,
Bharata.

Re: [PATCH v5 1/3] powerpc/book3s64/radix: Add H_RPT_INVALIDATE pgsize encodings to mmu_psize_def

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 4037 bytes --]

On Tue, Mar 02, 2021 at 09:51:28AM +0530, Bharata B Rao wrote:
> On Tue, Mar 02, 2021 at 12:28:34PM +1100, David Gibson wrote:
> > On Wed, Feb 24, 2021 at 01:55:08PM +0530, Bharata B Rao wrote:
> > > Add a field to mmu_psize_def to store the page size encodings
> > > of H_RPT_INVALIDATE hcall. Initialize this while scanning the radix
> > > AP encodings. This will be used when invalidating with required
> > > page size encoding in the hcall.
> > > 
> > > Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
> > > ---
> > >  arch/powerpc/include/asm/book3s/64/mmu.h | 1 +
> > >  arch/powerpc/mm/book3s64/radix_pgtable.c | 5 +++++
> > >  2 files changed, 6 insertions(+)
> > > 
> > > diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
> > > index eace8c3f7b0a..c02f42d1031e 100644
> > > --- a/arch/powerpc/include/asm/book3s/64/mmu.h
> > > +++ b/arch/powerpc/include/asm/book3s/64/mmu.h
> > > @@ -19,6 +19,7 @@ struct mmu_psize_def {
> > >  	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
> > >  	unsigned int	tlbiel;	/* tlbiel supported for that page size */
> > >  	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
> > > +	unsigned long   h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */
> > >  	union {
> > >  		unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
> > >  		unsigned long ap;	/* Ap encoding used by PowerISA 3.0 */
> > > diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
> > > index 98f0b243c1ab..1b749899016b 100644
> > > --- a/arch/powerpc/mm/book3s64/radix_pgtable.c
> > > +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
> > > @@ -486,6 +486,7 @@ static int __init radix_dt_scan_page_sizes(unsigned long node,
> > >  		def = &mmu_psize_defs[idx];
> > >  		def->shift = shift;
> > >  		def->ap  = ap;
> > > +		def->h_rpt_pgsize = psize_to_rpti_pgsize(idx);
> > >  	}
> > >  
> > >  	/* needed ? */
> > > @@ -560,9 +561,13 @@ void __init radix__early_init_devtree(void)
> > >  		 */
> > >  		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
> > >  		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
> > > +		mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize =
> > > +			psize_to_rpti_pgsize(MMU_PAGE_4K);
> > 
> > Hm.  TBH, I was thinking of this as replacing psize_to_rpti_pgsize() -
> > that is, you directly put the correct codes in there, then just have
> > psize_to_rpti_pgsize() look them up in the table.
> > 
> > I guess that could be a followup change, though.
> > 
> > >  
> > >  		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
> > >  		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
> > > +		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
> > > +			psize_to_rpti_pgsize(MMU_PAGE_64K);
> 
> Hmm if you see I got rid of rpti_pgsize_to_psize() by having the
> defines directly in mmu_psize_def[].

I realize that, but I'm talking about the reverse direction:
psize_to_rpti_pgsize().  You should be able to reduce it a table
lookup, so the mmu_psize_defs table is the only place this information
exists.

> There are two cases in the above code (radix__early_init_devtree)
> 
> 1. If radix pagesize encodings are present in the DT, we walk
> the page sizes in the loop and populate the enconding for
> H_RPT_INVALIDATE. I am not sure if we can use the direct codes
> in this case.

I'm not understanding the problem.

In any case the existing implementation of psize

Why ever not?  You can just update the mmu_psize_defs when you parse
the device tree.  Plus AFAICT, the existing psize_to_rpti
implementation doesn't take into account any device tree eencodings.

> 2. If DT doesn't have the radix pagesize encodings, 4K and 64K
> sizes are assumed as fallback sizes where we can use direct
> encodings.

Right... still not seeing the problem.

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE

[Bharata B Rao]

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 <bharata@linux.ibm.com>
---
 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 <asm/hvcall.h>
 
+#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, unsigned long lpid,
+				    unsigned long type, unsigned long pg_sizes,
+				    unsigned long start, unsigned long end)
+{
+	unsigned long psize;
+	struct mmu_psize_def *def;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+		def = &mmu_psize_defs[psize];
+		if (pg_sizes & def->h_rpt_pgsize)
+			do_h_rpt_invalidate(pid, lpid, type,
+					    (1UL << def->shift), psize,
+					    start, end);
+	}
+}
+
+static void kvmppc_nested_rpt_invalidate(struct kvm_vcpu *vcpu)
+{
+	do_h_rpt_invalidate_prs(kvmppc_get_gpr(vcpu, 4),
+				vcpu->arch.nested->shadow_lpid,
+				kvmppc_get_gpr(vcpu, 5),
+				kvmppc_get_gpr(vcpu, 6),
+				kvmppc_get_gpr(vcpu, 7),
+				kvmppc_get_gpr(vcpu, 8));
+	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+}
+
+static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
+				    unsigned long pid, unsigned long target,
+				    unsigned long type, unsigned long pg_sizes,
+				    unsigned long start, unsigned long end)
+{
+	if (!kvm_is_radix(vcpu->kvm))
+		return H_UNSUPPORTED;
+
+	/*
+	 * For nested guests, this hcall is handled in
+	 * L0. See kvmppc_handle_nested_exit() for details.
+	 */
+	if (kvmhv_on_pseries())
+		return H_UNSUPPORTED;
+
+	if (end < start)
+		return H_P5;
+
+	if (type & H_RPTI_TYPE_NESTED) {
+		if (!nesting_enabled(vcpu->kvm))
+			return H_FUNCTION;
+
+		/* Support only cores as target */
+		if (target != H_RPTI_TARGET_CMMU)
+			return H_P2;
+
+		return kvmhv_h_rpti_nested(vcpu, pid,
+					   (type & ~H_RPTI_TYPE_NESTED),
+					    pg_sizes, start, end);
+	}
+
+	do_h_rpt_invalidate_prs(pid, vcpu->kvm->arch.lpid, type, pg_sizes,
+				start, end);
+	return H_SUCCESS;
+}
+
 int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 {
 	unsigned long req = kvmppc_get_gpr(vcpu, 3);
@@ -1129,6 +1192,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		 */
 		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
 		break;
+	case H_RPT_INVALIDATE:
+		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
+					      kvmppc_get_gpr(vcpu, 5),
+					      kvmppc_get_gpr(vcpu, 6),
+					      kvmppc_get_gpr(vcpu, 7),
+					      kvmppc_get_gpr(vcpu, 8),
+					      kvmppc_get_gpr(vcpu, 9));
+		break;
 
 	default:
 		return RESUME_HOST;
@@ -1175,6 +1246,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_XIRR_X:
 #endif
 	case H_PAGE_INIT:
+	case H_RPT_INVALIDATE:
 		return 1;
 	}
 
@@ -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;
+		}
+
+		r = RESUME_HOST;
+		break;
+	}
 	default:
 		r = RESUME_HOST;
 		break;
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 0cd0e7aad588..ca43b2d38dce 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -1191,6 +1191,83 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
 	return H_SUCCESS;
 }
 
+static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
+					 unsigned long lpid,
+					 unsigned long page_size,
+					 unsigned long ap,
+					 unsigned long start,
+					 unsigned long end)
+{
+	unsigned long addr = start;
+	int ret;
+
+	do {
+		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
+						   get_epn(addr));
+		if (ret)
+			return ret;
+		addr += page_size;
+	} while (addr < end);
+
+	return ret;
+}
+
+static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
+					 unsigned long lpid)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_nested_guest *gp;
+
+	gp = kvmhv_get_nested(kvm, lpid, false);
+	if (gp) {
+		kvmhv_emulate_tlbie_lpid(vcpu, gp, RIC_FLUSH_ALL);
+		kvmhv_put_nested(gp);
+	}
+	return H_SUCCESS;
+}
+
+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)
+{
+	struct kvm_nested_guest *gp;
+	long ret;
+	unsigned long psize, ap;
+
+	/*
+	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
+	 *
+	 * However, nested KVM issues a L2 lpid flush call when creating
+	 * partition table entries for L2. This happens even before the
+	 * corresponding shadow lpid is created in HV which happens in
+	 * H_ENTER_NESTED call. Since we can't differentiate this case from
+	 * the invalid case, we ignore such flush requests and return success.
+	 */
+	gp = kvmhv_find_nested(vcpu->kvm, lpid);
+	if (!gp)
+		return H_SUCCESS;
+
+	if ((type & H_RPTI_TYPE_NESTED_ALL) == H_RPTI_TYPE_NESTED_ALL)
+		return do_tlb_invalidate_nested_all(vcpu, lpid);
+
+	if ((type & H_RPTI_TYPE_TLB) == H_RPTI_TYPE_TLB) {
+		struct mmu_psize_def *def;
+
+		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+			def = &mmu_psize_defs[psize];
+			if (!(pg_sizes & def->h_rpt_pgsize))
+				continue;
+
+			ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
+							   (1UL << def->shift),
+							   ap, start, end);
+			if (ret)
+				return H_P4;
+		}
+	}
+	return H_SUCCESS;
+}
+
 /* Used to convert a nested guest real address to a L1 guest real address */
 static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
 				       struct kvm_nested_guest *gp,
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a2a68a958fa0..be33b5321a76 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -682,6 +682,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
 		       !kvmppc_hv_ops->enable_dawr1(NULL));
 		break;
+	case KVM_CAP_PPC_RPT_INVALIDATE:
+		r = 1;
+		break;
 #endif
 	default:
 		r = 0;
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 409e61210789..440d84fffa8c 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -20,10 +20,6 @@
 
 #include "internal.h"
 
-#define RIC_FLUSH_TLB 0
-#define RIC_FLUSH_PWC 1
-#define RIC_FLUSH_ALL 2
-
 /*
  * tlbiel instruction for radix, set invalidation
  * i.e., r=1 and is=01 or is=10 or is=11
@@ -130,6 +126,21 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static __always_inline void __tlbie_pid_lpid(unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = PPC_BIT(53); /* IS = 1 */
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
 static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -190,6 +201,23 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
+static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
+					    unsigned long lpid,
+					    unsigned long ap, unsigned long ric)
+{
+	unsigned long rb, rs, prs, r;
+
+	rb = va & ~(PPC_BITMASK(52, 63));
+	rb |= ap << PPC_BITLSHIFT(58);
+	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
+	prs = 1; /* process scoped */
+	r = 1;   /* radix format */
+
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
+		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
+	trace_tlbie(0, 0, rb, rs, ric, prs, r);
+}
+
 static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
 					    unsigned long ap, unsigned long ric)
 {
@@ -235,6 +263,22 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
 	}
 }
 
+static inline void fixup_tlbie_va_range_lpid(unsigned long va,
+					     unsigned long pid,
+					     unsigned long lpid,
+					     unsigned long ap)
+{
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
+	}
+}
+
 static inline void fixup_tlbie_pid(unsigned long pid)
 {
 	/*
@@ -254,6 +298,25 @@ static inline void fixup_tlbie_pid(unsigned long pid)
 	}
 }
 
+static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
+{
+	/*
+	 * We can use any address for the invalidation, pick one which is
+	 * probably unused as an optimisation.
+	 */
+	unsigned long va = ((1UL << 52) - 1);
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
+	}
+
+	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
+		asm volatile("ptesync" : : : "memory");
+		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
+				RIC_FLUSH_TLB);
+	}
+}
 
 static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
 				       unsigned long ap)
@@ -344,6 +407,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
+				   unsigned long ric)
+{
+	asm volatile("ptesync" : : : "memory");
+
+	/*
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
+	 */
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
+		fixup_tlbie_pid_lpid(pid, lpid);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
+		fixup_tlbie_pid_lpid(pid, lpid);
+	}
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
 struct tlbiel_pid {
 	unsigned long pid;
 	unsigned long ric;
@@ -469,6 +557,20 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
 	fixup_tlbie_va_range(addr - page_size, pid, ap);
 }
 
+static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					 unsigned long pid, unsigned long lpid,
+					 unsigned long page_size,
+					 unsigned long psize)
+{
+	unsigned long addr;
+	unsigned long ap = mmu_get_ap(psize);
+
+	for (addr = start; addr < end; addr += page_size)
+		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
+
+	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
+}
+
 static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
 				      unsigned long psize, unsigned long ric)
 {
@@ -549,6 +651,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
+					unsigned long pid, unsigned long lpid,
+					unsigned long page_size,
+					unsigned long psize, bool also_pwc)
+{
+	asm volatile("ptesync" : : : "memory");
+	if (also_pwc)
+		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+}
+
 static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
 				unsigned long start, unsigned long end,
 				unsigned long pid, unsigned long page_size,
@@ -1381,4 +1495,29 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 	}
 }
 EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
+
+/*
+ * Process-scoped invalidations for a given LPID.
+ */
+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)
+{
+	if ((type & H_RPTI_TYPE_ALL) == H_RPTI_TYPE_ALL) {
+		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
+		return;
+	}
+
+	if (type & H_RPTI_TYPE_PWC)
+		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
+
+	if (!start && end == -1) /* PID */
+		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
+	else /* EA */
+		_tlbie_va_range_lpid(start, end, pid, lpid, page_size,
+				     psize, false);
+}
+EXPORT_SYMBOL_GPL(do_h_rpt_invalidate);
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 8b281f722e5b..f8c84a62e8f3 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1078,6 +1078,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_DIRTY_LOG_RING 192
 #define KVM_CAP_X86_BUS_LOCK_EXIT 193
 #define KVM_CAP_PPC_DAWR1 194
+#define KVM_CAP_PPC_RPT_INVALIDATE 195
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.26.2

Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE

[Fabiano Rosas]

Bharata B Rao <bharata@linux.ibm.com> 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 <bharata@linux.ibm.com>
> ---
>  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 <asm/hvcall.h>
>  
> +#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, unsigned long lpid,
> +				    unsigned long type, unsigned long pg_sizes,
> +				    unsigned long start, unsigned long end)
> +{
> +	unsigned long psize;
> +	struct mmu_psize_def *def;
> +
> +	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +		def = &mmu_psize_defs[psize];
> +		if (pg_sizes & def->h_rpt_pgsize)
> +			do_h_rpt_invalidate(pid, lpid, type,
> +					    (1UL << def->shift), psize,
> +					    start, end);
> +	}
> +}
> +
> +static void kvmppc_nested_rpt_invalidate(struct kvm_vcpu *vcpu)
> +{
> +	do_h_rpt_invalidate_prs(kvmppc_get_gpr(vcpu, 4),
> +				vcpu->arch.nested->shadow_lpid,
> +				kvmppc_get_gpr(vcpu, 5),
> +				kvmppc_get_gpr(vcpu, 6),
> +				kvmppc_get_gpr(vcpu, 7),
> +				kvmppc_get_gpr(vcpu, 8));
> +	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
> +}
> +
> +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
> +				    unsigned long pid, unsigned long target,
> +				    unsigned long type, unsigned long pg_sizes,
> +				    unsigned long start, unsigned long end)
> +{
> +	if (!kvm_is_radix(vcpu->kvm))
> +		return H_UNSUPPORTED;
> +
> +	/*
> +	 * For nested guests, this hcall is handled in
> +	 * L0. See kvmppc_handle_nested_exit() for details.
> +	 */
> +	if (kvmhv_on_pseries())
> +		return H_UNSUPPORTED;
> +
> +	if (end < start)
> +		return H_P5;
> +
> +	if (type & H_RPTI_TYPE_NESTED) {
> +		if (!nesting_enabled(vcpu->kvm))
> +			return H_FUNCTION;
> +
> +		/* Support only cores as target */
> +		if (target != H_RPTI_TARGET_CMMU)
> +			return H_P2;
> +
> +		return kvmhv_h_rpti_nested(vcpu, pid,
> +					   (type & ~H_RPTI_TYPE_NESTED),
> +					    pg_sizes, start, end);
> +	}
> +
> +	do_h_rpt_invalidate_prs(pid, vcpu->kvm->arch.lpid, type, pg_sizes,
> +				start, end);
> +	return H_SUCCESS;
> +}
> +
>  int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
>  {
>  	unsigned long req = kvmppc_get_gpr(vcpu, 3);
> @@ -1129,6 +1192,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
>  		 */
>  		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
>  		break;
> +	case H_RPT_INVALIDATE:
> +		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
> +					      kvmppc_get_gpr(vcpu, 5),
> +					      kvmppc_get_gpr(vcpu, 6),
> +					      kvmppc_get_gpr(vcpu, 7),
> +					      kvmppc_get_gpr(vcpu, 8),
> +					      kvmppc_get_gpr(vcpu, 9));
> +		break;
>  
>  	default:
>  		return RESUME_HOST;
> @@ -1175,6 +1246,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
>  	case H_XIRR_X:
>  #endif
>  	case H_PAGE_INIT:
> +	case H_RPT_INVALIDATE:
>  		return 1;
>  	}
>  
> @@ -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.

> +
> +		r = RESUME_HOST;
> +		break;
> +	}
>  	default:
>  		r = RESUME_HOST;
>  		break;
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index 0cd0e7aad588..ca43b2d38dce 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -1191,6 +1191,83 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
>  	return H_SUCCESS;
>  }
>  
> +static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid,
> +					 unsigned long page_size,
> +					 unsigned long ap,
> +					 unsigned long start,
> +					 unsigned long end)
> +{
> +	unsigned long addr = start;
> +	int ret;
> +
> +	do {
> +		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
> +						   get_epn(addr));
> +		if (ret)
> +			return ret;
> +		addr += page_size;
> +	} while (addr < end);
> +
> +	return ret;
> +}
> +
> +static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid)
> +{
> +	struct kvm *kvm = vcpu->kvm;
> +	struct kvm_nested_guest *gp;
> +
> +	gp = kvmhv_get_nested(kvm, lpid, false);
> +	if (gp) {
> +		kvmhv_emulate_tlbie_lpid(vcpu, gp, RIC_FLUSH_ALL);
> +		kvmhv_put_nested(gp);
> +	}
> +	return H_SUCCESS;
> +}
> +
> +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)
> +{
> +	struct kvm_nested_guest *gp;
> +	long ret;
> +	unsigned long psize, ap;
> +
> +	/*
> +	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
> +	 *
> +	 * However, nested KVM issues a L2 lpid flush call when creating
> +	 * partition table entries for L2. This happens even before the
> +	 * corresponding shadow lpid is created in HV which happens in
> +	 * H_ENTER_NESTED call. Since we can't differentiate this case from
> +	 * the invalid case, we ignore such flush requests and return success.
> +	 */
> +	gp = kvmhv_find_nested(vcpu->kvm, lpid);
> +	if (!gp)
> +		return H_SUCCESS;
> +
> +	if ((type & H_RPTI_TYPE_NESTED_ALL) == H_RPTI_TYPE_NESTED_ALL)
> +		return do_tlb_invalidate_nested_all(vcpu, lpid);
> +
> +	if ((type & H_RPTI_TYPE_TLB) == H_RPTI_TYPE_TLB) {
> +		struct mmu_psize_def *def;
> +
> +		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +			def = &mmu_psize_defs[psize];
> +			if (!(pg_sizes & def->h_rpt_pgsize))
> +				continue;
> +
> +			ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
> +							   (1UL << def->shift),
> +							   ap, start, end);
> +			if (ret)
> +				return H_P4;
> +		}
> +	}
> +	return H_SUCCESS;
> +}
> +
>  /* Used to convert a nested guest real address to a L1 guest real address */
>  static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
>  				       struct kvm_nested_guest *gp,
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index a2a68a958fa0..be33b5321a76 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -682,6 +682,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  		r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
>  		       !kvmppc_hv_ops->enable_dawr1(NULL));
>  		break;
> +	case KVM_CAP_PPC_RPT_INVALIDATE:
> +		r = 1;
> +		break;
>  #endif
>  	default:
>  		r = 0;
> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
> index 409e61210789..440d84fffa8c 100644
> --- a/arch/powerpc/mm/book3s64/radix_tlb.c
> +++ b/arch/powerpc/mm/book3s64/radix_tlb.c
> @@ -20,10 +20,6 @@
>  
>  #include "internal.h"
>  
> -#define RIC_FLUSH_TLB 0
> -#define RIC_FLUSH_PWC 1
> -#define RIC_FLUSH_ALL 2
> -
>  /*
>   * tlbiel instruction for radix, set invalidation
>   * i.e., r=1 and is=01 or is=10 or is=11
> @@ -130,6 +126,21 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
>  	trace_tlbie(0, 0, rb, rs, ric, prs, r);
>  }
>  
> +static __always_inline void __tlbie_pid_lpid(unsigned long pid,
> +					     unsigned long lpid,
> +					     unsigned long ric)
> +{
> +	unsigned long rb, rs, prs, r;
> +
> +	rb = PPC_BIT(53); /* IS = 1 */
> +	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> +	prs = 1; /* process scoped */
> +	r = 1;   /* radix format */
> +
> +	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> +		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> +	trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
>  static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
>  {
>  	unsigned long rb,rs,prs,r;
> @@ -190,6 +201,23 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
>  	trace_tlbie(0, 0, rb, rs, ric, prs, r);
>  }
>  
> +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
> +					    unsigned long lpid,
> +					    unsigned long ap, unsigned long ric)
> +{
> +	unsigned long rb, rs, prs, r;
> +
> +	rb = va & ~(PPC_BITMASK(52, 63));
> +	rb |= ap << PPC_BITLSHIFT(58);
> +	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> +	prs = 1; /* process scoped */
> +	r = 1;   /* radix format */
> +
> +	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> +		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> +	trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
> +
>  static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
>  					    unsigned long ap, unsigned long ric)
>  {
> @@ -235,6 +263,22 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
>  	}
>  }
>  
> +static inline void fixup_tlbie_va_range_lpid(unsigned long va,
> +					     unsigned long pid,
> +					     unsigned long lpid,
> +					     unsigned long ap)
> +{
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> +	}
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
> +	}
> +}
> +
>  static inline void fixup_tlbie_pid(unsigned long pid)
>  {
>  	/*
> @@ -254,6 +298,25 @@ static inline void fixup_tlbie_pid(unsigned long pid)
>  	}
>  }
>  
> +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
> +{
> +	/*
> +	 * We can use any address for the invalidation, pick one which is
> +	 * probably unused as an optimisation.
> +	 */
> +	unsigned long va = ((1UL << 52) - 1);
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> +	}
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
> +				RIC_FLUSH_TLB);
> +	}
> +}
>  
>  static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
>  				       unsigned long ap)
> @@ -344,6 +407,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
>  	asm volatile("eieio; tlbsync; ptesync": : :"memory");
>  }
>  
> +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
> +				   unsigned long ric)
> +{
> +	asm volatile("ptesync" : : : "memory");
> +
> +	/*
> +	 * Workaround the fact that the "ric" argument to __tlbie_pid
> +	 * must be a compile-time contraint to match the "i" constraint
> +	 * in the asm statement.
> +	 */
> +	switch (ric) {
> +	case RIC_FLUSH_TLB:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> +		fixup_tlbie_pid_lpid(pid, lpid);
> +		break;
> +	case RIC_FLUSH_PWC:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +		break;
> +	case RIC_FLUSH_ALL:
> +	default:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> +		fixup_tlbie_pid_lpid(pid, lpid);
> +	}
> +	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
>  struct tlbiel_pid {
>  	unsigned long pid;
>  	unsigned long ric;
> @@ -469,6 +557,20 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
>  	fixup_tlbie_va_range(addr - page_size, pid, ap);
>  }
>  
> +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
> +					 unsigned long pid, unsigned long lpid,
> +					 unsigned long page_size,
> +					 unsigned long psize)
> +{
> +	unsigned long addr;
> +	unsigned long ap = mmu_get_ap(psize);
> +
> +	for (addr = start; addr < end; addr += page_size)
> +		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
> +
> +	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
> +}
> +
>  static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
>  				      unsigned long psize, unsigned long ric)
>  {
> @@ -549,6 +651,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
>  	asm volatile("eieio; tlbsync; ptesync": : :"memory");
>  }
>  
> +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
> +					unsigned long pid, unsigned long lpid,
> +					unsigned long page_size,
> +					unsigned long psize, bool also_pwc)
> +{
> +	asm volatile("ptesync" : : : "memory");
> +	if (also_pwc)
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
> +	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
> +
>  static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
>  				unsigned long start, unsigned long end,
>  				unsigned long pid, unsigned long page_size,
> @@ -1381,4 +1495,29 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
>  	}
>  }
>  EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
> +
> +/*
> + * Process-scoped invalidations for a given LPID.
> + */
> +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)
> +{
> +	if ((type & H_RPTI_TYPE_ALL) == H_RPTI_TYPE_ALL) {
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> +		return;
> +	}
> +
> +	if (type & H_RPTI_TYPE_PWC)
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +
> +	if (!start && end == -1) /* PID */
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> +	else /* EA */
> +		_tlbie_va_range_lpid(start, end, pid, lpid, page_size,
> +				     psize, false);
> +}
> +EXPORT_SYMBOL_GPL(do_h_rpt_invalidate);
> +
>  #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 8b281f722e5b..f8c84a62e8f3 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1078,6 +1078,7 @@ struct kvm_ppc_resize_hpt {
>  #define KVM_CAP_DIRTY_LOG_RING 192
>  #define KVM_CAP_X86_BUS_LOCK_EXIT 193
>  #define KVM_CAP_PPC_DAWR1 194
> +#define KVM_CAP_PPC_RPT_INVALIDATE 195
>  
>  #ifdef KVM_CAP_IRQ_ROUTING

Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE

[Bharata B Rao]

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

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 20757 bytes --]

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 <bharata@linux.ibm.com>
> ---
>  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 <asm/hvcall.h>
>  
> +#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, unsigned long lpid,
> +				    unsigned long type, unsigned long pg_sizes,
> +				    unsigned long start, unsigned long end)
> +{
> +	unsigned long psize;
> +	struct mmu_psize_def *def;
> +
> +	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +		def = &mmu_psize_defs[psize];
> +		if (pg_sizes & def->h_rpt_pgsize)
> +			do_h_rpt_invalidate(pid, lpid, type,
> +					    (1UL << def->shift), psize,
> +					    start, end);
> +	}
> +}
> +
> +static void kvmppc_nested_rpt_invalidate(struct kvm_vcpu *vcpu)
> +{
> +	do_h_rpt_invalidate_prs(kvmppc_get_gpr(vcpu, 4),
> +				vcpu->arch.nested->shadow_lpid,
> +				kvmppc_get_gpr(vcpu, 5),
> +				kvmppc_get_gpr(vcpu, 6),
> +				kvmppc_get_gpr(vcpu, 7),
> +				kvmppc_get_gpr(vcpu, 8));
> +	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
> +}
> +
> +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
> +				    unsigned long pid, unsigned long target,
> +				    unsigned long type, unsigned long pg_sizes,
> +				    unsigned long start, unsigned long end)
> +{
> +	if (!kvm_is_radix(vcpu->kvm))
> +		return H_UNSUPPORTED;
> +
> +	/*
> +	 * For nested guests, this hcall is handled in
> +	 * L0. See kvmppc_handle_nested_exit() for details.
> +	 */
> +	if (kvmhv_on_pseries())
> +		return H_UNSUPPORTED;
> +
> +	if (end < start)
> +		return H_P5;
> +
> +	if (type & H_RPTI_TYPE_NESTED) {
> +		if (!nesting_enabled(vcpu->kvm))
> +			return H_FUNCTION;
> +
> +		/* Support only cores as target */
> +		if (target != H_RPTI_TARGET_CMMU)
> +			return H_P2;
> +

IIUC, we'll hit this code path if an L1 calls this on behalf of an L2,
whereas we'll hit the nested exit code path going straight to
kvmhv_h_rpti_nested() if an L2 calls it on behalf of an L3.  Is that
right?

> +		return kvmhv_h_rpti_nested(vcpu, pid,
> +					   (type & ~H_RPTI_TYPE_NESTED),
> +					    pg_sizes, start, end);
> +	}
> +
> +	do_h_rpt_invalidate_prs(pid, vcpu->kvm->arch.lpid, type, pg_sizes,
> +				start, end);
> +	return H_SUCCESS;
> +}
> +
>  int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
>  {
>  	unsigned long req = kvmppc_get_gpr(vcpu, 3);
> @@ -1129,6 +1192,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
>  		 */
>  		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
>  		break;
> +	case H_RPT_INVALIDATE:
> +		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
> +					      kvmppc_get_gpr(vcpu, 5),
> +					      kvmppc_get_gpr(vcpu, 6),
> +					      kvmppc_get_gpr(vcpu, 7),
> +					      kvmppc_get_gpr(vcpu, 8),
> +					      kvmppc_get_gpr(vcpu, 9));
> +		break;
>  
>  	default:
>  		return RESUME_HOST;
> @@ -1175,6 +1246,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
>  	case H_XIRR_X:
>  #endif
>  	case H_PAGE_INIT:
> +	case H_RPT_INVALIDATE:
>  		return 1;
>  	}
>  
> @@ -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.
> +		 */

What if the L2 is not calling this for the GTSE=0 case, but on behalf
of an L3?

> +		if (req == H_RPT_INVALIDATE) {
> +			kvmppc_nested_rpt_invalidate(vcpu);
> +			r = RESUME_GUEST;
> +			break;
> +		}
> +
> +		r = RESUME_HOST;
> +		break;
> +	}
>  	default:
>  		r = RESUME_HOST;
>  		break;
> diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> index 0cd0e7aad588..ca43b2d38dce 100644
> --- a/arch/powerpc/kvm/book3s_hv_nested.c
> +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> @@ -1191,6 +1191,83 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
>  	return H_SUCCESS;
>  }
>  
> +static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid,
> +					 unsigned long page_size,
> +					 unsigned long ap,
> +					 unsigned long start,
> +					 unsigned long end)
> +{
> +	unsigned long addr = start;
> +	int ret;
> +
> +	do {
> +		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
> +						   get_epn(addr));
> +		if (ret)
> +			return ret;
> +		addr += page_size;
> +	} while (addr < end);
> +
> +	return ret;
> +}
> +
> +static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
> +					 unsigned long lpid)
> +{
> +	struct kvm *kvm = vcpu->kvm;
> +	struct kvm_nested_guest *gp;
> +
> +	gp = kvmhv_get_nested(kvm, lpid, false);
> +	if (gp) {
> +		kvmhv_emulate_tlbie_lpid(vcpu, gp, RIC_FLUSH_ALL);
> +		kvmhv_put_nested(gp);
> +	}
> +	return H_SUCCESS;
> +}
> +
> +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)
> +{
> +	struct kvm_nested_guest *gp;
> +	long ret;
> +	unsigned long psize, ap;
> +
> +	/*
> +	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
> +	 *
> +	 * However, nested KVM issues a L2 lpid flush call when creating
> +	 * partition table entries for L2. This happens even before the
> +	 * corresponding shadow lpid is created in HV which happens in
> +	 * H_ENTER_NESTED call. Since we can't differentiate this case from
> +	 * the invalid case, we ignore such flush requests and return success.
> +	 */

What if this is being called on behalf of an L3 or deeper?  Do we need
something to do a translation from L3 to L2 addresses?

> +	gp = kvmhv_find_nested(vcpu->kvm, lpid);
> +	if (!gp)
> +		return H_SUCCESS;
> +
> +	if ((type & H_RPTI_TYPE_NESTED_ALL) == H_RPTI_TYPE_NESTED_ALL)
> +		return do_tlb_invalidate_nested_all(vcpu, lpid);
> +
> +	if ((type & H_RPTI_TYPE_TLB) == H_RPTI_TYPE_TLB) {
> +		struct mmu_psize_def *def;
> +
> +		for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> +			def = &mmu_psize_defs[psize];
> +			if (!(pg_sizes & def->h_rpt_pgsize))
> +				continue;
> +
> +			ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
> +							   (1UL << def->shift),
> +							   ap, start, end);
> +			if (ret)
> +				return H_P4;
> +		}
> +	}
> +	return H_SUCCESS;
> +}
> +
>  /* Used to convert a nested guest real address to a L1 guest real address */
>  static int kvmhv_translate_addr_nested(struct kvm_vcpu *vcpu,
>  				       struct kvm_nested_guest *gp,
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index a2a68a958fa0..be33b5321a76 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -682,6 +682,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
>  		r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
>  		       !kvmppc_hv_ops->enable_dawr1(NULL));
>  		break;
> +	case KVM_CAP_PPC_RPT_INVALIDATE:
> +		r = 1;
> +		break;
>  #endif
>  	default:
>  		r = 0;
> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
> index 409e61210789..440d84fffa8c 100644
> --- a/arch/powerpc/mm/book3s64/radix_tlb.c
> +++ b/arch/powerpc/mm/book3s64/radix_tlb.c
> @@ -20,10 +20,6 @@
>  
>  #include "internal.h"
>  
> -#define RIC_FLUSH_TLB 0
> -#define RIC_FLUSH_PWC 1
> -#define RIC_FLUSH_ALL 2
> -
>  /*
>   * tlbiel instruction for radix, set invalidation
>   * i.e., r=1 and is=01 or is=10 or is=11
> @@ -130,6 +126,21 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
>  	trace_tlbie(0, 0, rb, rs, ric, prs, r);
>  }
>  
> +static __always_inline void __tlbie_pid_lpid(unsigned long pid,
> +					     unsigned long lpid,
> +					     unsigned long ric)
> +{
> +	unsigned long rb, rs, prs, r;
> +
> +	rb = PPC_BIT(53); /* IS = 1 */
> +	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> +	prs = 1; /* process scoped */
> +	r = 1;   /* radix format */
> +
> +	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> +		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> +	trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
>  static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
>  {
>  	unsigned long rb,rs,prs,r;
> @@ -190,6 +201,23 @@ static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
>  	trace_tlbie(0, 0, rb, rs, ric, prs, r);
>  }
>  
> +static __always_inline void __tlbie_va_lpid(unsigned long va, unsigned long pid,
> +					    unsigned long lpid,
> +					    unsigned long ap, unsigned long ric)
> +{
> +	unsigned long rb, rs, prs, r;
> +
> +	rb = va & ~(PPC_BITMASK(52, 63));
> +	rb |= ap << PPC_BITLSHIFT(58);
> +	rs = (pid << PPC_BITLSHIFT(31)) | (lpid & ~(PPC_BITMASK(0, 31)));
> +	prs = 1; /* process scoped */
> +	r = 1;   /* radix format */
> +
> +	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
> +		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
> +	trace_tlbie(0, 0, rb, rs, ric, prs, r);
> +}
> +
>  static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
>  					    unsigned long ap, unsigned long ric)
>  {
> @@ -235,6 +263,22 @@ static inline void fixup_tlbie_va_range(unsigned long va, unsigned long pid,
>  	}
>  }
>  
> +static inline void fixup_tlbie_va_range_lpid(unsigned long va,
> +					     unsigned long pid,
> +					     unsigned long lpid,
> +					     unsigned long ap)
> +{
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> +	}
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_va_lpid(va, pid, lpid, ap, RIC_FLUSH_TLB);
> +	}
> +}
> +
>  static inline void fixup_tlbie_pid(unsigned long pid)
>  {
>  	/*
> @@ -254,6 +298,25 @@ static inline void fixup_tlbie_pid(unsigned long pid)
>  	}
>  }
>  
> +static inline void fixup_tlbie_pid_lpid(unsigned long pid, unsigned long lpid)
> +{
> +	/*
> +	 * We can use any address for the invalidation, pick one which is
> +	 * probably unused as an optimisation.
> +	 */
> +	unsigned long va = ((1UL << 52) - 1);
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_ERAT_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_pid_lpid(0, lpid, RIC_FLUSH_TLB);
> +	}
> +
> +	if (cpu_has_feature(CPU_FTR_P9_TLBIE_STQ_BUG)) {
> +		asm volatile("ptesync" : : : "memory");
> +		__tlbie_va_lpid(va, pid, lpid, mmu_get_ap(MMU_PAGE_64K),
> +				RIC_FLUSH_TLB);
> +	}
> +}
>  
>  static inline void fixup_tlbie_lpid_va(unsigned long va, unsigned long lpid,
>  				       unsigned long ap)
> @@ -344,6 +407,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
>  	asm volatile("eieio; tlbsync; ptesync": : :"memory");
>  }
>  
> +static inline void _tlbie_pid_lpid(unsigned long pid, unsigned long lpid,
> +				   unsigned long ric)
> +{
> +	asm volatile("ptesync" : : : "memory");
> +
> +	/*
> +	 * Workaround the fact that the "ric" argument to __tlbie_pid
> +	 * must be a compile-time contraint to match the "i" constraint
> +	 * in the asm statement.
> +	 */
> +	switch (ric) {
> +	case RIC_FLUSH_TLB:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> +		fixup_tlbie_pid_lpid(pid, lpid);
> +		break;
> +	case RIC_FLUSH_PWC:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +		break;
> +	case RIC_FLUSH_ALL:
> +	default:
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> +		fixup_tlbie_pid_lpid(pid, lpid);
> +	}
> +	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
>  struct tlbiel_pid {
>  	unsigned long pid;
>  	unsigned long ric;
> @@ -469,6 +557,20 @@ static inline void __tlbie_va_range(unsigned long start, unsigned long end,
>  	fixup_tlbie_va_range(addr - page_size, pid, ap);
>  }
>  
> +static inline void __tlbie_va_range_lpid(unsigned long start, unsigned long end,
> +					 unsigned long pid, unsigned long lpid,
> +					 unsigned long page_size,
> +					 unsigned long psize)
> +{
> +	unsigned long addr;
> +	unsigned long ap = mmu_get_ap(psize);
> +
> +	for (addr = start; addr < end; addr += page_size)
> +		__tlbie_va_lpid(addr, pid, lpid, ap, RIC_FLUSH_TLB);
> +
> +	fixup_tlbie_va_range_lpid(addr - page_size, pid, lpid, ap);
> +}
> +
>  static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
>  				      unsigned long psize, unsigned long ric)
>  {
> @@ -549,6 +651,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
>  	asm volatile("eieio; tlbsync; ptesync": : :"memory");
>  }
>  
> +static inline void _tlbie_va_range_lpid(unsigned long start, unsigned long end,
> +					unsigned long pid, unsigned long lpid,
> +					unsigned long page_size,
> +					unsigned long psize, bool also_pwc)
> +{
> +	asm volatile("ptesync" : : : "memory");
> +	if (also_pwc)
> +		__tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +	__tlbie_va_range_lpid(start, end, pid, lpid, page_size, psize);
> +	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
> +}
> +
>  static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
>  				unsigned long start, unsigned long end,
>  				unsigned long pid, unsigned long page_size,
> @@ -1381,4 +1495,29 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
>  	}
>  }
>  EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
> +
> +/*
> + * Process-scoped invalidations for a given LPID.
> + */
> +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)
> +{
> +	if ((type & H_RPTI_TYPE_ALL) == H_RPTI_TYPE_ALL) {
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_ALL);
> +		return;
> +	}
> +
> +	if (type & H_RPTI_TYPE_PWC)
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_PWC);
> +
> +	if (!start && end == -1) /* PID */
> +		_tlbie_pid_lpid(pid, lpid, RIC_FLUSH_TLB);
> +	else /* EA */
> +		_tlbie_va_range_lpid(start, end, pid, lpid, page_size,
> +				     psize, false);
> +}
> +EXPORT_SYMBOL_GPL(do_h_rpt_invalidate);
> +
>  #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 8b281f722e5b..f8c84a62e8f3 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1078,6 +1078,7 @@ struct kvm_ppc_resize_hpt {
>  #define KVM_CAP_DIRTY_LOG_RING 192
>  #define KVM_CAP_X86_BUS_LOCK_EXIT 193
>  #define KVM_CAP_PPC_DAWR1 194
> +#define KVM_CAP_PPC_RPT_INVALIDATE 195
>  
>  #ifdef KVM_CAP_IRQ_ROUTING
>  

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE

[Bharata B Rao]

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 <asm/hvcall.h>
> >  
> > +#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, unsigned long lpid,
> > +				    unsigned long type, unsigned long pg_sizes,
> > +				    unsigned long start, unsigned long end)
> > +{
> > +	unsigned long psize;
> > +	struct mmu_psize_def *def;
> > +
> > +	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> > +		def = &mmu_psize_defs[psize];
> > +		if (pg_sizes & def->h_rpt_pgsize)
> > +			do_h_rpt_invalidate(pid, lpid, type,
> > +					    (1UL << def->shift), psize,
> > +					    start, end);
> > +	}
> > +}
> > +
> > +static void kvmppc_nested_rpt_invalidate(struct kvm_vcpu *vcpu)
> > +{
> > +	do_h_rpt_invalidate_prs(kvmppc_get_gpr(vcpu, 4),
> > +				vcpu->arch.nested->shadow_lpid,
> > +				kvmppc_get_gpr(vcpu, 5),
> > +				kvmppc_get_gpr(vcpu, 6),
> > +				kvmppc_get_gpr(vcpu, 7),
> > +				kvmppc_get_gpr(vcpu, 8));
> > +	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
> > +}
> > +
> > +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
> > +				    unsigned long pid, unsigned long target,
> > +				    unsigned long type, unsigned long pg_sizes,
> > +				    unsigned long start, unsigned long end)
> > +{
> > +	if (!kvm_is_radix(vcpu->kvm))
> > +		return H_UNSUPPORTED;
> > +
> > +	/*
> > +	 * For nested guests, this hcall is handled in
> > +	 * L0. See kvmppc_handle_nested_exit() for details.
> > +	 */
> > +	if (kvmhv_on_pseries())
> > +		return H_UNSUPPORTED;
> > +
> > +	if (end < start)
> > +		return H_P5;
> > +
> > +	if (type & H_RPTI_TYPE_NESTED) {
> > +		if (!nesting_enabled(vcpu->kvm))
> > +			return H_FUNCTION;
> > +
> > +		/* Support only cores as target */
> > +		if (target != H_RPTI_TARGET_CMMU)
> > +			return H_P2;
> > +
> 
> IIUC, we'll hit this code path if an L1 calls this on behalf of an L2,

Correct.

> whereas we'll hit the nested exit code path going straight to
> kvmhv_h_rpti_nested() if an L2 calls it on behalf of an L3.  Is that
> right?

We will hit the nested exit code path when L2 calls it on behalf
of L3. Looks like I am not handling this case (hcall issued by
L2 on behalf of L3 for handling partition scoped translations)
in the nested exit path.

> 
> > +		return kvmhv_h_rpti_nested(vcpu, pid,
> > +					   (type & ~H_RPTI_TYPE_NESTED),
> > +					    pg_sizes, start, end);
> > +	}
> > +
> > +	do_h_rpt_invalidate_prs(pid, vcpu->kvm->arch.lpid, type, pg_sizes,
> > +				start, end);
> > +	return H_SUCCESS;
> > +}
> > +
> >  int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
> >  {
> >  	unsigned long req = kvmppc_get_gpr(vcpu, 3);
> > @@ -1129,6 +1192,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
> >  		 */
> >  		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
> >  		break;
> > +	case H_RPT_INVALIDATE:
> > +		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
> > +					      kvmppc_get_gpr(vcpu, 5),
> > +					      kvmppc_get_gpr(vcpu, 6),
> > +					      kvmppc_get_gpr(vcpu, 7),
> > +					      kvmppc_get_gpr(vcpu, 8),
> > +					      kvmppc_get_gpr(vcpu, 9));
> > +		break;
> >  
> >  	default:
> >  		return RESUME_HOST;
> > @@ -1175,6 +1246,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
> >  	case H_XIRR_X:
> >  #endif
> >  	case H_PAGE_INIT:
> > +	case H_RPT_INVALIDATE:
> >  		return 1;
> >  	}
> >  
> > @@ -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.
> > +		 */
> 
> What if the L2 is not calling this for the GTSE=0 case, but on behalf
> of an L3?

That case would be for flushing partition scoped translations. I am
realizing that I am not handling that case, but it should be handled
here in the nested hcall exit path.

Currently I am handling only the hcall requests for process scoped
translations from nested guests here.

> 
> > +		if (req == H_RPT_INVALIDATE) {
> > +			kvmppc_nested_rpt_invalidate(vcpu);
> > +			r = RESUME_GUEST;
> > +			break;
> > +		}
> > +
> > +		r = RESUME_HOST;
> > +		break;
> > +	}
> >  	default:
> >  		r = RESUME_HOST;
> >  		break;
> > diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> > index 0cd0e7aad588..ca43b2d38dce 100644
> > --- a/arch/powerpc/kvm/book3s_hv_nested.c
> > +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> > @@ -1191,6 +1191,83 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
> >  	return H_SUCCESS;
> >  }
> >  
> > +static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
> > +					 unsigned long lpid,
> > +					 unsigned long page_size,
> > +					 unsigned long ap,
> > +					 unsigned long start,
> > +					 unsigned long end)
> > +{
> > +	unsigned long addr = start;
> > +	int ret;
> > +
> > +	do {
> > +		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
> > +						   get_epn(addr));
> > +		if (ret)
> > +			return ret;
> > +		addr += page_size;
> > +	} while (addr < end);
> > +
> > +	return ret;
> > +}
> > +
> > +static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
> > +					 unsigned long lpid)
> > +{
> > +	struct kvm *kvm = vcpu->kvm;
> > +	struct kvm_nested_guest *gp;
> > +
> > +	gp = kvmhv_get_nested(kvm, lpid, false);
> > +	if (gp) {
> > +		kvmhv_emulate_tlbie_lpid(vcpu, gp, RIC_FLUSH_ALL);
> > +		kvmhv_put_nested(gp);
> > +	}
> > +	return H_SUCCESS;
> > +}
> > +
> > +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)
> > +{
> > +	struct kvm_nested_guest *gp;
> > +	long ret;
> > +	unsigned long psize, ap;
> > +
> > +	/*
> > +	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
> > +	 *
> > +	 * However, nested KVM issues a L2 lpid flush call when creating
> > +	 * partition table entries for L2. This happens even before the
> > +	 * corresponding shadow lpid is created in HV which happens in
> > +	 * H_ENTER_NESTED call. Since we can't differentiate this case from
> > +	 * the invalid case, we ignore such flush requests and return success.
> > +	 */
> 
> What if this is being called on behalf of an L3 or deeper?  Do we need
> something to do a translation from L3 to L2 addresses?

I am not sure, I will have to check if gp->shadow_lpid points to
correct nested LPID in all the cases.

> 
> > +	gp = kvmhv_find_nested(vcpu->kvm, lpid);
> > +	if (!gp)
> > +		return H_SUCCESS;

Regards,
Bharata.

Re: [PATCH v5 2/3] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE

[David Gibson]

[-- Attachment #1: Type: text/plain, Size: 12561 bytes --]

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 <asm/hvcall.h>
> > >  
> > > +#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, unsigned long lpid,
> > > +				    unsigned long type, unsigned long pg_sizes,
> > > +				    unsigned long start, unsigned long end)
> > > +{
> > > +	unsigned long psize;
> > > +	struct mmu_psize_def *def;
> > > +
> > > +	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
> > > +		def = &mmu_psize_defs[psize];
> > > +		if (pg_sizes & def->h_rpt_pgsize)
> > > +			do_h_rpt_invalidate(pid, lpid, type,
> > > +					    (1UL << def->shift), psize,
> > > +					    start, end);
> > > +	}
> > > +}
> > > +
> > > +static void kvmppc_nested_rpt_invalidate(struct kvm_vcpu *vcpu)
> > > +{
> > > +	do_h_rpt_invalidate_prs(kvmppc_get_gpr(vcpu, 4),
> > > +				vcpu->arch.nested->shadow_lpid,
> > > +				kvmppc_get_gpr(vcpu, 5),
> > > +				kvmppc_get_gpr(vcpu, 6),
> > > +				kvmppc_get_gpr(vcpu, 7),
> > > +				kvmppc_get_gpr(vcpu, 8));
> > > +	kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
> > > +}
> > > +
> > > +static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,
> > > +				    unsigned long pid, unsigned long target,
> > > +				    unsigned long type, unsigned long pg_sizes,
> > > +				    unsigned long start, unsigned long end)
> > > +{
> > > +	if (!kvm_is_radix(vcpu->kvm))
> > > +		return H_UNSUPPORTED;
> > > +
> > > +	/*
> > > +	 * For nested guests, this hcall is handled in
> > > +	 * L0. See kvmppc_handle_nested_exit() for details.
> > > +	 */
> > > +	if (kvmhv_on_pseries())
> > > +		return H_UNSUPPORTED;
> > > +
> > > +	if (end < start)
> > > +		return H_P5;
> > > +
> > > +	if (type & H_RPTI_TYPE_NESTED) {
> > > +		if (!nesting_enabled(vcpu->kvm))
> > > +			return H_FUNCTION;
> > > +
> > > +		/* Support only cores as target */
> > > +		if (target != H_RPTI_TARGET_CMMU)
> > > +			return H_P2;
> > > +
> > 
> > IIUC, we'll hit this code path if an L1 calls this on behalf of an L2,
> 
> Correct.
> 
> > whereas we'll hit the nested exit code path going straight to
> > kvmhv_h_rpti_nested() if an L2 calls it on behalf of an L3.  Is that
> > right?
> 
> We will hit the nested exit code path when L2 calls it on behalf
> of L3. Looks like I am not handling this case (hcall issued by
> L2 on behalf of L3 for handling partition scoped translations)
> in the nested exit path.
> 
> > 
> > > +		return kvmhv_h_rpti_nested(vcpu, pid,
> > > +					   (type & ~H_RPTI_TYPE_NESTED),
> > > +					    pg_sizes, start, end);
> > > +	}
> > > +
> > > +	do_h_rpt_invalidate_prs(pid, vcpu->kvm->arch.lpid, type, pg_sizes,
> > > +				start, end);
> > > +	return H_SUCCESS;
> > > +}
> > > +
> > >  int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
> > >  {
> > >  	unsigned long req = kvmppc_get_gpr(vcpu, 3);
> > > @@ -1129,6 +1192,14 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
> > >  		 */
> > >  		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
> > >  		break;
> > > +	case H_RPT_INVALIDATE:
> > > +		ret = kvmppc_h_rpt_invalidate(vcpu, kvmppc_get_gpr(vcpu, 4),
> > > +					      kvmppc_get_gpr(vcpu, 5),
> > > +					      kvmppc_get_gpr(vcpu, 6),
> > > +					      kvmppc_get_gpr(vcpu, 7),
> > > +					      kvmppc_get_gpr(vcpu, 8),
> > > +					      kvmppc_get_gpr(vcpu, 9));
> > > +		break;
> > >  
> > >  	default:
> > >  		return RESUME_HOST;
> > > @@ -1175,6 +1246,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
> > >  	case H_XIRR_X:
> > >  #endif
> > >  	case H_PAGE_INIT:
> > > +	case H_RPT_INVALIDATE:
> > >  		return 1;
> > >  	}
> > >  
> > > @@ -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.
> > > +		 */
> > 
> > What if the L2 is not calling this for the GTSE=0 case, but on behalf
> > of an L3?
> 
> That case would be for flushing partition scoped translations. I am
> realizing that I am not handling that case, but it should be handled
> here in the nested hcall exit path.
> 
> Currently I am handling only the hcall requests for process scoped
> translations from nested guests here.

Ok.  At the very least you need to detect and fail for that case.

> > 
> > > +		if (req == H_RPT_INVALIDATE) {
> > > +			kvmppc_nested_rpt_invalidate(vcpu);
> > > +			r = RESUME_GUEST;
> > > +			break;
> > > +		}
> > > +
> > > +		r = RESUME_HOST;
> > > +		break;
> > > +	}
> > >  	default:
> > >  		r = RESUME_HOST;
> > >  		break;
> > > diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
> > > index 0cd0e7aad588..ca43b2d38dce 100644
> > > --- a/arch/powerpc/kvm/book3s_hv_nested.c
> > > +++ b/arch/powerpc/kvm/book3s_hv_nested.c
> > > @@ -1191,6 +1191,83 @@ long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu)
> > >  	return H_SUCCESS;
> > >  }
> > >  
> > > +static long do_tlb_invalidate_nested_tlb(struct kvm_vcpu *vcpu,
> > > +					 unsigned long lpid,
> > > +					 unsigned long page_size,
> > > +					 unsigned long ap,
> > > +					 unsigned long start,
> > > +					 unsigned long end)
> > > +{
> > > +	unsigned long addr = start;
> > > +	int ret;
> > > +
> > > +	do {
> > > +		ret = kvmhv_emulate_tlbie_tlb_addr(vcpu, lpid, ap,
> > > +						   get_epn(addr));
> > > +		if (ret)
> > > +			return ret;
> > > +		addr += page_size;
> > > +	} while (addr < end);
> > > +
> > > +	return ret;
> > > +}
> > > +
> > > +static long do_tlb_invalidate_nested_all(struct kvm_vcpu *vcpu,
> > > +					 unsigned long lpid)
> > > +{
> > > +	struct kvm *kvm = vcpu->kvm;
> > > +	struct kvm_nested_guest *gp;
> > > +
> > > +	gp = kvmhv_get_nested(kvm, lpid, false);
> > > +	if (gp) {
> > > +		kvmhv_emulate_tlbie_lpid(vcpu, gp, RIC_FLUSH_ALL);
> > > +		kvmhv_put_nested(gp);
> > > +	}
> > > +	return H_SUCCESS;
> > > +}
> > > +
> > > +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)
> > > +{
> > > +	struct kvm_nested_guest *gp;
> > > +	long ret;
> > > +	unsigned long psize, ap;
> > > +
> > > +	/*
> > > +	 * If L2 lpid isn't valid, we need to return H_PARAMETER.
> > > +	 *
> > > +	 * However, nested KVM issues a L2 lpid flush call when creating
> > > +	 * partition table entries for L2. This happens even before the
> > > +	 * corresponding shadow lpid is created in HV which happens in
> > > +	 * H_ENTER_NESTED call. Since we can't differentiate this case from
> > > +	 * the invalid case, we ignore such flush requests and return success.
> > > +	 */
> > 
> > What if this is being called on behalf of an L3 or deeper?  Do we need
> > something to do a translation from L3 to L2 addresses?
> 
> I am not sure, I will have to check if gp->shadow_lpid points to
> correct nested LPID in all the cases.
> 
> > 
> > > +	gp = kvmhv_find_nested(vcpu->kvm, lpid);
> > > +	if (!gp)
> > > +		return H_SUCCESS;
> 
> Regards,
> Bharata.
> 

-- 
David Gibson			| I'll have my music baroque, and my code
david AT gibson.dropbear.id.au	| minimalist, thank you.  NOT _the_ _other_
				| _way_ _around_!
http://www.ozlabs.org/~dgibson

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH v5 3/3] KVM: PPC: Book3S HV: Use H_RPT_INVALIDATE in nested KVM

[Bharata B Rao]

In the nested KVM case, replace H_TLB_INVALIDATE by the new hcall
H_RPT_INVALIDATE if available. The availability of this hcall
is determined from "hcall-rpt-invalidate" string in ibm,hypertas-functions
DT property.

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
Reviewed-by: Fabiano Rosas <farosas@linux.ibm.com>
---
 arch/powerpc/kvm/book3s_64_mmu_radix.c | 27 +++++++++++++++++++++-----
 arch/powerpc/kvm/book3s_hv_nested.c    | 12 ++++++++++--
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index bb35490400e9..7ea5459022cb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -21,6 +21,7 @@
 #include <asm/pte-walk.h>
 #include <asm/ultravisor.h>
 #include <asm/kvm_book3s_uvmem.h>
+#include <asm/plpar_wrappers.h>
 
 /*
  * Supported radix tree geometry.
@@ -318,9 +319,19 @@ void kvmppc_radix_tlbie_page(struct kvm *kvm, unsigned long addr,
 	}
 
 	psi = shift_to_mmu_psize(pshift);
-	rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
-	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
-				lpid, rb);
+
+	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) {
+		rb = addr | (mmu_get_ap(psi) << PPC_BITLSHIFT(58));
+		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(0, 0, 1),
+					lpid, rb);
+	} else {
+		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
+					    H_RPTI_TYPE_NESTED |
+					    H_RPTI_TYPE_TLB,
+					    psize_to_rpti_pgsize(psi),
+					    addr, addr + psize);
+	}
+
 	if (rc)
 		pr_err("KVM: TLB page invalidation hcall failed, rc=%ld\n", rc);
 }
@@ -334,8 +345,14 @@ static void kvmppc_radix_flush_pwc(struct kvm *kvm, unsigned int lpid)
 		return;
 	}
 
-	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
-				lpid, TLBIEL_INVAL_SET_LPID);
+	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
+		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(1, 0, 1),
+					lpid, TLBIEL_INVAL_SET_LPID);
+	else
+		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
+					    H_RPTI_TYPE_NESTED |
+					    H_RPTI_TYPE_PWC, H_RPTI_PAGE_ALL,
+					    0, -1UL);
 	if (rc)
 		pr_err("KVM: TLB PWC invalidation hcall failed, rc=%ld\n", rc);
 }
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index ca43b2d38dce..2a6570e6c2c4 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -19,6 +19,7 @@
 #include <asm/pgalloc.h>
 #include <asm/pte-walk.h>
 #include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
 
 static struct patb_entry *pseries_partition_tb;
 
@@ -444,8 +445,15 @@ static void kvmhv_flush_lpid(unsigned int lpid)
 		return;
 	}
 
-	rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
-				lpid, TLBIEL_INVAL_SET_LPID);
+	if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE))
+		rc = plpar_hcall_norets(H_TLB_INVALIDATE, H_TLBIE_P1_ENC(2, 0, 1),
+					lpid, TLBIEL_INVAL_SET_LPID);
+	else
+		rc = pseries_rpt_invalidate(lpid, H_RPTI_TARGET_CMMU,
+					    H_RPTI_TYPE_NESTED |
+					    H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC |
+					    H_RPTI_TYPE_PAT,
+					    H_RPTI_PAGE_ALL, 0, -1UL);
 	if (rc)
 		pr_err("KVM: TLB LPID invalidation hcall failed, rc=%ld\n", rc);
 }
-- 
2.26.2