Support for H_RPT_INVALIDATE in PowerPC KVM
Subsystems (4)
v7 cover Support for H_RPT_INVALIDATE in PowerPC KVM
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 v7:
-------------
- Fixed a bug where LPID of nested guest was being fetched wrongly in the process scoped invalidation part of nested guest exit handler.
(In kvmppc_nested_h_rpt_invalidate() of patch 4/6)
- Moved the movement of RIC_FLUSH_ definitions to appropriate patch.
v6: https://lore.kernel.org/linuxppc-dev/[email protected]/
Aneesh Kumar K.V (1):
KVM: PPC: Book3S HV: Fix comments of H_RPT_INVALIDATE arguments
Bharata B Rao (5):
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: Nested support in H_RPT_INVALIDATE
KVM: PPC: Book3S HV: Add KVM_CAP_PPC_RPT_INVALIDATE capability
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/hvcall.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 | 106 ++++++++++++ arch/powerpc/kvm/book3s_hv_nested.c | 116 ++++++++++++- arch/powerpc/kvm/powerpc.c | 3 + arch/powerpc/mm/book3s64/radix_pgtable.c | 5 + arch/powerpc/mm/book3s64/radix_tlb.c | 152 +++++++++++++++++- include/uapi/linux/kvm.h | 1 + 13 files changed, 438 insertions(+), 13 deletions(-)
Signature · 1 line
2.26.2
PATCH v7 1/6 KVM: PPC: Book3S HV: Fix comments of H_RPT_INVALIDATE arguments
From: "Aneesh Kumar K.V" <[email protected]>
The type values H_RPTI_TYPE_PRT and H_RPTI_TYPE_PAT indicate invalidating the caching of process and partition scoped entries respectively.
--- arch/powerpc/include/asm/hvcall.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/powerpc/include/asm/hvcall.h +2 -2
@@ -413,9 +413,9 @@#define H_RPTI_TYPE_NESTED 0x0001/* Invalidate nested guest partition-scope */ #define H_RPTI_TYPE_TLB 0x0002/* Invalidate TLB */ #define H_RPTI_TYPE_PWC 0x0004/* Invalidate Page Walk Cache */ -/* Invalidate Process Table Entries if H_RPTI_TYPE_NESTED is clear */ +/* Invalidate caching of Process Table Entries if H_RPTI_TYPE_NESTED is clear */ #define H_RPTI_TYPE_PRT 0x0008 -/* Invalidate Partition Table Entries if H_RPTI_TYPE_NESTED is set */ +/* Invalidate caching of Partition Table Entries if H_RPTI_TYPE_NESTED is set */ #define H_RPTI_TYPE_PAT 0x0008#define H_RPTI_TYPE_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \ H_RPTI_TYPE_PRT)
Signature · 1 line
2.26.2
PATCH v7 2/6 powerpc/book3s64/radix: Add H_RPT_INVALIDATE pgsize encodings to mmu_psize_def
In reply to Bharata B RaoAdd 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.
--- arch/powerpc/include/asm/book3s/64/mmu.h | 1 + arch/powerpc/mm/book3s64/radix_pgtable.c | 5 +++++ 2 files changed, 6 insertions(+)
arch/powerpc/include/asm/book3s/64/mmu.h +1 -0
@@ -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 */
arch/powerpc/mm/book3s64/radix_pgtable.c +5 -0
@@ -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 ); }/*
Signature · 1 line
2.26.2
PATCH v7 3/6 KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
In reply to Bharata B RaoH_RPT_INVALIDATE does two types of TLB invalidations:
1. Process-scoped invalidations for guests when 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 is currently handled
by H_TLB_INVALIDATE hcall and this new replaces the old that.
This commit enables process-scoped invalidations for L1 guests. Support for process-scoped and partition-scoped invalidations from/for nested guests will be added separately.
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.
A description of H_RPT_INVALIDATE follows:
int64 /* H_Success: Return code on successful completion */ /* H_Busy - repeat the call with the same */ /* H_Parameter, H_P2, H_P3, H_P4, H_P5 : Invalid
parameters */
hcall(const uint64 H_RPT_INVALIDATE, /* Invalidate RPT
translation lookaside information */
uint64 id, /* PID/LPID to invalidate */ uint64 target, /* Invalidation target */ uint64 type, /* Type of lookaside information */ uint64 pg_sizes, /* Page sizes */
uint64 start, /* Start of Effective Address (EA)
range (inclusive) */
uint64 end) /* End of EA range (exclusive) */
Invalidation targets (target)
-----------------------------
Core MMU 0x01 /* All virtual processors in the
partition */
Core local MMU 0x02 /* Current virtual processor */ Nest MMU 0x04 /* All nest/accelerator agents
in use by the partition */
A combination of the above can be specified,
except core and core local.
Type of translation to invalidate (type)
---------------------------------------
NESTED 0x0001 /* invalidate nested guest partition-scope */ TLB 0x0002 /* Invalidate TLB */
PWC 0x0004 /* Invalidate Page Walk Cache */ PRT 0x0008 /* Invalidate caching of Process Table
Entries if NESTED is clear */
PAT 0x0008 /* Invalidate caching of Partition Table
Entries if NESTED is set */
A combination of the above can be specified.
Page size mask (pages)
----------------------
4K 0x01
64K 0x02
2M 0x04
1G 0x08
All sizes (-1UL)
A combination of the above can be specified.
All page sizes can be selected with -1.
Semantics: Invalidate radix tree lookaside information matching the parameters given.
* Return H_P2, H_P3 or H_P4 if target, type, or pageSizes parameters are different from the defined values.
* Return H_PARAMETER if NESTED is set and pid is not a valid nested LPID allocated to this partition
* Return H_P5 if (start, end) doesn't form a valid range. Start and end should be a valid Quadrant address and end > start.
* Return H_NotSupported if the partition is not in running in radix translation mode.
* May invalidate more translation information than requested.
* If start = 0 and end = -1, set the range to cover all valid addresses. Else start and end should be aligned to 4kB (lower 11 bits clear).
* If NESTED is clear, then invalidate process scoped lookaside information. Else pid specifies a nested LPID, and the invalidation is performed on nested guest partition table and nested guest partition scope real addresses.
* If pid = 0 and NESTED is clear, then valid addresses are quadrant 3 and quadrant 0 spaces, Else valid addresses are quadrant 0.
* Pages which are fully covered by the range are to be invalidated. Those which are partially covered are considered outside invalidation range, which allows a caller to optimally invalidate ranges that may contain mixed page sizes.
* Return H_SUCCESS on success.
--- arch/powerpc/include/asm/mmu_context.h | 11 ++ arch/powerpc/kvm/book3s_hv.c | 46 ++++++++ arch/powerpc/mm/book3s64/radix_tlb.c | 148 +++++++++++++++++++++++++ 3 files changed, 205 insertions(+)
arch/powerpc/include/asm/mmu_context.h +11 -0
@@ -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_prt (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_prt (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);
arch/powerpc/kvm/book3s_hv.c +46 -0
70 lines not on this page · raw message
arch/powerpc/mm/book3s64/radix_tlb.c +148 -0
194 lines not on this page · raw message
Signature · 1 line
2.26.2
Nicholas Piggin
reviewerRe: [PATCH v7 3/6] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
Excerpts from Bharata B Rao's message of May 6, 2021 1:46 am:
Quoted 162 lines
H_RPT_INVALIDATEdoes two types of TLB invalidations:1. Process-scoped invalidations for guests when 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 is currently handled
byH_TLB_INVALIDATEhcall and this new replaces the old that.This commit enables process-scoped invalidations for L1 guests. Support for process-scoped and partition-scoped invalidations from/for nested guests will be added separately.
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_INVALIDATEhcall.A description of
H_RPT_INVALIDATEfollows:int64 /*
H_Success: Return code on successful completion */ /*H_Busy- repeat the call with the same */ /*H_Parameter,H_P2,H_P3,H_P4,H_P5: Invalid
parameters */
hcall(const uint64H_RPT_INVALIDATE, /* Invalidate RPT
translation lookaside information */
uint64 id, /* PID/LPID to invalidate */ uint64 target, /* Invalidation target */ uint64 type, /* Type of lookaside information */ uint64pg_sizes, /* Page sizes */
uint64 start, /* Start of Effective Address (EA)
range (inclusive) */
uint64 end) /* End of EA range (exclusive) */Invalidation targets (target)
-----------------------------
Core MMU0x01/* All virtual processors in the
partition */
Core local MMU0x02/* Current virtual processor */ Nest MMU0x04/* All nest/accelerator agents
in use by the partition */A combination of the above can be specified,
except core and core local.Type of translation to invalidate (type)
---------------------------------------
NESTED 0x0001 /* invalidate nested guest partition-scope */ TLB 0x0002 /* Invalidate TLB */
PWC 0x0004 /* Invalidate Page Walk Cache */ PRT 0x0008 /* Invalidate caching of Process Table
Entries if NESTED is clear */
PAT 0x0008 /* Invalidate caching of Partition Table
Entries if NESTED is set */A combination of the above can be specified.
Page size mask (pages)
----------------------
4K0x01
64K0x02
2M0x04
1G0x08
All sizes (-1UL)A combination of the above can be specified.
All page sizes can be selected with -1.Semantics: Invalidate radix tree lookaside information matching the parameters given.
* ReturnH_P2,H_P3orH_P4if target, type, or pageSizes parameters are different from the defined values.
* ReturnH_PARAMETERif NESTED is set and pid is not a valid nested LPID allocated to this partition
* ReturnH_P5if (start, end) doesn't form a valid range. Start and end should be a valid Quadrant address and end > start.
* ReturnH_NotSupportedif the partition is not in running in radix translation mode.
* May invalidate more translation information than requested.
* If start = 0 and end = -1, set the range to cover all valid addresses. Else start and end should be aligned to 4kB (lower 11 bits clear).
* If NESTED is clear, then invalidate process scoped lookaside information. Else pid specifies a nested LPID, and the invalidation is performed on nested guest partition table and nested guest partition scope real addresses.
* If pid = 0 and NESTED is clear, then valid addresses are quadrant 3 and quadrant 0 spaces, Else valid addresses are quadrant 0.
* Pages which are fully covered by the range are to be invalidated. Those which are partially covered are considered outside invalidation range, which allows a caller to optimally invalidate ranges that may contain mixed page sizes.
* ReturnH_SUCCESSon success.Signed-off-by Bharata B Rao <[email protected]>Reviewed-by David Gibson <[email protected]>--- arch/powerpc/include/asm/mmu_context.h | 11 ++ arch/powerpc/kvm/book3s_hv.c | 46 ++++++++ arch/powerpc/mm/book3s64/radix_tlb.c | 148 +++++++++++++++++++++++++ 3 files changed, 205 insertions(+)arch/powerpc/include/asm/mmu_context.h +11
-0@@ -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_prt (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_prt (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);arch/powerpc/kvm/book3s_hv.c +19
-0@@ -76,6 +76,7 @@#include <asm/kvm_book3s_uvmem.h> #include <asm/ultravisor.h> #include <asm/dtl.h> +#include <asm/plpar_wrappers.h> #include "book3s.h" @@ -924,6 +925,42 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)return yield_count; } +static long kvmppc_h_rpt_invalidate (struct kvm_vcpu *vcpu, +unsigned long id,unsigned long target, +unsigned long type,unsigned long pg_sizes, +unsigned long start,unsigned long end) +{ +unsigned long psize; +struct mmu_psize_def *def; + +if (!kvm_is_radix (vcpu->kvm)) +return H_UNSUPPORTED ; + +if (end < start) +return H_P5 ; + +/* +* Partition-scoped invalidation for nested guests. +* Not yet supported +*/
arch/powerpc/kvm/book3s_hv.c static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu) · line 955
Quoted 10 lines
arch/powerpc/kvm/book3s_hv.c +10
-0+if (type &H_RPTI_TYPE_NESTED ) +return H_P3 ; + +/* +* Process-scoped invalidation for L1 guests. +*/ +for (psize =0 ; psize <MMU_PAGE_COUNT ; psize++) { + def = &mmu_psize_defs[psize]; +if (!(pg_sizes & def->h_rpt_pgsize)) +continue ;
Not that it really matters but why did you go this approach rather than use a bitmask iteration over h_rpt_pgsize?
I would actually prefer to put this loop into the TLB invalidation code itself.
The reason is that not all flush types are based on page size. You only need to do IS=1/2/3 flushes once and it takes out all page sizes.
You don't need to do all these optimisations right now, but it would be good to make them possible to implement.
Quoted 226 lines
arch/powerpc/kvm/book3s_hv.c +17
-0+ +do_h_rpt_invalidate_prt (id, vcpu->kvm->arch.lpid, + type, (1UL << def->shift), + psize, start, end); + } +return H_SUCCESS ; +} +int kvmppc_pseries_do_hcall (struct kvm_vcpu *vcpu) {unsigned long req =kvmppc_get_gpr (vcpu,3 );@@ -1132,6 +1169,14 @@ 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 ;@@ -1178,6 +1223,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)case H_XIRR_X :#endif case H_PAGE_INIT : +case H_RPT_INVALIDATE :return 1 ; }arch/powerpc/mm/book3s64/radix_tlb.c +135
-0@@ -130,6 +130,21 @@ 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 +205,23 @@ 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 +267,22 @@ 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 )) { + asmvolatile ("ptesync" : : :"memory" ); +__tlbie_pid_lpid (0 , lpid,RIC_FLUSH_TLB ); + } + +if (cpu_has_feature (CPU_FTR_P9_TLBIE_STQ_BUG )) { + asmvolatile ("ptesync" : : :"memory" ); +__tlbie_va_lpid (va, pid, lpid, ap,RIC_FLUSH_TLB ); + } +} +static inline void fixup_tlbie_pid (unsigned long pid) {/* @@ -254,6 +302,25 @@ 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 )) { + asmvolatile ("ptesync" : : :"memory" ); +__tlbie_pid_lpid (0 , lpid,RIC_FLUSH_TLB ); + } + +if (cpu_has_feature (CPU_FTR_P9_TLBIE_STQ_BUG )) { + asmvolatile ("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 +411,31 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric) asmvolatile ("eieio; tlbsync; ptesync" : : :"memory" ); } +static inline void _tlbie_pid_lpid (unsigned long pid,unsigned long lpid, +unsigned long ric) +{ + asmvolatile ("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); + } + asmvolatile ("eieio; tlbsync; ptesync" : : :"memory" ); +}struct tlbiel_pid {unsigned long pid;unsigned long ric;@@ -469,6 +561,20 @@ 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 +655,18 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end, asmvolatile ("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) +{ + asmvolatile ("ptesync" : : :"memory" ); +if (also_pwc) +__tlbie_pid_lpid (pid, lpid,RIC_FLUSH_PWC ); +__tlbie_va_range_lpid (start, end, pid, lpid, page_size, psize); + asmvolatile ("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 +1499,34 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) } }EXPORT_SYMBOL_GPL (radix_kvm_prefetch_workaround); + +/* +* Performs process-scoped invalidations for a given LPID +* as part of H_RPT_INVALIDATE hcall. +*/ +void do_h_rpt_invalidate_prt (unsigned long pid,unsigned long lpid, +unsigned long type,unsigned long page_size, +unsigned long psize,unsigned long start, +unsigned long end) +{ +/* +* A H_RPTI_TYPE_ALL request implies RIC=3, hence +* do a single IS=1 based flush. +*/ +if ((type &H_RPTI_TYPE_ALL ) ==H_RPTI_TYPE_ALL ) { +_tlbie_pid_lpid (pid, lpid,RIC_FLUSH_ALL ); +return ;
arch/powerpc/mm/book3s64/radix_tlb.c extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) · line 1528
Quoted 10 lines
arch/powerpc/mm/book3s64/radix_tlb.c +10
-0+ } + +if (type &H_RPTI_TYPE_PWC ) +_tlbie_pid_lpid (pid, lpid,RIC_FLUSH_PWC ); + +if (start ==0 && 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);
At least one thing that is probably needed is to use the single_page_flush_ceiling to flip the va range flush over to a pid flush, so the guest can't cause problems in the hypervisor with an enormous range.
Thanks,
Nick
Quoted 8 lines
arch/powerpc/mm/book3s64/radix_tlb.c +3
-0+} +EXPORT_SYMBOL_GPL (do_h_rpt_invalidate_prt); +#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ Signature · 1 line
2.26.2
Re: [PATCH v7 3/6] KVM: PPC: Book3S HV: Add support for H_RPT_INVALIDATE
Quoted 25 lines · Nicholas Piggin
Excerpts from Bharata B Rao's message of May 6, 2021 1:46 am:
Quoted 24 lines
arch/powerpc/kvm/book3s_hv.c +23
-0+static long kvmppc_h_rpt_invalidate (struct kvm_vcpu *vcpu, +unsigned long id,unsigned long target, +unsigned long type,unsigned long pg_sizes, +unsigned long start,unsigned long end) +{ +unsigned long psize; +struct mmu_psize_def *def; + +if (!kvm_is_radix (vcpu->kvm)) +return H_UNSUPPORTED ; + +if (end < start) +return H_P5 ; + +/* +* Partition-scoped invalidation for nested guests. +* Not yet supported +*/ +if (type &H_RPTI_TYPE_NESTED ) +return H_P3 ; + +/* +* Process-scoped invalidation for L1 guests.
Quoted 8 lines
arch/powerpc/kvm/book3s_hv.c static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu) · line 955
Quoted 5 lines
arch/powerpc/kvm/book3s_hv.c +5
-0+*/ +for (psize =0 ; psize <MMU_PAGE_COUNT ; psize++) { + def = &mmu_psize_defs[psize]; +if (!(pg_sizes & def->h_rpt_pgsize)) +continue ;Not that it really matters but why did you go this approach rather than use a bitmask iteration over
h_rpt_pgsize?
If you are asking why I am not just looping over the hcall argument @pg_sizes bitmask then, I was doing that in my earlier version. But David suggested that it would be good to have page size encodings of H_RPT_INVALIDATE within mmu_pgsize_defs[]. Based on this, I am populating mmu_pgsize_defs[] during radix page size initialization and using that here to check for those page sizes that have been set in @pg_sizes.
Quoted 3 lines
I would actually prefer to put this loop into the TLB invalidation code itself.
Yes, I could easily move it there.
Quoted 3 lines
The reason is that not all flush types are based on page size. You only need to do IS=1/2/3 flushes once and it takes out all page sizes.
I see. So we have to do explicit flushing for different page sizes only if we are doing range based invalidation (IS=0). For rest of the cases (IS=1/2/3), that's not necessary.
Quoted 3 lines
You don't need to do all these optimisations right now, but it would be good to make them possible to implement.
Sure.
Quoted 19 lines
Quoted 19 lines
arch/powerpc/mm/book3s64/radix_tlb.c +19
-0+void do_h_rpt_invalidate_prt (unsigned long pid,unsigned long lpid, +unsigned long type,unsigned long page_size, +unsigned long psize,unsigned long start, +unsigned long end) +{ +/* +* A H_RPTI_TYPE_ALL request implies RIC=3, hence +* do a single IS=1 based flush. +*/ +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 ==0 && end ==-1 )/* PID */ +_tlbie_pid_lpid (pid, lpid,RIC_FLUSH_TLB );
Quoted 8 lines
arch/powerpc/mm/book3s64/radix_tlb.c extern void radix_kvm_prefetch_workaround(struct mm_struct *mm) · line 1528
Quoted 3 lines
arch/powerpc/mm/book3s64/radix_tlb.c +3
-0+else /* EA */ +_tlbie_va_range_lpid (start, end, pid, lpid, page_size, + psize, false);At least one thing that is probably needed is to use the
single_page_flush_ceilingto flip the va range flush over to a pid flush, so the guest can't cause problems in the hypervisor with an enormous range.
Yes, makes sense. I shall do this and the above as later optimizations.
Regards,
Bharata.
PATCH v7 4/6 KVM: PPC: Book3S HV: Nested support in H_RPT_INVALIDATE
In reply to Bharata B RaoEnable support for process-scoped invalidations from nested guests and partition-scoped invalidations for nested guests.
Process-scoped invalidations for any level of nested guests are handled by implementing H_RPT_INVALIDATE handler in the nested guest exit path in L0.
Partition-scoped invalidation requests are forwarded to the right nested guest, handled there and passed down to L0 for eventual handling.
--- .../include/asm/book3s/64/tlbflush-radix.h | 4 + arch/powerpc/include/asm/kvm_book3s.h | 3 + arch/powerpc/kvm/book3s_hv.c | 66 ++++++++++- arch/powerpc/kvm/book3s_hv_nested.c | 104 ++++++++++++++++++ arch/powerpc/mm/book3s64/radix_tlb.c | 4 - 5 files changed, 174 insertions(+), 7 deletions(-)
arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +4 -0
@@ -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 ;
arch/powerpc/include/asm/kvm_book3s.h +3 -0
@@ -307,6 +307,9 @@ 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 do_h_rpt_invalidate_pat (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);
arch/powerpc/kvm/book3s_hv.c +63 -3
85 lines not on this page · raw message
arch/powerpc/kvm/book3s_hv_nested.c +104 -0
110 lines not on this page · raw message
arch/powerpc/mm/book3s64/radix_tlb.c +0 -4
@@ -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
Signature · 1 line
2.26.2
Nicholas Piggin
reviewerRe: [PATCH v7 4/6] KVM: PPC: Book3S HV: Nested support in H_RPT_INVALIDATE
Excerpts from Bharata B Rao's message of May 6, 2021 1:46 am:
Quoted 161 lines
Enable support for process-scoped invalidations from nested guests and partition-scoped invalidations for nested guests.
Process-scoped invalidations for any level of nested guests are handled by implementing
H_RPT_INVALIDATEhandler in the nested guest exit path in L0.Partition-scoped invalidation requests are forwarded to the right nested guest, handled there and passed down to L0 for eventual handling.
Signed-off-by Bharata B Rao <[email protected]>Signed-off-by Aneesh Kumar K.V <[email protected]>[Nested guest partition-scoped invalidation changes]--- .../include/asm/book3s/64/tlbflush-radix.h | 4 + arch/powerpc/include/asm/kvm_book3s.h | 3 + arch/powerpc/kvm/book3s_hv.c | 66 ++++++++++- arch/powerpc/kvm/book3s_hv_nested.c | 104 ++++++++++++++++++ arch/powerpc/mm/book3s64/radix_tlb.c | 4 - 5 files changed, 174 insertions(+), 7 deletions(-)arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +4
-0@@ -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 ;arch/powerpc/include/asm/kvm_book3s.h +3
-0@@ -307,6 +307,9 @@ 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 do_h_rpt_invalidate_pat (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);arch/powerpc/kvm/book3s_hv.c +63
-3@@ -925,6 +925,41 @@ static int kvmppc_get_yield_count(struct kvm_vcpu *vcpu)return yield_count; } +/* +* H_RPT_INVALIDATE hcall handler for nested guests. +* +* Handles only nested process-scoped invalidation requests in L0. +*/ +static int kvmppc_nested_h_rpt_invalidate (struct kvm_vcpu *vcpu) +{ +unsigned long type =kvmppc_get_gpr (vcpu,6 ); +unsigned long pid, pg_sizes, start, end, psize; +struct mmu_psize_def *def; + +/* +* The partition-scoped invalidations aren't handled here in L0. +*/ +if (type &H_RPTI_TYPE_NESTED ) +return RESUME_HOST ; + + pid =kvmppc_get_gpr (vcpu,4 ); + pg_sizes =kvmppc_get_gpr (vcpu,7 ); + start =kvmppc_get_gpr (vcpu,8 ); + end =kvmppc_get_gpr (vcpu,9 ); + +for (psize =0 ; psize <MMU_PAGE_COUNT ; psize++) { + def = &mmu_psize_defs[psize]; +if (pg_sizes & def->h_rpt_pgsize) +do_h_rpt_invalidate_prt (pid, + vcpu->arch.nested->shadow_lpid, + type, (1UL << def->shift), + psize, start, end); + } + +kvmppc_set_gpr (vcpu,3 ,H_SUCCESS ); +return RESUME_GUEST ; +} + static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu, unsigned long id, unsigned long target, unsigned long type, unsigned long pg_sizes,@@ -941,10 +976,18 @@ static long kvmppc_h_rpt_invalidate(struct kvm_vcpu *vcpu,/* * Partition-scoped invalidation for nested guests. -* Not yet supported */ -if (type &H_RPTI_TYPE_NESTED ) -return H_P3 ; +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 do_h_rpt_invalidate_pat (vcpu, id, type, pg_sizes, + start, end); + }/* * Process-scoped invalidation for L1 guests. @@ -1639,6 +1682,23 @@ 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 ) { + r =kvmppc_nested_h_rpt_invalidate (vcpu); +break ; + } + + r =RESUME_HOST ; +break ; + }default : r =RESUME_HOST ;break ;arch/powerpc/kvm/book3s_hv_nested.c +10
-0@@ -1214,6 +1214,110 @@ 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; +
arch/powerpc/kvm/book3s_hv_nested.c long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu) · line 1236
Quoted 10 lines
arch/powerpc/kvm/book3s_hv_nested.c +10
-0+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; +}
Similar comments for single page thresholds, and multiple page sizes.
Quoted 52 lines
arch/powerpc/kvm/book3s_hv_nested.c +52
-0+ +static long do_tlb_invalidate_nested_all (struct kvm_vcpu *vcpu, +unsigned long lpid,unsigned long ric) +{ +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); +kvmhv_put_nested (gp); + } +return H_SUCCESS ; +} + +/* +* Performs partition-scoped invalidations for nested guests +* as part of H_RPT_INVALIDATE hcall. +*/ +long do_h_rpt_invalidate_pat (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 ; + +/* +* A flush all request can be handled by a full lpid flush only. +*/ +if ((type &H_RPTI_TYPE_NESTED_ALL ) ==H_RPTI_TYPE_NESTED_ALL ) +return do_tlb_invalidate_nested_all (vcpu, lpid,RIC_FLUSH_ALL ); + +#if 0 +/* +* We don't need to handle a PWC flush like process table here, +* because intermediate partition scoped table in nested guest doesn't +* really have PWC. Only level we have PWC is in L0 and for nested +* invalidate at L0 we always do kvm_flush_lpid() which does
arch/powerpc/kvm/book3s_hv_nested.c long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu) · line 1298
Quoted 10 lines
arch/powerpc/kvm/book3s_hv_nested.c +10
-0+* radix__flush_all_lpid(). For range invalidate at any level, we +* are not removing the higher level page tables and hence there is +* no PWC invalidate needed. +*/ +if (type &H_RPTI_TYPE_PWC ) { + ret =do_tlb_invalidate_nested_all (vcpu, lpid,RIC_FLUSH_PWC ); +if (ret) +return H_P4 ; + } +#endif
I think removing this #if 0 and the unnecessary code is fine, just a bit more explanation in the comment would help. And "doesn't really" implies it sort of might a little bit, I think what you want is "really doesn't" :)
As I understand it, the L0 does not cache any intermediate levels of the nested guest's partition scope at all. Only the nested HV's pte entries are copied into the shadow page table, so we only care if the PTEs are changed, and the PWCs that the processor creates for the shadow page table are managed by the kvmppc_unmap_pte() etc functions... I think?
Thanks,
Nick
Quoted 44 lines
arch/powerpc/kvm/book3s_hv_nested.c +22
-0+ +if (start ==0 && end ==-1 ) +return do_tlb_invalidate_nested_all (vcpu, lpid,RIC_FLUSH_TLB ); + +if (type &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,arch/powerpc/mm/book3s64/radix_tlb.c +0
-4@@ -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 Signature · 1 line
2.26.2
Re: [PATCH v7 4/6] KVM: PPC: Book3S HV: Nested support in H_RPT_INVALIDATE
Nicholas Piggin <[email protected]> writes:
...
Quoted 41 lines
+ */
Quoted 40 lines
arch/powerpc/kvm/book3s_hv_nested.c +40
-0+long do_h_rpt_invalidate_pat (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 ; + +/* +* A flush all request can be handled by a full lpid flush only. +*/ +if ((type &H_RPTI_TYPE_NESTED_ALL ) ==H_RPTI_TYPE_NESTED_ALL ) +return do_tlb_invalidate_nested_all (vcpu, lpid,RIC_FLUSH_ALL ); + +#if 0 +/* +* We don't need to handle a PWC flush like process table here, +* because intermediate partition scoped table in nested guest doesn't +* really have PWC. Only level we have PWC is in L0 and for nested +* invalidate at L0 we always do kvm_flush_lpid() which does +* radix__flush_all_lpid(). For range invalidate at any level, we +* are not removing the higher level page tables and hence there is +* no PWC invalidate needed. +*/ +if (type &H_RPTI_TYPE_PWC ) { + ret =do_tlb_invalidate_nested_all (vcpu, lpid,RIC_FLUSH_PWC ); +if (ret)
Quoted 8 lines
arch/powerpc/kvm/book3s_hv_nested.c long kvmhv_do_nested_tlbie(struct kvm_vcpu *vcpu) · line 1298
Quoted 3 lines
arch/powerpc/kvm/book3s_hv_nested.c +3
-0+ return H_P4; + } +#endif I think removing this #if 0 and the unnecessary code is fine, just a bit more explanation in the comment would help. And "doesn't really" implies it sort of might a little bit, I think what you want is "really doesn't" :)
yes.
Quoted 6 lines
As I understand it, the L0 does not cache any intermediate levels of the nested guest's partition scope at all. Only the nested HV's pte entries are copied into the shadow page table, so we only care if the PTEs are changed, and the PWCs that the processor creates for the shadow page table are managed by the
kvmppc_unmap_pte()etc functions... I think?
That is correct. The reason I added the comment there was to clarify why the PWC type is not handled in case of partition scoped invalidate similar to process scoped invalidate. The code fragment was left as an indication of what should happen theoretically.
All higher levels of guest (L1, L2.. etc) have partition tables that are not really used for hardware page table walk. H_RPT_INVALIDATE hcall is used as a hint to free those page table entries. L0 on receiving the hcall will forward the same to higher levels guest which after invalidating its shadow pte will further issue the H_RPT_INVALIDATE hcall to clear parition scoped entries of the current guest.
If it is a range TLB flush, we just clear the shadow pte, higher levels page tables are not modified and hence no PWC flush is required.
If it is full lpid flush because of RIC=1/2 or because range is 0 -> -1 we do free the full partition table and does a kvmhv_flush_lpid() which will eventually ends up calling radix__flush_all_lpid().
These function names are kept in the comment so that a new person looking at the code can easily follow the code path.
-aneesh
PATCH v7 5/6 KVM: PPC: Book3S HV: Add KVM_CAP_PPC_RPT_INVALIDATE capability
In reply to Bharata B RaoNow that we have H_RPT_INVALIDATE fully implemented, enable support for the same via KVM_CAP_PPC_RPT_INVALIDATE KVM capability
--- Documentation/virt/kvm/api.rst | 18 ++++++++++++++++++ arch/powerpc/kvm/powerpc.c | 3 +++ include/uapi/linux/kvm.h | 1 + 3 files changed, 22 insertions(+)
Documentation/virt/kvm/api.rst +18 -0
@@ -6362,6 +6362,24 @@ default. See Documentation/x86/sgx/2.Kernel-internals.rst for more details. +7.26 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. ======================
arch/powerpc/kvm/powerpc.c +3 -0
@@ -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 ;
include/uapi/linux/kvm.h +1 -0
@@ -1082,6 +1082,7 @@ struct kvm_ppc_resize_hpt {#define KVM_CAP_SGX_ATTRIBUTE 196#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197#define KVM_CAP_PTP_KVM 198 +#define KVM_CAP_PPC_RPT_INVALIDATE 199#ifdef KVM_CAP_IRQ_ROUTING
Signature · 1 line
2.26.2
PATCH v7 6/6 KVM: PPC: Book3S HV: Use H_RPT_INVALIDATE in nested KVM
In reply to Bharata B RaoIn 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.
--- arch/powerpc/kvm/book3s_64_mmu_radix.c | 27 +++++++++++++++++++++----- arch/powerpc/kvm/book3s_hv_nested.c | 12 ++++++++++-- 2 files changed, 32 insertions(+), 7 deletions(-)
arch/powerpc/kvm/book3s_64_mmu_radix.c +22 -5
@@ -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); }
arch/powerpc/kvm/book3s_hv_nested.c +10 -2
@@ -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;
@@ -467,8 +468,15 @@ 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); }
Signature · 1 line
2.26.2