@@ -6032,6 +6032,23 @@ KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications which user space
can then handle to implement model specific MSR handling and/or user notifications
to inform a user that an MSR was not handled.
+7.22 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 always enabled.
+
8. Other capabilities.
======================
@@ -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;
@@ -21,6 +25,20 @@ static inline u64 psize_to_rpti_pgsize(unsigned long psize)
return H_RPTI_PAGE_ALL;
}
+static inline int rpti_pgsize_to_psize(unsigned long page_size)
+{
+ if (page_size == H_RPTI_PAGE_4K)
+ return MMU_PAGE_4K;
+ if (page_size == H_RPTI_PAGE_64K)
+ return MMU_PAGE_64K;
+ if (page_size == H_RPTI_PAGE_2M)
+ return MMU_PAGE_2M;
+ if (page_size == H_RPTI_PAGE_1G)
+ return MMU_PAGE_1G;
+ else
+ return MMU_PAGE_64K; /* Default */
+}
+
static inline int mmu_get_ap(int psize)
{
return mmu_psize_defs[psize].ap;
@@ -298,6 +298,9 @@ 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);
@@ -124,8 +124,15 @@ 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 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 type,
+ unsigned long page_size,
+ unsigned long psize, unsigned long start,
+ unsigned long end) { }
#endif
extern void switch_cop(struct mm_struct *next);
@@ -904,6 +904,53 @@ 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 pid, unsigned long target,
+ unsigned long type, unsigned long pg_sizes,
+ unsigned long start, unsigned long end)
+{
+ unsigned long psize;
+
+ if (!kvm_is_radix(vcpu->kvm))
+ 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);
+ }
+
+ if (pg_sizes & H_RPTI_PAGE_64K) {
+ psize = rpti_pgsize_to_psize(pg_sizes & H_RPTI_PAGE_64K);
+ do_h_rpt_invalidate(pid, type, (1UL << 16), psize,
+ start, end);
+ }
+
+ if (pg_sizes & H_RPTI_PAGE_2M) {
+ psize = rpti_pgsize_to_psize(pg_sizes & H_RPTI_PAGE_2M);
+ do_h_rpt_invalidate(pid, type, (1UL << 21), psize,
+ start, end);
+ }
+
+ if (pg_sizes & H_RPTI_PAGE_1G) {
+ psize = rpti_pgsize_to_psize(pg_sizes & H_RPTI_PAGE_1G);
+ do_h_rpt_invalidate(pid, type, (1UL << 30), psize,
+ start, end);
+ }
+
+ return H_SUCCESS;
+}
+
int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
{
unsigned long req = kvmppc_get_gpr(vcpu, 3);
@@ -1112,6 +1159,14 @@ 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;
@@ -1158,6 +1213,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
case H_XIRR_X:
#endif
case H_PAGE_INIT:
+ case H_RPT_INVALIDATE:
return 1;
}
@@ -1149,6 +1149,102 @@ 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) {
+ if (pg_sizes & H_RPTI_PAGE_64K) {
+ psize = rpti_pgsize_to_psize(pg_sizes & H_RPTI_PAGE_64K);
+ ap = mmu_get_ap(psize);
+
+ ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
+ (1UL << 16),
+ ap, start, end);
+ if (ret)
+ return H_P4;
+ }
+
+ if (pg_sizes & H_RPTI_PAGE_2M) {
+ psize = rpti_pgsize_to_psize(pg_sizes & H_RPTI_PAGE_2M);
+ ap = mmu_get_ap(psize);
+
+ ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
+ (1UL << 21),
+ ap, start, end);
+ if (ret)
+ return H_P4;
+ }
+
+ if (pg_sizes & H_RPTI_PAGE_1G) {
+ psize = rpti_pgsize_to_psize(pg_sizes & H_RPTI_PAGE_1G);
+ ap = mmu_get_ap(psize);
+
+ ret = do_tlb_invalidate_nested_tlb(vcpu, lpid,
+ (1UL << 30),
+ 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,
@@ -678,6 +678,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = hv_enabled && kvmppc_hv_ops->enable_svm &&
!kvmppc_hv_ops->enable_svm(NULL);
break;
+ case KVM_CAP_PPC_RPT_INVALIDATE:
+ r = 1;
+ break;
#endif
default:
r = 0;
@@ -18,10 +18,6 @@
#include <asm/cputhreads.h>
#include <asm/plpar_wrappers.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
@@ -1286,4 +1282,24 @@ extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
}
}
EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
+
+void do_h_rpt_invalidate(unsigned long pid, 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(pid, RIC_FLUSH_ALL);
+ return;
+ }
+
+ if (type & H_RPTI_TYPE_PWC)
+ _tlbie_pid(pid, RIC_FLUSH_PWC);
+
+ if (!start && end == -1) /* PID */
+ _tlbie_pid(pid, RIC_FLUSH_TLB);
+ else /* EA */
+ _tlbie_va_range(start, end, pid, page_size, psize, false);
+}
+EXPORT_SYMBOL_GPL(do_h_rpt_invalidate);
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
@@ -1056,6 +1056,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
#define KVM_CAP_SYS_HYPERV_CPUID 191
#define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_PPC_RPT_INVALIDATE 193
#ifdef KVM_CAP_IRQ_ROUTING
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. Signed-off-by: Bharata B Rao <bharata@linux.ibm.com> --- Documentation/virt/kvm/api.rst | 17 ++++ .../include/asm/book3s/64/tlbflush-radix.h | 18 ++++ arch/powerpc/include/asm/kvm_book3s.h | 3 + arch/powerpc/include/asm/mmu_context.h | 7 ++ arch/powerpc/kvm/book3s_hv.c | 56 +++++++++++ arch/powerpc/kvm/book3s_hv_nested.c | 96 +++++++++++++++++++ arch/powerpc/kvm/powerpc.c | 3 + arch/powerpc/mm/book3s64/radix_tlb.c | 24 ++++- include/uapi/linux/kvm.h | 1 + 9 files changed, 221 insertions(+), 4 deletions(-)