Re: [PATCH v5 09/33] KVM: PPC: Book3S HV: Streamlined guest entry/exit path on P9 for radix guests
On Mon, Oct 08, 2018 at 04:30:55PM +1100, Paul Mackerras wrote:
> This creates an alternative guest entry/exit path which is used for
> radix guests on POWER9 systems when we have indep_threads_mode=Y. In
> these circumstances there is exactly one vcpu per vcore and there is
> no coordination required between vcpus or vcores; the vcpu can enter
> the guest without needing to synchronize with anything else.
>
> The new fast path is implemented almost entirely in C in book3s_hv.c
> and runs with the MMU on until the guest is entered. On guest exit
> we use the existing path until the point where we are committed to
> exiting the guest (as distinct from handling an interrupt in the
> low-level code and returning to the guest) and we have pulled the
> guest context from the XIVE. At that point we check a flag in the
> stack frame to see whether we came in via the old path and the new
> path; if we came in via the new path then we go back to C code to do
> the rest of the process of saving the guest context and restoring the
> host context.
>
> The C code is split into separate functions for handling the
> OS-accessible state and the hypervisor state, with the idea that the
> latter can be replaced by a hypercall when we implement nested
> virtualization.
>
> Signed-off-by: Paul Mackerras
Reviewed-by: David Gibson
> ---
> arch/powerpc/include/asm/asm-prototypes.h | 2 +
> arch/powerpc/include/asm/kvm_ppc.h| 2 +
> arch/powerpc/kvm/book3s_hv.c | 429
> +-
> arch/powerpc/kvm/book3s_hv_ras.c | 2 +
> arch/powerpc/kvm/book3s_hv_rmhandlers.S | 95 ++-
> arch/powerpc/kvm/book3s_xive.c| 63 +
> 6 files changed, 589 insertions(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/asm-prototypes.h
> b/arch/powerpc/include/asm/asm-prototypes.h
> index 0c1a2b0..5c9b00c 100644
> --- a/arch/powerpc/include/asm/asm-prototypes.h
> +++ b/arch/powerpc/include/asm/asm-prototypes.h
> @@ -165,4 +165,6 @@ void kvmhv_load_host_pmu(void);
> void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use);
> void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu);
>
> +int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu);
> +
> #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
> diff --git a/arch/powerpc/include/asm/kvm_ppc.h
> b/arch/powerpc/include/asm/kvm_ppc.h
> index 83d61b8..245e564 100644
> --- a/arch/powerpc/include/asm/kvm_ppc.h
> +++ b/arch/powerpc/include/asm/kvm_ppc.h
> @@ -585,6 +585,7 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64
> icpval);
>
> extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
> int level, bool line_status);
> +extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
> #else
> static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
> u32 priority) { return -1; }
> @@ -607,6 +608,7 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu
> *vcpu, u64 icpval) { retur
>
> static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id,
> u32 irq,
> int level, bool line_status) { return
> -ENODEV; }
> +static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
> #endif /* CONFIG_KVM_XIVE */
>
> /*
> diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
> index 0e17593..0c1dd76 100644
> --- a/arch/powerpc/kvm/book3s_hv.c
> +++ b/arch/powerpc/kvm/book3s_hv.c
> @@ -3080,6 +3080,269 @@ static noinline void kvmppc_run_core(struct
> kvmppc_vcore *vc)
> }
>
> /*
> + * Load up hypervisor-mode registers on P9.
> + */
> +static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit)
> +{
> + struct kvmppc_vcore *vc = vcpu->arch.vcore;
> + s64 hdec;
> + u64 tb, purr, spurr;
> + int trap;
> + unsigned long host_hfscr = mfspr(SPRN_HFSCR);
> + unsigned long host_ciabr = mfspr(SPRN_CIABR);
> + unsigned long host_dawr = mfspr(SPRN_DAWR);
> + unsigned long host_dawrx = mfspr(SPRN_DAWRX);
> + unsigned long host_psscr = mfspr(SPRN_PSSCR);
> + unsigned long host_pidr = mfspr(SPRN_PID);
> +
> + hdec = time_limit - mftb();
> + if (hdec < 0)
> + return BOOK3S_INTERRUPT_HV_DECREMENTER;
> + mtspr(SPRN_HDEC, hdec);
> +
> + if (vc->tb_offset) {
> + u64 new_tb = mftb() + vc->tb_offset;
> + mtspr(SPRN_TBU40, new_tb);
> + tb = mftb();
> + if ((tb & 0xff) < (new_tb & 0xff))
> + mtspr(SPRN_TBU40, new_tb + 0x100);
> + vc->tb_offset_applied = vc->tb_offset;
> + }
> +
> + if (vc->pcr)
> + mtspr(SPRN_PCR, vc->pcr);
> + mtspr(SPRN_DPDES, vc->dpdes);
> + mtspr(SPRN_VTB, vc->vtb);
> +
> + local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
> + local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
> + mtspr(SPRN_PURR,
[PATCH v5 09/33] KVM: PPC: Book3S HV: Streamlined guest entry/exit path on P9 for radix guests
This creates an alternative guest entry/exit path which is used for
radix guests on POWER9 systems when we have indep_threads_mode=Y. In
these circumstances there is exactly one vcpu per vcore and there is
no coordination required between vcpus or vcores; the vcpu can enter
the guest without needing to synchronize with anything else.
The new fast path is implemented almost entirely in C in book3s_hv.c
and runs with the MMU on until the guest is entered. On guest exit
we use the existing path until the point where we are committed to
exiting the guest (as distinct from handling an interrupt in the
low-level code and returning to the guest) and we have pulled the
guest context from the XIVE. At that point we check a flag in the
stack frame to see whether we came in via the old path and the new
path; if we came in via the new path then we go back to C code to do
the rest of the process of saving the guest context and restoring the
host context.
The C code is split into separate functions for handling the
OS-accessible state and the hypervisor state, with the idea that the
latter can be replaced by a hypercall when we implement nested
virtualization.
Signed-off-by: Paul Mackerras
---
arch/powerpc/include/asm/asm-prototypes.h | 2 +
arch/powerpc/include/asm/kvm_ppc.h| 2 +
arch/powerpc/kvm/book3s_hv.c | 429 +-
arch/powerpc/kvm/book3s_hv_ras.c | 2 +
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 95 ++-
arch/powerpc/kvm/book3s_xive.c| 63 +
6 files changed, 589 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/asm-prototypes.h
b/arch/powerpc/include/asm/asm-prototypes.h
index 0c1a2b0..5c9b00c 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -165,4 +165,6 @@ void kvmhv_load_host_pmu(void);
void kvmhv_save_guest_pmu(struct kvm_vcpu *vcpu, bool pmu_in_use);
void kvmhv_load_guest_pmu(struct kvm_vcpu *vcpu);
+int __kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu);
+
#endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h
b/arch/powerpc/include/asm/kvm_ppc.h
index 83d61b8..245e564 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -585,6 +585,7 @@ extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64
icpval);
extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
int level, bool line_status);
+extern void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu);
#else
static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
u32 priority) { return -1; }
@@ -607,6 +608,7 @@ static inline int kvmppc_xive_set_icp(struct kvm_vcpu
*vcpu, u64 icpval) { retur
static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32
irq,
int level, bool line_status) { return
-ENODEV; }
+static inline void kvmppc_xive_push_vcpu(struct kvm_vcpu *vcpu) { }
#endif /* CONFIG_KVM_XIVE */
/*
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0e17593..0c1dd76 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3080,6 +3080,269 @@ static noinline void kvmppc_run_core(struct
kvmppc_vcore *vc)
}
/*
+ * Load up hypervisor-mode registers on P9.
+ */
+static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit)
+{
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ s64 hdec;
+ u64 tb, purr, spurr;
+ int trap;
+ unsigned long host_hfscr = mfspr(SPRN_HFSCR);
+ unsigned long host_ciabr = mfspr(SPRN_CIABR);
+ unsigned long host_dawr = mfspr(SPRN_DAWR);
+ unsigned long host_dawrx = mfspr(SPRN_DAWRX);
+ unsigned long host_psscr = mfspr(SPRN_PSSCR);
+ unsigned long host_pidr = mfspr(SPRN_PID);
+
+ hdec = time_limit - mftb();
+ if (hdec < 0)
+ return BOOK3S_INTERRUPT_HV_DECREMENTER;
+ mtspr(SPRN_HDEC, hdec);
+
+ if (vc->tb_offset) {
+ u64 new_tb = mftb() + vc->tb_offset;
+ mtspr(SPRN_TBU40, new_tb);
+ tb = mftb();
+ if ((tb & 0xff) < (new_tb & 0xff))
+ mtspr(SPRN_TBU40, new_tb + 0x100);
+ vc->tb_offset_applied = vc->tb_offset;
+ }
+
+ if (vc->pcr)
+ mtspr(SPRN_PCR, vc->pcr);
+ mtspr(SPRN_DPDES, vc->dpdes);
+ mtspr(SPRN_VTB, vc->vtb);
+
+ local_paca->kvm_hstate.host_purr = mfspr(SPRN_PURR);
+ local_paca->kvm_hstate.host_spurr = mfspr(SPRN_SPURR);
+ mtspr(SPRN_PURR, vcpu->arch.purr);
+ mtspr(SPRN_SPURR, vcpu->arch.spurr);
+
+ if (cpu_has_feature(CPU_FTR_DAWR)) {
+ mtspr(SPRN_DAWR, vcpu->arch.dawr);
+ mtspr(SPRN_DAWRX, vcpu->arch.dawrx);
+ }
+ mtspr(SPRN_CIABR,
