From: Gautam Menghani <gautam@linux.ibm.com> To: mpe@ellerman.id.au, npiggin@gmail.com, christophe.leroy@csgroup.eu, aneesh.kumar@kernel.org, naveen.n.rao@linux.ibm.com Cc: Gautam Menghani <gautam@linux.ibm.com>, linuxppc-dev@lists.ozlabs.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, Vaibhav Jain <vaibhav@linux.ibm.com> Subject: [PATCH v5] arch/powerpc/kvm: Add support for reading VPA counters for pseries guests Date: Mon, 1 Apr 2024 16:55:42 +0530 [thread overview] Message-ID: <20240401112544.51764-1-gautam@linux.ibm.com> (raw) PAPR hypervisor has introduced three new counters in the VPA area of LPAR CPUs for KVM L2 guest (see [1] for terminology) observability - 2 for context switches from host to guest and vice versa, and 1 counter for getting the total time spent inside the KVM guest. Add a tracepoint that enables reading the counters for use by ftrace/perf. Note that this tracepoint is only available for nestedv2 API (i.e, KVM on PowerVM). Also maintain an aggregation of the context switch times in vcpu->arch. This will be useful in getting the aggregate times with a pmu driver which will be upstreamed in the near future. [1] Terminology: a. L1 refers to the VM (LPAR) booted on top of PAPR hypervisor b. L2 refers to the KVM guest booted on top of L1. Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com> Signed-off-by: Gautam Menghani <gautam@linux.ibm.com> --- arch/powerpc/include/asm/kvm_host.h | 5 ++++ arch/powerpc/include/asm/lppaca.h | 11 +++++--- arch/powerpc/kvm/book3s_hv.c | 40 +++++++++++++++++++++++++++++ arch/powerpc/kvm/trace_hv.h | 25 ++++++++++++++++++ 4 files changed, 78 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 8abac532146e..d953b32dd68a 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -847,6 +847,11 @@ struct kvm_vcpu_arch { gpa_t nested_io_gpr; /* For nested APIv2 guests*/ struct kvmhv_nestedv2_io nestedv2_io; + + /* Aggregate context switch and guest run time info (in ns) */ + u64 l1_to_l2_cs_agg; + u64 l2_to_l1_cs_agg; + u64 l2_runtime_agg; #endif #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 61ec2447dabf..bda6b86b9f13 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -62,7 +62,8 @@ struct lppaca { u8 donate_dedicated_cpu; /* Donate dedicated CPU cycles */ u8 fpregs_in_use; u8 pmcregs_in_use; - u8 reserved8[28]; + u8 l2_accumul_cntrs_enable; /* Enable usage of counters for KVM guest */ + u8 reserved8[27]; __be64 wait_state_cycles; /* Wait cycles for this proc */ u8 reserved9[28]; __be16 slb_count; /* # of SLBs to maintain */ @@ -92,9 +93,13 @@ struct lppaca { /* cacheline 4-5 */ __be32 page_ins; /* CMO Hint - # page ins by OS */ - u8 reserved12[148]; + u8 reserved12[28]; + volatile __be64 l1_to_l2_cs_tb; + volatile __be64 l2_to_l1_cs_tb; + volatile __be64 l2_runtime_tb; + u8 reserved13[96]; volatile __be64 dtl_idx; /* Dispatch Trace Log head index */ - u8 reserved13[96]; + u8 reserved14[96]; } ____cacheline_aligned; #define lppaca_of(cpu) (*paca_ptrs[cpu]->lppaca_ptr) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 8e86eb577eb8..fea1c1429975 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4108,6 +4108,37 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) } } +static inline int kvmhv_get_l2_accumul(void) +{ + return get_lppaca()->l2_accumul_cntrs_enable; +} + +static inline void kvmhv_set_l2_accumul(int val) +{ + get_lppaca()->l2_accumul_cntrs_enable = val; +} + +static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu) +{ + struct lppaca *lp = get_lppaca(); + u64 l1_to_l2_ns, l2_to_l1_ns, l2_runtime_ns; + + l1_to_l2_ns = tb_to_ns(be64_to_cpu(lp->l1_to_l2_cs_tb)); + l2_to_l1_ns = tb_to_ns(be64_to_cpu(lp->l2_to_l1_cs_tb)); + l2_runtime_ns = tb_to_ns(be64_to_cpu(lp->l2_runtime_tb)); + trace_kvmppc_vcpu_exit_cs_time(vcpu, l1_to_l2_ns, l2_to_l1_ns, + l2_runtime_ns); + lp->l1_to_l2_cs_tb = 0; + lp->l2_to_l1_cs_tb = 0; + lp->l2_runtime_tb = 0; + kvmhv_set_l2_accumul(0); + + // Maintain an aggregate of context switch times + vcpu->arch.l1_to_l2_cs_agg += l1_to_l2_ns; + vcpu->arch.l2_to_l1_cs_agg += l2_to_l1_ns; + vcpu->arch.l2_runtime_agg += l2_runtime_ns; +} + static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) { @@ -4130,6 +4161,11 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_gse_put_u64(io->vcpu_run_input, KVMPPC_GSID_LPCR, lpcr); accumulate_time(vcpu, &vcpu->arch.in_guest); + + /* Enable the guest host context switch time tracking */ + if (unlikely(trace_kvmppc_vcpu_exit_cs_time_enabled())) + kvmhv_set_l2_accumul(1); + rc = plpar_guest_run_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id, &trap, &i); @@ -4156,6 +4192,10 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, timer_rearm_host_dec(*tb); + /* Record context switch and guest_run_time data */ + if (kvmhv_get_l2_accumul()) + do_trace_nested_cs_time(vcpu); + return trap; } diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index 8d57c8428531..ab19977c91b4 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -491,6 +491,31 @@ TRACE_EVENT(kvmppc_run_vcpu_enter, TP_printk("VCPU %d: tgid=%d", __entry->vcpu_id, __entry->tgid) ); +TRACE_EVENT(kvmppc_vcpu_exit_cs_time, + TP_PROTO(struct kvm_vcpu *vcpu, u64 l1_to_l2_cs, u64 l2_to_l1_cs, + u64 l2_runtime), + + TP_ARGS(vcpu, l1_to_l2_cs, l2_to_l1_cs, l2_runtime), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(__u64, l1_to_l2_cs_ns) + __field(__u64, l2_to_l1_cs_ns) + __field(__u64, l2_runtime_ns) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->l1_to_l2_cs_ns = l1_to_l2_cs; + __entry->l2_to_l1_cs_ns = l2_to_l1_cs; + __entry->l2_runtime_ns = l2_runtime; + ), + + TP_printk("VCPU %d: l1_to_l2_cs_time=%llu-ns l2_to_l1_cs_time=%llu-ns l2_runtime=%llu-ns", + __entry->vcpu_id, __entry->l1_to_l2_cs_ns, + __entry->l2_to_l1_cs_ns, __entry->l2_runtime_ns) +); + TRACE_EVENT(kvmppc_run_vcpu_exit, TP_PROTO(struct kvm_vcpu *vcpu), -- 2.43.2
WARNING: multiple messages have this Message-ID (diff)
From: Gautam Menghani <gautam@linux.ibm.com> To: mpe@ellerman.id.au, npiggin@gmail.com, christophe.leroy@csgroup.eu, aneesh.kumar@kernel.org, naveen.n.rao@linux.ibm.com Cc: Vaibhav Jain <vaibhav@linux.ibm.com>, Gautam Menghani <gautam@linux.ibm.com>, linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org Subject: [PATCH v5] arch/powerpc/kvm: Add support for reading VPA counters for pseries guests Date: Mon, 1 Apr 2024 16:55:42 +0530 [thread overview] Message-ID: <20240401112544.51764-1-gautam@linux.ibm.com> (raw) PAPR hypervisor has introduced three new counters in the VPA area of LPAR CPUs for KVM L2 guest (see [1] for terminology) observability - 2 for context switches from host to guest and vice versa, and 1 counter for getting the total time spent inside the KVM guest. Add a tracepoint that enables reading the counters for use by ftrace/perf. Note that this tracepoint is only available for nestedv2 API (i.e, KVM on PowerVM). Also maintain an aggregation of the context switch times in vcpu->arch. This will be useful in getting the aggregate times with a pmu driver which will be upstreamed in the near future. [1] Terminology: a. L1 refers to the VM (LPAR) booted on top of PAPR hypervisor b. L2 refers to the KVM guest booted on top of L1. Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com> Signed-off-by: Gautam Menghani <gautam@linux.ibm.com> --- arch/powerpc/include/asm/kvm_host.h | 5 ++++ arch/powerpc/include/asm/lppaca.h | 11 +++++--- arch/powerpc/kvm/book3s_hv.c | 40 +++++++++++++++++++++++++++++ arch/powerpc/kvm/trace_hv.h | 25 ++++++++++++++++++ 4 files changed, 78 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 8abac532146e..d953b32dd68a 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -847,6 +847,11 @@ struct kvm_vcpu_arch { gpa_t nested_io_gpr; /* For nested APIv2 guests*/ struct kvmhv_nestedv2_io nestedv2_io; + + /* Aggregate context switch and guest run time info (in ns) */ + u64 l1_to_l2_cs_agg; + u64 l2_to_l1_cs_agg; + u64 l2_runtime_agg; #endif #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h index 61ec2447dabf..bda6b86b9f13 100644 --- a/arch/powerpc/include/asm/lppaca.h +++ b/arch/powerpc/include/asm/lppaca.h @@ -62,7 +62,8 @@ struct lppaca { u8 donate_dedicated_cpu; /* Donate dedicated CPU cycles */ u8 fpregs_in_use; u8 pmcregs_in_use; - u8 reserved8[28]; + u8 l2_accumul_cntrs_enable; /* Enable usage of counters for KVM guest */ + u8 reserved8[27]; __be64 wait_state_cycles; /* Wait cycles for this proc */ u8 reserved9[28]; __be16 slb_count; /* # of SLBs to maintain */ @@ -92,9 +93,13 @@ struct lppaca { /* cacheline 4-5 */ __be32 page_ins; /* CMO Hint - # page ins by OS */ - u8 reserved12[148]; + u8 reserved12[28]; + volatile __be64 l1_to_l2_cs_tb; + volatile __be64 l2_to_l1_cs_tb; + volatile __be64 l2_runtime_tb; + u8 reserved13[96]; volatile __be64 dtl_idx; /* Dispatch Trace Log head index */ - u8 reserved13[96]; + u8 reserved14[96]; } ____cacheline_aligned; #define lppaca_of(cpu) (*paca_ptrs[cpu]->lppaca_ptr) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 8e86eb577eb8..fea1c1429975 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4108,6 +4108,37 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu) } } +static inline int kvmhv_get_l2_accumul(void) +{ + return get_lppaca()->l2_accumul_cntrs_enable; +} + +static inline void kvmhv_set_l2_accumul(int val) +{ + get_lppaca()->l2_accumul_cntrs_enable = val; +} + +static void do_trace_nested_cs_time(struct kvm_vcpu *vcpu) +{ + struct lppaca *lp = get_lppaca(); + u64 l1_to_l2_ns, l2_to_l1_ns, l2_runtime_ns; + + l1_to_l2_ns = tb_to_ns(be64_to_cpu(lp->l1_to_l2_cs_tb)); + l2_to_l1_ns = tb_to_ns(be64_to_cpu(lp->l2_to_l1_cs_tb)); + l2_runtime_ns = tb_to_ns(be64_to_cpu(lp->l2_runtime_tb)); + trace_kvmppc_vcpu_exit_cs_time(vcpu, l1_to_l2_ns, l2_to_l1_ns, + l2_runtime_ns); + lp->l1_to_l2_cs_tb = 0; + lp->l2_to_l1_cs_tb = 0; + lp->l2_runtime_tb = 0; + kvmhv_set_l2_accumul(0); + + // Maintain an aggregate of context switch times + vcpu->arch.l1_to_l2_cs_agg += l1_to_l2_ns; + vcpu->arch.l2_to_l1_cs_agg += l2_to_l1_ns; + vcpu->arch.l2_runtime_agg += l2_runtime_ns; +} + static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpcr, u64 *tb) { @@ -4130,6 +4161,11 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_gse_put_u64(io->vcpu_run_input, KVMPPC_GSID_LPCR, lpcr); accumulate_time(vcpu, &vcpu->arch.in_guest); + + /* Enable the guest host context switch time tracking */ + if (unlikely(trace_kvmppc_vcpu_exit_cs_time_enabled())) + kvmhv_set_l2_accumul(1); + rc = plpar_guest_run_vcpu(0, vcpu->kvm->arch.lpid, vcpu->vcpu_id, &trap, &i); @@ -4156,6 +4192,10 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit, timer_rearm_host_dec(*tb); + /* Record context switch and guest_run_time data */ + if (kvmhv_get_l2_accumul()) + do_trace_nested_cs_time(vcpu); + return trap; } diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index 8d57c8428531..ab19977c91b4 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -491,6 +491,31 @@ TRACE_EVENT(kvmppc_run_vcpu_enter, TP_printk("VCPU %d: tgid=%d", __entry->vcpu_id, __entry->tgid) ); +TRACE_EVENT(kvmppc_vcpu_exit_cs_time, + TP_PROTO(struct kvm_vcpu *vcpu, u64 l1_to_l2_cs, u64 l2_to_l1_cs, + u64 l2_runtime), + + TP_ARGS(vcpu, l1_to_l2_cs, l2_to_l1_cs, l2_runtime), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(__u64, l1_to_l2_cs_ns) + __field(__u64, l2_to_l1_cs_ns) + __field(__u64, l2_runtime_ns) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu->vcpu_id; + __entry->l1_to_l2_cs_ns = l1_to_l2_cs; + __entry->l2_to_l1_cs_ns = l2_to_l1_cs; + __entry->l2_runtime_ns = l2_runtime; + ), + + TP_printk("VCPU %d: l1_to_l2_cs_time=%llu-ns l2_to_l1_cs_time=%llu-ns l2_runtime=%llu-ns", + __entry->vcpu_id, __entry->l1_to_l2_cs_ns, + __entry->l2_to_l1_cs_ns, __entry->l2_runtime_ns) +); + TRACE_EVENT(kvmppc_run_vcpu_exit, TP_PROTO(struct kvm_vcpu *vcpu), -- 2.43.2
next reply other threads:[~2024-04-01 11:26 UTC|newest] Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top 2024-04-01 11:25 Gautam Menghani [this message] 2024-04-01 11:25 ` [PATCH v5] arch/powerpc/kvm: Add support for reading VPA counters for pseries guests Gautam Menghani
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20240401112544.51764-1-gautam@linux.ibm.com \ --to=gautam@linux.ibm.com \ --cc=aneesh.kumar@kernel.org \ --cc=christophe.leroy@csgroup.eu \ --cc=kvm@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linuxppc-dev@lists.ozlabs.org \ --cc=mpe@ellerman.id.au \ --cc=naveen.n.rao@linux.ibm.com \ --cc=npiggin@gmail.com \ --cc=vaibhav@linux.ibm.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.