Received-SPF: pass (google.com: domain of linux-kernel+bounces-175605-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Gautam Menghani <gautam@linux.ibm.com>
To: mpe@ellerman.id.au, npiggin@gmail.com, christophe.leroy@csgroup.eu,
        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,
        Naveen N Rao <naveen@kernel.org>, Vaibhav Jain <vaibhav@linux.ibm.com>
Subject: [PATCH v8] arch/powerpc/kvm: Add support for reading VPA counters for pseries guests
Date: Fri, 10 May 2024 16:19:38 +0530
Message-ID: <20240510104941.78410-1-gautam@linux.ibm.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

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).

[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.

Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Naveen N Rao <naveen@kernel.org>
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Gautam Menghani <gautam@linux.ibm.com>
---
v7 -> v8:
1. Use per_cpu vars instead of paca members.
2. Fix build error for powernv config.

v6 -> v7:
1. Use TRACE_EVENT_FN_COND to handle zero counters case.
2. Use for_each_present_cpu() to handle hotplugs.

v5 -> v6:
1. Use TRACE_EVENT_FN to enable/disable counters only once.
2. Remove the agg. counters from vcpu->arch.
3. Use PACA to maintain old counter values instead of zeroing on every
entry.
4. Simplify variable names

v4 -> v5:
1. Define helper functions for getting/setting the accumulation counter
in L2's VPA

v3 -> v4:
1. After vcpu_run, check the VPA flag instead of checking for tracepoint
being enabled for disabling the cs time accumulation.

v2 -> v3:
1. Move the counter disabling and zeroing code to a different function.
2. Move the get_lppaca() inside the tracepoint_enabled() branch.
3. Add the aggregation logic to maintain total context switch time.

v1 -> v2:
1. Fix the build error due to invalid struct member reference.

 arch/powerpc/include/asm/kvm_book3s_64.h |  6 ++
 arch/powerpc/include/asm/lppaca.h        | 11 +++-
 arch/powerpc/kvm/book3s_hv.c             |  4 ++
 arch/powerpc/kvm/book3s_hv_nestedv2.c    | 80 ++++++++++++++++++++++++
 arch/powerpc/kvm/trace_hv.h              | 31 +++++++++
 5 files changed, 129 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index d8729ec81ca0..083f93881cbb 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -684,6 +684,12 @@ int kvmhv_nestedv2_set_ptbl_entry(unsigned long lpid, u64 dw0, u64 dw1);
 int kvmhv_nestedv2_parse_output(struct kvm_vcpu *vcpu);
 int kvmhv_nestedv2_set_vpa(struct kvm_vcpu *vcpu, unsigned long vpa);
 
+int kvmhv_get_l2_counters_status(void);
+void kvmhv_set_l2_counters_status(int cpu, bool status);
+int kmvhv_counters_tracepoint_regfunc(void);
+void kmvhv_counters_tracepoint_unregfunc(void);
+void do_trace_nested_cs_time(struct kvm_vcpu *vcpu);
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 61ec2447dabf..f40a646bee3c 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_counters_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..2f49b3a5a4c0 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4156,6 +4156,10 @@ 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_counters_status())
+		do_trace_nested_cs_time(vcpu);
+
 	return trap;
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index 8e6f5355f08b..0a99ca137f7a 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -1037,3 +1037,83 @@ void kvmhv_nestedv2_vcpu_free(struct kvm_vcpu *vcpu,
 	kvmhv_nestedv2_host_free(vcpu, io);
 }
 EXPORT_SYMBOL_GPL(kvmhv_nestedv2_vcpu_free);
+
+/* Helper functions for reading L2's stats from L1's VPA */
+
+#ifdef CONFIG_PPC_PSERIES
+
+static DEFINE_PER_CPU(u64, l1_to_l2_cs);
+static DEFINE_PER_CPU(u64, l2_to_l1_cs);
+static DEFINE_PER_CPU(u64, l2_runtime_agg);
+
+int kvmhv_get_l2_counters_status(void)
+{
+	return firmware_has_feature(FW_FEATURE_LPAR) &&
+		get_lppaca()->l2_counters_enable;
+}
+EXPORT_SYMBOL_GPL(kvmhv_get_l2_counters_status);
+
+void kvmhv_set_l2_counters_status(int cpu, bool status)
+{
+	if (!firmware_has_feature(FW_FEATURE_LPAR))
+		return;
+	if (status)
+		lppaca_of(cpu).l2_counters_enable = 1;
+	else
+		lppaca_of(cpu).l2_counters_enable = 0;
+}
+EXPORT_SYMBOL_GPL(kvmhv_set_l2_counters_status);
+
+int kmvhv_counters_tracepoint_regfunc(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		kvmhv_set_l2_counters_status(cpu, true);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kmvhv_counters_tracepoint_regfunc);
+
+void kmvhv_counters_tracepoint_unregfunc(void)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		kvmhv_set_l2_counters_status(cpu, false);
+	}
+}
+EXPORT_SYMBOL_GPL(kmvhv_counters_tracepoint_unregfunc);
+
+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;
+	u64 *l1_to_l2_cs_ptr = this_cpu_ptr(&l1_to_l2_cs);
+	u64 *l2_to_l1_cs_ptr = this_cpu_ptr(&l2_to_l1_cs);
+	u64 *l2_runtime_agg_ptr = this_cpu_ptr(&l2_runtime_agg);
+
+	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_stats(vcpu, l1_to_l2_ns - *l1_to_l2_cs_ptr,
+					l2_to_l1_ns - *l2_to_l1_cs_ptr,
+					l2_runtime_ns - *l2_runtime_agg_ptr);
+	*l1_to_l2_cs_ptr = l1_to_l2_ns;
+	*l2_to_l1_cs_ptr = l2_to_l1_ns;
+	*l2_runtime_agg_ptr = l2_runtime_ns;
+}
+EXPORT_SYMBOL_GPL(do_trace_nested_cs_time);
+
+#else
+int kvmhv_get_l2_counters_status(void)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvmhv_get_l2_counters_status);
+
+void do_trace_nested_cs_time(struct kvm_vcpu *vcpu)
+{
+}
+EXPORT_SYMBOL_GPL(do_trace_nested_cs_time);
+#endif
diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index 8d57c8428531..1e3213a66702 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -512,6 +512,37 @@ TRACE_EVENT(kvmppc_run_vcpu_exit,
 			__entry->vcpu_id, __entry->exit, __entry->ret)
 );
 
+#ifdef CONFIG_PPC_PSERIES
+int kmvhv_counters_tracepoint_regfunc(void);
+void kmvhv_counters_tracepoint_unregfunc(void);
+
+TRACE_EVENT_FN_COND(kvmppc_vcpu_stats,
+	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_CONDITION(l1_to_l2_cs || l2_to_l1_cs || l2_runtime),
+
+	TP_STRUCT__entry(
+		__field(int,		vcpu_id)
+		__field(u64,		l1_to_l2_cs)
+		__field(u64,		l2_to_l1_cs)
+		__field(u64,		l2_runtime)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id  = vcpu->vcpu_id;
+		__entry->l1_to_l2_cs = l1_to_l2_cs;
+		__entry->l2_to_l1_cs = l2_to_l1_cs;
+		__entry->l2_runtime = 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,
+		__entry->l2_to_l1_cs, __entry->l2_runtime),
+	kmvhv_counters_tracepoint_regfunc, kmvhv_counters_tracepoint_unregfunc
+);
+#endif
 #endif /* _TRACE_KVM_HV_H */
 
 /* This part must be outside protection */
-- 
2.45.0