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 v7] arch/powerpc/kvm: Add support for reading VPA counters for pseries guests
Date: Tue, 7 May 2024 17:13:48 +0530 [thread overview]
Message-ID: <20240507114352.51819-1-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).
[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.
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>
---
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/lppaca.h | 11 +++++--
arch/powerpc/include/asm/paca.h | 5 +++
arch/powerpc/kvm/book3s_hv.c | 52 +++++++++++++++++++++++++++++++
arch/powerpc/kvm/trace_hv.h | 29 +++++++++++++++++
4 files changed, 94 insertions(+), 3 deletions(-)
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/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 1d58da946739..f20ac7a6efa4 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -278,6 +278,11 @@ struct paca_struct {
struct mce_info *mce_info;
u8 mce_pending_irq_work;
#endif /* CONFIG_PPC_BOOK3S_64 */
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ u64 l1_to_l2_cs;
+ u64 l2_to_l1_cs;
+ u64 l2_runtime_agg;
+#endif
} ____cacheline_aligned;
extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8e86eb577eb8..6acfe59c9b4f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -4108,6 +4108,54 @@ static void vcpu_vpa_increment_dispatch(struct kvm_vcpu *vcpu)
}
}
+static inline int kvmhv_get_l2_counters_status(void)
+{
+ return get_lppaca()->l2_counters_enable;
+}
+
+static inline void kvmhv_set_l2_counters_status(int cpu, bool status)
+{
+ if (status)
+ lppaca_of(cpu).l2_counters_enable = 1;
+ else
+ lppaca_of(cpu).l2_counters_enable = 0;
+}
+
+int kmvhv_counters_tracepoint_regfunc(void)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ kvmhv_set_l2_counters_status(cpu, true);
+ }
+ return 0;
+}
+
+void kmvhv_counters_tracepoint_unregfunc(void)
+{
+ int cpu;
+
+ for_each_present_cpu(cpu) {
+ kvmhv_set_l2_counters_status(cpu, false);
+ }
+}
+
+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_stats(vcpu, l1_to_l2_ns - local_paca->l1_to_l2_cs,
+ l2_to_l1_ns - local_paca->l2_to_l1_cs,
+ l2_runtime_ns - local_paca->l2_runtime_agg);
+ local_paca->l1_to_l2_cs = l1_to_l2_ns;
+ local_paca->l2_to_l1_cs = l2_to_l1_ns;
+ local_paca->l2_runtime_agg = l2_runtime_ns;
+}
+
static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
unsigned long lpcr, u64 *tb)
{
@@ -4156,6 +4204,10 @@ 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/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index 8d57c8428531..8c563e9438db 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -238,6 +238,9 @@
{H_MULTI_THREADS_ACTIVE, "H_MULTI_THREADS_ACTIVE"}, \
{H_OUTSTANDING_COP_OPS, "H_OUTSTANDING_COP_OPS"}
+int kmvhv_counters_tracepoint_regfunc(void);
+void kmvhv_counters_tracepoint_unregfunc(void);
+
TRACE_EVENT(kvm_guest_enter,
TP_PROTO(struct kvm_vcpu *vcpu),
TP_ARGS(vcpu),
@@ -512,6 +515,32 @@ TRACE_EVENT(kvmppc_run_vcpu_exit,
__entry->vcpu_id, __entry->exit, __entry->ret)
);
+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 /* _TRACE_KVM_HV_H */
/* This part must be outside protection */
--
2.44.0
reply other threads:[~2024-05-07 11:44 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20240507114352.51819-1-gautam@linux.ibm.com \
--to=gautam@linux.ibm.com \
--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=naveen@kernel.org \
--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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).