@@ -827,11 +827,13 @@ struct kvm_vcpu_arch {
struct kvmhv_tb_accumulator *cur_activity; /* What we're timing */
u64 cur_tb_start; /* when it started */
#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING
- struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */
- struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */
- struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */
- struct kvmhv_tb_accumulator guest_time; /* guest execution */
- struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */
+ struct kvmhv_tb_accumulator vcpu_entry;
+ struct kvmhv_tb_accumulator vcpu_exit;
+ struct kvmhv_tb_accumulator in_guest;
+ struct kvmhv_tb_accumulator hcall;
+ struct kvmhv_tb_accumulator pg_fault;
+ struct kvmhv_tb_accumulator guest_entry;
+ struct kvmhv_tb_accumulator guest_exit;
#else
struct kvmhv_tb_accumulator rm_entry; /* real-mode entry code */
struct kvmhv_tb_accumulator rm_intr; /* real-mode intr handling */
@@ -135,10 +135,11 @@ config KVM_BOOK3S_HV_P9_TIMING
select KVM_BOOK3S_HV_EXIT_TIMING
depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
help
- Calculate time taken for each vcpu in various parts of the
- code. The total, minimum and maximum times in nanoseconds
- together with the number of executions are reported in debugfs in
- kvm/vm#/vcpu#/timings.
+ Calculate time taken for each vcpu during vcpu entry and
+ exit, time spent inside the guest and time spent handling
+ hypercalls and page faults. The total, minimum and maximum
+ times in nanoseconds together with the number of executions
+ are reported in debugfs in kvm/vm#/vcpu#/timings.
If unsure, say N.
@@ -2654,11 +2654,13 @@ static struct debugfs_timings_element {
size_t offset;
} timings[] = {
#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING
- {"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
- {"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
- {"rm_exit", offsetof(struct kvm_vcpu, arch.rm_exit)},
- {"guest", offsetof(struct kvm_vcpu, arch.guest_time)},
- {"cede", offsetof(struct kvm_vcpu, arch.cede_time)},
+ {"vcpu_entry", offsetof(struct kvm_vcpu, arch.vcpu_entry)},
+ {"guest_entry", offsetof(struct kvm_vcpu, arch.guest_entry)},
+ {"in_guest", offsetof(struct kvm_vcpu, arch.in_guest)},
+ {"guest_exit", offsetof(struct kvm_vcpu, arch.guest_exit)},
+ {"vcpu_exit", offsetof(struct kvm_vcpu, arch.vcpu_exit)},
+ {"hypercall", offsetof(struct kvm_vcpu, arch.hcall)},
+ {"page_fault", offsetof(struct kvm_vcpu, arch.pg_fault)},
#else
{"rm_entry", offsetof(struct kvm_vcpu, arch.rm_entry)},
{"rm_intr", offsetof(struct kvm_vcpu, arch.rm_intr)},
@@ -4006,8 +4008,10 @@ static int kvmhv_vcpu_entry_p9_nested(struct kvm_vcpu *vcpu, u64 time_limit, uns
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
switch_pmu_to_guest(vcpu, &host_os_sprs);
+ accumulate_time(vcpu, &vcpu->arch.in_guest);
trap = plpar_hcall_norets(H_ENTER_NESTED, __pa(&hvregs),
__pa(&vcpu->arch.regs));
+ accumulate_time(vcpu, &vcpu->arch.guest_exit);
kvmhv_restore_hv_return_state(vcpu, &hvregs);
switch_pmu_to_host(vcpu, &host_os_sprs);
vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
@@ -4661,6 +4665,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
struct kvm *kvm;
unsigned long msr;
+ start_timing(vcpu, &vcpu->arch.vcpu_entry);
+
if (!vcpu->arch.sane) {
run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
return -EINVAL;
@@ -4726,6 +4732,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
do {
+ accumulate_time(vcpu, &vcpu->arch.guest_entry);
if (cpu_has_feature(CPU_FTR_ARCH_300))
r = kvmhv_run_single_vcpu(vcpu, ~(u64)0,
vcpu->arch.vcore->lpcr);
@@ -4733,6 +4740,8 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
r = kvmppc_run_vcpu(vcpu);
if (run->exit_reason == KVM_EXIT_PAPR_HCALL) {
+ accumulate_time(vcpu, &vcpu->arch.hcall);
+
if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_PR)) {
/*
* These should have been caught reflected
@@ -4748,6 +4757,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
trace_kvm_hcall_exit(vcpu, r);
kvmppc_core_prepare_to_enter(vcpu);
} else if (r == RESUME_PAGE_FAULT) {
+ accumulate_time(vcpu, &vcpu->arch.pg_fault);
srcu_idx = srcu_read_lock(&kvm->srcu);
r = kvmppc_book3s_hv_page_fault(vcpu,
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
@@ -4759,12 +4769,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_vcpu *vcpu)
r = kvmppc_xics_rm_complete(vcpu, 0);
}
} while (is_kvmppc_resume_guest(r));
+ accumulate_time(vcpu, &vcpu->arch.vcpu_exit);
vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
atomic_dec(&kvm->arch.vcpus_running);
srr_regs_clobbered();
+ end_timing(vcpu);
+
return r;
}
@@ -772,8 +772,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_HV);
WARN_ON_ONCE(!(vcpu->arch.shregs.msr & MSR_ME));
- start_timing(vcpu, &vcpu->arch.rm_entry);
-
vcpu->arch.ceded = 0;
/* Save MSR for restore, with EE clear. */
@@ -934,13 +932,13 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
mtspr(SPRN_SRR1, vcpu->arch.shregs.srr1);
- accumulate_time(vcpu, &vcpu->arch.guest_time);
-
switch_pmu_to_guest(vcpu, &host_os_sprs);
+ accumulate_time(vcpu, &vcpu->arch.in_guest);
+
kvmppc_p9_enter_guest(vcpu);
- switch_pmu_to_host(vcpu, &host_os_sprs);
- accumulate_time(vcpu, &vcpu->arch.rm_intr);
+ accumulate_time(vcpu, &vcpu->arch.guest_exit);
+ switch_pmu_to_host(vcpu, &host_os_sprs);
/* XXX: Could get these from r11/12 and paca exsave instead */
vcpu->arch.shregs.srr0 = mfspr(SPRN_SRR0);
@@ -1035,8 +1033,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
#endif
}
- accumulate_time(vcpu, &vcpu->arch.rm_exit);
-
/* Advance host PURR/SPURR by the amount used by guest */
purr = mfspr(SPRN_PURR);
spurr = mfspr(SPRN_SPURR);
@@ -1143,8 +1139,6 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
asm volatile(PPC_CP_ABORT);
out:
- end_timing(vcpu);
-
return trap;
}
EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9);
Alter the data collection points for the debug timing code in the P9 path to be more in line with what the code does. The points where we accumulate time are now the following: vcpu_entry: From vcpu_run_hv entry until the start of the inner loop; guest_entry: From the start of the inner loop until the guest entry in asm; in_guest: From the guest entry in asm until the return to KVM C code; guest_exit: From the return into KVM C code until the corresponding hypercall/page fault handling or re-entry into the guest; hypercall: Time spent handling hcalls in the kernel (hcalls can go to QEMU, not accounted here); page_fault: Time spent handling page faults; vcpu_exit: vcpu_run_hv exit (almost no code here currently). Like before, these are exposed in debugfs in a file called "timings". There are four values: - number of occurrences of the accumulation point; - total time the vcpu spent in the phase in ns; - shortest time the vcpu spent in the phase in ns; - longest time the vcpu spent in the phase in ns; === Before: rm_entry: 53132 16793518 256 4060 rm_intr: 53132 2125914 22 340 rm_exit: 53132 24108344 374 2180 guest: 53132 40980507996 404 9997650 cede: 0 0 0 0 After: vcpu_entry: 34637 7716108 178 4416 guest_entry: 52414 49365608 324 747542 in_guest: 52411 40828715840 258 9997480 guest_exit: 52410 19681717182 826 102496674 vcpu_exit: 34636 1744462 38 182 hypercall: 45712 22878288 38 1307962 page_fault: 992 111104034 568 168688 With just one instruction (hcall): vcpu_entry: 1 942 942 942 guest_entry: 1 4044 4044 4044 in_guest: 1 1540 1540 1540 guest_exit: 1 3542 3542 3542 vcpu_exit: 1 80 80 80 hypercall: 0 0 0 0 page_fault: 0 0 0 0 === Signed-off-by: Fabiano Rosas <farosas@linux.ibm.com> --- arch/powerpc/include/asm/kvm_host.h | 12 +++++++----- arch/powerpc/kvm/Kconfig | 9 +++++---- arch/powerpc/kvm/book3s_hv.c | 23 ++++++++++++++++++----- arch/powerpc/kvm/book3s_hv_p9_entry.c | 14 ++++---------- 4 files changed, 34 insertions(+), 24 deletions(-)