UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'topic/ppc-kvm' into next 

Merge KVM related commits we are keeping in a topic branch in case of
any conflicts with generic KVM changes.
This commit is contained in:
Michael Ellerman 2022-07-09 19:32:20 +10:00
parent 7e74dabc3d 81e9685dd4
commit ac2a230301
11 changed files with 119 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
arch/powerpc/include/asm/hvcall.h
View File

@ -350,6 +350,14 @@
/* Platform specific hcalls, used by KVM */
#define H_RTAS 0xf000
/*
* Platform specific hcalls, used by QEMU/SLOF. These are ignored by
* KVM and only kept here so we can identify them during tracing.
*/
#define H_LOGICAL_MEMOP 0xF001
#define H_CAS 0XF002
#define H_UPDATE_DT 0XF003
/* "Platform specific hcalls", provided by PHYP */
#define H_GET_24X7_CATALOG_PAGE 0xF078
#define H_GET_24X7_DATA 0xF07C

16
arch/powerpc/include/asm/kvm_host.h
View File

@ -523,7 +523,11 @@ struct kvm_vcpu_arch {
struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
#endif
struct pt_regs regs;
/*
* This is passed along to the HV via H_ENTER_NESTED. Align to
* prevent it crossing a real 4K page.
*/
struct pt_regs regs __aligned(512);
struct thread_fp_state fp;
@ -830,11 +834,21 @@ struct kvm_vcpu_arch {
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
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 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 */
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 */
#endif
#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
};

2
arch/powerpc/kernel/asm-offsets.c
View File

@ -379,7 +379,7 @@ int main(void)
OFFSET(VCPU_SPRG2, kvm_vcpu, arch.shregs.sprg2);
OFFSET(VCPU_SPRG3, kvm_vcpu, arch.shregs.sprg3);
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
OFFSET(VCPU_TB_RMENTRY, kvm_vcpu, arch.rm_entry);
OFFSET(VCPU_TB_RMINTR, kvm_vcpu, arch.rm_intr);
OFFSET(VCPU_TB_RMEXIT, kvm_vcpu, arch.rm_exit);

21
arch/powerpc/kvm/Kconfig
View File

@ -128,8 +128,25 @@ config KVM_BOOK3S_64_PR
and system calls on the host.
config KVM_BOOK3S_HV_EXIT_TIMING
bool "Detailed timing for hypervisor real-mode code"
bool
config KVM_BOOK3S_HV_P9_TIMING
bool "Detailed timing for the P9 entry point"
select KVM_BOOK3S_HV_EXIT_TIMING
depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
help
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.
config KVM_BOOK3S_HV_P8_TIMING
bool "Detailed timing for hypervisor real-mode code (for POWER8)"
select KVM_BOOK3S_HV_EXIT_TIMING
depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS && !KVM_BOOK3S_HV_P9_TIMING
help
Calculate time taken for each vcpu in the real-mode guest entry,
exit, and interrupt handling code, plus time spent in the guest
@ -149,7 +166,7 @@ config KVM_BOOK3S_HV_NESTED_PMU_WORKAROUND
Old nested HV capable Linux guests have a bug where they don't
reflect the PMU in-use status of their L2 guest to the L0 host
while the L2 PMU registers are live. This can result in loss
of L2 PMU register state, causing perf to not work correctly in
of L2 PMU register state, causing perf to not work correctly in
L2 guests.
Selecting this option for the L0 host implements a workaround for

2
arch/powerpc/kvm/book3s_64_vio.c
View File

@ -307,7 +307,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
return ret;
ret = -ENOMEM;
stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL);
stt = kzalloc(struct_size(stt, pages, npages), GFP_KERNEL | __GFP_NOWARN);
if (!stt)
goto fail_acct;

26
arch/powerpc/kvm/book3s_hv.c
View File

@ -2660,11 +2660,21 @@ static struct debugfs_timings_element {
const char *name;
size_t offset;
} timings[] = {
#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING
{"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)},
{"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)},
#endif
};
#define N_TIMINGS (ARRAY_SIZE(timings))
@ -2783,8 +2793,9 @@ static const struct file_operations debugfs_timings_ops = {
/* Create a debugfs directory for the vcpu */
static int kvmppc_arch_create_vcpu_debugfs_hv(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry)
{
debugfs_create_file("timings", 0444, debugfs_dentry, vcpu,
&debugfs_timings_ops);
if (cpu_has_feature(CPU_FTR_ARCH_300) == IS_ENABLED(CONFIG_KVM_BOOK3S_HV_P9_TIMING))
debugfs_create_file("timings", 0444, debugfs_dentry, vcpu,
&debugfs_timings_ops);
return 0;
}
@ -4005,8 +4016,10 @@ 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;
@ -4694,6 +4707,8 @@ 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;
@ -4759,6 +4774,7 @@ 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);
@ -4766,6 +4782,8 @@ 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
@ -4781,6 +4799,7 @@ 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);
@ -4792,12 +4811,15 @@ 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;
}

10
arch/powerpc/kvm/book3s_hv.h
View File

@ -40,3 +40,13 @@ void switch_pmu_to_guest(struct kvm_vcpu *vcpu,
struct p9_host_os_sprs *host_os_sprs);
void switch_pmu_to_host(struct kvm_vcpu *vcpu,
struct p9_host_os_sprs *host_os_sprs);
#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING
void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next);
#define start_timing(vcpu, next) accumulate_time(vcpu, next)
#define end_timing(vcpu) accumulate_time(vcpu, NULL)
#else
#define accumulate_time(vcpu, next) do {} while (0)
#define start_timing(vcpu, next) do {} while (0)
#define end_timing(vcpu) do {} while (0)
#endif

38
arch/powerpc/kvm/book3s_hv_p9_entry.c
View File

@ -437,17 +437,8 @@ void restore_p9_host_os_sprs(struct kvm_vcpu *vcpu,
}
EXPORT_SYMBOL_GPL(restore_p9_host_os_sprs);
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
static void __start_timing(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
u64 tb = mftb() - vc->tb_offset_applied;
vcpu->arch.cur_activity = next;
vcpu->arch.cur_tb_start = tb;
}
static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
#ifdef CONFIG_KVM_BOOK3S_HV_P9_TIMING
void accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator *next)
{
struct kvmppc_vcore *vc = vcpu->arch.vcore;
struct kvmhv_tb_accumulator *curr;
@ -477,14 +468,7 @@ static void __accumulate_time(struct kvm_vcpu *vcpu, struct kvmhv_tb_accumulator
smp_wmb();
curr->seqcount = seq + 2;
}
#define start_timing(vcpu, next) __start_timing(vcpu, next)
#define end_timing(vcpu) __start_timing(vcpu, NULL)
#define accumulate_time(vcpu, next) __accumulate_time(vcpu, next)
#else
#define start_timing(vcpu, next) do {} while (0)
#define end_timing(vcpu) do {} while (0)
#define accumulate_time(vcpu, next) do {} while (0)
EXPORT_SYMBOL_GPL(accumulate_time);
#endif
static inline u64 mfslbv(unsigned int idx)
@ -795,8 +779,6 @@ 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. */
@ -957,13 +939,13 @@ tm_return_to_guest:
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);
kvmppc_p9_enter_guest(vcpu);
switch_pmu_to_host(vcpu, &host_os_sprs);
accumulate_time(vcpu, &vcpu->arch.in_guest);
accumulate_time(vcpu, &vcpu->arch.rm_intr);
kvmppc_p9_enter_guest(vcpu);
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);
@ -1058,8 +1040,6 @@ tm_return_to_guest:
#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);
@ -1166,8 +1146,6 @@ tm_return_to_guest:
asm volatile(PPC_CP_ABORT);
out:
end_timing(vcpu);
return trap;
}
EXPORT_SYMBOL_GPL(kvmhv_vcpu_entry_p9);

24
arch/powerpc/kvm/book3s_hv_rmhandlers.S
View File

@ -237,14 +237,14 @@ kvm_novcpu_wakeup:
cmpdi r4, 0
beq kvmppc_primary_no_guest
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
addi r3, r4, VCPU_TB_RMENTRY
bl kvmhv_start_timing
#endif
b kvmppc_got_guest
kvm_novcpu_exit:
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
beq 13f
@ -523,7 +523,7 @@ kvmppc_hv_entry:
li r6, KVM_GUEST_MODE_HOST_HV
stb r6, HSTATE_IN_GUEST(r13)
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
/* Store initial timestamp */
cmpdi r4, 0
beq 1f
@ -894,7 +894,7 @@ fast_guest_return:
li r9, KVM_GUEST_MODE_GUEST_HV
stb r9, HSTATE_IN_GUEST(r13)
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
/* Accumulate timing */
addi r3, r4, VCPU_TB_GUEST
bl kvmhv_accumulate_time
@ -945,7 +945,7 @@ secondary_too_late:
cmpdi r4, 0
beq 11f
stw r12, VCPU_TRAP(r4)
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
#endif
@ -959,7 +959,7 @@ hdec_soon:
li r12, BOOK3S_INTERRUPT_HV_DECREMENTER
12: stw r12, VCPU_TRAP(r4)
mr r9, r4
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
addi r3, r4, VCPU_TB_RMEXIT
bl kvmhv_accumulate_time
#endif
@ -1056,7 +1056,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
li r0, MSR_RI
mtmsrd r0, 1
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
addi r3, r9, VCPU_TB_RMINTR
mr r4, r9
bl kvmhv_accumulate_time
@ -1135,7 +1135,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
addi r3, r9, VCPU_TB_RMEXIT
mr r4, r9
bl kvmhv_accumulate_time
@ -1495,7 +1495,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mtspr SPRN_LPCR,r8
isync
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
/* Finish timing, if we have a vcpu */
ld r4, HSTATE_KVM_VCPU(r13)
cmpdi r4, 0
@ -2153,7 +2153,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_TM)
ld r4, HSTATE_KVM_VCPU(r13)
std r3, VCPU_DEC_EXPIRES(r4)
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
ld r4, HSTATE_KVM_VCPU(r13)
addi r3, r4, VCPU_TB_CEDE
bl kvmhv_accumulate_time
@ -2221,7 +2221,7 @@ kvm_end_cede:
/* get vcpu pointer */
ld r4, HSTATE_KVM_VCPU(r13)
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
addi r3, r4, VCPU_TB_RMINTR
bl kvmhv_accumulate_time
#endif
@ -2961,7 +2961,7 @@ kvmppc_fix_pmao:
isync
blr
#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
#ifdef CONFIG_KVM_BOOK3S_HV_P8_TIMING
/*
* Start timing an activity
* r3 = pointer to time accumulation struct, r4 = vcpu

1
arch/powerpc/kvm/book3s_xics.h
View File

@ -143,6 +143,7 @@ static inline struct kvmppc_ics *kvmppc_xics_find_ics(struct kvmppc_xics *xics,
}
extern unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu);
extern unsigned long xics_rm_h_xirr_x(struct kvm_vcpu *vcpu);
extern int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
unsigned long mfrr);
extern int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);

21
arch/powerpc/kvm/trace_hv.h
View File

@ -94,6 +94,7 @@
{H_GET_HCA_INFO, "H_GET_HCA_INFO"}, \
{H_GET_PERF_COUNT, "H_GET_PERF_COUNT"}, \
{H_MANAGE_TRACE, "H_MANAGE_TRACE"}, \
{H_GET_CPU_CHARACTERISTICS, "H_GET_CPU_CHARACTERISTICS"}, \
{H_FREE_LOGICAL_LAN_BUFFER, "H_FREE_LOGICAL_LAN_BUFFER"}, \
{H_QUERY_INT_STATE, "H_QUERY_INT_STATE"}, \
{H_POLL_PENDING, "H_POLL_PENDING"}, \
@ -125,7 +126,25 @@
{H_COP, "H_COP"}, \
{H_GET_MPP_X, "H_GET_MPP_X"}, \
{H_SET_MODE, "H_SET_MODE"}, \
{H_RTAS, "H_RTAS"}
{H_REGISTER_PROC_TBL, "H_REGISTER_PROC_TBL"}, \
{H_QUERY_VAS_CAPABILITIES, "H_QUERY_VAS_CAPABILITIES"}, \
{H_INT_GET_SOURCE_INFO, "H_INT_GET_SOURCE_INFO"}, \
{H_INT_SET_SOURCE_CONFIG, "H_INT_SET_SOURCE_CONFIG"}, \
{H_INT_GET_QUEUE_INFO, "H_INT_GET_QUEUE_INFO"}, \
{H_INT_SET_QUEUE_CONFIG, "H_INT_SET_QUEUE_CONFIG"}, \
{H_INT_ESB, "H_INT_ESB"}, \
{H_INT_RESET, "H_INT_RESET"}, \
{H_RPT_INVALIDATE, "H_RPT_INVALIDATE"}, \
{H_RTAS, "H_RTAS"}, \
{H_LOGICAL_MEMOP, "H_LOGICAL_MEMOP"}, \
{H_CAS, "H_CAS"}, \
{H_UPDATE_DT, "H_UPDATE_DT"}, \
{H_GET_PERF_COUNTER_INFO, "H_GET_PERF_COUNTER_INFO"}, \
{H_SET_PARTITION_TABLE, "H_SET_PARTITION_TABLE"}, \
{H_ENTER_NESTED, "H_ENTER_NESTED"}, \
{H_TLB_INVALIDATE, "H_TLB_INVALIDATE"}, \
{H_COPY_TOFROM_GUEST, "H_COPY_TOFROM_GUEST"}
#define kvm_trace_symbol_kvmret \
{RESUME_GUEST, "RESUME_GUEST"}, \