Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit b6c295df authored by Paul Mackerras's avatar Paul Mackerras Committed by Alexander Graf
Browse files

KVM: PPC: Book3S HV: Accumulate timing information for real-mode code 



This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code.  Currently these
times are accumulated per vcpu in 5 parts of the code:

* rm_entry - time taken from the start of kvmppc_hv_entry() until
  just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
  guest until we either re-enter the guest or decide to exit to the
  host.  This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
  return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
  while other threads in the same vcore are active.

These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings".  This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.

The overhead of the extra code amounts to about 30ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), which is about 25%.  Since
production environments may not wish to incur this overhead, the new
code is conditional on a new config symbol,
CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.

Signed-off-by: default avatarPaul Mackerras <paulus@samba.org>
Signed-off-by: default avatarAlexander Graf <agraf@suse.de>
parent e23a808b

arch/powerpc/include/asm/kvm_host.h

+21 −0
Original line number Diff line number Diff line
@@ -369,6 +369,14 @@ struct kvmppc_slb { 
	u8 base_page_size;	/* MMU_PAGE_xxx */

};



/* Struct used to accumulate timing information in HV real mode code */

struct kvmhv_tb_accumulator {

	u64	seqcount;	/* used to synchronize access, also count * 2 */

	u64	tb_total;	/* total time in timebase ticks */

	u64	tb_min;		/* min time */

	u64	tb_max;		/* max time */

};



# ifdef CONFIG_PPC_FSL_BOOK3E

#define KVMPPC_BOOKE_IAC_NUM	2

#define KVMPPC_BOOKE_DAC_NUM	2
@@ -657,6 +665,19 @@ struct kvm_vcpu_arch { 


	u32 emul_inst;

#endif



#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING

	struct kvmhv_tb_accumulator *cur_activity;	/* What we're timing */

	u64	cur_tb_start;			/* when it started */

	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 dentry *debugfs_dir;

	struct dentry *debugfs_timings;

#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */

};



#define VCPU_FPR(vcpu, i)	(vcpu)->arch.fp.fpr[i][TS_FPROFFSET]

arch/powerpc/include/asm/time.h

+3 −0
Original line number Diff line number Diff line
@@ -211,5 +211,8 @@ extern void secondary_cpu_time_init(void); 


DECLARE_PER_CPU(u64, decrementers_next_tb);



/* Convert timebase ticks to nanoseconds */

unsigned long long tb_to_ns(unsigned long long tb_ticks);



#endif /* __KERNEL__ */

#endif /* __POWERPC_TIME_H */

arch/powerpc/kernel/asm-offsets.c

+13 −0
Original line number Diff line number Diff line
@@ -458,6 +458,19 @@ int main(void) 
	DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1));

	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));

	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));

#endif

#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING

	DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));

	DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));

	DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));

	DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));

	DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));

	DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));

	DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));

	DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));

	DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));

	DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));

	DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));

#endif

	DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));

	DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));

arch/powerpc/kernel/time.c

+6 −0
Original line number Diff line number Diff line
@@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void) 
}

#endif



unsigned long long tb_to_ns(unsigned long long ticks)

{

	return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;

}

EXPORT_SYMBOL_GPL(tb_to_ns);



/*

 * Scheduler clock - returns current time in nanosec units.

 *

arch/powerpc/kvm/Kconfig

+14 −0
Original line number Diff line number Diff line
@@ -110,6 +110,20 @@ config KVM_BOOK3S_64_PR 
	  processor, including emulating 32-bit processors on a 64-bit

	  host.



config KVM_BOOK3S_HV_EXIT_TIMING

	bool "Detailed timing for hypervisor real-mode code"

	depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS

	---help---

	  Calculate time taken for each vcpu in the real-mode guest entry,

	  exit, and interrupt handling code, plus time spent in the guest

	  and in nap mode due to idle (cede) while other threads are still

	  in the guest.  The total, minimum and maximum times in nanoseconds

	  together with the number of executions are reported in debugfs in

	  kvm/vm#/vcpu#/timings.  The overhead is of the order of 30 - 40

	  ns per exit on POWER8.



	  If unsure, say N.



config KVM_BOOKE_HV

	bool