Commit 2c47e7a7 authored by Colton Lewis's avatar Colton Lewis Committed by Ingo Molnar
Browse files

perf/core: Correct perf sampling with guest VMs 



Previously any PMU overflow interrupt that fired while a VCPU was
loaded was recorded as a guest event whether it truly was or not. This
resulted in nonsense perf recordings that did not honor
perf_event_attr.exclude_guest and recorded guest IPs where it should
have recorded host IPs.

Rework the sampling logic to only record guest samples for events with
exclude_guest = 0. This way any host-only events with exclude_guest
set will never see unexpected guest samples. The behaviour of events
with exclude_guest = 0 is unchanged.

Note that events configured to sample both host and guest may still
misattribute a PMI that arrived in the host as a guest event depending
on KVM arch and vendor behavior.

Signed-off-by: default avatarColton Lewis <coltonlewis@google.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
Reviewed-by: default avatarOliver Upton <oliver.upton@linux.dev>
Acked-by: default avatarMark Rutland <mark.rutland@arm.com>
Acked-by: default avatarKan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241113190156.2145593-6-coltonlewis@google.com
parent baff01f3

arch/arm64/include/asm/perf_event.h

+0 −4
Original line number Diff line number Diff line
@@ -10,10 +10,6 @@ 
#include <asm/ptrace.h>



#ifdef CONFIG_PERF_EVENTS

struct pt_regs;

extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);

extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);

#define perf_arch_misc_flags(regs)	perf_misc_flags(regs)

#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs

#endif

arch/arm64/kernel/perf_callchain.c

+0 −28
Original line number Diff line number Diff line
@@ -38,31 +38,3 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, 


	arch_stack_walk(callchain_trace, entry, current, regs);

}
 


unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)

{

	if (perf_guest_state())

		return perf_guest_get_ip();



	return instruction_pointer(regs);

}



unsigned long perf_arch_misc_flags(struct pt_regs *regs)

{

	unsigned int guest_state = perf_guest_state();

	int misc = 0;



	if (guest_state) {

		if (guest_state & PERF_GUEST_USER)

			misc |= PERF_RECORD_MISC_GUEST_USER;

		else

			misc |= PERF_RECORD_MISC_GUEST_KERNEL;

	} else {

		if (user_mode(regs))

			misc |= PERF_RECORD_MISC_USER;

		else

			misc |= PERF_RECORD_MISC_KERNEL;

	}



	return misc;

}

arch/x86/events/core.c

+0 −3
Original line number Diff line number Diff line
@@ -3005,9 +3005,6 @@ static unsigned long code_segment_base(struct pt_regs *regs) 


unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)

{

	if (perf_guest_state())

		return perf_guest_get_ip();



	return regs->ip + code_segment_base(regs);

}

include/linux/perf_event.h

+19 −2
Original line number Diff line number Diff line
@@ -1676,8 +1676,9 @@ extern void perf_tp_event(u16 event_type, u64 count, void *record, 
			  struct task_struct *task);

extern void perf_bp_event(struct perf_event *event, void *data);



extern unsigned long perf_misc_flags(struct pt_regs *regs);

extern unsigned long perf_instruction_pointer(struct pt_regs *regs);

extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs);

extern unsigned long perf_instruction_pointer(struct perf_event *event,

					      struct pt_regs *regs);



#ifndef perf_arch_misc_flags

# define perf_arch_misc_flags(regs) \
@@ -1688,6 +1689,22 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs); 
# define perf_arch_bpf_user_pt_regs(regs) regs

#endif



#ifndef perf_arch_guest_misc_flags

static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)

{

	unsigned long guest_state = perf_guest_state();



	if (!(guest_state & PERF_GUEST_ACTIVE))

		return 0;



	if (guest_state & PERF_GUEST_USER)

		return PERF_RECORD_MISC_GUEST_USER;

	else

		return PERF_RECORD_MISC_GUEST_KERNEL;

}

# define perf_arch_guest_misc_flags(regs)	perf_arch_guest_misc_flags(regs)

#endif



static inline bool has_branch_stack(struct perf_event *event)

{

	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;

kernel/events/core.c

+17 −4
Original line number Diff line number Diff line
@@ -7026,13 +7026,26 @@ void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) 
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);

#endif



unsigned long perf_misc_flags(struct pt_regs *regs)

static bool should_sample_guest(struct perf_event *event)

{

	return !event->attr.exclude_guest && perf_guest_state();

}



unsigned long perf_misc_flags(struct perf_event *event,

			      struct pt_regs *regs)

{

	if (should_sample_guest(event))

		return perf_arch_guest_misc_flags(regs);



	return perf_arch_misc_flags(regs);

}



unsigned long perf_instruction_pointer(struct pt_regs *regs)

unsigned long perf_instruction_pointer(struct perf_event *event,

				       struct pt_regs *regs)

{

	if (should_sample_guest(event))

		return perf_guest_get_ip();



	return perf_arch_instruction_pointer(regs);

}
@@ -7853,7 +7866,7 @@ void perf_prepare_sample(struct perf_sample_data *data, 
	__perf_event_header__init_id(data, event, filtered_sample_type);



	if (filtered_sample_type & PERF_SAMPLE_IP) {

		data->ip = perf_instruction_pointer(regs);

		data->ip = perf_instruction_pointer(event, regs);

		data->sample_flags |= PERF_SAMPLE_IP;

	}
@@ -8017,7 +8030,7 @@ void perf_prepare_header(struct perf_event_header *header, 
{

	header->type = PERF_RECORD_SAMPLE;

	header->size = perf_sample_data_size(data, event);

	header->misc = perf_misc_flags(regs);

	header->misc = perf_misc_flags(event, regs);



	/*

	 * If you're adding more sample types here, you likely need to do