lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <655de93b-26cf-4588-aec5-9d0eba997c4e@linux.intel.com>
Date: Thu, 7 Nov 2024 14:46:24 -0500
From: "Liang, Kan" <kan.liang@...ux.intel.com>
To: Colton Lewis <coltonlewis@...gle.com>, kvm@...r.kernel.org
Cc: Oliver Upton <oliver.upton@...ux.dev>,
 Sean Christopherson <seanjc@...gle.com>,
 Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
 Arnaldo Carvalho de Melo <acme@...nel.org>,
 Namhyung Kim <namhyung@...nel.org>, Mark Rutland <mark.rutland@....com>,
 Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
 Jiri Olsa <jolsa@...nel.org>, Ian Rogers <irogers@...gle.com>,
 Adrian Hunter <adrian.hunter@...el.com>, Will Deacon <will@...nel.org>,
 Russell King <linux@...linux.org.uk>,
 Catalin Marinas <catalin.marinas@....com>,
 Michael Ellerman <mpe@...erman.id.au>, Nicholas Piggin <npiggin@...il.com>,
 Christophe Leroy <christophe.leroy@...roup.eu>,
 Naveen N Rao <naveen@...nel.org>, Heiko Carstens <hca@...ux.ibm.com>,
 Vasily Gorbik <gor@...ux.ibm.com>, Alexander Gordeev
 <agordeev@...ux.ibm.com>, Christian Borntraeger <borntraeger@...ux.ibm.com>,
 Sven Schnelle <svens@...ux.ibm.com>, Thomas Gleixner <tglx@...utronix.de>,
 Borislav Petkov <bp@...en8.de>, Dave Hansen <dave.hansen@...ux.intel.com>,
 x86@...nel.org, "H . Peter Anvin" <hpa@...or.com>,
 linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
 linux-arm-kernel@...ts.infradead.org, linuxppc-dev@...ts.ozlabs.org,
 linux-s390@...r.kernel.org
Subject: Re: [PATCH v7 5/5] perf: Correct perf sampling with guest VMs



On 2024-11-07 2:03 p.m., Colton Lewis wrote:
> 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: Colton Lewis <coltonlewis@...gle.com>
> Acked-by: Mark Rutland <mark.rutland@....com>
> Reviewed-by: Oliver Upton <oliver.upton@...ux.dev>
> ---

Acked-by: Kan Liang <kan.liang@...ux.intel.com>

Thanks,
Kan
>  arch/arm64/include/asm/perf_event.h |  4 ----
>  arch/arm64/kernel/perf_callchain.c  | 28 ----------------------------
>  arch/x86/events/core.c              | 16 ++++------------
>  include/linux/perf_event.h          | 21 +++++++++++++++++++--
>  kernel/events/core.c                | 21 +++++++++++++++++----
>  5 files changed, 40 insertions(+), 50 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
> index 31a5584ed423..ee45b4e77347 100644
> --- a/arch/arm64/include/asm/perf_event.h
> +++ b/arch/arm64/include/asm/perf_event.h
> @@ -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
>  
> diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
> index 01a9d08fc009..9b7f26b128b5 100644
> --- a/arch/arm64/kernel/perf_callchain.c
> +++ b/arch/arm64/kernel/perf_callchain.c
> @@ -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;
> -}
> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
> index 9fdc5fa22c66..d85e12ca4263 100644
> --- a/arch/x86/events/core.c
> +++ b/arch/x86/events/core.c
> @@ -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);
>  }
>  
> @@ -3035,17 +3032,12 @@ unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
>  
>  unsigned long perf_arch_misc_flags(struct pt_regs *regs)
>  {
> -	unsigned int guest_state = perf_guest_state();
>  	unsigned long misc = common_misc_flags(regs);
>  
> -	if (guest_state) {
> -		misc |= perf_arch_guest_misc_flags(regs);
> -	} else {
> -		if (user_mode(regs))
> -			misc |= PERF_RECORD_MISC_USER;
> -		else
> -			misc |= PERF_RECORD_MISC_KERNEL;
> -	}
> +	if (user_mode(regs))
> +		misc |= PERF_RECORD_MISC_USER;
> +	else
> +		misc |= PERF_RECORD_MISC_KERNEL;
>  
>  	return misc;
>  }
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 772ad352856b..368ea0e9577c 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -1655,8 +1655,9 @@ 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) \
> @@ -1667,6 +1668,22 @@ 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;
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 2c44ffd6f4d8..c62164a2ff23 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -7022,13 +7022,26 @@ 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);
>  }
>  
> @@ -7849,7 +7862,7 @@ 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;
>  	}
>  
> @@ -8013,7 +8026,7 @@ 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


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ