Re: [PATCH v6 perf, bpf-next 1/7] perf, bpf: Introduce PERF_RECORD_KSYMBOL

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Wed, Jan 09, 2019 at 11:21:05AM -0800, Song Liu escreveu:
> For better performance analysis of dynamically JITed and loaded kernel
> functions, such as BPF programs, this patch introduces
> PERF_RECORD_KSYMBOL, a new perf_event_type that exposes kernel symbol
> register/unregister information to user space.
> 
> The following data structure is used for PERF_RECORD_KSYMBOL.
> 
>     /*
>      * struct {
>      *      struct perf_event_header        header;
>      *      u64                             addr;
>      *      u32                             len;
>      *      u16                             ksym_type;
>      *      u16                             flags;
>      *      char                            name[];
>      *      struct sample_id                sample_id;
>      * };
>      */

So, I couldn't find where this gets used, the intention here is just to
add the interfaces and afterwards is that you will wire this up? I would
like to test the whole shebang to see it working.

- Arnaldo
 
> Signed-off-by: Song Liu <songliubraving@fb.com>
> ---
>  include/linux/perf_event.h      | 13 +++++
>  include/uapi/linux/perf_event.h | 26 ++++++++-
>  kernel/events/core.c            | 98 ++++++++++++++++++++++++++++++++-
>  3 files changed, 135 insertions(+), 2 deletions(-)
> 
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 1d5c551a5add..6b5f08db5ef3 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -1113,6 +1113,13 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
>  }
>  
>  extern void perf_event_mmap(struct vm_area_struct *vma);
> +
> +/* callback function to generate ksymbol name */
> +typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data);
> +extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
> +			       bool unregister,
> +			       perf_ksymbol_get_name_f get_name, void *data);
> +
>  extern struct perf_guest_info_callbacks *perf_guest_cbs;
>  extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
>  extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
> @@ -1333,6 +1340,12 @@ static inline int perf_unregister_guest_info_callbacks
>  (struct perf_guest_info_callbacks *callbacks)				{ return 0; }
>  
>  static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
> +
> +typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data);
> +static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
> +				      bool unregister,
> +				      perf_ksymbol_get_name_f get_name,
> +				      void *data) 			{ }
>  static inline void perf_event_exec(void)				{ }
>  static inline void perf_event_comm(struct task_struct *tsk, bool exec)	{ }
>  static inline void perf_event_namespaces(struct task_struct *tsk)	{ }
> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
> index 9de8780ac8d9..68c4da0227c5 100644
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -372,7 +372,8 @@ struct perf_event_attr {
>  				context_switch :  1, /* context switch data */
>  				write_backward :  1, /* Write ring buffer from end to beginning */
>  				namespaces     :  1, /* include namespaces data */
> -				__reserved_1   : 35;
> +				ksymbol        :  1, /* include ksymbol events */
> +				__reserved_1   : 34;
>  
>  	union {
>  		__u32		wakeup_events;	  /* wakeup every n events */
> @@ -965,9 +966,32 @@ enum perf_event_type {
>  	 */
>  	PERF_RECORD_NAMESPACES			= 16,
>  
> +	/*
> +	 * Record ksymbol register/unregister events:
> +	 *
> +	 * struct {
> +	 *	struct perf_event_header	header;
> +	 *	u64				addr;
> +	 *	u32				len;
> +	 *	u16				ksym_type;
> +	 *	u16				flags;
> +	 *	char				name[];
> +	 *	struct sample_id		sample_id;
> +	 * };
> +	 */
> +	PERF_RECORD_KSYMBOL			= 17,
> +
>  	PERF_RECORD_MAX,			/* non-ABI */
>  };
>  
> +enum perf_record_ksymbol_type {
> +	PERF_RECORD_KSYMBOL_TYPE_UNKNOWN	= 0,
> +	PERF_RECORD_KSYMBOL_TYPE_BPF		= 1,
> +	PERF_RECORD_KSYMBOL_TYPE_MAX		/* non-ABI */
> +};
> +
> +#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER	(1 << 0)
> +
>  #define PERF_MAX_STACK_DEPTH		127
>  #define PERF_MAX_CONTEXTS_PER_STACK	  8
>  
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 3cd13a30f732..ef27f2776999 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -385,6 +385,7 @@ static atomic_t nr_namespaces_events __read_mostly;
>  static atomic_t nr_task_events __read_mostly;
>  static atomic_t nr_freq_events __read_mostly;
>  static atomic_t nr_switch_events __read_mostly;
> +static atomic_t nr_ksymbol_events __read_mostly;
>  
>  static LIST_HEAD(pmus);
>  static DEFINE_MUTEX(pmus_lock);
> @@ -4235,7 +4236,7 @@ static bool is_sb_event(struct perf_event *event)
>  
>  	if (attr->mmap || attr->mmap_data || attr->mmap2 ||
>  	    attr->comm || attr->comm_exec ||
> -	    attr->task ||
> +	    attr->task || attr->ksymbol ||
>  	    attr->context_switch)
>  		return true;
>  	return false;
> @@ -4305,6 +4306,8 @@ static void unaccount_event(struct perf_event *event)
>  		dec = true;
>  	if (has_branch_stack(event))
>  		dec = true;
> +	if (event->attr.ksymbol)
> +		atomic_dec(&nr_ksymbol_events);
>  
>  	if (dec) {
>  		if (!atomic_add_unless(&perf_sched_count, -1, 1))
> @@ -7650,6 +7653,97 @@ static void perf_log_throttle(struct perf_event *event, int enable)
>  	perf_output_end(&handle);
>  }
>  
> +/*
> + * ksymbol register/unregister tracking
> + */
> +
> +struct perf_ksymbol_event {
> +	const char	*name;
> +	int		name_len;
> +	struct {
> +		struct perf_event_header        header;
> +		u64				addr;
> +		u32				len;
> +		u16				ksym_type;
> +		u16				flags;
> +	} event_id;
> +};
> +
> +static int perf_event_ksymbol_match(struct perf_event *event)
> +{
> +	return event->attr.ksymbol;
> +}
> +
> +static void perf_event_ksymbol_output(struct perf_event *event, void *data)
> +{
> +	struct perf_ksymbol_event *ksymbol_event = data;
> +	struct perf_output_handle handle;
> +	struct perf_sample_data sample;
> +	int ret;
> +
> +	if (!perf_event_ksymbol_match(event))
> +		return;
> +
> +	perf_event_header__init_id(&ksymbol_event->event_id.header,
> +				   &sample, event);
> +	ret = perf_output_begin(&handle, event,
> +				ksymbol_event->event_id.header.size);
> +	if (ret)
> +		return;
> +
> +	perf_output_put(&handle, ksymbol_event->event_id);
> +	__output_copy(&handle, ksymbol_event->name, ksymbol_event->name_len);
> +	perf_event__output_id_sample(event, &handle, &sample);
> +
> +	perf_output_end(&handle);
> +}
> +
> +void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
> +			perf_ksymbol_get_name_f get_name, void *data)
> +{
> +	struct perf_ksymbol_event ksymbol_event;
> +	char name[KSYM_NAME_LEN];
> +	u16 flags = 0;
> +	int name_len;
> +
> +	if (!atomic_read(&nr_ksymbol_events))
> +		return;
> +
> +	if (ksym_type >= PERF_RECORD_KSYMBOL_TYPE_MAX ||
> +	    ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN)
> +		goto err;
> +
> +	get_name(name, KSYM_NAME_LEN, data);
> +	name_len = strlen(name) + 1;
> +	while (!IS_ALIGNED(name_len, sizeof(u64)))
> +		name[name_len++] = '\0';
> +	BUILD_BUG_ON(KSYM_NAME_LEN % sizeof(u64));
> +
> +	if (unregister)
> +		flags |= PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER;
> +
> +	ksymbol_event = (struct perf_ksymbol_event){
> +		.name = name,
> +		.name_len = name_len,
> +		.event_id = {
> +			.header = {
> +				.type = PERF_RECORD_KSYMBOL,
> +				.size = sizeof(ksymbol_event.event_id) +
> +					name_len,
> +			},
> +			.addr = addr,
> +			.len = len,
> +			.ksym_type = ksym_type,
> +			.flags = flags,
> +		},
> +	};
> +
> +	perf_iterate_sb(perf_event_ksymbol_output, &ksymbol_event, NULL);
> +	return;
> +err:
> +	WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type);
> +}
> +
>  void perf_event_itrace_started(struct perf_event *event)
>  {
>  	event->attach_state |= PERF_ATTACH_ITRACE;
> @@ -9900,6 +9994,8 @@ static void account_event(struct perf_event *event)
>  		inc = true;
>  	if (is_cgroup_event(event))
>  		inc = true;
> +	if (event->attr.ksymbol)
> +		atomic_inc(&nr_ksymbol_events);
>  
>  	if (inc) {
>  		/*
> -- 
> 2.17.1

-- 

- Arnaldo