Commit 6ee52e2a authored by Song Liu's avatar Song Liu Committed by Arnaldo Carvalho de Melo
Browse files

perf, bpf: Introduce PERF_RECORD_BPF_EVENT 



For better performance analysis of BPF programs, this patch introduces
PERF_RECORD_BPF_EVENT, a new perf_event_type that exposes BPF program
load/unload information to user space.

Each BPF program may contain up to BPF_MAX_SUBPROGS (256) sub programs.
The following example shows kernel symbols for a BPF program with 7 sub
programs:

    ffffffffa0257cf9 t bpf_prog_b07ccb89267cf242_F
    ffffffffa02592e1 t bpf_prog_2dcecc18072623fc_F
    ffffffffa025b0e9 t bpf_prog_bb7a405ebaec5d5c_F
    ffffffffa025dd2c t bpf_prog_a7540d4a39ec1fc7_F
    ffffffffa025fcca t bpf_prog_05762d4ade0e3737_F
    ffffffffa026108f t bpf_prog_db4bd11e35df90d4_F
    ffffffffa0263f00 t bpf_prog_89d64e4abf0f0126_F
    ffffffffa0257cf9 t bpf_prog_ae31629322c4b018__dummy_tracepoi

When a bpf program is loaded, PERF_RECORD_KSYMBOL is generated for each
of these sub programs. Therefore, PERF_RECORD_BPF_EVENT is not needed
for simple profiling.

For annotation, user space need to listen to PERF_RECORD_BPF_EVENT and
gather more information about these (sub) programs via sys_bpf.

Signed-off-by: default avatarSong Liu <songliubraving@fb.com>
Reviewed-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarPeter Zijlstra (Intel) <peterz@infradeaed.org>
Tested-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-4-songliubraving@fb.com


Signed-off-by: default avatarArnaldo Carvalho de Melo <acme@redhat.com>
parent d764ac64

include/linux/filter.h

+7 −0
Original line number Diff line number Diff line
@@ -951,6 +951,7 @@ bpf_address_lookup(unsigned long addr, unsigned long *size, 


void bpf_prog_kallsyms_add(struct bpf_prog *fp);

void bpf_prog_kallsyms_del(struct bpf_prog *fp);

void bpf_get_prog_name(const struct bpf_prog *prog, char *sym);



#else /* CONFIG_BPF_JIT */
@@ -1006,6 +1007,12 @@ static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) 
static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp)

{

}



static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)

{

	sym[0] = '\0';

}



#endif /* CONFIG_BPF_JIT */



void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);

include/linux/perf_event.h

+6 −0
Original line number Diff line number Diff line
@@ -1125,6 +1125,9 @@ extern void perf_event_mmap(struct vm_area_struct *vma); 


extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,

			       bool unregister, const char *sym);

extern void perf_event_bpf_event(struct bpf_prog *prog,

				 enum perf_bpf_event_type type,

				 u16 flags);



extern struct perf_guest_info_callbacks *perf_guest_cbs;

extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
@@ -1350,6 +1353,9 @@ 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, const char *sym)	{ }

static inline void perf_event_bpf_event(struct bpf_prog *prog,

					enum perf_bpf_event_type type,

					u16 flags)			{ }

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)	{ }

include/uapi/linux/perf_event.h

+28 −1
Original line number Diff line number Diff line
@@ -373,7 +373,8 @@ struct perf_event_attr { 
				write_backward :  1, /* Write ring buffer from end to beginning */

				namespaces     :  1, /* include namespaces data */

				ksymbol        :  1, /* include ksymbol events */

				__reserved_1   : 34;

				bpf_event      :  1, /* include bpf events */

				__reserved_1   : 33;



	union {

		__u32		wakeup_events;	  /* wakeup every n events */
@@ -979,6 +980,25 @@ enum perf_event_type { 
	 */

	PERF_RECORD_KSYMBOL			= 17,



	/*

	 * Record bpf events:

	 *  enum perf_bpf_event_type {

	 *	PERF_BPF_EVENT_UNKNOWN		= 0,

	 *	PERF_BPF_EVENT_PROG_LOAD	= 1,

	 *	PERF_BPF_EVENT_PROG_UNLOAD	= 2,

	 *  };

	 *

	 * struct {

	 *	struct perf_event_header	header;

	 *	u16				type;

	 *	u16				flags;

	 *	u32				id;

	 *	u8				tag[BPF_TAG_SIZE];

	 *	struct sample_id		sample_id;

	 * };

	 */

	PERF_RECORD_BPF_EVENT			= 18,



	PERF_RECORD_MAX,			/* non-ABI */

};
@@ -990,6 +1010,13 @@ enum perf_record_ksymbol_type { 


#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER	(1 << 0)



enum perf_bpf_event_type {

	PERF_BPF_EVENT_UNKNOWN		= 0,

	PERF_BPF_EVENT_PROG_LOAD	= 1,

	PERF_BPF_EVENT_PROG_UNLOAD	= 2,

	PERF_BPF_EVENT_MAX,		/* non-ABI */

};



#define PERF_MAX_STACK_DEPTH		127

#define PERF_MAX_CONTEXTS_PER_STACK	  8

kernel/bpf/core.c

+1 −1
Original line number Diff line number Diff line
@@ -495,7 +495,7 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, 
	*symbol_end   = addr + hdr->pages * PAGE_SIZE;

}



static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)

void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)

{

	const char *end = sym + KSYM_NAME_LEN;

	const struct btf_type *type;

kernel/bpf/syscall.c

+2 −0
Original line number Diff line number Diff line
@@ -1211,6 +1211,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) 
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)

{

	if (atomic_dec_and_test(&prog->aux->refcnt)) {

		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);

		/* bpf_prog_free_id() must be called first */

		bpf_prog_free_id(prog, do_idr_lock);

		bpf_prog_kallsyms_del_all(prog);
@@ -1554,6 +1555,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) 
	}



	bpf_prog_kallsyms_add(prog);

	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);

	return err;



free_used_maps:

CRA Git | Maintained and supported by SUSTech CRA and CCSE