[PATCH 14/24] perf, bpf: Introduce PERF_RECORD_KSYMBOL

[PATCH 14/24] perf, bpf: Introduce PERF_RECORD_KSYMBOL

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

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;
     * };
     */

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Alexei Starovoitov <ast@kernel.org>
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/20190117161521.1341602-2-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 include/linux/perf_event.h      |  8 +++
 include/uapi/linux/perf_event.h | 26 ++++++++-
 kernel/events/core.c            | 98 ++++++++++++++++++++++++++++++++-
 3 files changed, 130 insertions(+), 2 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4eb88065a9b5..136fe0495374 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1122,6 +1122,10 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 }
 
 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 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);
@@ -1342,6 +1346,10 @@ 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, const char *sym)	{ }
 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 ea19b5d491bf..1dee5c8f166b 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 */
@@ -963,9 +964,32 @@ 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 bc525cd1615c..e04ab5f325cf 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))
@@ -7653,6 +7656,97 @@ 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,
+			const char *sym)
+{
+	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;
+
+	strlcpy(name, sym, KSYM_NAME_LEN);
+	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;
@@ -9912,6 +10006,8 @@ 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) {
 		/*
-- 
2.20.1

[PATCH 15/24] tools headers uapi: Sync tools/include/uapi/linux/perf_event.h

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

Sync changes for PERF_RECORD_KSYMBOL.

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
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/20190117161521.1341602-3-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index ea19b5d491bf..1dee5c8f166b 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/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 */
@@ -963,9 +964,32 @@ 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
 
-- 
2.20.1

[PATCH 16/24] perf, bpf: Introduce PERF_RECORD_BPF_EVENT

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

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: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradeaed.org>
Tested-by: Arnaldo 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: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 include/linux/filter.h          |   7 ++
 include/linux/perf_event.h      |   6 ++
 include/uapi/linux/perf_event.h |  29 +++++++-
 kernel/bpf/core.c               |   2 +-
 kernel/bpf/syscall.c            |   2 +
 kernel/events/core.c            | 115 ++++++++++++++++++++++++++++++++
 6 files changed, 159 insertions(+), 2 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index ad106d845b22..d531d4250bff 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -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);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 136fe0495374..a79e59fc3b7d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -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)	{ }
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 1dee5c8f166b..7198ddd0c6b1 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -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
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f908b9356025..19c49313c709 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -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;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b155cd17c1bd..30ebd085790b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -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:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e04ab5f325cf..236bb8ddb7bc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -386,6 +386,7 @@ 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 atomic_t nr_bpf_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -4308,6 +4309,8 @@ static void unaccount_event(struct perf_event *event)
 		dec = true;
 	if (event->attr.ksymbol)
 		atomic_dec(&nr_ksymbol_events);
+	if (event->attr.bpf_event)
+		atomic_dec(&nr_bpf_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -7747,6 +7750,116 @@ void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
 	WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type);
 }
 
+/*
+ * bpf program load/unload tracking
+ */
+
+struct perf_bpf_event {
+	struct bpf_prog	*prog;
+	struct {
+		struct perf_event_header        header;
+		u16				type;
+		u16				flags;
+		u32				id;
+		u8				tag[BPF_TAG_SIZE];
+	} event_id;
+};
+
+static int perf_event_bpf_match(struct perf_event *event)
+{
+	return event->attr.bpf_event;
+}
+
+static void perf_event_bpf_output(struct perf_event *event, void *data)
+{
+	struct perf_bpf_event *bpf_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_bpf_match(event))
+		return;
+
+	perf_event_header__init_id(&bpf_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				bpf_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, bpf_event->event_id);
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
+					 enum perf_bpf_event_type type)
+{
+	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
+	char sym[KSYM_NAME_LEN];
+	int i;
+
+	if (prog->aux->func_cnt == 0) {
+		bpf_get_prog_name(prog, sym);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+				   (u64)(unsigned long)prog->bpf_func,
+				   prog->jited_len, unregister, sym);
+	} else {
+		for (i = 0; i < prog->aux->func_cnt; i++) {
+			struct bpf_prog *subprog = prog->aux->func[i];
+
+			bpf_get_prog_name(subprog, sym);
+			perf_event_ksymbol(
+				PERF_RECORD_KSYMBOL_TYPE_BPF,
+				(u64)(unsigned long)subprog->bpf_func,
+				subprog->jited_len, unregister, sym);
+		}
+	}
+}
+
+void perf_event_bpf_event(struct bpf_prog *prog,
+			  enum perf_bpf_event_type type,
+			  u16 flags)
+{
+	struct perf_bpf_event bpf_event;
+
+	if (type <= PERF_BPF_EVENT_UNKNOWN ||
+	    type >= PERF_BPF_EVENT_MAX)
+		return;
+
+	switch (type) {
+	case PERF_BPF_EVENT_PROG_LOAD:
+	case PERF_BPF_EVENT_PROG_UNLOAD:
+		if (atomic_read(&nr_ksymbol_events))
+			perf_event_bpf_emit_ksymbols(prog, type);
+		break;
+	default:
+		break;
+	}
+
+	if (!atomic_read(&nr_bpf_events))
+		return;
+
+	bpf_event = (struct perf_bpf_event){
+		.prog = prog,
+		.event_id = {
+			.header = {
+				.type = PERF_RECORD_BPF_EVENT,
+				.size = sizeof(bpf_event.event_id),
+			},
+			.type = type,
+			.flags = flags,
+			.id = prog->aux->id,
+		},
+	};
+
+	BUILD_BUG_ON(BPF_TAG_SIZE % sizeof(u64));
+
+	memcpy(bpf_event.event_id.tag, prog->tag, BPF_TAG_SIZE);
+	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -10008,6 +10121,8 @@ static void account_event(struct perf_event *event)
 		inc = true;
 	if (event->attr.ksymbol)
 		atomic_inc(&nr_ksymbol_events);
+	if (event->attr.bpf_event)
+		atomic_inc(&nr_bpf_events);
 
 	if (inc) {
 		/*
-- 
2.20.1

[PATCH 17/24] tools headers uapi: Sync tools/include/uapi/linux/perf_event.h

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

Sync for PERF_RECORD_BPF_EVENT.

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
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/20190117161521.1341602-5-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 29 ++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 1dee5c8f166b..7198ddd0c6b1 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -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
 
-- 
2.20.1

[PATCH 18/24] perf tools: Handle PERF_RECORD_KSYMBOL

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

This patch handles PERF_RECORD_KSYMBOL in perf record/report.
Specifically, map and symbol are created for ksymbol register, and
removed for ksymbol unregister.

This patch also sets perf_event_attr.ksymbol properly. The flag is ON by
default.

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
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/20190117161521.1341602-6-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/event.c   | 21 +++++++++++++++
 tools/perf/util/event.h   | 20 ++++++++++++++
 tools/perf/util/evsel.c   | 10 ++++++-
 tools/perf/util/evsel.h   |  1 +
 tools/perf/util/machine.c | 55 +++++++++++++++++++++++++++++++++++++++
 tools/perf/util/machine.h |  3 +++
 tools/perf/util/session.c |  4 +++
 tools/perf/util/tool.h    |  4 ++-
 8 files changed, 116 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 937a5a4f71cc..3c8a6a8dd260 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -24,6 +24,7 @@
 #include "symbol/kallsyms.h"
 #include "asm/bug.h"
 #include "stat.h"
+#include "session.h"
 
 #define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
 
@@ -45,6 +46,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_SWITCH]			= "SWITCH",
 	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
 	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
+	[PERF_RECORD_KSYMBOL]			= "KSYMBOL",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -1329,6 +1331,14 @@ int perf_event__process_switch(struct perf_tool *tool __maybe_unused,
 	return machine__process_switch_event(machine, event);
 }
 
+int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample __maybe_unused,
+				struct machine *machine)
+{
+	return machine__process_ksymbol(machine, event, sample);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -1461,6 +1471,14 @@ static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)
 	return fprintf(fp, " lost %" PRIu64 "\n", event->lost.lost);
 }
 
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " ksymbol event with addr %lx len %u type %u flags 0x%x name %s\n",
+		       event->ksymbol_event.addr, event->ksymbol_event.len,
+		       event->ksymbol_event.ksym_type,
+		       event->ksymbol_event.flags, event->ksymbol_event.name);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -1496,6 +1514,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_LOST:
 		ret += perf_event__fprintf_lost(event, fp);
 		break;
+	case PERF_RECORD_KSYMBOL:
+		ret += perf_event__fprintf_ksymbol(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index eb95f3384958..018322f2a13e 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -5,6 +5,7 @@
 #include <limits.h>
 #include <stdio.h>
 #include <linux/kernel.h>
+#include <linux/bpf.h>
 
 #include "../perf.h"
 #include "build-id.h"
@@ -84,6 +85,19 @@ struct throttle_event {
 	u64 stream_id;
 };
 
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 256
+#endif
+
+struct ksymbol_event {
+	struct perf_event_header header;
+	u64 addr;
+	u32 len;
+	u16 ksym_type;
+	u16 flags;
+	char name[KSYM_NAME_LEN];
+};
+
 #define PERF_SAMPLE_MASK				\
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
@@ -651,6 +665,7 @@ union perf_event {
 	struct stat_round_event		stat_round;
 	struct time_conv_event		time_conv;
 	struct feature_event		feat;
+	struct ksymbol_event		ksymbol_event;
 };
 
 void perf_event__print_totals(void);
@@ -748,6 +763,10 @@ int perf_event__process_exit(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_event__process_ksymbol(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct machine *machine);
 int perf_tool__process_synth_event(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct machine *machine,
@@ -811,6 +830,7 @@ size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbc0466db368..9c8dc6d1aa7f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1035,6 +1035,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	attr->mmap  = track;
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
+	attr->ksymbol = track && !perf_missing_features.ksymbol;
 
 	if (opts->record_namespaces)
 		attr->namespaces  = track;
@@ -1652,6 +1653,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(context_switch, p_unsigned);
 	PRINT_ATTRf(write_backward, p_unsigned);
 	PRINT_ATTRf(namespaces, p_unsigned);
+	PRINT_ATTRf(ksymbol, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
@@ -1811,6 +1813,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 				     PERF_SAMPLE_BRANCH_NO_CYCLES);
 	if (perf_missing_features.group_read && evsel->attr.inherit)
 		evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
+	if (perf_missing_features.ksymbol)
+		evsel->attr.ksymbol = 0;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1930,7 +1934,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
+	if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) {
+		perf_missing_features.ksymbol = true;
+		pr_debug2("switching off ksymbol\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
 		perf_missing_features.write_backward = true;
 		pr_debug2("switching off write_backward\n");
 		goto out_close;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 82a289ce8b0c..4a8c3e7f4808 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -168,6 +168,7 @@ struct perf_missing_features {
 	bool lbr_flags;
 	bool write_backward;
 	bool group_read;
+	bool ksymbol;
 };
 
 extern struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 143f7057d581..9bca61c7d5bf 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -681,6 +681,59 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+static int machine__process_ksymbol_register(struct machine *machine,
+					     union perf_event *event,
+					     struct perf_sample *sample __maybe_unused)
+{
+	struct symbol *sym;
+	struct map *map;
+
+	map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+	if (!map) {
+		map = dso__new_map(event->ksymbol_event.name);
+		if (!map)
+			return -ENOMEM;
+
+		map->start = event->ksymbol_event.addr;
+		map->pgoff = map->start;
+		map->end = map->start + event->ksymbol_event.len;
+		map_groups__insert(&machine->kmaps, map);
+	}
+
+	sym = symbol__new(event->ksymbol_event.addr, event->ksymbol_event.len,
+			  0, 0, event->ksymbol_event.name);
+	if (!sym)
+		return -ENOMEM;
+	dso__insert_symbol(map->dso, sym);
+	return 0;
+}
+
+static int machine__process_ksymbol_unregister(struct machine *machine,
+					       union perf_event *event,
+					       struct perf_sample *sample __maybe_unused)
+{
+	struct map *map;
+
+	map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+	if (map)
+		map_groups__remove(&machine->kmaps, map);
+
+	return 0;
+}
+
+int machine__process_ksymbol(struct machine *machine __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample)
+{
+	if (dump_trace)
+		perf_event__fprintf_ksymbol(event, stdout);
+
+	if (event->ksymbol_event.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
+		return machine__process_ksymbol_unregister(machine, event,
+							   sample);
+	return machine__process_ksymbol_register(machine, event, sample);
+}
+
 static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
 {
 	const char *dup_filename;
@@ -1812,6 +1865,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 	case PERF_RECORD_SWITCH:
 	case PERF_RECORD_SWITCH_CPU_WIDE:
 		ret = machine__process_switch_event(machine, event); break;
+	case PERF_RECORD_KSYMBOL:
+		ret = machine__process_ksymbol(machine, event, sample); break;
 	default:
 		ret = -1;
 		break;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a5d1da60f751..4ecd380ce1b4 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -130,6 +130,9 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
 				 struct perf_sample *sample);
+int machine__process_ksymbol(struct machine *machine,
+			     union perf_event *event,
+			     struct perf_sample *sample);
 int machine__process_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b26bc9c54200..dcfacfb036a3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -379,6 +379,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->itrace_start = perf_event__process_itrace_start;
 	if (tool->context_switch == NULL)
 		tool->context_switch = perf_event__process_switch;
+	if (tool->ksymbol == NULL)
+		tool->ksymbol = perf_event__process_ksymbol;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -1310,6 +1312,8 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_SWITCH:
 	case PERF_RECORD_SWITCH_CPU_WIDE:
 		return tool->context_switch(tool, event, sample, machine);
+	case PERF_RECORD_KSYMBOL:
+		return tool->ksymbol(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 56e4ca54020a..9c81ca2f3cf7 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -53,7 +53,9 @@ struct perf_tool {
 			itrace_start,
 			context_switch,
 			throttle,
-			unthrottle;
+			unthrottle,
+			ksymbol;
+
 	event_attr_op	attr;
 	event_attr_op	event_update;
 	event_op2	tracing_data;
-- 
2.20.1

[PATCH 19/24] perf tools: Handle PERF_RECORD_BPF_EVENT

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

This patch adds basic handling of PERF_RECORD_BPF_EVENT.  Tracking of
PERF_RECORD_BPF_EVENT is OFF by default. Option --bpf-event is added to
turn it on.

Committer notes:

Add dummy machine__process_bpf_event() variant that returns zero for
systems without HAVE_LIBBPF_SUPPORT, such as Alpine Linux, unbreaking
the build in such systems.

Remove the needless include <machine.h> from bpf->event.h, provide just
forward declarations for the structs and unions in the parameters, to
reduce compilation time and needless rebuilds when machine.h gets
changed.

Committer testing:

When running with:

 # perf record --bpf-event

On an older kernel where PERF_RECORD_BPF_EVENT and PERF_RECORD_KSYMBOL
is not present, we fallback to removing those two bits from
perf_event_attr, making the tool to continue to work on older kernels:

  perf_event_attr:
    size                             112
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|PERIOD
    read_format                      ID
    disabled                         1
    inherit                          1
    mmap                             1
    comm                             1
    freq                             1
    enable_on_exec                   1
    task                             1
    precise_ip                       3
    sample_id_all                    1
    exclude_guest                    1
    mmap2                            1
    comm_exec                        1
    ksymbol                          1
    bpf_event                        1
  ------------------------------------------------------------
  sys_perf_event_open: pid 5779  cpu 0  group_fd -1  flags 0x8
  sys_perf_event_open failed, error -22
  switching off bpf_event
  ------------------------------------------------------------
  perf_event_attr:
    size                             112
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|PERIOD
    read_format                      ID
    disabled                         1
    inherit                          1
    mmap                             1
    comm                             1
    freq                             1
    enable_on_exec                   1
    task                             1
    precise_ip                       3
    sample_id_all                    1
    exclude_guest                    1
    mmap2                            1
    comm_exec                        1
    ksymbol                          1
  ------------------------------------------------------------
  sys_perf_event_open: pid 5779  cpu 0  group_fd -1  flags 0x8
  sys_perf_event_open failed, error -22
  switching off ksymbol
  ------------------------------------------------------------
  perf_event_attr:
    size                             112
    { sample_period, sample_freq }   4000
    sample_type                      IP|TID|TIME|PERIOD
    read_format                      ID
    disabled                         1
    inherit                          1
    mmap                             1
    comm                             1
    freq                             1
    enable_on_exec                   1
    task                             1
    precise_ip                       3
    sample_id_all                    1
    exclude_guest                    1
    mmap2                            1
    comm_exec                        1
  ------------------------------------------------------------

And then proceeds to work without those two features.

As passing --bpf-event is an explicit action performed by the user, perhaps we
should emit a warning telling that the kernel has no such feature, but this can
be done on top of this patch.

Now with a kernel that supports these events, start the 'record --bpf-event -a'
and then run 'perf trace sleep 10000' that will use the BPF
augmented_raw_syscalls.o prebuilt (for another kernel version even) and thus
should generate PERF_RECORD_BPF_EVENT events:

  [root@quaco ~]# perf record -e dummy -a --bpf-event
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.713 MB perf.data ]

  [root@quaco ~]# bpftool prog
  13: cgroup_skb  tag 7be49e3934a125ba  gpl
  	loaded_at 2019-01-19T09:09:43-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 13,14
  14: cgroup_skb  tag 2a142ef67aaad174  gpl
  	loaded_at 2019-01-19T09:09:43-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 13,14
  15: cgroup_skb  tag 7be49e3934a125ba  gpl
  	loaded_at 2019-01-19T09:09:43-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 15,16
  16: cgroup_skb  tag 2a142ef67aaad174  gpl
  	loaded_at 2019-01-19T09:09:43-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 15,16
  17: cgroup_skb  tag 7be49e3934a125ba  gpl
  	loaded_at 2019-01-19T09:09:44-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 17,18
  18: cgroup_skb  tag 2a142ef67aaad174  gpl
  	loaded_at 2019-01-19T09:09:44-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 17,18
  21: cgroup_skb  tag 7be49e3934a125ba  gpl
  	loaded_at 2019-01-19T09:09:45-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 21,22
  22: cgroup_skb  tag 2a142ef67aaad174  gpl
  	loaded_at 2019-01-19T09:09:45-0300  uid 0
  	xlated 296B  jited 229B  memlock 4096B  map_ids 21,22
  31: tracepoint  name sys_enter  tag 12504ba9402f952f  gpl
  	loaded_at 2019-01-19T09:19:56-0300  uid 0
  	xlated 512B  jited 374B  memlock 4096B  map_ids 30,29,28
  32: tracepoint  name sys_exit  tag c1bd85c092d6e4aa  gpl
  	loaded_at 2019-01-19T09:19:56-0300  uid 0
  	xlated 256B  jited 191B  memlock 4096B  map_ids 30,29
  # perf report -D | grep PERF_RECORD_BPF_EVENT | nl
     1	0 55834574849 0x4fc8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
     2	0 60129542145 0x5118 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
     3	0 64424509441 0x5268 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
     4	0 68719476737 0x53b8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
     5	0 73014444033 0x5508 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
     6	0 77309411329 0x5658 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
     7	0 90194313217 0x57a8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
     8	0 94489280513 0x58f8 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
     9	7 620922484360 0xb6390 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 29
    10	7 620922486018 0xb6410 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 29
    11	7 620922579199 0xb6490 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 30
    12	7 620922580240 0xb6510 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 2, flags 0, id 30
    13	7 620922765207 0xb6598 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 31
    14	7 620922874543 0xb6620 [0x30]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 32
  #

There, the 31 and 32 tracepoint BPF programs put in place by 'perf trace'.

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
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/20190117161521.1341602-7-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c |  1 +
 tools/perf/perf.h           |  1 +
 tools/perf/util/Build       |  2 ++
 tools/perf/util/bpf-event.c | 15 +++++++++++++++
 tools/perf/util/bpf-event.h | 22 ++++++++++++++++++++++
 tools/perf/util/event.c     | 20 ++++++++++++++++++++
 tools/perf/util/event.h     | 16 ++++++++++++++++
 tools/perf/util/evsel.c     | 11 ++++++++++-
 tools/perf/util/evsel.h     |  1 +
 tools/perf/util/machine.c   |  3 +++
 tools/perf/util/session.c   |  4 ++++
 tools/perf/util/tool.h      |  3 ++-
 12 files changed, 97 insertions(+), 2 deletions(-)
 create mode 100644 tools/perf/util/bpf-event.c
 create mode 100644 tools/perf/util/bpf-event.h

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 882285fb9f64..deaf9b902094 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1839,6 +1839,7 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
 		    "synthesize non-sample events at the end of output"),
 	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
+	OPT_BOOLEAN(0, "bpf-event", &record.opts.bpf_event, "record bpf events"),
 	OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
 		    "Fail if the specified frequency can't be used"),
 	OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 388c6dd128b8..5941fb6eccfc 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -66,6 +66,7 @@ struct record_opts {
 	bool	     ignore_missing_thread;
 	bool	     strict_freq;
 	bool	     sample_id;
+	bool	     bpf_event;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3ad6a800948d..c359af408334 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -154,6 +154,8 @@ endif
 
 libperf-y += perf-hooks.o
 
+libperf-$(CONFIG_LIBBPF) += bpf-event.o
+
 libperf-$(CONFIG_CXX) += c++/
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
new file mode 100644
index 000000000000..87004706874f
--- /dev/null
+++ b/tools/perf/util/bpf-event.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <bpf/bpf.h>
+#include "bpf-event.h"
+#include "debug.h"
+#include "symbol.h"
+
+int machine__process_bpf_event(struct machine *machine __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused)
+{
+	if (dump_trace)
+		perf_event__fprintf_bpf_event(event, stdout);
+	return 0;
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
new file mode 100644
index 000000000000..da0dfc035fc6
--- /dev/null
+++ b/tools/perf/util/bpf-event.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_BPF_EVENT_H
+#define __PERF_BPF_EVENT_H
+
+#include <linux/compiler.h>
+
+struct machine;
+union perf_event;
+struct perf_sample;
+
+#ifdef HAVE_LIBBPF_SUPPORT
+int machine__process_bpf_event(struct machine *machine, union perf_event *event,
+			       struct perf_sample *sample);
+#else
+static inline int machine__process_bpf_event(struct machine *machine __maybe_unused,
+					     union perf_event *event __maybe_unused,
+					     struct perf_sample *sample __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+#endif
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 3c8a6a8dd260..3b646d27374e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -25,6 +25,7 @@
 #include "asm/bug.h"
 #include "stat.h"
 #include "session.h"
+#include "bpf-event.h"
 
 #define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
 
@@ -47,6 +48,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
 	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
 	[PERF_RECORD_KSYMBOL]			= "KSYMBOL",
+	[PERF_RECORD_BPF_EVENT]			= "BPF_EVENT",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -1339,6 +1341,14 @@ int perf_event__process_ksymbol(struct perf_tool *tool __maybe_unused,
 	return machine__process_ksymbol(machine, event, sample);
 }
 
+int perf_event__process_bpf_event(struct perf_tool *tool __maybe_unused,
+				  union perf_event *event,
+				  struct perf_sample *sample __maybe_unused,
+				  struct machine *machine)
+{
+	return machine__process_bpf_event(machine, event, sample);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -1479,6 +1489,13 @@ size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
 		       event->ksymbol_event.flags, event->ksymbol_event.name);
 }
 
+size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " bpf event with type %u, flags %u, id %u\n",
+		       event->bpf_event.type, event->bpf_event.flags,
+		       event->bpf_event.id);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -1517,6 +1534,9 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_KSYMBOL:
 		ret += perf_event__fprintf_ksymbol(event, fp);
 		break;
+	case PERF_RECORD_BPF_EVENT:
+		ret += perf_event__fprintf_bpf_event(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 018322f2a13e..dad32b81fe71 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -98,6 +98,16 @@ struct ksymbol_event {
 	char name[KSYM_NAME_LEN];
 };
 
+struct bpf_event {
+	struct perf_event_header header;
+	u16 type;
+	u16 flags;
+	u32 id;
+
+	/* for bpf_prog types */
+	u8 tag[BPF_TAG_SIZE];  // prog tag
+};
+
 #define PERF_SAMPLE_MASK				\
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID |		\
 	 PERF_SAMPLE_TIME | PERF_SAMPLE_ADDR |		\
@@ -666,6 +676,7 @@ union perf_event {
 	struct time_conv_event		time_conv;
 	struct feature_event		feat;
 	struct ksymbol_event		ksymbol_event;
+	struct bpf_event		bpf_event;
 };
 
 void perf_event__print_totals(void);
@@ -767,6 +778,10 @@ int perf_event__process_ksymbol(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct machine *machine);
+int perf_event__process_bpf_event(struct perf_tool *tool,
+				  union perf_event *event,
+				  struct perf_sample *sample,
+				  struct machine *machine);
 int perf_tool__process_synth_event(struct perf_tool *tool,
 				   union perf_event *event,
 				   struct machine *machine,
@@ -831,6 +846,7 @@ size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_bpf_event(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 int kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9c8dc6d1aa7f..684c893ca6bc 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1036,6 +1036,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 	attr->ksymbol = track && !perf_missing_features.ksymbol;
+	attr->bpf_event = track && opts->bpf_event &&
+		!perf_missing_features.bpf_event;
 
 	if (opts->record_namespaces)
 		attr->namespaces  = track;
@@ -1654,6 +1656,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(write_backward, p_unsigned);
 	PRINT_ATTRf(namespaces, p_unsigned);
 	PRINT_ATTRf(ksymbol, p_unsigned);
+	PRINT_ATTRf(bpf_event, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
@@ -1815,6 +1818,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		evsel->attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID);
 	if (perf_missing_features.ksymbol)
 		evsel->attr.ksymbol = 0;
+	if (perf_missing_features.bpf_event)
+		evsel->attr.bpf_event = 0;
 retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
@@ -1934,7 +1939,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) {
+	if (!perf_missing_features.bpf_event && evsel->attr.bpf_event) {
+		perf_missing_features.bpf_event = true;
+		pr_debug2("switching off bpf_event\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) {
 		perf_missing_features.ksymbol = true;
 		pr_debug2("switching off ksymbol\n");
 		goto fallback_missing_features;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4a8c3e7f4808..29c5eb68c44b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -169,6 +169,7 @@ struct perf_missing_features {
 	bool write_backward;
 	bool group_read;
 	bool ksymbol;
+	bool bpf_event;
 };
 
 extern struct perf_missing_features perf_missing_features;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9bca61c7d5bf..ae85106bb5bf 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -21,6 +21,7 @@
 #include "unwind.h"
 #include "linux/hash.h"
 #include "asm/bug.h"
+#include "bpf-event.h"
 
 #include "sane_ctype.h"
 #include <symbol/kallsyms.h>
@@ -1867,6 +1868,8 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_switch_event(machine, event); break;
 	case PERF_RECORD_KSYMBOL:
 		ret = machine__process_ksymbol(machine, event, sample); break;
+	case PERF_RECORD_BPF_EVENT:
+		ret = machine__process_bpf_event(machine, event, sample); break;
 	default:
 		ret = -1;
 		break;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index dcfacfb036a3..24fd62528a33 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -381,6 +381,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->context_switch = perf_event__process_switch;
 	if (tool->ksymbol == NULL)
 		tool->ksymbol = perf_event__process_ksymbol;
+	if (tool->bpf_event == NULL)
+		tool->bpf_event = perf_event__process_bpf_event;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -1314,6 +1316,8 @@ static int machines__deliver_event(struct machines *machines,
 		return tool->context_switch(tool, event, sample, machine);
 	case PERF_RECORD_KSYMBOL:
 		return tool->ksymbol(tool, event, sample, machine);
+	case PERF_RECORD_BPF_EVENT:
+		return tool->bpf_event(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 9c81ca2f3cf7..250391672f9f 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -54,7 +54,8 @@ struct perf_tool {
 			context_switch,
 			throttle,
 			unthrottle,
-			ksymbol;
+			ksymbol,
+			bpf_event;
 
 	event_attr_op	attr;
 	event_attr_op	event_update;
-- 
2.20.1

[PATCH 20/24] perf tools: Synthesize PERF_RECORD_* for loaded BPF programs

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

This patch synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for
BPF programs loaded before perf-record. This is achieved by gathering
information about all BPF programs via sys_bpf.

Committer testing:

  # perf record --bpf-event sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.021 MB perf.data (7 samples) ]
  # perf report -D | grep PERF_RECORD_BPF_EVENT | nl
     1	0 0x4b10 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 13
     2	0 0x4c60 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 14
     3	0 0x4db0 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 15
     4	0 0x4f00 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 16
     5	0 0x5050 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 17
     6	0 0x51a0 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 18
     7	0 0x52f0 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 21
     8	0 0x5440 [0x18]: PERF_RECORD_BPF_EVENT bpf event with type 1, flags 0, id 22
  # bpftool prog
  13: cgroup_skb  tag 7be49e3934a125ba  gpl
	loaded_at 2019-01-19T09:09:43-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 13,14
  14: cgroup_skb  tag 2a142ef67aaad174  gpl
	loaded_at 2019-01-19T09:09:43-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 13,14
  15: cgroup_skb  tag 7be49e3934a125ba  gpl
	loaded_at 2019-01-19T09:09:43-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 15,16
  16: cgroup_skb  tag 2a142ef67aaad174  gpl
	loaded_at 2019-01-19T09:09:43-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 15,16
  17: cgroup_skb  tag 7be49e3934a125ba  gpl
	loaded_at 2019-01-19T09:09:44-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 17,18
  18: cgroup_skb  tag 2a142ef67aaad174  gpl
	loaded_at 2019-01-19T09:09:44-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 17,18
  21: cgroup_skb  tag 7be49e3934a125ba  gpl
	loaded_at 2019-01-19T09:09:45-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 21,22
  22: cgroup_skb  tag 2a142ef67aaad174  gpl
	loaded_at 2019-01-19T09:09:45-0300  uid 0
	xlated 296B  jited 229B  memlock 4096B  map_ids 21,22
  #

  # perf report -D | grep -B22 PERF_RECORD_KSYMBOL
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 ff 44 06 c0 ff ff ff ff  ......8..D......
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 37 62 65 34 39 65 33 39 33 34 61 31 32 35 62  _7be49e3934a125b
  .  0030:  61 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  a...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  7b e4 9e 39 34 a1 25 ba 00 00 00 00 00 00 00 00  {..94.%.........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x49d8 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc00644ff len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba
  --
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 48 6d 06 c0 ff ff ff ff  ......8.Hm......
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 32 61 31 34 32 65 66 36 37 61 61 61 64 31 37  _2a142ef67aaad17
  .  0030:  34 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  4...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  2a 14 2e f6 7a aa d1 74 00 00 00 00 00 00 00 00  *...z..t........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x4b28 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0066d48 len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174
  --
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 04 cf 03 c0 ff ff ff ff  ......8.........
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 37 62 65 34 39 65 33 39 33 34 61 31 32 35 62  _7be49e3934a125b
  .  0030:  61 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  a...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  7b e4 9e 39 34 a1 25 ba 00 00 00 00 00 00 00 00  {..94.%.........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x4c78 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc003cf04 len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba
  --
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 96 28 04 c0 ff ff ff ff  ......8..(......
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 32 61 31 34 32 65 66 36 37 61 61 61 64 31 37  _2a142ef67aaad17
  .  0030:  34 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  4...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  2a 14 2e f6 7a aa d1 74 00 00 00 00 00 00 00 00  *...z..t........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x4dc8 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0042896 len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174
  --
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 05 13 17 c0 ff ff ff ff  ......8.........
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 37 62 65 34 39 65 33 39 33 34 61 31 32 35 62  _7be49e3934a125b
  .  0030:  61 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  a...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  7b e4 9e 39 34 a1 25 ba 00 00 00 00 00 00 00 00  {..94.%.........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x4f18 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0171305 len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba
  --
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 0a 8c 23 c0 ff ff ff ff  ......8...#.....
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 32 61 31 34 32 65 66 36 37 61 61 61 64 31 37  _2a142ef67aaad17
  .  0030:  34 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  4...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  2a 14 2e f6 7a aa d1 74 00 00 00 00 00 00 00 00  *...z..t........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x5068 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0238c0a len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174
  --
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 2a a5 a4 c0 ff ff ff ff  ......8.*.......
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 37 62 65 34 39 65 33 39 33 34 61 31 32 35 62  _7be49e3934a125b
  .  0030:  61 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  a...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  7b e4 9e 39 34 a1 25 ba 00 00 00 00 00 00 00 00  {..94.%.........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x51b8 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0a4a52a len 229 type 1 flags 0x0 name bpf_prog_7be49e3934a125ba
  --
  . ... raw event: size 312 bytes
  .  0000:  11 00 00 00 00 00 38 01 9b c9 a4 c0 ff ff ff ff  ......8.........
  .  0010:  e5 00 00 00 01 00 00 00 62 70 66 5f 70 72 6f 67  ........bpf_prog
  .  0020:  5f 32 61 31 34 32 65 66 36 37 61 61 61 64 31 37  _2a142ef67aaad17
  .  0030:  34 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  4...............
   <SNIP zeroes>
  .  0110:  00 00 00 00 00 00 00 00 21 00 00 00 00 00 00 00  ........!.......
  .  0120:  2a 14 2e f6 7a aa d1 74 00 00 00 00 00 00 00 00  *...z..t........
  .  0130:  00 00 00 00 00 00 00 00                          ........

  0 0x5308 [0x138]: PERF_RECORD_KSYMBOL ksymbol event with addr ffffffffc0a4c99b len 229 type 1 flags 0x0 name bpf_prog_2a142ef67aaad174

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
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/20190117161521.1341602-8-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-record.c |   6 +
 tools/perf/util/bpf-event.c | 241 ++++++++++++++++++++++++++++++++++++
 tools/perf/util/bpf-event.h |  16 +++
 3 files changed, 263 insertions(+)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index deaf9b902094..88ea11d57c6f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -41,6 +41,7 @@
 #include "util/perf-hooks.h"
 #include "util/time-utils.h"
 #include "util/units.h"
+#include "util/bpf-event.h"
 #include "asm/bug.h"
 
 #include <errno.h>
@@ -1082,6 +1083,11 @@ static int record__synthesize(struct record *rec, bool tail)
 		return err;
 	}
 
+	err = perf_event__synthesize_bpf_events(tool, process_synthesized_event,
+						machine, opts);
+	if (err < 0)
+		pr_warning("Couldn't synthesize bpf events.\n");
+
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
 					    process_synthesized_event, opts->sample_address,
 					    1);
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 87004706874f..126f9728a756 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -1,10 +1,24 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <linux/btf.h>
 #include "bpf-event.h"
 #include "debug.h"
 #include "symbol.h"
 
+#define ptr_to_u64(ptr)    ((__u64)(unsigned long)(ptr))
+
+static int snprintf_hex(char *buf, size_t size, unsigned char *data, size_t len)
+{
+	int ret = 0;
+	size_t i;
+
+	for (i = 0; i < len; i++)
+		ret += snprintf(buf + ret, size - ret, "%02x", data[i]);
+	return ret;
+}
+
 int machine__process_bpf_event(struct machine *machine __maybe_unused,
 			       union perf_event *event,
 			       struct perf_sample *sample __maybe_unused)
@@ -13,3 +27,230 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused,
 		perf_event__fprintf_bpf_event(event, stdout);
 	return 0;
 }
+
+/*
+ * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf
+ * program. One PERF_RECORD_BPF_EVENT is generated for the program. And
+ * one PERF_RECORD_KSYMBOL is generated for each sub program.
+ *
+ * Returns:
+ *    0 for success;
+ *   -1 for failures;
+ *   -2 for lack of kernel support.
+ */
+static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
+					       perf_event__handler_t process,
+					       struct machine *machine,
+					       int fd,
+					       union perf_event *event,
+					       struct record_opts *opts)
+{
+	struct ksymbol_event *ksymbol_event = &event->ksymbol_event;
+	struct bpf_event *bpf_event = &event->bpf_event;
+	u32 sub_prog_cnt, i, func_info_rec_size;
+	u8 (*prog_tags)[BPF_TAG_SIZE] = NULL;
+	struct bpf_prog_info info = {};
+	u32 info_len = sizeof(info);
+	void *func_infos = NULL;
+	u64 *prog_addrs = NULL;
+	struct btf *btf = NULL;
+	u32 *prog_lens = NULL;
+	bool has_btf = false;
+	char errbuf[512];
+	int err = 0;
+
+	/* Call bpf_obj_get_info_by_fd() to get sizes of arrays */
+	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+
+	if (err) {
+		pr_debug("%s: failed to get BPF program info: %s, aborting\n",
+			 __func__, str_error_r(errno, errbuf, sizeof(errbuf)));
+		return -1;
+	}
+	if (info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+		pr_debug("%s: the kernel is too old, aborting\n", __func__);
+		return -2;
+	}
+
+	/* number of ksyms, func_lengths, and tags should match */
+	sub_prog_cnt = info.nr_jited_ksyms;
+	if (sub_prog_cnt != info.nr_prog_tags ||
+	    sub_prog_cnt != info.nr_jited_func_lens)
+		return -1;
+
+	/* check BTF func info support */
+	if (info.btf_id && info.nr_func_info && info.func_info_rec_size) {
+		/* btf func info number should be same as sub_prog_cnt */
+		if (sub_prog_cnt != info.nr_func_info) {
+			pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
+			return -1;
+		}
+		if (btf__get_from_id(info.btf_id, &btf)) {
+			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info.btf_id);
+			return -1;
+		}
+		func_info_rec_size = info.func_info_rec_size;
+		func_infos = calloc(sub_prog_cnt, func_info_rec_size);
+		if (!func_infos) {
+			pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__);
+			return -1;
+		}
+		has_btf = true;
+	}
+
+	/*
+	 * We need address, length, and tag for each sub program.
+	 * Allocate memory and call bpf_obj_get_info_by_fd() again
+	 */
+	prog_addrs = calloc(sub_prog_cnt, sizeof(u64));
+	if (!prog_addrs) {
+		pr_debug("%s: failed to allocate memory for prog_addrs, aborting\n", __func__);
+		goto out;
+	}
+	prog_lens = calloc(sub_prog_cnt, sizeof(u32));
+	if (!prog_lens) {
+		pr_debug("%s: failed to allocate memory for prog_lens, aborting\n", __func__);
+		goto out;
+	}
+	prog_tags = calloc(sub_prog_cnt, BPF_TAG_SIZE);
+	if (!prog_tags) {
+		pr_debug("%s: failed to allocate memory for prog_tags, aborting\n", __func__);
+		goto out;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.nr_jited_ksyms = sub_prog_cnt;
+	info.nr_jited_func_lens = sub_prog_cnt;
+	info.nr_prog_tags = sub_prog_cnt;
+	info.jited_ksyms = ptr_to_u64(prog_addrs);
+	info.jited_func_lens = ptr_to_u64(prog_lens);
+	info.prog_tags = ptr_to_u64(prog_tags);
+	info_len = sizeof(info);
+	if (has_btf) {
+		info.nr_func_info = sub_prog_cnt;
+		info.func_info_rec_size = func_info_rec_size;
+		info.func_info = ptr_to_u64(func_infos);
+	}
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (err) {
+		pr_debug("%s: failed to get BPF program info, aborting\n", __func__);
+		goto out;
+	}
+
+	/* Synthesize PERF_RECORD_KSYMBOL */
+	for (i = 0; i < sub_prog_cnt; i++) {
+		const struct bpf_func_info *finfo;
+		const char *short_name = NULL;
+		const struct btf_type *t;
+		int name_len;
+
+		*ksymbol_event = (struct ksymbol_event){
+			.header = {
+				.type = PERF_RECORD_KSYMBOL,
+				.size = sizeof(struct ksymbol_event),
+			},
+			.addr = prog_addrs[i],
+			.len = prog_lens[i],
+			.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+			.flags = 0,
+		};
+		name_len = snprintf(ksymbol_event->name, KSYM_NAME_LEN,
+				    "bpf_prog_");
+		name_len += snprintf_hex(ksymbol_event->name + name_len,
+					 KSYM_NAME_LEN - name_len,
+					 prog_tags[i], BPF_TAG_SIZE);
+		if (has_btf) {
+			finfo = func_infos + i * info.func_info_rec_size;
+			t = btf__type_by_id(btf, finfo->type_id);
+			short_name = btf__name_by_offset(btf, t->name_off);
+		} else if (i == 0 && sub_prog_cnt == 1) {
+			/* no subprog */
+			if (info.name[0])
+				short_name = info.name;
+		} else
+			short_name = "F";
+		if (short_name)
+			name_len += snprintf(ksymbol_event->name + name_len,
+					     KSYM_NAME_LEN - name_len,
+					     "_%s", short_name);
+
+		ksymbol_event->header.size += PERF_ALIGN(name_len + 1,
+							 sizeof(u64));
+		err = perf_tool__process_synth_event(tool, event,
+						     machine, process);
+	}
+
+	/* Synthesize PERF_RECORD_BPF_EVENT */
+	if (opts->bpf_event) {
+		*bpf_event = (struct bpf_event){
+			.header = {
+				.type = PERF_RECORD_BPF_EVENT,
+				.size = sizeof(struct bpf_event),
+			},
+			.type = PERF_BPF_EVENT_PROG_LOAD,
+			.flags = 0,
+			.id = info.id,
+		};
+		memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE);
+		err = perf_tool__process_synth_event(tool, event,
+						     machine, process);
+	}
+
+out:
+	free(prog_tags);
+	free(prog_lens);
+	free(prog_addrs);
+	free(func_infos);
+	free(btf);
+	return err ? -1 : 0;
+}
+
+int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      struct record_opts *opts)
+{
+	union perf_event *event;
+	__u32 id = 0;
+	int err;
+	int fd;
+
+	event = malloc(sizeof(event->bpf_event) + KSYM_NAME_LEN);
+	if (!event)
+		return -1;
+	while (true) {
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT) {
+				err = 0;
+				break;
+			}
+			pr_debug("%s: can't get next program: %s%s",
+				 __func__, strerror(errno),
+				 errno == EINVAL ? " -- kernel too old?" : "");
+			/* don't report error on old kernel */
+			err = (errno == EINVAL) ? 0 : -1;
+			break;
+		}
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0) {
+			pr_debug("%s: failed to get fd for prog_id %u\n",
+				 __func__, id);
+			continue;
+		}
+
+		err = perf_event__synthesize_one_bpf_prog(tool, process,
+							  machine, fd,
+							  event, opts);
+		close(fd);
+		if (err) {
+			/* do not return error for old kernel */
+			if (err == -2)
+				err = 0;
+			break;
+		}
+	}
+	free(event);
+	return err;
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index da0dfc035fc6..7890067e1a37 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -3,14 +3,22 @@
 #define __PERF_BPF_EVENT_H
 
 #include <linux/compiler.h>
+#include "event.h"
 
 struct machine;
 union perf_event;
 struct perf_sample;
+struct perf_tool;
+struct record_opts;
 
 #ifdef HAVE_LIBBPF_SUPPORT
 int machine__process_bpf_event(struct machine *machine, union perf_event *event,
 			       struct perf_sample *sample);
+
+int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      struct record_opts *opts);
 #else
 static inline int machine__process_bpf_event(struct machine *machine __maybe_unused,
 					     union perf_event *event __maybe_unused,
@@ -18,5 +26,13 @@ static inline int machine__process_bpf_event(struct machine *machine __maybe_unu
 {
 	return 0;
 }
+
+static inline int perf_event__synthesize_bpf_events(struct perf_tool *tool __maybe_unused,
+						    perf_event__handler_t process __maybe_unused,
+						    struct machine *machine __maybe_unused,
+						    struct record_opts *opts __maybe_unused)
+{
+	return 0;
+}
 #endif // HAVE_LIBBPF_SUPPORT
 #endif
-- 
2.20.1

[PATCH 21/24] perf top: Synthesize BPF events for pre-existing loaded BPF programs

[Arnaldo Carvalho de Melo]

From: Arnaldo Carvalho de Melo <acme@redhat.com>

So that we can resolve symbols and map names.

Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: http://lkml.kernel.org/r/20190117161521.1341602-9-songliubraving@fb.com
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-top.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index f64e312db787..5a486d4de56e 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -22,6 +22,7 @@
 #include "perf.h"
 
 #include "util/annotate.h"
+#include "util/bpf-event.h"
 #include "util/config.h"
 #include "util/color.h"
 #include "util/drv_configs.h"
@@ -1215,6 +1216,12 @@ static int __cmd_top(struct perf_top *top)
 
 	init_process_thread(top);
 
+	ret = perf_event__synthesize_bpf_events(&top->tool, perf_event__process,
+						&top->session->machines.host,
+						&top->record_opts);
+	if (ret < 0)
+		pr_warning("Couldn't synthesize bpf events.\n");
+
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
 				    top->evlist->threads, false,
 				    top->nr_threads_synthesize);
-- 
2.20.1

[PATCH 22/24] bpf: Add module name [bpf] to ksymbols for bpf programs

[Arnaldo Carvalho de Melo]

From: Song Liu <songliubraving@fb.com>

With this patch, /proc/kallsyms will show BPF programs as

  <addr> t bpf_prog_<tag>_<name> [bpf]

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Alexei Starovoitov <ast@kernel.org>
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/20190117161521.1341602-10-songliubraving@fb.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 kernel/kallsyms.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index f3a04994e063..14934afa9e68 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -494,7 +494,7 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
-	iter->module_name[0] = '\0';
+	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
 	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
 			       &iter->value, &iter->type,
-- 
2.20.1