* [PATCH v7 perf, bpf-next 1/8] perf, bpf: Introduce PERF_RECORD_KSYMBOL
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 2/8] sync tools/include/uapi/linux/perf_event.h Song Liu
` (7 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
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>
---
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..77b2560f2dc7 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 67ecac337374..dbcc90c79893 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
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v7 perf, bpf-next 2/8] sync tools/include/uapi/linux/perf_event.h
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 1/8] perf, bpf: Introduce PERF_RECORD_KSYMBOL Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 3/8] perf, bpf: introduce PERF_RECORD_BPF_EVENT Song Liu
` (6 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
sync changes for PERF_RECORD_KSYMBOL
Signed-off-by: Song Liu <songliubraving@fb.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 9de8780ac8d9..68c4da0227c5 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 */
@@ -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
--
2.17.1
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v7 perf, bpf-next 3/8] perf, bpf: introduce PERF_RECORD_BPF_EVENT
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 1/8] perf, bpf: Introduce PERF_RECORD_KSYMBOL Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 2/8] sync tools/include/uapi/linux/perf_event.h Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 4/8] sync tools/include/uapi/linux/perf_event.h Song Liu
` (5 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
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>
---
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 | 86 +++++++++++++++++++++++++++++++++
6 files changed, 130 insertions(+), 2 deletions(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 8c8544b375eb..bcb086ed01d4 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -955,6 +955,7 @@ 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 */
@@ -1010,6 +1011,12 @@ 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 77b2560f2dc7..0b539a2e21af 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1119,6 +1119,9 @@ 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 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);
@@ -1346,6 +1349,9 @@ 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_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 68c4da0227c5..8bd78a34e396 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 */
@@ -981,6 +982,25 @@ 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 */
};
@@ -992,6 +1012,13 @@ 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 38de580abcc2..5c6b0fe6fbf7 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -494,7 +494,7 @@ 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 0607db304def..4af63c8c95eb 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 dbcc90c79893..8a8fa1b066ff 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))
@@ -7744,6 +7747,87 @@ 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 int perf_event_bpf_get_name(char *name, int len, void *data)
+{
+ struct bpf_prog *prog = data;
+
+ bpf_get_prog_name(prog, name);
+ return 0;
+}
+
+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;
+
+ 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,
+ },
+ };
+
+ 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;
@@ -9996,6 +10080,8 @@ 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) {
/*
--
2.17.1
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v7 perf, bpf-next 4/8] sync tools/include/uapi/linux/perf_event.h
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
` (2 preceding siblings ...)
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 3/8] perf, bpf: introduce PERF_RECORD_BPF_EVENT Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 5/8] perf, bpf: emit PERF_RECORD_KSYMBOL for BPF program load/unload Song Liu
` (4 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
sync for PERF_RECORD_BPF_EVENT
Signed-off-by: Song Liu <songliubraving@fb.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 68c4da0227c5..8bd78a34e396 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 */
@@ -981,6 +982,25 @@ 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 */
};
@@ -992,6 +1012,13 @@ 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
--
2.17.1
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v7 perf, bpf-next 5/8] perf, bpf: emit PERF_RECORD_KSYMBOL for BPF program load/unload
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
` (3 preceding siblings ...)
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 4/8] sync tools/include/uapi/linux/perf_event.h Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL Song Liu
` (3 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
This patch enables emitting PERF_RECORD_KSYMBOL for BPF program load and
unload. A PERF_RECORD_KSYMBOL is issued for each BPF sub program.
Signed-off-by: Song Liu <songliubraving@fb.com>
---
kernel/events/core.c | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8a8fa1b066ff..023821605b8d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7798,6 +7798,30 @@ static int perf_event_bpf_get_name(char *name, int len, void *data)
return 0;
}
+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;
+ int i;
+
+ if (prog->aux->func_cnt == 0) {
+ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+ (u64)(unsigned long)prog->bpf_func,
+ prog->jited_len, unregister,
+ perf_event_bpf_get_name, prog);
+ } else {
+ for (i = 0; i < prog->aux->func_cnt; i++) {
+ struct bpf_prog *subprog = prog->aux->func[i];
+
+ perf_event_ksymbol(
+ PERF_RECORD_KSYMBOL_TYPE_BPF,
+ (u64)(unsigned long)subprog->bpf_func,
+ subprog->jited_len, unregister,
+ perf_event_bpf_get_name, subprog);
+ }
+ }
+}
+
void perf_event_bpf_event(struct bpf_prog *prog,
enum perf_bpf_event_type type,
u16 flags)
@@ -7808,6 +7832,16 @@ void perf_event_bpf_event(struct bpf_prog *prog,
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;
--
2.17.1
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
` (4 preceding siblings ...)
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 5/8] perf, bpf: emit PERF_RECORD_KSYMBOL for BPF program load/unload Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-14 17:11 ` Arnaldo Carvalho de Melo
2019-01-15 17:56 ` Arnaldo Carvalho de Melo
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 7/8] perf util: handle PERF_RECORD_BPF_EVENT Song Liu
` (2 subsequent siblings)
8 siblings, 2 replies; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
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 set perf_event_attr.ksymbol properly. The flag is
ON by default.
Signed-off-by: Song Liu <songliubraving@fb.com>
---
tools/perf/util/event.c | 21 +++++++++++++++
tools/perf/util/event.h | 20 ++++++++++++++
tools/perf/util/evsel.c | 9 +++++++
tools/perf/util/evsel.h | 1 +
tools/perf/util/machine.c | 57 +++++++++++++++++++++++++++++++++++++++
tools/perf/util/machine.h | 3 +++
tools/perf/util/session.c | 4 +++
tools/perf/util/tool.h | 4 ++-
8 files changed, 118 insertions(+), 1 deletion(-)
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..de34ce875648 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;
@@ -1955,6 +1959,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
perf_missing_features.exclude_guest = true;
pr_debug2("switching off exclude_guest, exclude_host\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;
} else if (!perf_missing_features.sample_id_all) {
perf_missing_features.sample_id_all = true;
pr_debug2("switching off sample_id_all\n");
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 6fcb3bce0442..1734ca027661 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -681,6 +681,61 @@ 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("bpf_prog");
+ 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, stderr);
+
+ 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 +1867,8 @@ 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 78a067777144..a9c98c3914ed 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -376,6 +376,8 @@ 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)
@@ -1305,6 +1307,8 @@ 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;
--
2.17.1
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL Song Liu
@ 2019-01-14 17:11 ` Arnaldo Carvalho de Melo
2019-01-15 17:56 ` Arnaldo Carvalho de Melo
1 sibling, 0 replies; 16+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-01-14 17:11 UTC (permalink / raw)
To: Song Liu; +Cc: linux-kernel, netdev, peterz, ast, daniel, kernel-team, dsahern
Em Thu, Jan 10, 2019 at 04:19:31PM -0800, Song Liu escreveu:
> 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 set perf_event_attr.ksymbol properly. The flag is
> ON by default.
>
> Signed-off-by: Song Liu <songliubraving@fb.com>
> ---
> tools/perf/util/event.c | 21 +++++++++++++++
> tools/perf/util/event.h | 20 ++++++++++++++
> tools/perf/util/evsel.c | 9 +++++++
> tools/perf/util/evsel.h | 1 +
> tools/perf/util/machine.c | 57 +++++++++++++++++++++++++++++++++++++++
> tools/perf/util/machine.h | 3 +++
> tools/perf/util/session.c | 4 +++
> tools/perf/util/tool.h | 4 ++-
> 8 files changed, 118 insertions(+), 1 deletion(-)
>
> 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..de34ce875648 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;
> @@ -1955,6 +1959,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
> perf_missing_features.exclude_guest = true;
> pr_debug2("switching off exclude_guest, exclude_host\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;
> } else if (!perf_missing_features.sample_id_all) {
> perf_missing_features.sample_id_all = true;
> pr_debug2("switching off sample_id_all\n");
> 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 6fcb3bce0442..1734ca027661 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -681,6 +681,61 @@ 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("bpf_prog");
> + 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, stderr);
This should be stdout, otherwise we get garbled output from 'perf report
-D', that is what sets dump_trace to true.
Ditto for the machine__process_bpf_event case, i.e. this patch, each
hunk applied to the respective patch introducing the handling of those
events:
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index ee60c8b1e636..b06cd1789f1f 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -24,7 +24,7 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused,
struct perf_sample *sample __maybe_unused)
{
if (dump_trace)
- perf_event__fprintf_bpf_event(event, stderr);
+ perf_event__fprintf_bpf_event(event, stdout);
return 0;
}
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 292992d7b504..34bd8018e45a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -729,7 +729,7 @@ int machine__process_ksymbol(struct machine *machine __maybe_unused,
struct perf_sample *sample)
{
if (dump_trace)
- perf_event__fprintf_ksymbol(event, stderr);
+ perf_event__fprintf_ksymbol(event, stdout);
if (event->ksymbol_event.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
return machine__process_ksymbol_unregister(machine, event,
> +
> + 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 +1867,8 @@ 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 78a067777144..a9c98c3914ed 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -376,6 +376,8 @@ 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)
> @@ -1305,6 +1307,8 @@ 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;
> --
> 2.17.1
--
- Arnaldo
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL Song Liu
2019-01-14 17:11 ` Arnaldo Carvalho de Melo
@ 2019-01-15 17:56 ` Arnaldo Carvalho de Melo
2019-01-15 19:58 ` Song Liu
1 sibling, 1 reply; 16+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-01-15 17:56 UTC (permalink / raw)
To: Song Liu; +Cc: linux-kernel, netdev, peterz, ast, daniel, kernel-team, dsahern
Em Thu, Jan 10, 2019 at 04:19:31PM -0800, Song Liu escreveu:
> 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 set perf_event_attr.ksymbol properly. The flag is
> ON by default.
>
> Signed-off-by: Song Liu <songliubraving@fb.com>
> ---
> tools/perf/util/event.c | 21 +++++++++++++++
> tools/perf/util/event.h | 20 ++++++++++++++
> tools/perf/util/evsel.c | 9 +++++++
> tools/perf/util/evsel.h | 1 +
> tools/perf/util/machine.c | 57 +++++++++++++++++++++++++++++++++++++++
> tools/perf/util/machine.h | 3 +++
> tools/perf/util/session.c | 4 +++
> tools/perf/util/tool.h | 4 ++-
> 8 files changed, 118 insertions(+), 1 deletion(-)
>
> 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..de34ce875648 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;
> @@ -1955,6 +1959,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
> perf_missing_features.exclude_guest = true;
> pr_debug2("switching off exclude_guest, exclude_host\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;
Please move this to the top, see the comment there:
if (err != -EINVAL || cpu > 0 || thread > 0)
goto out_close;
/*
* 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) {
perf_missing_features.write_backward = true;
pr_debug2("switching off write_backward\n");
goto out_close;
} else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
perf_missing_features.clockid_wrong = true;
pr_debug2("switching off clockid\n");
goto fallback_missing_features;
So that when one asks for, say, attr.write_backward _and_ attr.ksymbol,
we first disable attr.ksymbol, to try the fallback, as it was added
after attr.write_backward.
Think about an older kernel where attr.write_backward is present but not
attr.ksymbol.
Ditto for the attr.bpf_event.
> } else if (!perf_missing_features.sample_id_all) {
> perf_missing_features.sample_id_all = true;
> pr_debug2("switching off sample_id_all\n");
> 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 6fcb3bce0442..1734ca027661 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -681,6 +681,61 @@ 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("bpf_prog");
> + 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, stderr);
> +
> + 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 +1867,8 @@ 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 78a067777144..a9c98c3914ed 100644
> --- a/tools/perf/util/session.c
> +++ b/tools/perf/util/session.c
> @@ -376,6 +376,8 @@ 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)
> @@ -1305,6 +1307,8 @@ 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;
> --
> 2.17.1
--
- Arnaldo
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL
2019-01-15 17:56 ` Arnaldo Carvalho de Melo
@ 2019-01-15 19:58 ` Song Liu
0 siblings, 0 replies; 16+ messages in thread
From: Song Liu @ 2019-01-15 19:58 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, netdev, peterz, ast, daniel, Kernel Team, dsahern
> On Jan 15, 2019, at 9:56 AM, Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
>
> Em Thu, Jan 10, 2019 at 04:19:31PM -0800, Song Liu escreveu:
>> 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 set perf_event_attr.ksymbol properly. The flag is
>> ON by default.
>>
>> Signed-off-by: Song Liu <songliubraving@fb.com>
>> ---
>> tools/perf/util/event.c | 21 +++++++++++++++
>> tools/perf/util/event.h | 20 ++++++++++++++
>> tools/perf/util/evsel.c | 9 +++++++
>> tools/perf/util/evsel.h | 1 +
>> tools/perf/util/machine.c | 57 +++++++++++++++++++++++++++++++++++++++
>> tools/perf/util/machine.h | 3 +++
>> tools/perf/util/session.c | 4 +++
>> tools/perf/util/tool.h | 4 ++-
>> 8 files changed, 118 insertions(+), 1 deletion(-)
>>
>> 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..de34ce875648 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;
>> @@ -1955,6 +1959,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
>> perf_missing_features.exclude_guest = true;
>> pr_debug2("switching off exclude_guest, exclude_host\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;
>
>
> Please move this to the top, see the comment there:
>
> if (err != -EINVAL || cpu > 0 || thread > 0)
> goto out_close;
>
> /*
> * 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) {
> perf_missing_features.write_backward = true;
> pr_debug2("switching off write_backward\n");
> goto out_close;
> } else if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
> perf_missing_features.clockid_wrong = true;
> pr_debug2("switching off clockid\n");
> goto fallback_missing_features;
>
>
> So that when one asks for, say, attr.write_backward _and_ attr.ksymbol,
> we first disable attr.ksymbol, to try the fallback, as it was added
> after attr.write_backward.
>
> Think about an older kernel where attr.write_backward is present but not
> attr.ksymbol.
>
> Ditto for the attr.bpf_event.
>
Thanks Arnaldo!
I will include the fix in next version.
Song
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v7 perf, bpf-next 7/8] perf util: handle PERF_RECORD_BPF_EVENT
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
` (5 preceding siblings ...)
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 6/8] perf util: handle PERF_RECORD_KSYMBOL Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-14 17:12 ` Arnaldo Carvalho de Melo
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 8/8] perf tools: synthesize PERF_RECORD_* for loaded BPF programs Song Liu
2019-01-11 16:26 ` [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Arnaldo Carvalho de Melo
8 siblings, 1 reply; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
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.
Signed-off-by: Song Liu <songliubraving@fb.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 | 11 +++++++++++
tools/perf/util/event.c | 20 ++++++++++++++++++++
tools/perf/util/event.h | 16 ++++++++++++++++
tools/perf/util/evsel.c | 10 ++++++++++
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, 86 insertions(+), 1 deletion(-)
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 af72be7f5b3b..fa8305390315 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -152,6 +152,8 @@ 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..f24f75506f51
--- /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, stderr);
+ return 0;
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
new file mode 100644
index 000000000000..d5ca355dd298
--- /dev/null
+++ b/tools/perf/util/bpf-event.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_BPF_EVENT_H
+#define __PERF_BPF_EVENT_H
+
+#include "machine.h"
+
+int machine__process_bpf_event(struct machine *machine,
+ union perf_event *event,
+ struct perf_sample *sample);
+
+#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 de34ce875648..1e8b7d2897e3 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;
@@ -1964,6 +1969,11 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
perf_missing_features.ksymbol = true;
pr_debug2("switching off ksymbol\n");
goto fallback_missing_features;
+ } else 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.sample_id_all) {
perf_missing_features.sample_id_all = true;
pr_debug2("switching off sample_id_all\n");
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 1734ca027661..8c0b16382226 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>
@@ -1869,6 +1870,8 @@ 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 a9c98c3914ed..dac8c9b62036 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -378,6 +378,8 @@ 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)
@@ -1309,6 +1311,8 @@ 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;
--
2.17.1
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v7 perf, bpf-next 7/8] perf util: handle PERF_RECORD_BPF_EVENT
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 7/8] perf util: handle PERF_RECORD_BPF_EVENT Song Liu
@ 2019-01-14 17:12 ` Arnaldo Carvalho de Melo
0 siblings, 0 replies; 16+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-01-14 17:12 UTC (permalink / raw)
To: Song Liu; +Cc: linux-kernel, netdev, peterz, ast, daniel, kernel-team, dsahern
Em Thu, Jan 10, 2019 at 04:19:32PM -0800, Song Liu escreveu:
> 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.
>
> Signed-off-by: Song Liu <songliubraving@fb.com>
Please add the following patch to your tree for the next revision:
commit 11860cb0ca8a5013c4b9dd8654dccf485ad7a61c
Author: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon Jan 14 12:19:34 2019 -0300
perf top: Synthesize BPF events for pre-existing loaded BPF programs
So that we can resolve symbols and map names.
Cc: Song Liu <songliubraving@fb.com>
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: kernel-team@fb.com
Cc: netdev@vger.kernel.org
Link: https://lkml.kernel.org/n/tip-h3loibff6htedj43q7uinon0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
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);
^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v7 perf, bpf-next 8/8] perf tools: synthesize PERF_RECORD_* for loaded BPF programs
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
` (6 preceding siblings ...)
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 7/8] perf util: handle PERF_RECORD_BPF_EVENT Song Liu
@ 2019-01-11 0:19 ` Song Liu
2019-01-11 18:44 ` Arnaldo Carvalho de Melo
2019-01-11 16:26 ` [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Arnaldo Carvalho de Melo
8 siblings, 1 reply; 16+ messages in thread
From: Song Liu @ 2019-01-11 0:19 UTC (permalink / raw)
To: linux-kernel, netdev
Cc: Song Liu, peterz, acme, ast, daniel, kernel-team, dsahern
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.
Signed-off-by: Song Liu <songliubraving@fb.com>
---
tools/perf/builtin-record.c | 6 ++
tools/perf/util/bpf-event.c | 205 ++++++++++++++++++++++++++++++++++++
tools/perf/util/bpf-event.h | 5 +
3 files changed, 216 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 f24f75506f51..ee60c8b1e636 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 +27,194 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused,
perf_event__fprintf_bpf_event(event, stderr);
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.
+ */
+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;
+ 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 || info_len < 192 /* need field prog_tags */)
+ return -1;
+
+ /* 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)
+ return -1;
+ if (btf__get_from_id(info.btf_id, &btf))
+ return -1;
+ func_info_rec_size = info.func_info_rec_size;
+ func_infos = malloc(sub_prog_cnt * func_info_rec_size);
+ if (!func_infos)
+ 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 = (u64 *)malloc(sizeof(u64) * sub_prog_cnt);
+ prog_lens = (u32 *)malloc(sizeof(u64) * sub_prog_cnt);
+ prog_tags = malloc(sizeof(u8) * BPF_TAG_SIZE * sub_prog_cnt);
+
+ err = !prog_addrs || !prog_lens || !prog_tags;
+ if (err)
+ 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)
+ 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_err("can't get next program: %s%s",
+ strerror(errno),
+ errno == EINVAL ? " -- kernel too old?" : "");
+ err = -1;
+ break;
+ }
+ fd = bpf_prog_get_fd_by_id(id);
+ if (fd < 0) {
+ pr_debug("Failed to get fd for prog_id %u\n", id);
+ continue;
+ }
+
+ err = perf_event__synthesize_one_bpf_prog(
+ tool, process, machine, fd, event, opts);
+ close(fd);
+ if (err)
+ break;
+ }
+ free(event);
+ return err;
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
index d5ca355dd298..38aee4040f12 100644
--- a/tools/perf/util/bpf-event.h
+++ b/tools/perf/util/bpf-event.h
@@ -8,4 +8,9 @@ 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);
+
#endif
--
2.17.1
^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v7 perf, bpf-next 8/8] perf tools: synthesize PERF_RECORD_* for loaded BPF programs
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 8/8] perf tools: synthesize PERF_RECORD_* for loaded BPF programs Song Liu
@ 2019-01-11 18:44 ` Arnaldo Carvalho de Melo
2019-01-11 19:23 ` Song Liu
0 siblings, 1 reply; 16+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-01-11 18:44 UTC (permalink / raw)
To: Song Liu; +Cc: linux-kernel, netdev, peterz, ast, daniel, kernel-team, dsahern
Em Thu, Jan 10, 2019 at 04:19:33PM -0800, Song Liu escreveu:
> 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.
>
> Signed-off-by: Song Liu <songliubraving@fb.com>
> ---
> tools/perf/builtin-record.c | 6 ++
> tools/perf/util/bpf-event.c | 205 ++++++++++++++++++++++++++++++++++++
> tools/perf/util/bpf-event.h | 5 +
> 3 files changed, 216 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");
> +
There should be no warnings on older systems, I build a kernel and tools
with your changes and then, before rebooting, I tried:
[root@quaco ~]# perf record ls
Couldn't synthesize bpf events.
<SNIP>
[root@quaco ~]# uname -a
Linux quaco 4.19.13-300.fc29.x86_64 #1 SMP Sat Dec 29 22:54:28 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
[root@quaco ~]#
At most this should be a pr_debug(), but then it should check if the
system is bpf capable and if not only warn if the user explicitely asked
for bpf events.
- Arnaldo
> 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 f24f75506f51..ee60c8b1e636 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 +27,194 @@ int machine__process_bpf_event(struct machine *machine __maybe_unused,
> perf_event__fprintf_bpf_event(event, stderr);
> 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.
> + */
> +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;
> + 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 || info_len < 192 /* need field prog_tags */)
> + return -1;
> +
> + /* 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)
> + return -1;
> + if (btf__get_from_id(info.btf_id, &btf))
> + return -1;
> + func_info_rec_size = info.func_info_rec_size;
> + func_infos = malloc(sub_prog_cnt * func_info_rec_size);
> + if (!func_infos)
> + 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 = (u64 *)malloc(sizeof(u64) * sub_prog_cnt);
> + prog_lens = (u32 *)malloc(sizeof(u64) * sub_prog_cnt);
> + prog_tags = malloc(sizeof(u8) * BPF_TAG_SIZE * sub_prog_cnt);
> +
> + err = !prog_addrs || !prog_lens || !prog_tags;
> + if (err)
> + 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)
> + 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_err("can't get next program: %s%s",
> + strerror(errno),
> + errno == EINVAL ? " -- kernel too old?" : "");
> + err = -1;
> + break;
> + }
> + fd = bpf_prog_get_fd_by_id(id);
> + if (fd < 0) {
> + pr_debug("Failed to get fd for prog_id %u\n", id);
> + continue;
> + }
> +
> + err = perf_event__synthesize_one_bpf_prog(
> + tool, process, machine, fd, event, opts);
> + close(fd);
> + if (err)
> + break;
> + }
> + free(event);
> + return err;
> +}
> diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
> index d5ca355dd298..38aee4040f12 100644
> --- a/tools/perf/util/bpf-event.h
> +++ b/tools/perf/util/bpf-event.h
> @@ -8,4 +8,9 @@ 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);
> +
> #endif
> --
> 2.17.1
--
- Arnaldo
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v7 perf, bpf-next 8/8] perf tools: synthesize PERF_RECORD_* for loaded BPF programs
2019-01-11 18:44 ` Arnaldo Carvalho de Melo
@ 2019-01-11 19:23 ` Song Liu
0 siblings, 0 replies; 16+ messages in thread
From: Song Liu @ 2019-01-11 19:23 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: lkml, netdev, peterz, ast, daniel, Kernel Team, dsahern
> On Jan 11, 2019, at 10:44 AM, Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
>
> Em Thu, Jan 10, 2019 at 04:19:33PM -0800, Song Liu escreveu:
>> 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.
>>
>> Signed-off-by: Song Liu <songliubraving@fb.com>
>> ---
>> tools/perf/builtin-record.c | 6 ++
>> tools/perf/util/bpf-event.c | 205 ++++++++++++++++++++++++++++++++++++
>> tools/perf/util/bpf-event.h | 5 +
>> 3 files changed, 216 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");
>> +
>
> There should be no warnings on older systems, I build a kernel and tools
> with your changes and then, before rebooting, I tried:
>
> [root@quaco ~]# perf record ls
> Couldn't synthesize bpf events.
> <SNIP>
> [root@quaco ~]# uname -a
> Linux quaco 4.19.13-300.fc29.x86_64 #1 SMP Sat Dec 29 22:54:28 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
> [root@quaco ~]#
>
> At most this should be a pr_debug(), but then it should check if the
> system is bpf capable and if not only warn if the user explicitely asked
> for bpf events.
Thanks Arnaldo! I will fix it in the next version.
Song
^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs
2019-01-11 0:19 [PATCH v7 perf, bpf-next 0/8] reveal invisible bpf programs Song Liu
` (7 preceding siblings ...)
2019-01-11 0:19 ` [PATCH v7 perf, bpf-next 8/8] perf tools: synthesize PERF_RECORD_* for loaded BPF programs Song Liu
@ 2019-01-11 16:26 ` Arnaldo Carvalho de Melo
8 siblings, 0 replies; 16+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-01-11 16:26 UTC (permalink / raw)
To: Song Liu; +Cc: linux-kernel, netdev, peterz, ast, daniel, kernel-team, dsahern
Em Thu, Jan 10, 2019 at 04:19:25PM -0800, Song Liu escreveu:
> This set catches symbol for all bpf programs loaded/unloaded
> before/during/after perf-record run PERF_RECORD_KSYMBOL and
> PERF_RECORD_BPF_EVENT.
>
> PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT includes key information
> of a bpf program load and unload. They are sent through perf ringbuffer,
> and stored in perf.data. PERF_RECORD_KSYMBOL includes basic information
> for simple profiling. It is ON by default. PERF_RECORD_BPF_EVENT is
> used to gather more information of the bpf program. It is necessary for
> perf-annotate of bpf programs.
>
> Before this patch, perf-report will not be able to recover symbols of
> bpf programs once the programs are unloaded.
>
> This is to follow up Alexei's early effort [2] to show bpf programs via
> mmap events.
>
> Thanks,
> Song
>
> Changes v6 -> PATCH v7:
> 1. Split "[3/7] introduce PERF_RECORD_BPF_EVENT" into two commits:
> [3/8] introduce PERF_RECORD_BPF_EVENT
> [5/8] emit PERF_RECORD_KSYMBOL for BPF program load/unload
Thanks, I'm trying now to build a kernel/tools combo to test this.
> Changes v5 -> PATCH v6:
> 1. Reduce len in PERF_RECORD_KSYMBOL from u64 to u32. Use the 32 free bits
> for ksym_type (u16) and flags (u16).
>
> Changes v4 -> PATCH v5:
> 1. Fixed build error reported by kbuild test bot.
>
> Changes v3 -> PATCH v4:
> 1. Split information about bpf program into PERF_RECORD_KSYMBOL (with
> name, addr, len); and PERF_RECORD_BPF_EVENT PERF_RECORD_BPF_EVENT
> (with id, tag);
> 2. Split the implementation in kernel and user space.
>
> Changes v2 -> PATCH v3:
> 1. Rebase on bpf-next tree, and on top of BPF sub program tag patches [1]
> for latest information in bpf_prog_info.
> 2. Complete handling and synthesizing PERF_RECORD_BPF_EVENT in perf.
>
> Changes v1 -> PATCH v2:
> 1. Only 3 of the 5 patches in v1, to focus on ABI first;
> 2. Generate PERF_RECORD_BPF_EVENT per bpf sub program instead of per prog;
> 3. Modify PERF_RECORD_BPF_EVENT with more details (addr, len, name),
> so that it can be used for basic profiling without calling sys_bpf.
>
> Changes RFC -> PATCH v1:
> 1. In perf-record, poll vip events in a separate thread;
> 2. Add tag to bpf prog name;
> 3. Small refactorings.
>
> [1] https://patchwork.ozlabs.org/project/netdev/list/?series=81037
> [2] https://www.spinics.net/lists/netdev/msg524232.html
>
> Song Liu (8):
> perf, bpf: Introduce PERF_RECORD_KSYMBOL
> sync tools/include/uapi/linux/perf_event.h
> perf, bpf: introduce PERF_RECORD_BPF_EVENT
> sync tools/include/uapi/linux/perf_event.h
> perf, bpf: emit PERF_RECORD_KSYMBOL for BPF program load/unload
> perf util: handle PERF_RECORD_KSYMBOL
> perf util: handle PERF_RECORD_BPF_EVENT
> perf tools: synthesize PERF_RECORD_* for loaded BPF programs
>
> include/linux/filter.h | 7 +
> include/linux/perf_event.h | 19 +++
> include/uapi/linux/perf_event.h | 53 ++++++-
> kernel/bpf/core.c | 2 +-
> kernel/bpf/syscall.c | 2 +
> kernel/events/core.c | 218 ++++++++++++++++++++++++-
> tools/include/uapi/linux/perf_event.h | 53 ++++++-
> tools/perf/builtin-record.c | 7 +
> tools/perf/perf.h | 1 +
> tools/perf/util/Build | 2 +
> tools/perf/util/bpf-event.c | 220 ++++++++++++++++++++++++++
> tools/perf/util/bpf-event.h | 16 ++
> tools/perf/util/event.c | 41 +++++
> tools/perf/util/event.h | 36 +++++
> tools/perf/util/evsel.c | 19 +++
> tools/perf/util/evsel.h | 2 +
> tools/perf/util/machine.c | 60 +++++++
> tools/perf/util/machine.h | 3 +
> tools/perf/util/session.c | 8 +
> tools/perf/util/tool.h | 5 +-
> 20 files changed, 769 insertions(+), 5 deletions(-)
> create mode 100644 tools/perf/util/bpf-event.c
> create mode 100644 tools/perf/util/bpf-event.h
>
> --
> 2.17.1
--
- Arnaldo
^ permalink raw reply [flat|nested] 16+ messages in thread