Merge tag 'perf-core-for-mingo-5.0-20190121' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

BPF:

  Song Liu:

  - Introduce PERF_RECORD_KSYMBOL to allow tooling to notice the addition
    of new kernel symbols and be able to resolve samples in such symbols.

  - Introduce PERF_RECORD_BPF_EVENT to notify tooling about the loading
    and unloading of BPF programs, making them visible and allowing for
    the request of further information to allow for things like annotation.

  - Change the userspace perf tools to handle those new events and to
    synthesize them for pre-existing loaded BPF programs.

Kernel:

  Arnaldo Carvalho de Melo:

  - Make perf_event_output() propagate the output() return, allowing
    users to check for -ENOSPC in the ring buffer.

perf report:

  Thomas Richter:

  - Display arch specific diagnostic counter sets, starting with s390
    diagnostic counter sets.

perf session:

  Jiri Olsa:

  - Introduce a reader object to prep for multithreaded processing
    of recorded events.

Misc:

  Rasmus Villemoes:

  - Replace automatic const char[] variables by statics, to avoid
    initializing them at runtime, instead having them in .rodata,
    reducing code size.

  YueHaibing:

  - Remove duplicated workqueue.h include from perf_event.h

  Brajeswar Ghosh:

  - Remove some more duplicated headers.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

45 files changed, 1358 insertions, 125 deletions

diff --git a/include/linux/filter.h b/include/linux/filter.h
index ad106d845b22..d531d4250bff 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -951,6 +951,7 @@ bpf_address_lookup(unsigned long addr, unsigned long *size,
 
 void bpf_prog_kallsyms_add(struct bpf_prog *fp);
 void bpf_prog_kallsyms_del(struct bpf_prog *fp);
+void bpf_get_prog_name(const struct bpf_prog *prog, char *sym);
 
 #else /* CONFIG_BPF_JIT */
 
@@ -1006,6 +1007,12 @@ static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp)
 static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 {
 }
+
+static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+{
+	sym[0] = '\0';
+}
+
 #endif /* CONFIG_BPF_JIT */
 
 void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index cec02dc63b51..a79e59fc3b7d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -53,7 +53,6 @@ struct perf_guest_info_callbacks {
 #include <linux/atomic.h>
 #include <linux/sysfs.h>
 #include <linux/perf_regs.h>
-#include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <asm/local.h>
 
@@ -979,9 +978,9 @@ extern void perf_event_output_forward(struct perf_event *event,
 extern void perf_event_output_backward(struct perf_event *event,
 				       struct perf_sample_data *data,
 				       struct pt_regs *regs);
-extern void perf_event_output(struct perf_event *event,
-			      struct perf_sample_data *data,
-			      struct pt_regs *regs);
+extern int perf_event_output(struct perf_event *event,
+			     struct perf_sample_data *data,
+			     struct pt_regs *regs);
 
 static inline bool
 is_default_overflow_handler(struct perf_event *event)
@@ -1123,6 +1122,13 @@ static inline void perf_event_task_sched_out(struct task_struct *prev,
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
+
+extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
+			       bool unregister, const char *sym);
+extern 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);
 extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
@@ -1343,6 +1349,13 @@ static inline int perf_unregister_guest_info_callbacks
 (struct perf_guest_info_callbacks *callbacks)				{ return 0; }
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
+
+typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data);
+static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len,
+				      bool unregister, const char *sym)	{ }
+static inline void perf_event_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 ea19b5d491bf..7198ddd0c6b1 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -372,7 +372,9 @@ 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 */
+				bpf_event      :  1, /* include bpf events */
+				__reserved_1   : 33;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -963,9 +965,58 @@ 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,
+
+	/*
+	 * 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 */
 };
 
+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)
+
+enum perf_bpf_event_type {
+	PERF_BPF_EVENT_UNKNOWN		= 0,
+	PERF_BPF_EVENT_PROG_LOAD	= 1,
+	PERF_BPF_EVENT_PROG_UNLOAD	= 2,
+	PERF_BPF_EVENT_MAX,		/* non-ABI */
+};
+
 #define PERF_MAX_STACK_DEPTH		127
 #define PERF_MAX_CONTEXTS_PER_STACK	  8
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f908b9356025..19c49313c709 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -495,7 +495,7 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog,
 	*symbol_end   = addr + hdr->pages * PAGE_SIZE;
 }
 
-static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
+void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 {
 	const char *end = sym + KSYM_NAME_LEN;
 	const struct btf_type *type;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b155cd17c1bd..30ebd085790b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1211,6 +1211,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
+		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
 		bpf_prog_kallsyms_del_all(prog);
@@ -1554,6 +1555,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	}
 
 	bpf_prog_kallsyms_add(prog);
+	perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);
 	return err;
 
 free_used_maps:
diff --git a/kernel/events/core.c b/kernel/events/core.c
index fbe59b793b36..236bb8ddb7bc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -385,6 +385,8 @@ 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 atomic_t nr_bpf_events __read_mostly;
 
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
@@ -4235,7 +4237,7 @@ 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 +4307,10 @@ 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 (event->attr.bpf_event)
+		atomic_dec(&nr_bpf_events);
 
 	if (dec) {
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
@@ -6489,7 +6495,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->phys_addr = perf_virt_to_phys(data->addr);
 }
 
-static __always_inline void
+static __always_inline int
 __perf_event_output(struct perf_event *event,
 		    struct perf_sample_data *data,
 		    struct pt_regs *regs,
@@ -6499,13 +6505,15 @@ __perf_event_output(struct perf_event *event,
 {
 	struct perf_output_handle handle;
 	struct perf_event_header header;
+	int err;
 
 	/* protect the callchain buffers */
 	rcu_read_lock();
 
 	perf_prepare_sample(&header, data, event, regs);
 
-	if (output_begin(&handle, event, header.size))
+	err = output_begin(&handle, event, header.size);
+	if (err)
 		goto exit;
 
 	perf_output_sample(&handle, &header, data, event);
@@ -6514,6 +6522,7 @@ __perf_event_output(struct perf_event *event,
 
 exit:
 	rcu_read_unlock();
+	return err;
 }
 
 void
@@ -6532,12 +6541,12 @@ perf_event_output_backward(struct perf_event *event,
 	__perf_event_output(event, data, regs, perf_output_begin_backward);
 }
 
-void
+int
 perf_event_output(struct perf_event *event,
 		  struct perf_sample_data *data,
 		  struct pt_regs *regs)
 {
-	__perf_event_output(event, data, regs, perf_output_begin);
+	return __perf_event_output(event, data, regs, perf_output_begin);
 }
 
 /*
@@ -7650,6 +7659,207 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 	perf_output_end(&handle);
 }
 
+/*
+ * ksymbol register/unregister tracking
+ */
+
+struct perf_ksymbol_event {
+	const char	*name;
+	int		name_len;
+	struct {
+		struct perf_event_header        header;
+		u64				addr;
+		u32				len;
+		u16				ksym_type;
+		u16				flags;
+	} event_id;
+};
+
+static int perf_event_ksymbol_match(struct perf_event *event)
+{
+	return event->attr.ksymbol;
+}
+
+static void perf_event_ksymbol_output(struct perf_event *event, void *data)
+{
+	struct perf_ksymbol_event *ksymbol_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_ksymbol_match(event))
+		return;
+
+	perf_event_header__init_id(&ksymbol_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				ksymbol_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, ksymbol_event->event_id);
+	__output_copy(&handle, ksymbol_event->name, ksymbol_event->name_len);
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister,
+			const char *sym)
+{
+	struct perf_ksymbol_event ksymbol_event;
+	char name[KSYM_NAME_LEN];
+	u16 flags = 0;
+	int name_len;
+
+	if (!atomic_read(&nr_ksymbol_events))
+		return;
+
+	if (ksym_type >= PERF_RECORD_KSYMBOL_TYPE_MAX ||
+	    ksym_type == PERF_RECORD_KSYMBOL_TYPE_UNKNOWN)
+		goto err;
+
+	strlcpy(name, sym, KSYM_NAME_LEN);
+	name_len = strlen(name) + 1;
+	while (!IS_ALIGNED(name_len, sizeof(u64)))
+		name[name_len++] = '\0';
+	BUILD_BUG_ON(KSYM_NAME_LEN % sizeof(u64));
+
+	if (unregister)
+		flags |= PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER;
+
+	ksymbol_event = (struct perf_ksymbol_event){
+		.name = name,
+		.name_len = name_len,
+		.event_id = {
+			.header = {
+				.type = PERF_RECORD_KSYMBOL,
+				.size = sizeof(ksymbol_event.event_id) +
+					name_len,
+			},
+			.addr = addr,
+			.len = len,
+			.ksym_type = ksym_type,
+			.flags = flags,
+		},
+	};
+
+	perf_iterate_sb(perf_event_ksymbol_output, &ksymbol_event, NULL);
+	return;
+err:
+	WARN_ONCE(1, "%s: Invalid KSYMBOL type 0x%x\n", __func__, ksym_type);
+}
+
+/*
+ * bpf program load/unload tracking
+ */
+
+struct perf_bpf_event {
+	struct bpf_prog	*prog;
+	struct {
+		struct perf_event_header        header;
+		u16				type;
+		u16				flags;
+		u32				id;
+		u8				tag[BPF_TAG_SIZE];
+	} event_id;
+};
+
+static int perf_event_bpf_match(struct perf_event *event)
+{
+	return event->attr.bpf_event;
+}
+
+static void perf_event_bpf_output(struct perf_event *event, void *data)
+{
+	struct perf_bpf_event *bpf_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	if (!perf_event_bpf_match(event))
+		return;
+
+	perf_event_header__init_id(&bpf_event->event_id.header,
+				   &sample, event);
+	ret = perf_output_begin(&handle, event,
+				bpf_event->event_id.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, bpf_event->event_id);
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+}
+
+static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
+					 enum perf_bpf_event_type type)
+{
+	bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
+	char sym[KSYM_NAME_LEN];
+	int i;
+
+	if (prog->aux->func_cnt == 0) {
+		bpf_get_prog_name(prog, sym);
+		perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+				   (u64)(unsigned long)prog->bpf_func,
+				   prog->jited_len, unregister, sym);
+	} else {
+		for (i = 0; i < prog->aux->func_cnt; i++) {
+			struct bpf_prog *subprog = prog->aux->func[i];
+
+			bpf_get_prog_name(subprog, sym);
+			perf_event_ksymbol(
+				PERF_RECORD_KSYMBOL_TYPE_BPF,
+				(u64)(unsigned long)subprog->bpf_func,
+				subprog->jited_len, unregister, sym);
+		}
+	}
+}
+
+void perf_event_bpf_event(struct bpf_prog *prog,
+			  enum perf_bpf_event_type type,
+			  u16 flags)
+{
+	struct perf_bpf_event bpf_event;
+
+	if (type <= PERF_BPF_EVENT_UNKNOWN ||
+	    type >= PERF_BPF_EVENT_MAX)
+		return;
+
+	switch (type) {
+	case PERF_BPF_EVENT_PROG_LOAD:
+	case PERF_BPF_EVENT_PROG_UNLOAD:
+		if (atomic_read(&nr_ksymbol_events))
+			perf_event_bpf_emit_ksymbols(prog, type);
+		break;
+	default:
+		break;
+	}
+
+	if (!atomic_read(&nr_bpf_events))
+		return;
+
+	bpf_event = (struct perf_bpf_event){
+		.prog = prog,
+		.event_id = {
+			.header = {
+				.type = PERF_RECORD_BPF_EVENT,
+				.size = sizeof(bpf_event.event_id),
+			},
+			.type = type,
+			.flags = flags,
+			.id = prog->aux->id,
+		},
+	};
+
+	BUILD_BUG_ON(BPF_TAG_SIZE % sizeof(u64));
+
+	memcpy(bpf_event.event_id.tag, prog->tag, BPF_TAG_SIZE);
+	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
+}
+
 void perf_event_itrace_started(struct perf_event *event)
 {
 	event->attach_state |= PERF_ATTACH_ITRACE;
@@ -9909,6 +10119,10 @@ 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 (event->attr.bpf_event)
+		atomic_inc(&nr_bpf_events);
 
 	if (inc) {
 		/*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index f3a04994e063..14934afa9e68 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -494,7 +494,7 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 
 static int get_ksymbol_bpf(struct kallsym_iter *iter)
 {
-	iter->module_name[0] = '\0';
+	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
 	return bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
 			       &iter->value, &iter->type,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 8b068adb9da1..088c2032ceaf 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -431,8 +431,7 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	if (unlikely(event->oncpu != cpu))
 		return -EOPNOTSUPP;
 
-	perf_event_output(event, sd, regs);
-	return 0;
+	return perf_event_output(event, sd, regs);
 }
 
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index ea19b5d491bf..7198ddd0c6b1 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -372,7 +372,9 @@ 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 */
+				bpf_event      :  1, /* include bpf events */
+				__reserved_1   : 33;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -963,9 +965,58 @@ 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,
+
+	/*
+	 * 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 */
 };
 
+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)
+
+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/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index d340d2e42776..f2863496dede 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2343,7 +2343,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	struct c2c_cacheline_browser *cl_browser;
 	struct hist_browser *browser;
 	int key = -1;
-	const char help[] =
+	static const char help[] =
 	" ENTER         Toggle callchains (if present) \n"
 	" n             Toggle Node details info \n"
 	" s             Toggle full length of symbol and source line columns \n"
@@ -2424,7 +2424,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
 {
 	struct hist_browser *browser;
 	int key = -1;
-	const char help[] =
+	static const char help[] =
 	" d             Display cacheline details \n"
 	" ENTER         Toggle callchains (if present) \n"
 	" q             Quit \n";
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index b63bca4b0c2a..088705c167bf 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -334,7 +334,7 @@ static int build_alloc_func_list(void)
 	struct alloc_func *func;
 	struct machine *machine = &kmem_session->machines.host;
 	regex_t alloc_func_regex;
-	const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+	static const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
 
 	ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);
 	if (ret) {
@@ -1924,7 +1924,7 @@ int cmd_kmem(int argc, const char **argv)
 		NULL
 	};
 	struct perf_session *session;
-	const char errmsg[] = "No %s allocation events found.  Have you run 'perf kmem record --%s'?\n";
+	static const char errmsg[] = "No %s allocation events found.  Have you run 'perf kmem record --%s'?\n";
 	int ret = perf_config(kmem_config, NULL);
 
 	if (ret)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 882285fb9f64..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);
@@ -1839,6 +1845,7 @@ 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/builtin-report.c b/tools/perf/builtin-report.c
index 4958095be4fc..794a0de5ac1d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -956,9 +956,9 @@ int cmd_report(int argc, const char **argv)
 	int branch_mode = -1;
 	bool branch_call_mode = false;
 #define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
-	const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
-					     CALLCHAIN_REPORT_HELP
-					     "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;
+	static const char report_callchain_help[] = "Display call graph (stack chain/backtrace):\n\n"
+						    CALLCHAIN_REPORT_HELP
+						    "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;
 	char callchain_default_opt[] = CALLCHAIN_DEFAULT_OPT;
 	const char * const report_usage[] = {
 		"perf report [<options>]",
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index cbf39dab19c1..2e0f0c65964a 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3336,7 +3336,7 @@ static int __cmd_record(int argc, const char **argv)
 
 int cmd_sched(int argc, const char **argv)
 {
-	const char default_sort_order[] = "avg, max, switch, runtime";
+	static const char default_sort_order[] = "avg, max, switch, runtime";
 	struct perf_sched sched = {
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 63a3afc7f32b..e587808591e8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -83,7 +83,6 @@
 #include <unistd.h>
 #include <sys/time.h>
 #include <sys/resource.h>
-#include <sys/wait.h>
 
 #include "sane_ctype.h"
 
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);
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..9e9d4c66e53c 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -141,8 +141,8 @@ int sys_enter(struct syscall_enter_args *args)
 		len = sizeof(augmented_args.args);
 	}
 
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
-	return 0;
+	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
+	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
 }
 
 SEC("raw_syscalls:sys_exit")
diff --git a/tools/perf/examples/bpf/augmented_syscalls.c b/tools/perf/examples/bpf/augmented_syscalls.c
index 2ae44813ef2d..b7dba114e36c 100644
--- a/tools/perf/examples/bpf/augmented_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_syscalls.c
@@ -55,9 +55,9 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 		len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;	\
 		len &= sizeof(augmented_args.filename.value) - 1;				\
 	}											\
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
-			  &augmented_args, len);						\
-	return 0;										\
+	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */	\
+	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 		\
+				 &augmented_args, len);						\
 }												\
 int syscall_exit(syscall)(struct syscall_exit_args *args)					\
 {												\
@@ -125,10 +125,10 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 /*		addrlen = augmented_args.args.addrlen;				     */		\
 /*										     */		\
 	probe_read(&augmented_args.addr, addrlen, args->addr_ptr); 				\
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
-			  &augmented_args, 							\
-			  sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);	\
-	return 0;										\
+	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */	\
+	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 		\
+				 &augmented_args, 						\
+				sizeof(augmented_args) - sizeof(augmented_args.addr) + addrlen);\
 }												\
 int syscall_exit(syscall)(struct syscall_exit_args *args)					\
 {												\
diff --git a/tools/perf/examples/bpf/etcsnoop.c b/tools/perf/examples/bpf/etcsnoop.c
index b59e8812ee8c..550e69c2e8d1 100644
--- a/tools/perf/examples/bpf/etcsnoop.c
+++ b/tools/perf/examples/bpf/etcsnoop.c
@@ -49,11 +49,11 @@ int syscall_enter(syscall)(struct syscall_enter_##syscall##_args *args)				\
 						      args->filename_ptr); 			\
 	if (__builtin_memcmp(augmented_args.filename.value, etc, 4) != 0)			\
 		return 0;									\
-	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 			\
-			  &augmented_args, 							\
-			  (sizeof(augmented_args) - sizeof(augmented_args.filename.value) +	\
-			   augmented_args.filename.size));					\
-	return 0;										\
+	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */	\
+	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, 		\
+				 &augmented_args,						\
+				 (sizeof(augmented_args) - sizeof(augmented_args.filename.value) + \
+				 augmented_args.filename.size));				\
 }
 
 struct syscall_enter_openat_args {
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/tests/bp_account.c b/tools/perf/tests/bp_account.c
index a20cbc445426..57fc544aedb0 100644
--- a/tools/perf/tests/bp_account.c
+++ b/tools/perf/tests/bp_account.c
@@ -15,7 +15,6 @@
 #include <sys/mman.h>
 #include <linux/compiler.h>
 #include <linux/hw_breakpoint.h>
-#include <sys/ioctl.h>
 
 #include "tests.h"
 #include "debug.h"
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
index d75492189acb..5aeb663dd184 100644
--- a/tools/perf/ui/browsers/header.c
+++ b/tools/perf/ui/browsers/header.c
@@ -35,7 +35,7 @@ static int list_menu__run(struct ui_browser *menu)
 {
 	int key;
 	unsigned long offset;
-	const char help[] =
+	static const char help[] =
 	"h/?/F1        Show this window\n"
 	"UP/DOWN/PGUP\n"
 	"PGDN/SPACE\n"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index ffac1d54a3d4..b32f505a7608 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2748,7 +2748,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"S             Zoom into current Processor Socket\n"		\
 
 	/* help messages are sorted by lexical order of the hotkey */
-	const char report_help[] = HIST_BROWSER_HELP_COMMON
+	static const char report_help[] = HIST_BROWSER_HELP_COMMON
 	"i             Show header information\n"
 	"P             Print histograms to perf.hist.N\n"
 	"r             Run available scripts\n"
@@ -2756,7 +2756,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
 	"/             Filter symbol by name";
-	const char top_help[] = HIST_BROWSER_HELP_COMMON
+	static const char top_help[] = HIST_BROWSER_HELP_COMMON
 	"P             Print histograms to perf.hist.N\n"
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index af72be7f5b3b..b69d6294c88c 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -35,6 +35,7 @@ libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += symbol_fprintf.o
 libperf-y += color.o
+libperf-y += color_config.o
 libperf-y += metricgroup.o
 libperf-y += header.o
 libperf-y += callchain.o
@@ -44,6 +45,8 @@ libperf-y += machine.o
 libperf-y += map.o
 libperf-y += pstack.o
 libperf-y += session.o
+libperf-y += sample-raw.o
+libperf-y += s390-sample-raw.o
 libperf-$(CONFIG_TRACE) += syscalltbl.o
 libperf-y += ordered-events.o
 libperf-y += namespaces.o
@@ -152,6 +155,8 @@ 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..01e1dc1bb7fb
--- /dev/null
+++ b/tools/perf/util/bpf-event.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdlib.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)
+{
+	if (dump_trace)
+		perf_event__fprintf_bpf_event(event, stdout);
+	return 0;
+}
+
+/*
+ * Synthesize PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT for one bpf
+ * program. One PERF_RECORD_BPF_EVENT is generated for the program. And
+ * one PERF_RECORD_KSYMBOL is generated for each sub program.
+ *
+ * Returns:
+ *    0 for success;
+ *   -1 for failures;
+ *   -2 for lack of kernel support.
+ */
+static int perf_event__synthesize_one_bpf_prog(struct perf_tool *tool,
+					       perf_event__handler_t process,
+					       struct machine *machine,
+					       int fd,
+					       union perf_event *event,
+					       struct record_opts *opts)
+{
+	struct ksymbol_event *ksymbol_event = &event->ksymbol_event;
+	struct bpf_event *bpf_event = &event->bpf_event;
+	u32 sub_prog_cnt, i, func_info_rec_size = 0;
+	u8 (*prog_tags)[BPF_TAG_SIZE] = NULL;
+	struct bpf_prog_info info = { .type = 0, };
+	u32 info_len = sizeof(info);
+	void *func_infos = NULL;
+	u64 *prog_addrs = NULL;
+	struct btf *btf = NULL;
+	u32 *prog_lens = NULL;
+	bool has_btf = false;
+	char errbuf[512];
+	int err = 0;
+
+	/* Call bpf_obj_get_info_by_fd() to get sizes of arrays */
+	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+
+	if (err) {
+		pr_debug("%s: failed to get BPF program info: %s, aborting\n",
+			 __func__, str_error_r(errno, errbuf, sizeof(errbuf)));
+		return -1;
+	}
+	if (info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+		pr_debug("%s: the kernel is too old, aborting\n", __func__);
+		return -2;
+	}
+
+	/* number of ksyms, func_lengths, and tags should match */
+	sub_prog_cnt = info.nr_jited_ksyms;
+	if (sub_prog_cnt != info.nr_prog_tags ||
+	    sub_prog_cnt != info.nr_jited_func_lens)
+		return -1;
+
+	/* check BTF func info support */
+	if (info.btf_id && info.nr_func_info && info.func_info_rec_size) {
+		/* btf func info number should be same as sub_prog_cnt */
+		if (sub_prog_cnt != info.nr_func_info) {
+			pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
+			return -1;
+		}
+		if (btf__get_from_id(info.btf_id, &btf)) {
+			pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info.btf_id);
+			return -1;
+		}
+		func_info_rec_size = info.func_info_rec_size;
+		func_infos = calloc(sub_prog_cnt, func_info_rec_size);
+		if (!func_infos) {
+			pr_debug("%s: failed to allocate memory for func_infos, aborting\n", __func__);
+			return -1;
+		}
+		has_btf = true;
+	}
+
+	/*
+	 * We need address, length, and tag for each sub program.
+	 * Allocate memory and call bpf_obj_get_info_by_fd() again
+	 */
+	prog_addrs = calloc(sub_prog_cnt, sizeof(u64));
+	if (!prog_addrs) {
+		pr_debug("%s: failed to allocate memory for prog_addrs, aborting\n", __func__);
+		goto out;
+	}
+	prog_lens = calloc(sub_prog_cnt, sizeof(u32));
+	if (!prog_lens) {
+		pr_debug("%s: failed to allocate memory for prog_lens, aborting\n", __func__);
+		goto out;
+	}
+	prog_tags = calloc(sub_prog_cnt, BPF_TAG_SIZE);
+	if (!prog_tags) {
+		pr_debug("%s: failed to allocate memory for prog_tags, aborting\n", __func__);
+		goto out;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.nr_jited_ksyms = sub_prog_cnt;
+	info.nr_jited_func_lens = sub_prog_cnt;
+	info.nr_prog_tags = sub_prog_cnt;
+	info.jited_ksyms = ptr_to_u64(prog_addrs);
+	info.jited_func_lens = ptr_to_u64(prog_lens);
+	info.prog_tags = ptr_to_u64(prog_tags);
+	info_len = sizeof(info);
+	if (has_btf) {
+		info.nr_func_info = sub_prog_cnt;
+		info.func_info_rec_size = func_info_rec_size;
+		info.func_info = ptr_to_u64(func_infos);
+	}
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
+	if (err) {
+		pr_debug("%s: failed to get BPF program info, aborting\n", __func__);
+		goto out;
+	}
+
+	/* Synthesize PERF_RECORD_KSYMBOL */
+	for (i = 0; i < sub_prog_cnt; i++) {
+		const struct bpf_func_info *finfo;
+		const char *short_name = NULL;
+		const struct btf_type *t;
+		int name_len;
+
+		*ksymbol_event = (struct ksymbol_event){
+			.header = {
+				.type = PERF_RECORD_KSYMBOL,
+				.size = sizeof(struct ksymbol_event),
+			},
+			.addr = prog_addrs[i],
+			.len = prog_lens[i],
+			.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+			.flags = 0,
+		};
+		name_len = snprintf(ksymbol_event->name, KSYM_NAME_LEN,
+				    "bpf_prog_");
+		name_len += snprintf_hex(ksymbol_event->name + name_len,
+					 KSYM_NAME_LEN - name_len,
+					 prog_tags[i], BPF_TAG_SIZE);
+		if (has_btf) {
+			finfo = func_infos + i * info.func_info_rec_size;
+			t = btf__type_by_id(btf, finfo->type_id);
+			short_name = btf__name_by_offset(btf, t->name_off);
+		} else if (i == 0 && sub_prog_cnt == 1) {
+			/* no subprog */
+			if (info.name[0])
+				short_name = info.name;
+		} else
+			short_name = "F";
+		if (short_name)
+			name_len += snprintf(ksymbol_event->name + name_len,
+					     KSYM_NAME_LEN - name_len,
+					     "_%s", short_name);
+
+		ksymbol_event->header.size += PERF_ALIGN(name_len + 1,
+							 sizeof(u64));
+		err = perf_tool__process_synth_event(tool, event,
+						     machine, process);
+	}
+
+	/* Synthesize PERF_RECORD_BPF_EVENT */
+	if (opts->bpf_event) {
+		*bpf_event = (struct bpf_event){
+			.header = {
+				.type = PERF_RECORD_BPF_EVENT,
+				.size = sizeof(struct bpf_event),
+			},
+			.type = PERF_BPF_EVENT_PROG_LOAD,
+			.flags = 0,
+			.id = info.id,
+		};
+		memcpy(bpf_event->tag, prog_tags[i], BPF_TAG_SIZE);
+		err = perf_tool__process_synth_event(tool, event,
+						     machine, process);
+	}
+
+out:
+	free(prog_tags);
+	free(prog_lens);
+	free(prog_addrs);
+	free(func_infos);
+	free(btf);
+	return err ? -1 : 0;
+}
+
+int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      struct record_opts *opts)
+{
+	union perf_event *event;
+	__u32 id = 0;
+	int err;
+	int fd;
+
+	event = malloc(sizeof(event->bpf_event) + KSYM_NAME_LEN);
+	if (!event)
+		return -1;
+	while (true) {
+		err = bpf_prog_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT) {
+				err = 0;
+				break;
+			}
+			pr_debug("%s: can't get next program: %s%s",
+				 __func__, strerror(errno),
+				 errno == EINVAL ? " -- kernel too old?" : "");
+			/* don't report error on old kernel */
+			err = (errno == EINVAL) ? 0 : -1;
+			break;
+		}
+		fd = bpf_prog_get_fd_by_id(id);
+		if (fd < 0) {
+			pr_debug("%s: failed to get fd for prog_id %u\n",
+				 __func__, id);
+			continue;
+		}
+
+		err = perf_event__synthesize_one_bpf_prog(tool, process,
+							  machine, fd,
+							  event, opts);
+		close(fd);
+		if (err) {
+			/* do not return error for old kernel */
+			if (err == -2)
+				err = 0;
+			break;
+		}
+	}
+	free(event);
+	return err;
+}
diff --git a/tools/perf/util/bpf-event.h b/tools/perf/util/bpf-event.h
new file mode 100644
index 000000000000..7890067e1a37
--- /dev/null
+++ b/tools/perf/util/bpf-event.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_BPF_EVENT_H
+#define __PERF_BPF_EVENT_H
+
+#include <linux/compiler.h>
+#include "event.h"
+
+struct machine;
+union perf_event;
+struct perf_sample;
+struct perf_tool;
+struct record_opts;
+
+#ifdef HAVE_LIBBPF_SUPPORT
+int machine__process_bpf_event(struct machine *machine, union perf_event *event,
+			       struct perf_sample *sample);
+
+int perf_event__synthesize_bpf_events(struct perf_tool *tool,
+				      perf_event__handler_t process,
+				      struct machine *machine,
+				      struct record_opts *opts);
+#else
+static inline int machine__process_bpf_event(struct machine *machine __maybe_unused,
+					     union perf_event *event __maybe_unused,
+					     struct perf_sample *sample __maybe_unused)
+{
+	return 0;
+}
+
+static inline int perf_event__synthesize_bpf_events(struct perf_tool *tool __maybe_unused,
+						    perf_event__handler_t process __maybe_unused,
+						    struct machine *machine __maybe_unused,
+						    struct record_opts *opts __maybe_unused)
+{
+	return 0;
+}
+#endif // HAVE_LIBBPF_SUPPORT
+#endif
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 39e628b8938e..39b8c4ec4e2e 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include "cache.h"
-#include "config.h"
 #include <stdlib.h>
 #include <stdio.h>
 #include "color.h"
@@ -10,44 +9,6 @@
 
 int perf_use_color_default = -1;
 
-int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
-{
-	if (value) {
-		if (!strcasecmp(value, "never"))
-			return 0;
-		if (!strcasecmp(value, "always"))
-			return 1;
-		if (!strcasecmp(value, "auto"))
-			goto auto_color;
-	}
-
-	/* Missing or explicit false to turn off colorization */
-	if (!perf_config_bool(var, value))
-		return 0;
-
-	/* any normal truth value defaults to 'auto' */
- auto_color:
-	if (stdout_is_tty < 0)
-		stdout_is_tty = isatty(1);
-	if (stdout_is_tty || pager_in_use()) {
-		char *term = getenv("TERM");
-		if (term && strcmp(term, "dumb"))
-			return 1;
-	}
-	return 0;
-}
-
-int perf_color_default_config(const char *var, const char *value,
-			      void *cb __maybe_unused)
-{
-	if (!strcmp(var, "color.ui")) {
-		perf_use_color_default = perf_config_colorbool(var, value, -1);
-		return 0;
-	}
-
-	return 0;
-}
-
 static int __color_vsnprintf(char *bf, size_t size, const char *color,
 			     const char *fmt, va_list args, const char *trail)
 {
diff --git a/tools/perf/util/color_config.c b/tools/perf/util/color_config.c
new file mode 100644
index 000000000000..817dc56e7e95
--- /dev/null
+++ b/tools/perf/util/color_config.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include "cache.h"
+#include "config.h"
+#include <stdlib.h>
+#include <stdio.h>
+#include "color.h"
+#include <math.h>
+#include <unistd.h>
+
+int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
+{
+	if (value) {
+		if (!strcasecmp(value, "never"))
+			return 0;
+		if (!strcasecmp(value, "always"))
+			return 1;
+		if (!strcasecmp(value, "auto"))
+			goto auto_color;
+	}
+
+	/* Missing or explicit false to turn off colorization */
+	if (!perf_config_bool(var, value))
+		return 0;
+
+	/* any normal truth value defaults to 'auto' */
+ auto_color:
+	if (stdout_is_tty < 0)
+		stdout_is_tty = isatty(1);
+	if (stdout_is_tty || pager_in_use()) {
+		char *term = getenv("TERM");
+		if (term && strcmp(term, "dumb"))
+			return 1;
+	}
+	return 0;
+}
+
+int perf_color_default_config(const char *var, const char *value,
+			      void *cb __maybe_unused)
+{
+	if (!strcmp(var, "color.ui")) {
+		perf_use_color_default = perf_config_colorbool(var, value, -1);
+		return 0;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 8c8a7abe809d..af2eda29660f 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -8,7 +8,6 @@
 #include <sys/types.h>
 #include <stdbool.h>
 #include "rwsem.h"
-#include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
 #include "namespaces.h"
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 937a5a4f71cc..1b5091a3d14f 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -24,6 +24,8 @@
 #include "symbol/kallsyms.h"
 #include "asm/bug.h"
 #include "stat.h"
+#include "session.h"
+#include "bpf-event.h"
 
 #define DEFAULT_PROC_MAP_PARSE_TIMEOUT 500
 
@@ -45,6 +47,8 @@ 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_BPF_EVENT]			= "BPF_EVENT",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
@@ -1329,6 +1333,22 @@ 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);
+}
+
+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",
@@ -1461,6 +1481,21 @@ 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 %" PRIx64 " 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_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",
@@ -1496,6 +1531,12 @@ 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;
+	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 eb95f3384958..dad32b81fe71 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 +85,29 @@ 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];
+};
+
+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 |		\
@@ -651,6 +675,8 @@ union perf_event {
 	struct stat_round_event		stat_round;
 	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);
@@ -748,6 +774,14 @@ 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_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,
@@ -811,6 +845,8 @@ 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_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/evlist.h b/tools/perf/util/evlist.h
index 868294491194..00ab43c6dd15 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -49,6 +49,9 @@ struct perf_evlist {
 	struct perf_evsel *selected;
 	struct events_stats stats;
 	struct perf_env	*env;
+	void (*trace_event_sample_raw)(struct perf_evlist *evlist,
+				       union perf_event *event,
+				       struct perf_sample *sample);
 	u64		first_sample_time;
 	u64		last_sample_time;
 };
@@ -314,5 +317,4 @@ void perf_evlist__force_leader(struct perf_evlist *evlist);
 
 struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist,
 						 struct perf_evsel *evsel);
-
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbc0466db368..684c893ca6bc 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1035,6 +1035,9 @@ 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;
+	attr->bpf_event = track && opts->bpf_event &&
+		!perf_missing_features.bpf_event;
 
 	if (opts->record_namespaces)
 		attr->namespaces  = track;
@@ -1652,6 +1655,8 @@ 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_ATTRf(bpf_event, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
@@ -1811,6 +1816,10 @@ fallback_missing_features:
 				     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;
+	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;
@@ -1930,7 +1939,15 @@ try_fallback:
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
+	if (!perf_missing_features.bpf_event && evsel->attr.bpf_event) {
+		perf_missing_features.bpf_event = true;
+		pr_debug2("switching off bpf_event\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.ksymbol && evsel->attr.ksymbol) {
+		perf_missing_features.ksymbol = true;
+		pr_debug2("switching off ksymbol\n");
+		goto fallback_missing_features;
+	} else if (!perf_missing_features.write_backward && evsel->attr.write_backward) {
 		perf_missing_features.write_backward = true;
 		pr_debug2("switching off write_backward\n");
 		goto out_close;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 82a289ce8b0c..29c5eb68c44b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -168,6 +168,8 @@ struct perf_missing_features {
 	bool lbr_flags;
 	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 143f7057d581..ae85106bb5bf 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -21,6 +21,7 @@
 #include "unwind.h"
 #include "linux/hash.h"
 #include "asm/bug.h"
+#include "bpf-event.h"
 
 #include "sane_ctype.h"
 #include <symbol/kallsyms.h>
@@ -681,6 +682,59 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+static int machine__process_ksymbol_register(struct machine *machine,
+					     union perf_event *event,
+					     struct perf_sample *sample __maybe_unused)
+{
+	struct symbol *sym;
+	struct map *map;
+
+	map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+	if (!map) {
+		map = dso__new_map(event->ksymbol_event.name);
+		if (!map)
+			return -ENOMEM;
+
+		map->start = event->ksymbol_event.addr;
+		map->pgoff = map->start;
+		map->end = map->start + event->ksymbol_event.len;
+		map_groups__insert(&machine->kmaps, map);
+	}
+
+	sym = symbol__new(event->ksymbol_event.addr, event->ksymbol_event.len,
+			  0, 0, event->ksymbol_event.name);
+	if (!sym)
+		return -ENOMEM;
+	dso__insert_symbol(map->dso, sym);
+	return 0;
+}
+
+static int machine__process_ksymbol_unregister(struct machine *machine,
+					       union perf_event *event,
+					       struct perf_sample *sample __maybe_unused)
+{
+	struct map *map;
+
+	map = map_groups__find(&machine->kmaps, event->ksymbol_event.addr);
+	if (map)
+		map_groups__remove(&machine->kmaps, map);
+
+	return 0;
+}
+
+int machine__process_ksymbol(struct machine *machine __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample)
+{
+	if (dump_trace)
+		perf_event__fprintf_ksymbol(event, stdout);
+
+	if (event->ksymbol_event.flags & PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER)
+		return machine__process_ksymbol_unregister(machine, event,
+							   sample);
+	return machine__process_ksymbol_register(machine, event, sample);
+}
+
 static void dso__adjust_kmod_long_name(struct dso *dso, const char *filename)
 {
 	const char *dup_filename;
@@ -1812,6 +1866,10 @@ 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;
+	case PERF_RECORD_BPF_EVENT:
+		ret = machine__process_bpf_event(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/s390-cpumcf-kernel.h b/tools/perf/util/s390-cpumcf-kernel.h
new file mode 100644
index 000000000000..d4356030b504
--- /dev/null
+++ b/tools/perf/util/s390-cpumcf-kernel.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Support for s390 CPU measurement counter set diagnostic facility
+ *
+ * Copyright IBM Corp. 2019
+   Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
+ *		Thomas Richter <tmricht@linux.ibm.com>
+ */
+#ifndef S390_CPUMCF_KERNEL_H
+#define S390_CPUMCF_KERNEL_H
+
+#define	S390_CPUMCF_DIAG_DEF	0xfeef	/* Counter diagnostic entry ID */
+#define	PERF_EVENT_CPUM_CF_DIAG	0xBC000	/* Event: Counter sets */
+
+struct cf_ctrset_entry {	/* CPU-M CF counter set entry (8 byte) */
+	unsigned int def:16;	/* 0-15  Data Entry Format */
+	unsigned int set:16;	/* 16-23 Counter set identifier */
+	unsigned int ctr:16;	/* 24-39 Number of stored counters */
+	unsigned int res1:16;	/* 40-63 Reserved */
+};
+
+struct cf_trailer_entry {	/* CPU-M CF trailer for raw traces (64 byte) */
+	/* 0 - 7 */
+	union {
+		struct {
+			unsigned int clock_base:1;	/* TOD clock base */
+			unsigned int speed:1;		/* CPU speed */
+			/* Measurement alerts */
+			unsigned int mtda:1;	/* Loss of MT ctr. data alert */
+			unsigned int caca:1;	/* Counter auth. change alert */
+			unsigned int lcda:1;	/* Loss of counter data alert */
+		};
+		unsigned long flags;		/* 0-63    All indicators */
+	};
+	/* 8 - 15 */
+	unsigned int cfvn:16;			/* 64-79   Ctr First Version */
+	unsigned int csvn:16;			/* 80-95   Ctr Second Version */
+	unsigned int cpu_speed:32;		/* 96-127  CPU speed */
+	/* 16 - 23 */
+	unsigned long timestamp;		/* 128-191 Timestamp (TOD) */
+	/* 24 - 55 */
+	union {
+		struct {
+			unsigned long progusage1;
+			unsigned long progusage2;
+			unsigned long progusage3;
+			unsigned long tod_base;
+		};
+		unsigned long progusage[4];
+	};
+	/* 56 - 63 */
+	unsigned int mach_type:16;		/* Machine type */
+	unsigned int res1:16;			/* Reserved */
+	unsigned int res2:32;			/* Reserved */
+};
+
+#define	CPUMF_CTR_SET_BASIC	0	/* Basic Counter Set */
+#define	CPUMF_CTR_SET_USER	1	/* Problem-State Counter Set */
+#define	CPUMF_CTR_SET_CRYPTO	2	/* Crypto-Activity Counter Set */
+#define	CPUMF_CTR_SET_EXT	3	/* Extended Counter Set */
+#define	CPUMF_CTR_SET_MT_DIAG	4	/* MT-diagnostic Counter Set */
+#endif
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 68b2570304ec..835249c77f56 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -162,6 +162,7 @@
 #include "auxtrace.h"
 #include "s390-cpumsf.h"
 #include "s390-cpumsf-kernel.h"
+#include "s390-cpumcf-kernel.h"
 #include "config.h"
 
 struct s390_cpumsf {
@@ -184,8 +185,58 @@ struct s390_cpumsf_queue {
 	struct auxtrace_buffer	*buffer;
 	int			cpu;
 	FILE			*logfile;
+	FILE			*logfile_ctr;
 };
 
+/* Check if the raw data should be dumped to file. If this is the case and
+ * the file to dump to has not been opened for writing, do so.
+ *
+ * Return 0 on success and greater zero on error so processing continues.
+ */
+static int s390_cpumcf_dumpctr(struct s390_cpumsf *sf,
+			       struct perf_sample *sample)
+{
+	struct s390_cpumsf_queue *sfq;
+	struct auxtrace_queue *q;
+	int rc = 0;
+
+	if (!sf->use_logfile || sf->queues.nr_queues <= sample->cpu)
+		return rc;
+
+	q = &sf->queues.queue_array[sample->cpu];
+	sfq = q->priv;
+	if (!sfq)		/* Queue not yet allocated */
+		return rc;
+
+	if (!sfq->logfile_ctr) {
+		char *name;
+
+		rc = (sf->logdir)
+			? asprintf(&name, "%s/aux.ctr.%02x",
+				 sf->logdir, sample->cpu)
+			: asprintf(&name, "aux.ctr.%02x", sample->cpu);
+		if (rc > 0)
+			sfq->logfile_ctr = fopen(name, "w");
+		if (sfq->logfile_ctr == NULL) {
+			pr_err("Failed to open counter set log file %s, "
+			       "continue...\n", name);
+			rc = 1;
+		}
+		free(name);
+	}
+
+	if (sfq->logfile_ctr) {
+		/* See comment above for -4 */
+		size_t n = fwrite(sample->raw_data, sample->raw_size - 4, 1,
+				  sfq->logfile_ctr);
+		if (n != 1) {
+			pr_err("Failed to write counter set data\n");
+			rc = 1;
+		}
+	}
+	return rc;
+}
+
 /* Display s390 CPU measurement facility basic-sampling data entry */
 static bool s390_cpumsf_basic_show(const char *color, size_t pos,
 				   struct hws_basic_entry *basic)
@@ -792,7 +843,7 @@ static int s390_cpumsf_lost(struct s390_cpumsf *sf, struct perf_sample *sample)
 }
 
 static int
-s390_cpumsf_process_event(struct perf_session *session __maybe_unused,
+s390_cpumsf_process_event(struct perf_session *session,
 			  union perf_event *event,
 			  struct perf_sample *sample,
 			  struct perf_tool *tool)
@@ -801,6 +852,8 @@ s390_cpumsf_process_event(struct perf_session *session __maybe_unused,
 					      struct s390_cpumsf,
 					      auxtrace);
 	u64 timestamp = sample->time;
+	struct perf_evsel *ev_bc000;
+
 	int err = 0;
 
 	if (dump_trace)
@@ -811,6 +864,16 @@ s390_cpumsf_process_event(struct perf_session *session __maybe_unused,
 		return -EINVAL;
 	}
 
+	if (event->header.type == PERF_RECORD_SAMPLE &&
+	    sample->raw_size) {
+		/* Handle event with raw data */
+		ev_bc000 = perf_evlist__event2evsel(session->evlist, event);
+		if (ev_bc000 &&
+		    ev_bc000->attr.config == PERF_EVENT_CPUM_CF_DIAG)
+			err = s390_cpumcf_dumpctr(sf, sample);
+		return err;
+	}
+
 	if (event->header.type == PERF_RECORD_AUX &&
 	    event->aux.flags & PERF_AUX_FLAG_TRUNCATED)
 		return s390_cpumsf_lost(sf, sample);
@@ -891,9 +954,15 @@ static void s390_cpumsf_free_queues(struct perf_session *session)
 		struct s390_cpumsf_queue *sfq = (struct s390_cpumsf_queue *)
 						queues->queue_array[i].priv;
 
-		if (sfq != NULL && sfq->logfile) {
-			fclose(sfq->logfile);
-			sfq->logfile = NULL;
+		if (sfq != NULL) {
+			if (sfq->logfile) {
+				fclose(sfq->logfile);
+				sfq->logfile = NULL;
+			}
+			if (sfq->logfile_ctr) {
+				fclose(sfq->logfile_ctr);
+				sfq->logfile_ctr = NULL;
+			}
 		}
 		zfree(&queues->queue_array[i].priv);
 	}
diff --git a/tools/perf/util/s390-sample-raw.c b/tools/perf/util/s390-sample-raw.c
new file mode 100644
index 000000000000..6650f599ed9c
--- /dev/null
+++ b/tools/perf/util/s390-sample-raw.c
@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2019
+ * Author(s): Thomas Richter <tmricht@linux.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ * Architecture specific trace_event function. Save event's bc000 raw data
+ * to file. File name is aux.ctr.## where ## stands for the CPU number the
+ * sample was taken from.
+ */
+
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+
+#include <sys/stat.h>
+#include <linux/compiler.h>
+#include <asm/byteorder.h>
+
+#include "debug.h"
+#include "util.h"
+#include "auxtrace.h"
+#include "session.h"
+#include "evlist.h"
+#include "config.h"
+#include "color.h"
+#include "sample-raw.h"
+#include "s390-cpumcf-kernel.h"
+#include "pmu-events/pmu-events.h"
+
+static size_t ctrset_size(struct cf_ctrset_entry *set)
+{
+	return sizeof(*set) + set->ctr * sizeof(u64);
+}
+
+static bool ctrset_valid(struct cf_ctrset_entry *set)
+{
+	return set->def == S390_CPUMCF_DIAG_DEF;
+}
+
+/* CPU Measurement Counter Facility raw data is a byte stream. It is 8 byte
+ * aligned and might have trailing padding bytes.
+ * Display the raw data on screen.
+ */
+static bool s390_cpumcfdg_testctr(struct perf_sample *sample)
+{
+	size_t len = sample->raw_size, offset = 0;
+	unsigned char *buf = sample->raw_data;
+	struct cf_trailer_entry *te;
+	struct cf_ctrset_entry *cep, ce;
+
+	if (!len)
+		return false;
+	while (offset < len) {
+		cep = (struct cf_ctrset_entry *)(buf + offset);
+		ce.def = be16_to_cpu(cep->def);
+		ce.set = be16_to_cpu(cep->set);
+		ce.ctr = be16_to_cpu(cep->ctr);
+		ce.res1 = be16_to_cpu(cep->res1);
+
+		if (!ctrset_valid(&ce) || offset + ctrset_size(&ce) > len) {
+			/* Raw data for counter sets are always multiple of 8
+			 * bytes. Prepending a 4 bytes size field to the
+			 * raw data block in the sample causes the perf tool
+			 * to append 4 padding bytes to make the raw data part
+			 * of the sample a multiple of eight bytes again.
+			 *
+			 * If the last entry (trailer) is 4 bytes off the raw
+			 * area data end, all is good.
+			 */
+			if (len - offset - sizeof(*te) == 4)
+				break;
+			pr_err("Invalid counter set entry at %zd\n", offset);
+			return false;
+		}
+		offset += ctrset_size(&ce);
+	}
+	return true;
+}
+
+/* Dump event bc000 on screen, already tested on correctness. */
+static void s390_cpumcfdg_dumptrail(const char *color, size_t offset,
+				    struct cf_trailer_entry *tep)
+{
+	struct cf_trailer_entry  te;
+
+	te.flags = be64_to_cpu(tep->flags);
+	te.cfvn = be16_to_cpu(tep->cfvn);
+	te.csvn = be16_to_cpu(tep->csvn);
+	te.cpu_speed = be32_to_cpu(tep->cpu_speed);
+	te.timestamp = be64_to_cpu(tep->timestamp);
+	te.progusage1 = be64_to_cpu(tep->progusage1);
+	te.progusage2 = be64_to_cpu(tep->progusage2);
+	te.progusage3 = be64_to_cpu(tep->progusage3);
+	te.tod_base = be64_to_cpu(tep->tod_base);
+	te.mach_type = be16_to_cpu(tep->mach_type);
+	te.res1 = be16_to_cpu(tep->res1);
+	te.res2 = be32_to_cpu(tep->res2);
+
+	color_fprintf(stdout, color, "    [%#08zx] Trailer:%c%c%c%c%c"
+		      " Cfvn:%d Csvn:%d Speed:%d TOD:%#llx\n",
+		      offset, te.clock_base ? 'T' : ' ',
+		      te.speed ? 'S' : ' ', te.mtda ? 'M' : ' ',
+		      te.caca ? 'C' : ' ', te.lcda ? 'L' : ' ',
+		      te.cfvn, te.csvn, te.cpu_speed, te.timestamp);
+	color_fprintf(stdout, color, "\t\t1:%lx 2:%lx 3:%lx TOD-Base:%#llx"
+		      " Type:%x\n\n",
+		      te.progusage1, te.progusage2, te.progusage3,
+		      te.tod_base, te.mach_type);
+}
+
+/* Return starting number of a counter set */
+static int get_counterset_start(int setnr)
+{
+	switch (setnr) {
+	case CPUMF_CTR_SET_BASIC:		/* Basic counter set */
+		return 0;
+	case CPUMF_CTR_SET_USER:		/* Problem state counter set */
+		return 32;
+	case CPUMF_CTR_SET_CRYPTO:		/* Crypto counter set */
+		return 64;
+	case CPUMF_CTR_SET_EXT:			/* Extended counter set */
+		return 128;
+	case CPUMF_CTR_SET_MT_DIAG:		/* Diagnostic counter set */
+		return 448;
+	default:
+		return -1;
+	}
+}
+
+/* Scan the PMU table and extract the logical name of a counter from the
+ * PMU events table. Input is the counter set and counter number with in the
+ * set. Construct the event number and use this as key. If they match return
+ * the name of this counter.
+ * If no match is found a NULL pointer is returned.
+ */
+static const char *get_counter_name(int set, int nr, struct pmu_events_map *map)
+{
+	int rc, event_nr, wanted = get_counterset_start(set) + nr;
+
+	if (map) {
+		struct pmu_event *evp = map->table;
+
+		for (; evp->name || evp->event || evp->desc; ++evp) {
+			if (evp->name == NULL || evp->event == NULL)
+				continue;
+			rc = sscanf(evp->event, "event=%x", &event_nr);
+			if (rc == 1 && event_nr == wanted)
+				return evp->name;
+		}
+	}
+	return NULL;
+}
+
+static void s390_cpumcfdg_dump(struct perf_sample *sample)
+{
+	size_t i, len = sample->raw_size, offset = 0;
+	unsigned char *buf = sample->raw_data;
+	const char *color = PERF_COLOR_BLUE;
+	struct cf_ctrset_entry *cep, ce;
+	struct pmu_events_map *map;
+	struct perf_pmu pmu;
+	u64 *p;
+
+	memset(&pmu, 0, sizeof(pmu));
+	map = perf_pmu__find_map(&pmu);
+	while (offset < len) {
+		cep = (struct cf_ctrset_entry *)(buf + offset);
+
+		ce.def = be16_to_cpu(cep->def);
+		ce.set = be16_to_cpu(cep->set);
+		ce.ctr = be16_to_cpu(cep->ctr);
+		ce.res1 = be16_to_cpu(cep->res1);
+
+		if (!ctrset_valid(&ce)) {	/* Print trailer */
+			s390_cpumcfdg_dumptrail(color, offset,
+						(struct cf_trailer_entry *)cep);
+			return;
+		}
+
+		color_fprintf(stdout, color, "    [%#08zx] Counterset:%d"
+			      " Counters:%d\n", offset, ce.set, ce.ctr);
+		for (i = 0, p = (u64 *)(cep + 1); i < ce.ctr; ++i, ++p) {
+			const char *ev_name = get_counter_name(ce.set, i, map);
+
+			color_fprintf(stdout, color,
+				      "\tCounter:%03d %s Value:%#018lx\n", i,
+				      ev_name ?: "<unknown>", be64_to_cpu(*p));
+		}
+		offset += ctrset_size(&ce);
+	}
+}
+
+/* S390 specific trace event function. Check for PERF_RECORD_SAMPLE events
+ * and if the event was triggered by a counter set diagnostic event display
+ * its raw data.
+ * The function is only invoked when the dump flag -D is set.
+ */
+void perf_evlist__s390_sample_raw(struct perf_evlist *evlist, union perf_event *event,
+				  struct perf_sample *sample)
+{
+	struct perf_evsel *ev_bc000;
+
+	if (event->header.type != PERF_RECORD_SAMPLE)
+		return;
+
+	ev_bc000 = perf_evlist__event2evsel(evlist, event);
+	if (ev_bc000 == NULL ||
+	    ev_bc000->attr.config != PERF_EVENT_CPUM_CF_DIAG)
+		return;
+
+	/* Display raw data on screen */
+	if (!s390_cpumcfdg_testctr(sample)) {
+		pr_err("Invalid counter set data encountered\n");
+		return;
+	}
+	s390_cpumcfdg_dump(sample);
+}
diff --git a/tools/perf/util/sample-raw.c b/tools/perf/util/sample-raw.c
new file mode 100644
index 000000000000..c21e1311fb0f
--- /dev/null
+++ b/tools/perf/util/sample-raw.c
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <string.h>
+#include "evlist.h"
+#include "env.h"
+#include "sample-raw.h"
+
+/*
+ * Check platform the perf data file was created on and perform platform
+ * specific interpretation.
+ */
+void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist)
+{
+	const char *arch_pf = perf_env__arch(evlist->env);
+
+	if (arch_pf && !strcmp("s390", arch_pf))
+		evlist->trace_event_sample_raw = perf_evlist__s390_sample_raw;
+}
diff --git a/tools/perf/util/sample-raw.h b/tools/perf/util/sample-raw.h
new file mode 100644
index 000000000000..95d445c87e93
--- /dev/null
+++ b/tools/perf/util/sample-raw.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __SAMPLE_RAW_H
+#define __SAMPLE_RAW_H 1
+
+struct perf_evlist;
+union perf_event;
+struct perf_sample;
+
+void perf_evlist__s390_sample_raw(struct perf_evlist *evlist,
+				  union perf_event *event,
+				  struct perf_sample *sample);
+
+void perf_evlist__init_trace_event_sample_raw(struct perf_evlist *evlist);
+#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5456c84c7dd1..24fd62528a33 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -23,6 +23,7 @@
 #include "auxtrace.h"
 #include "thread.h"
 #include "thread-stack.h"
+#include "sample-raw.h"
 #include "stat.h"
 #include "arch/common.h"
 
@@ -147,6 +148,8 @@ struct perf_session *perf_session__new(struct perf_data *data,
 				perf_session__set_id_hdr_size(session);
 				perf_session__set_comm_exec(session);
 			}
+
+			perf_evlist__init_trace_event_sample_raw(session->evlist);
 		}
 	} else  {
 		session->machines.host.env = &perf_env;
@@ -376,6 +379,10 @@ 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->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)
@@ -1065,6 +1072,8 @@ static void dump_event(struct perf_evlist *evlist, union perf_event *event,
 	       file_offset, event->header.size, event->header.type);
 
 	trace_event(event);
+	if (event->header.type == PERF_RECORD_SAMPLE && evlist->trace_event_sample_raw)
+		evlist->trace_event_sample_raw(evlist, event, sample);
 
 	if (sample)
 		perf_evlist__print_tstamp(evlist, event, sample);
@@ -1305,6 +1314,10 @@ 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);
+	case PERF_RECORD_BPF_EVENT:
+		return tool->bpf_event(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
@@ -1820,38 +1833,35 @@ fetch_mmaped_event(struct perf_session *session,
 #define NUM_MMAPS 128
 #endif
 
-static int __perf_session__process_events(struct perf_session *session,
-					  u64 data_offset, u64 data_size,
-					  u64 file_size)
+struct reader {
+	int	fd;
+	u64	data_size;
+	u64	data_offset;
+};
+
+static int
+reader__process_events(struct reader *rd, struct perf_session *session,
+		       struct ui_progress *prog)
 {
-	struct ordered_events *oe = &session->ordered_events;
-	struct perf_tool *tool = session->tool;
-	int fd = perf_data__fd(session->data);
+	u64 data_size = rd->data_size;
 	u64 head, page_offset, file_offset, file_pos, size;
-	int err, mmap_prot, mmap_flags, map_idx = 0;
+	int err = 0, mmap_prot, mmap_flags, map_idx = 0;
 	size_t	mmap_size;
 	char *buf, *mmaps[NUM_MMAPS];
 	union perf_event *event;
-	struct ui_progress prog;
 	s64 skip;
 
-	perf_tool__fill_defaults(tool);
-
-	page_offset = page_size * (data_offset / page_size);
+	page_offset = page_size * (rd->data_offset / page_size);
 	file_offset = page_offset;
-	head = data_offset - page_offset;
+	head = rd->data_offset - page_offset;
 
-	if (data_size == 0)
-		goto out;
-
-	if (data_offset + data_size < file_size)
-		file_size = data_offset + data_size;
+	ui_progress__init_size(prog, data_size, "Processing events...");
 
-	ui_progress__init_size(&prog, file_size, "Processing events...");
+	data_size += rd->data_offset;
 
 	mmap_size = MMAP_SIZE;
-	if (mmap_size > file_size) {
-		mmap_size = file_size;
+	if (mmap_size > data_size) {
+		mmap_size = data_size;
 		session->one_mmap = true;
 	}
 
@@ -1865,12 +1875,12 @@ static int __perf_session__process_events(struct perf_session *session,
 		mmap_flags = MAP_PRIVATE;
 	}
 remap:
-	buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, fd,
+	buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, rd->fd,
 		   file_offset);
 	if (buf == MAP_FAILED) {
 		pr_err("failed to mmap file\n");
 		err = -errno;
-		goto out_err;
+		goto out;
 	}
 	mmaps[map_idx] = buf;
 	map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
@@ -1902,7 +1912,7 @@ more:
 		       file_offset + head, event->header.size,
 		       event->header.type);
 		err = -EINVAL;
-		goto out_err;
+		goto out;
 	}
 
 	if (skip)
@@ -1911,15 +1921,40 @@ more:
 	head += size;
 	file_pos += size;
 
-	ui_progress__update(&prog, size);
+	ui_progress__update(prog, size);
 
 	if (session_done())
 		goto out;
 
-	if (file_pos < file_size)
+	if (file_pos < data_size)
 		goto more;
 
 out:
+	return err;
+}
+
+static int __perf_session__process_events(struct perf_session *session)
+{
+	struct reader rd = {
+		.fd		= perf_data__fd(session->data),
+		.data_size	= session->header.data_size,
+		.data_offset	= session->header.data_offset,
+	};
+	struct ordered_events *oe = &session->ordered_events;
+	struct perf_tool *tool = session->tool;
+	struct ui_progress prog;
+	int err;
+
+	perf_tool__fill_defaults(tool);
+
+	if (rd.data_size == 0)
+		return -1;
+
+	ui_progress__init_size(&prog, rd.data_size, "Processing events...");
+
+	err = reader__process_events(&rd, session, &prog);
+	if (err)
+		goto out_err;
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
 	if (err)
@@ -1944,20 +1979,13 @@ out_err:
 
 int perf_session__process_events(struct perf_session *session)
 {
-	u64 size = perf_data__size(session->data);
-	int err;
-
 	if (perf_session__register_idle_thread(session) < 0)
 		return -ENOMEM;
 
-	if (!perf_data__is_pipe(session->data))
-		err = __perf_session__process_events(session,
-						     session->header.data_offset,
-						     session->header.data_size, size);
-	else
-		err = __perf_session__process_pipe_events(session);
+	if (perf_data__is_pipe(session->data))
+		return __perf_session__process_pipe_events(session);
 
-	return err;
+	return __perf_session__process_events(session);
 }
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 63f758c655d5..64d1f36dee99 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -17,6 +17,8 @@ if cc == "clang":
             vars[var] = sub("-mcet", "", vars[var])
         if not clang_has_option("-fcf-protection"):
             vars[var] = sub("-fcf-protection", "", vars[var])
+        if not clang_has_option("-fstack-clash-protection"):
+            vars[var] = sub("-fstack-clash-protection", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 56e4ca54020a..250391672f9f 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -53,7 +53,10 @@ struct perf_tool {
 			itrace_start,
 			context_switch,
 			throttle,
-			unthrottle;
+			unthrottle,
+			ksymbol,
+			bpf_event;
+
 	event_attr_op	attr;
 	event_attr_op	event_update;
 	event_op2	tracing_data;
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
index 902ce6384f57..512ad7c09b13 100644
--- a/tools/perf/util/zlib.c
+++ b/tools/perf/util/zlib.c
@@ -6,7 +6,6 @@
 #include <sys/mman.h>
 #include <zlib.h>
 #include <linux/compiler.h>
-#include <unistd.h>
 
 #include "util/compress.h"
 #include "util/util.h"