13 files changed, 329 insertions, 125 deletions

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index d7e3b008a613..14f812bb07a7 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -20,6 +20,7 @@ perf-y += parse-events.o
 perf-y += perf_regs.o
 perf-y += path.o
 perf-y += print_binary.o
+perf-y += rlimit.o
 perf-y += argv_split.o
 perf-y += rbtree.o
 perf-y += libstring.o
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 67b88b599a53..3d1c34fc4d68 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2460,7 +2460,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 
 		/* Something went wrong, no need to continue */
 		if (!inode) {
-			err = PTR_ERR(inode);
+			err = -ENOMEM;
 			goto err_free_metadata;
 		}
 
@@ -2517,8 +2517,10 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	session->auxtrace = &etm->auxtrace;
 
 	etm->unknown_thread = thread__new(999999999, 999999999);
-	if (!etm->unknown_thread)
+	if (!etm->unknown_thread) {
+		err = -ENOMEM;
 		goto err_free_queues;
+	}
 
 	/*
 	 * Initialize list node so that at thread__zput() we can avoid
@@ -2530,8 +2532,10 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	if (err)
 		goto err_delete_thread;
 
-	if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+	if (thread__init_map_groups(etm->unknown_thread, etm->machine)) {
+		err = -ENOMEM;
 		goto err_delete_thread;
+	}
 
 	if (dump_trace) {
 		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
@@ -2575,5 +2579,5 @@ err_free_traceid_list:
 err_free_hdr:
 	zfree(&hdr);
 
-	return -EINVAL;
+	return err;
 }
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 2394c7506abe..ffbb3e7d3288 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -20,70 +20,14 @@
 #include "db-export.h"
 #include <linux/zalloc.h>
 
-struct deferred_export {
-	struct list_head node;
-	struct comm *comm;
-};
-
-static int db_export__deferred(struct db_export *dbe)
-{
-	struct deferred_export *de;
-	int err;
-
-	while (!list_empty(&dbe->deferred)) {
-		de = list_entry(dbe->deferred.next, struct deferred_export,
-				node);
-		err = dbe->export_comm(dbe, de->comm);
-		list_del_init(&de->node);
-		free(de);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static void db_export__free_deferred(struct db_export *dbe)
-{
-	struct deferred_export *de;
-
-	while (!list_empty(&dbe->deferred)) {
-		de = list_entry(dbe->deferred.next, struct deferred_export,
-				node);
-		list_del_init(&de->node);
-		free(de);
-	}
-}
-
-static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
-{
-	struct deferred_export *de;
-
-	de = zalloc(sizeof(struct deferred_export));
-	if (!de)
-		return -ENOMEM;
-
-	de->comm = comm;
-	list_add_tail(&de->node, &dbe->deferred);
-
-	return 0;
-}
-
 int db_export__init(struct db_export *dbe)
 {
 	memset(dbe, 0, sizeof(struct db_export));
-	INIT_LIST_HEAD(&dbe->deferred);
 	return 0;
 }
 
-int db_export__flush(struct db_export *dbe)
-{
-	return db_export__deferred(dbe);
-}
-
 void db_export__exit(struct db_export *dbe)
 {
-	db_export__free_deferred(dbe);
 	call_return_processor__free(dbe->crp);
 	dbe->crp = NULL;
 }
@@ -115,71 +59,73 @@ int db_export__machine(struct db_export *dbe, struct machine *machine)
 }
 
 int db_export__thread(struct db_export *dbe, struct thread *thread,
-		      struct machine *machine, struct comm *comm)
+		      struct machine *machine, struct thread *main_thread)
 {
-	struct thread *main_thread;
 	u64 main_thread_db_id = 0;
-	int err;
 
 	if (thread->db_id)
 		return 0;
 
 	thread->db_id = ++dbe->thread_last_db_id;
 
-	if (thread->pid_ != -1) {
-		if (thread->pid_ == thread->tid) {
-			main_thread = thread;
-		} else {
-			main_thread = machine__findnew_thread(machine,
-							      thread->pid_,
-							      thread->pid_);
-			if (!main_thread)
-				return -ENOMEM;
-			err = db_export__thread(dbe, main_thread, machine,
-						comm);
-			if (err)
-				goto out_put;
-			if (comm) {
-				err = db_export__comm_thread(dbe, comm, thread);
-				if (err)
-					goto out_put;
-			}
-		}
+	if (main_thread)
 		main_thread_db_id = main_thread->db_id;
-		if (main_thread != thread)
-			thread__put(main_thread);
-	}
 
 	if (dbe->export_thread)
 		return dbe->export_thread(dbe, thread, main_thread_db_id,
 					  machine);
 
 	return 0;
+}
 
-out_put:
-	thread__put(main_thread);
-	return err;
+static int __db_export__comm(struct db_export *dbe, struct comm *comm,
+			     struct thread *thread)
+{
+	comm->db_id = ++dbe->comm_last_db_id;
+
+	if (dbe->export_comm)
+		return dbe->export_comm(dbe, comm, thread);
+
+	return 0;
 }
 
 int db_export__comm(struct db_export *dbe, struct comm *comm,
-		    struct thread *main_thread)
+		    struct thread *thread)
+{
+	if (comm->db_id)
+		return 0;
+
+	return __db_export__comm(dbe, comm, thread);
+}
+
+/*
+ * Export the "exec" comm. The "exec" comm is the program / application command
+ * name at the time it first executes. It is used to group threads for the same
+ * program. Note that the main thread pid (or thread group id tgid) cannot be
+ * used because it does not change when a new program is exec'ed.
+ */
+int db_export__exec_comm(struct db_export *dbe, struct comm *comm,
+			 struct thread *main_thread)
 {
 	int err;
 
 	if (comm->db_id)
 		return 0;
 
-	comm->db_id = ++dbe->comm_last_db_id;
-
-	if (dbe->export_comm) {
-		if (main_thread->comm_set)
-			err = dbe->export_comm(dbe, comm);
-		else
-			err = db_export__defer_comm(dbe, comm);
-		if (err)
-			return err;
-	}
+	err = __db_export__comm(dbe, comm, main_thread);
+	if (err)
+		return err;
 
+	/*
+	 * Record the main thread for this comm. Note that the main thread can
+	 * have many "exec" comms because there will be a new one every time it
+	 * exec's. An "exec" comm however will only ever have 1 main thread.
+	 * That is different to any other threads for that same program because
+	 * exec() will effectively kill them, so the relationship between the
+	 * "exec" comm and non-main threads is 1-to-1. That is why
+	 * db_export__comm_thread() is called here for the main thread, but it
+	 * is called for non-main threads when they are exported.
+	 */
 	return db_export__comm_thread(dbe, comm, main_thread);
 }
 
@@ -340,11 +286,65 @@ int db_export__branch_type(struct db_export *dbe, u32 branch_type,
 	return 0;
 }
 
+static int db_export__threads(struct db_export *dbe, struct thread *thread,
+			      struct thread *main_thread,
+			      struct machine *machine, struct comm **comm_ptr)
+{
+	struct comm *comm = NULL;
+	struct comm *curr_comm;
+	int err;
+
+	if (main_thread) {
+		/*
+		 * A thread has a reference to the main thread, so export the
+		 * main thread first.
+		 */
+		err = db_export__thread(dbe, main_thread, machine, main_thread);
+		if (err)
+			return err;
+		/*
+		 * Export comm before exporting the non-main thread because
+		 * db_export__comm_thread() can be called further below.
+		 */
+		comm = machine__thread_exec_comm(machine, main_thread);
+		if (comm) {
+			err = db_export__exec_comm(dbe, comm, main_thread);
+			if (err)
+				return err;
+			*comm_ptr = comm;
+		}
+	}
+
+	if (thread != main_thread) {
+		/*
+		 * For a non-main thread, db_export__comm_thread() must be
+		 * called only if thread has not previously been exported.
+		 */
+		bool export_comm_thread = comm && !thread->db_id;
+
+		err = db_export__thread(dbe, thread, machine, main_thread);
+		if (err)
+			return err;
+
+		if (export_comm_thread) {
+			err = db_export__comm_thread(dbe, comm, thread);
+			if (err)
+				return err;
+		}
+	}
+
+	curr_comm = thread__comm(thread);
+	if (curr_comm)
+		return db_export__comm(dbe, curr_comm, thread);
+
+	return 0;
+}
+
 int db_export__sample(struct db_export *dbe, union perf_event *event,
 		      struct perf_sample *sample, struct perf_evsel *evsel,
 		      struct addr_location *al)
 {
-	struct thread* thread = al->thread;
+	struct thread *thread = al->thread;
 	struct export_sample es = {
 		.event = event,
 		.sample = sample,
@@ -364,19 +364,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 		return err;
 
 	main_thread = thread__main_thread(al->machine, thread);
-	if (main_thread)
-		comm = machine__thread_exec_comm(al->machine, main_thread);
 
-	err = db_export__thread(dbe, thread, al->machine, comm);
+	err = db_export__threads(dbe, thread, main_thread, al->machine, &comm);
 	if (err)
 		goto out_put;
 
-	if (comm) {
-		err = db_export__comm(dbe, comm, main_thread);
-		if (err)
-			goto out_put;
+	if (comm)
 		es.comm_db_id = comm->db_id;
-	}
 
 	es.db_id = ++dbe->sample_last_db_id;
 
@@ -525,3 +519,92 @@ int db_export__call_return(struct db_export *dbe, struct call_return *cr,
 
 	return 0;
 }
+
+static int db_export__pid_tid(struct db_export *dbe, struct machine *machine,
+			      pid_t pid, pid_t tid, u64 *db_id,
+			      struct comm **comm_ptr, bool *is_idle)
+{
+	struct thread *thread = machine__find_thread(machine, pid, tid);
+	struct thread *main_thread;
+	int err = 0;
+
+	if (!thread || !thread->comm_set)
+		goto out_put;
+
+	*is_idle = !thread->pid_ && !thread->tid;
+
+	main_thread = thread__main_thread(machine, thread);
+
+	err = db_export__threads(dbe, thread, main_thread, machine, comm_ptr);
+
+	*db_id = thread->db_id;
+
+	thread__put(main_thread);
+out_put:
+	thread__put(thread);
+
+	return err;
+}
+
+int db_export__switch(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct machine *machine)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	bool out_preempt = out &&
+		(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT);
+	int flags = out | (out_preempt << 1);
+	bool is_idle_a = false, is_idle_b = false;
+	u64 th_a_id = 0, th_b_id = 0;
+	u64 comm_out_id, comm_in_id;
+	struct comm *comm_a = NULL;
+	struct comm *comm_b = NULL;
+	u64 th_out_id, th_in_id;
+	u64 db_id;
+	int err;
+
+	err = db_export__machine(dbe, machine);
+	if (err)
+		return err;
+
+	err = db_export__pid_tid(dbe, machine, sample->pid, sample->tid,
+				 &th_a_id, &comm_a, &is_idle_a);
+	if (err)
+		return err;
+
+	if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) {
+		pid_t pid = event->context_switch.next_prev_pid;
+		pid_t tid = event->context_switch.next_prev_tid;
+
+		err = db_export__pid_tid(dbe, machine, pid, tid, &th_b_id,
+					 &comm_b, &is_idle_b);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Do not export if both threads are unknown (i.e. not being traced),
+	 * or one is unknown and the other is the idle task.
+	 */
+	if ((!th_a_id || is_idle_a) && (!th_b_id || is_idle_b))
+		return 0;
+
+	db_id = ++dbe->context_switch_last_db_id;
+
+	if (out) {
+		th_out_id   = th_a_id;
+		th_in_id    = th_b_id;
+		comm_out_id = comm_a ? comm_a->db_id : 0;
+		comm_in_id  = comm_b ? comm_b->db_id : 0;
+	} else {
+		th_out_id   = th_b_id;
+		th_in_id    = th_a_id;
+		comm_out_id = comm_b ? comm_b->db_id : 0;
+		comm_in_id  = comm_a ? comm_a->db_id : 0;
+	}
+
+	if (dbe->export_context_switch)
+		return dbe->export_context_switch(dbe, db_id, machine, sample,
+						  th_out_id, comm_out_id,
+						  th_in_id, comm_in_id, flags);
+	return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index e8a64028a386..ba1f62a5fe10 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -43,7 +43,8 @@ struct db_export {
 	int (*export_machine)(struct db_export *dbe, struct machine *machine);
 	int (*export_thread)(struct db_export *dbe, struct thread *thread,
 			     u64 main_thread_db_id, struct machine *machine);
-	int (*export_comm)(struct db_export *dbe, struct comm *comm);
+	int (*export_comm)(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread);
 	int (*export_comm_thread)(struct db_export *dbe, u64 db_id,
 				  struct comm *comm, struct thread *thread);
 	int (*export_dso)(struct db_export *dbe, struct dso *dso,
@@ -56,6 +57,11 @@ struct db_export {
 	int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
 	int (*export_call_return)(struct db_export *dbe,
 				  struct call_return *cr);
+	int (*export_context_switch)(struct db_export *dbe, u64 db_id,
+				     struct machine *machine,
+				     struct perf_sample *sample,
+				     u64 th_out_id, u64 comm_out_id,
+				     u64 th_in_id, u64 comm_in_id, int flags);
 	struct call_return_processor *crp;
 	struct call_path_root *cpr;
 	u64 evsel_last_db_id;
@@ -68,18 +74,19 @@ struct db_export {
 	u64 sample_last_db_id;
 	u64 call_path_last_db_id;
 	u64 call_return_last_db_id;
-	struct list_head deferred;
+	u64 context_switch_last_db_id;
 };
 
 int db_export__init(struct db_export *dbe);
-int db_export__flush(struct db_export *dbe);
 void db_export__exit(struct db_export *dbe);
 int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
 int db_export__machine(struct db_export *dbe, struct machine *machine);
 int db_export__thread(struct db_export *dbe, struct thread *thread,
-		      struct machine *machine, struct comm *comm);
+		      struct machine *machine, struct thread *main_thread);
 int db_export__comm(struct db_export *dbe, struct comm *comm,
-		    struct thread *main_thread);
+		    struct thread *thread);
+int db_export__exec_comm(struct db_export *dbe, struct comm *comm,
+			 struct thread *main_thread);
 int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
 			   struct thread *thread);
 int db_export__dso(struct db_export *dbe, struct dso *dso,
@@ -97,5 +104,7 @@ int db_export__branch_types(struct db_export *dbe);
 int db_export__call_path(struct db_export *dbe, struct call_path *cp);
 int db_export__call_return(struct db_export *dbe, struct call_return *cr,
 			   u64 *parent_db_id);
+int db_export__switch(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct machine *machine);
 
 #endif
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0c3b55d0617d..cd1eb73cfe83 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1562,6 +1562,17 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
 		str = tmp + 1;
 	}
 
+	tmp = strchr(str, '@');
+	if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */
+		if (!user_access_is_supported()) {
+			semantic_error("ftrace does not support user access\n");
+			return -EINVAL;
+		}
+		*tmp = '\0';
+		arg->user_access = true;
+		pr_debug("user_access ");
+	}
+
 	tmp = strchr(str, ':');
 	if (tmp) {	/* Type setting */
 		*tmp = '\0';
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 05c8d571a901..96a319cd2378 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -37,6 +37,7 @@ struct probe_trace_point {
 struct probe_trace_arg_ref {
 	struct probe_trace_arg_ref	*next;	/* Next reference */
 	long				offset;	/* Offset value */
+	bool				user_access;	/* User-memory access */
 };
 
 /* kprobe-tracer and uprobe-tracer tracing argument */
@@ -82,6 +83,7 @@ struct perf_probe_arg {
 	char				*var;	/* Variable name */
 	char				*type;	/* Type name */
 	struct perf_probe_arg_field	*field;	/* Structure fields */
+	bool				user_access;	/* User-memory access */
 };
 
 /* Perf probe probing event (point + arg) */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index c2998f90b23c..5b4d49382932 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -1005,6 +1005,7 @@ enum ftrace_readme {
 	FTRACE_README_PROBE_TYPE_X = 0,
 	FTRACE_README_KRETPROBE_OFFSET,
 	FTRACE_README_UPROBE_REF_CTR,
+	FTRACE_README_USER_ACCESS,
 	FTRACE_README_END,
 };
 
@@ -1017,6 +1018,7 @@ static struct {
 	DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
 	DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
 	DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"),
+	DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"),
 };
 
 static bool scan_ftrace_readme(enum ftrace_readme type)
@@ -1077,3 +1079,8 @@ bool uprobe_ref_ctr_is_supported(void)
 {
 	return scan_ftrace_readme(FTRACE_README_UPROBE_REF_CTR);
 }
+
+bool user_access_is_supported(void)
+{
+	return scan_ftrace_readme(FTRACE_README_USER_ACCESS);
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 2a249182f2a6..986c1c94f64f 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -70,6 +70,7 @@ int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
 bool kretprobe_offset_is_supported(void);
 bool uprobe_ref_ctr_is_supported(void);
+bool user_access_is_supported(void);
 #else	/* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused)
 {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 7d8c99734928..025fc4491993 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -280,7 +280,7 @@ static_var:
 
 static int convert_variable_type(Dwarf_Die *vr_die,
 				 struct probe_trace_arg *tvar,
-				 const char *cast)
+				 const char *cast, bool user_access)
 {
 	struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
 	Dwarf_Die type;
@@ -320,7 +320,8 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	pr_debug("%s type is %s.\n",
 		 dwarf_diename(vr_die), dwarf_diename(&type));
 
-	if (cast && strcmp(cast, "string") == 0) {	/* String type */
+	if (cast && (!strcmp(cast, "string") || !strcmp(cast, "ustring"))) {
+		/* String type */
 		ret = dwarf_tag(&type);
 		if (ret != DW_TAG_pointer_type &&
 		    ret != DW_TAG_array_type) {
@@ -343,6 +344,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 				pr_warning("Out of memory error\n");
 				return -ENOMEM;
 			}
+			(*ref_ptr)->user_access = user_access;
 		}
 		if (!die_compare_name(&type, "char") &&
 		    !die_compare_name(&type, "unsigned char")) {
@@ -397,7 +399,7 @@ formatted:
 static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 				    struct perf_probe_arg_field *field,
 				    struct probe_trace_arg_ref **ref_ptr,
-				    Dwarf_Die *die_mem)
+				    Dwarf_Die *die_mem, bool user_access)
 {
 	struct probe_trace_arg_ref *ref = *ref_ptr;
 	Dwarf_Die type;
@@ -434,6 +436,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 				*ref_ptr = ref;
 		}
 		ref->offset += dwarf_bytesize(&type) * field->index;
+		ref->user_access = user_access;
 		goto next;
 	} else if (tag == DW_TAG_pointer_type) {
 		/* Check the pointer and dereference */
@@ -505,17 +508,18 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 		}
 	}
 	ref->offset += (long)offs;
+	ref->user_access = user_access;
 
 	/* If this member is unnamed, we need to reuse this field */
 	if (!dwarf_diename(die_mem))
 		return convert_variable_fields(die_mem, varname, field,
-						&ref, die_mem);
+						&ref, die_mem, user_access);
 
 next:
 	/* Converting next field */
 	if (field->next)
 		return convert_variable_fields(die_mem, field->name,
-					field->next, &ref, die_mem);
+				field->next, &ref, die_mem, user_access);
 	else
 		return 0;
 }
@@ -541,11 +545,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
 					      pf->pvar->field, &pf->tvar->ref,
-					      &die_mem);
+					      &die_mem, pf->pvar->user_access);
 		vr_die = &die_mem;
 	}
 	if (ret == 0)
-		ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type);
+		ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type,
+					    pf->pvar->user_access);
 	/* *expr will be cached in libdw. Don't free it. */
 	return ret;
 }
diff --git a/tools/perf/util/rlimit.c b/tools/perf/util/rlimit.c
new file mode 100644
index 000000000000..13521d392a22
--- /dev/null
+++ b/tools/perf/util/rlimit.c
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
+#include "util/debug.h"
+#include "util/rlimit.h"
+#include <sys/time.h>
+#include <sys/resource.h>
+
+/*
+ * Bump the memlock so that we can get bpf maps of a reasonable size,
+ * like the ones used with 'perf trace' and with 'perf test bpf',
+ * improve this to some specific request if needed.
+ */
+void rlimit__bump_memlock(void)
+{
+	struct rlimit rlim;
+
+	if (getrlimit(RLIMIT_MEMLOCK, &rlim) == 0) {
+		rlim.rlim_cur *= 4;
+		rlim.rlim_max *= 4;
+
+		if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0) {
+			rlim.rlim_cur /= 2;
+			rlim.rlim_max /= 2;
+
+			if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0)
+				pr_debug("Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc\n");
+		}
+	}
+}
diff --git a/tools/perf/util/rlimit.h b/tools/perf/util/rlimit.h
new file mode 100644
index 000000000000..9f59d8e710a3
--- /dev/null
+++ b/tools/perf/util/rlimit.h
@@ -0,0 +1,6 @@
+#ifndef __PERF_RLIMIT_H_
+#define __PERF_RLIMIT_H_
+/* SPDX-License-Identifier: LGPL-2.1 */
+
+void rlimit__bump_memlock(void);
+#endif // __PERF_RLIMIT_H_
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 112bed65232f..25dc1d765553 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -113,6 +113,7 @@ struct tables {
 	PyObject		*call_path_handler;
 	PyObject		*call_return_handler;
 	PyObject		*synth_handler;
+	PyObject		*context_switch_handler;
 	bool			db_export_mode;
 };
 
@@ -1011,15 +1012,19 @@ static int python_export_thread(struct db_export *dbe, struct thread *thread,
 	return 0;
 }
 
-static int python_export_comm(struct db_export *dbe, struct comm *comm)
+static int python_export_comm(struct db_export *dbe, struct comm *comm,
+			      struct thread *thread)
 {
 	struct tables *tables = container_of(dbe, struct tables, dbe);
 	PyObject *t;
 
-	t = tuple_new(2);
+	t = tuple_new(5);
 
 	tuple_set_u64(t, 0, comm->db_id);
 	tuple_set_string(t, 1, comm__str(comm));
+	tuple_set_u64(t, 2, thread->db_id);
+	tuple_set_u64(t, 3, comm->start);
+	tuple_set_s32(t, 4, comm->exec);
 
 	call_object(tables->comm_handler, t, "comm_table");
 
@@ -1233,6 +1238,34 @@ static int python_export_call_return(struct db_export *dbe,
 	return 0;
 }
 
+static int python_export_context_switch(struct db_export *dbe, u64 db_id,
+					struct machine *machine,
+					struct perf_sample *sample,
+					u64 th_out_id, u64 comm_out_id,
+					u64 th_in_id, u64 comm_in_id, int flags)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(9);
+
+	tuple_set_u64(t, 0, db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_u64(t, 2, sample->time);
+	tuple_set_s32(t, 3, sample->cpu);
+	tuple_set_u64(t, 4, th_out_id);
+	tuple_set_u64(t, 5, comm_out_id);
+	tuple_set_u64(t, 6, th_in_id);
+	tuple_set_u64(t, 7, comm_in_id);
+	tuple_set_s32(t, 8, flags);
+
+	call_object(tables->context_switch_handler, t, "context_switch");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
 static int python_process_call_return(struct call_return *cr, u64 *parent_db_id,
 				      void *data)
 {
@@ -1296,6 +1329,16 @@ static void python_process_event(union perf_event *event,
 	}
 }
 
+static void python_process_switch(union perf_event *event,
+				  struct perf_sample *sample,
+				  struct machine *machine)
+{
+	struct tables *tables = &tables_global;
+
+	if (tables->db_export_mode)
+		db_export__switch(&tables->dbe, event, sample, machine);
+}
+
 static void get_handler_name(char *str, size_t size,
 			     struct perf_evsel *evsel)
 {
@@ -1511,6 +1554,7 @@ static void set_table_handlers(struct tables *tables)
 	SET_TABLE_HANDLER(sample);
 	SET_TABLE_HANDLER(call_path);
 	SET_TABLE_HANDLER(call_return);
+	SET_TABLE_HANDLER(context_switch);
 
 	/*
 	 * Synthesized events are samples but with architecture-specific data
@@ -1620,9 +1664,7 @@ error:
 
 static int python_flush_script(void)
 {
-	struct tables *tables = &tables_global;
-
-	return db_export__flush(&tables->dbe);
+	return 0;
 }
 
 /*
@@ -1831,6 +1873,7 @@ struct scripting_ops python_scripting_ops = {
 	.flush_script		= python_flush_script,
 	.stop_script		= python_stop_script,
 	.process_event		= python_process_event,
+	.process_switch		= python_process_switch,
 	.process_stat		= python_process_stat,
 	.process_stat_interval	= python_process_stat_interval,
 	.generate_script	= python_generate_script,
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index d9b0a942090a..c7002fe11673 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -81,6 +81,9 @@ struct scripting_ops {
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
 			       struct addr_location *al);
+	void (*process_switch)(union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine);
 	void (*process_stat)(struct perf_stat_config *config,
 			     struct perf_evsel *evsel, u64 tstamp);
 	void (*process_stat_interval)(u64 tstamp);