Merge tag 'perf-for-bpf-2020-05-06' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into bpf-next

CAP_PERFMON for BPF

include/linux/capability.h

@@ -251,6 +251,10 @@ extern bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct
 extern bool capable_wrt_inode_uidgid(const struct inode *inode, int cap);
 extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
+static inline bool perfmon_capable(void)
+{
+	return capable(CAP_PERFMON) || capable(CAP_SYS_ADMIN);
+}
 
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);

include/uapi/linux/capability.h

@@ -367,8 +367,14 @@ struct vfs_ns_cap_data {
 
 #define CAP_AUDIT_READ		37
 
+/*
+ * Allow system performance and observability privileged operations
+ * using perf_events, i915_perf and other kernel subsystems
+ */
 
-#define CAP_LAST_CAP         CAP_AUDIT_READ
+#define CAP_PERFMON		38
+
+#define CAP_LAST_CAP         CAP_PERFMON
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 

security/selinux/include/classmap.h

@@ -27,9 +27,9 @@
 	    "audit_control", "setfcap"
 
 #define COMMON_CAP2_PERMS  "mac_override", "mac_admin", "syslog", \
-		"wake_alarm", "block_suspend", "audit_read"
+		"wake_alarm", "block_suspend", "audit_read", "perfmon"
 
-#if CAP_LAST_CAP > CAP_AUDIT_READ
+#if CAP_LAST_CAP > CAP_PERFMON
 #error New capability defined, please update COMMON_CAP2_PERMS.
 #endif
 

tools/perf/builtin-stat.c

@@ -686,8 +686,11 @@ try_again_reset:
 					break;
 			}
 		}
-		if (child_pid != -1)
+		if (child_pid != -1) {
+			if (timeout)
+				kill(child_pid, SIGTERM);
 			wait4(child_pid, &status, 0, &stat_config.ru_data);
+		}
 
 		if (workload_exec_errno) {
 			const char *emsg = str_error_r(workload_exec_errno, msg, sizeof(msg));

tools/perf/util/annotate.c

@@ -1821,6 +1821,24 @@ static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
 }
 #endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
 
+static int
+symbol__disassemble_bpf_image(struct symbol *sym,
+			      struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *dl;
+
+	args->offset = -1;
+	args->line = strdup("to be implemented");
+	args->line_nr = 0;
+	dl = disasm_line__new(args);
+	if (dl)
+		annotation_line__add(&dl->al, &notes->src->source);
+
+	free(args->line);
+	return 0;
+}
+
 /*
  * Possibly create a new version of line with tabs expanded. Returns the
  * existing or new line, storage is updated if a new line is allocated. If
@@ -1920,6 +1938,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
 		return symbol__disassemble_bpf(sym, args);
+	} else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
+		return symbol__disassemble_bpf_image(sym, args);
 	} else if (dso__is_kcore(dso)) {
 		kce.kcore_filename = symfs_filename;
 		kce.addr = map__rip_2objdump(map, sym->start);

tools/perf/util/bpf-event.c

@@ -6,6 +6,9 @@
 #include <bpf/libbpf.h>
 #include <linux/btf.h>
 #include <linux/err.h>
+#include <linux/string.h>
+#include <internal/lib.h>
+#include <symbol/kallsyms.h>
 #include "bpf-event.h"
 #include "debug.h"
 #include "dso.h"
@@ -290,11 +293,82 @@ out:
 	return err ? -1 : 0;
 }
 
+struct kallsyms_parse {
+	union perf_event	*event;
+	perf_event__handler_t	 process;
+	struct machine		*machine;
+	struct perf_tool	*tool;
+};
+
+static int
+process_bpf_image(char *name, u64 addr, struct kallsyms_parse *data)
+{
+	struct machine *machine = data->machine;
+	union perf_event *event = data->event;
+	struct perf_record_ksymbol *ksymbol;
+	int len;
+
+	ksymbol = &event->ksymbol;
+
+	*ksymbol = (struct perf_record_ksymbol) {
+		.header = {
+			.type = PERF_RECORD_KSYMBOL,
+			.size = offsetof(struct perf_record_ksymbol, name),
+		},
+		.addr      = addr,
+		.len       = page_size,
+		.ksym_type = PERF_RECORD_KSYMBOL_TYPE_BPF,
+		.flags     = 0,
+	};
+
+	len = scnprintf(ksymbol->name, KSYM_NAME_LEN, "%s", name);
+	ksymbol->header.size += PERF_ALIGN(len + 1, sizeof(u64));
+	memset((void *) event + event->header.size, 0, machine->id_hdr_size);
+	event->header.size += machine->id_hdr_size;
+
+	return perf_tool__process_synth_event(data->tool, event, machine,
+					      data->process);
+}
+
+static int
+kallsyms_process_symbol(void *data, const char *_name,
+			char type __maybe_unused, u64 start)
+{
+	char disp[KSYM_NAME_LEN];
+	char *module, *name;
+	unsigned long id;
+	int err = 0;
+
+	module = strchr(_name, '\t');
+	if (!module)
+		return 0;
+
+	/* We are going after [bpf] module ... */
+	if (strcmp(module + 1, "[bpf]"))
+		return 0;
+
+	name = memdup(_name, (module - _name) + 1);
+	if (!name)
+		return -ENOMEM;
+
+	name[module - _name] = 0;
+
+	/* .. and only for trampolines and dispatchers */
+	if ((sscanf(name, "bpf_trampoline_%lu", &id) == 1) ||
+	    (sscanf(name, "bpf_dispatcher_%s", disp) == 1))
+		err = process_bpf_image(name, start, data);
+
+	free(name);
+	return err;
+}
+
 int perf_event__synthesize_bpf_events(struct perf_session *session,
 				      perf_event__handler_t process,
 				      struct machine *machine,
 				      struct record_opts *opts)
 {
+	const char *kallsyms_filename = "/proc/kallsyms";
+	struct kallsyms_parse arg;
 	union perf_event *event;
 	__u32 id = 0;
 	int err;
@@ -303,6 +377,8 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 	event = malloc(sizeof(event->bpf) + KSYM_NAME_LEN + machine->id_hdr_size);
 	if (!event)
 		return -1;
+
+	/* Synthesize all the bpf programs in system. */
 	while (true) {
 		err = bpf_prog_get_next_id(id, &id);
 		if (err) {
@@ -335,6 +411,23 @@ int perf_event__synthesize_bpf_events(struct perf_session *session,
 			break;
 		}
 	}
+
+	/* Synthesize all the bpf images - trampolines/dispatchers. */
+	if (symbol_conf.kallsyms_name != NULL)
+		kallsyms_filename = symbol_conf.kallsyms_name;
+
+	arg = (struct kallsyms_parse) {
+		.event   = event,
+		.process = process,
+		.machine = machine,
+		.tool    = session->tool,
+	};
+
+	if (kallsyms__parse(kallsyms_filename, &arg, kallsyms_process_symbol)) {
+		pr_err("%s: failed to synthesize bpf images: %s\n",
+		       __func__, strerror(errno));
+	}
+
 	free(event);
 	return err;
 }

tools/perf/util/dso.c

@@ -191,6 +191,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
 	case DSO_BINARY_TYPE__JAVA_JIT:
 	case DSO_BINARY_TYPE__BPF_PROG_INFO:
+	case DSO_BINARY_TYPE__BPF_IMAGE:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 		ret = -1;
 		break;

tools/perf/util/dso.h

@@ -40,6 +40,7 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__GUEST_KCORE,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__BPF_PROG_INFO,
+	DSO_BINARY_TYPE__BPF_IMAGE,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
 

tools/perf/util/machine.c

@@ -736,6 +736,12 @@ int machine__process_switch_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
+static int is_bpf_image(const char *name)
+{
+	return strncmp(name, "bpf_trampoline_", sizeof("bpf_trampoline_") - 1) ||
+	       strncmp(name, "bpf_dispatcher_", sizeof("bpf_dispatcher_") - 1);
+}
+
 static int machine__process_ksymbol_register(struct machine *machine,
 					     union perf_event *event,
 					     struct perf_sample *sample __maybe_unused)
@@ -759,6 +765,12 @@ static int machine__process_ksymbol_register(struct machine *machine,
 		map->start = event->ksymbol.addr;
 		map->end = map->start + event->ksymbol.len;
 		maps__insert(&machine->kmaps, map);
+		dso__set_loaded(dso);
+
+		if (is_bpf_image(event->ksymbol.name)) {
+			dso->binary_type = DSO_BINARY_TYPE__BPF_IMAGE;
+			dso__set_long_name(dso, "", false);
+		}
 	}
 
 	sym = symbol__new(map->map_ip(map, map->start),

tools/perf/util/symbol.c

@@ -1544,6 +1544,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 		return true;
 
 	case DSO_BINARY_TYPE__BPF_PROG_INFO:
+	case DSO_BINARY_TYPE__BPF_IMAGE:
 	case DSO_BINARY_TYPE__NOT_FOUND:
 	default:
 		return false;