perf/core improvements and fixes

index 1a3f1be93372..966eddce1609 100644
@@ -1939,39 +1939,40 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 	r->total_run_time += r->dt_run;
 }
 
-static bool is_idle_sample(struct perf_sched *sched,
-			   struct perf_sample *sample,
-			   struct perf_evsel *evsel,
-			   struct machine *machine)
+static bool is_idle_sample(struct perf_sample *sample,
+			   struct perf_evsel *evsel)
 {
-	struct thread *thread;
-	struct callchain_cursor *cursor = &callchain_cursor;
-
 	/* pid 0 == swapper == idle task */
-	if (sample->pid == 0)
-		return true;
+	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0)
+		return perf_evsel__intval(evsel, sample, "prev_pid") == 0;
 
-	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0) {
-		if (perf_evsel__intval(evsel, sample, "prev_pid") == 0)
-			return true;
-	}
+	return sample->pid == 0;
+}
+
+static void save_task_callchain(struct perf_sched *sched,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	struct callchain_cursor *cursor = &callchain_cursor;
+	struct thread *thread;
 
 	/* want main thread for process - has maps */
 	thread = machine__findnew_thread(machine, sample->pid, sample->pid);
 	if (thread == NULL) {
 		pr_debug("Failed to get thread for pid %d.\n", sample->pid);
-		return false;
+		return;
 	}
 
 	if (!symbol_conf.use_callchain || sample->callchain == NULL)
-		return false;
+		return;
 
 	if (thread__resolve_callchain(thread, cursor, evsel, sample,
 				      NULL, NULL, sched->max_stack + 2) != 0) {
 		if (verbose)
 			error("Failed to resolve callchain. Skipping\n");
 
-		return false;
+		return;
 	}
 
 	callchain_cursor_commit(cursor);

@@ -1994,8 +1995,6 @@ static bool is_idle_sample(struct perf_sched *sched,
 
 		callchain_cursor_advance(cursor);
 	}
-
-	return false;
 }
 
 /*

@@ -2111,7 +2110,7 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 {
 	struct thread *thread;
 
-	if (is_idle_sample(sched, sample, evsel, machine)) {
+	if (is_idle_sample(sample, evsel)) {
 		thread = get_idle_thread(sample->cpu);
 		if (thread == NULL)
 			pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);

@@ -2124,6 +2123,8 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 			pr_debug("Failed to get thread for tid %d. skipping sample.\n",
 				 sample->tid);
 		}
+
+		save_task_callchain(sched, sample, evsel, machine);
 	}
 
 	return thread;

index 966eddce1609..e108b0f6a246 100644
@@ -230,6 +230,15 @@ struct evsel_runtime {
 	u32 ncpu;       /* highest cpu slot allocated */
 };
 
+/* per cpu idle time data */
+struct idle_thread_runtime {
+	struct thread_runtime	tr;
+	struct thread		*last_thread;
+	struct rb_root		sorted_root;
+	struct callchain_root	callchain;
+	struct callchain_cursor	cursor;
+};
+
 /* track idle times per cpu */
 static struct thread **idle_threads;
 static int idle_max_cpu;

@@ -1997,13 +2006,31 @@ static void save_task_callchain(struct perf_sched *sched,
 	}
 }
 
+static int init_idle_thread(struct thread *thread)
+{
+	struct idle_thread_runtime *itr;
+
+	thread__set_comm(thread, idle_comm, 0);
+
+	itr = zalloc(sizeof(*itr));
+	if (itr == NULL)
+		return -ENOMEM;
+
+	init_stats(&itr->tr.run_stats);
+	callchain_init(&itr->callchain);
+	callchain_cursor_reset(&itr->cursor);
+	thread__set_priv(thread, itr);
+
+	return 0;
+}
+
 /*
  * Track idle stats per cpu by maintaining a local thread
  * struct for the idle task on each cpu.
  */
 static int init_idle_threads(int ncpu)
 {
-	int i;
+	int i, ret;
 
 	idle_threads = zalloc(ncpu * sizeof(struct thread *));
 	if (!idle_threads)

@@ -2017,7 +2044,9 @@ static int init_idle_threads(int ncpu)
 		if (idle_threads[i] == NULL)
 			return -ENOMEM;
 
-		thread__set_comm(idle_threads[i], idle_comm, 0);
+		ret = init_idle_thread(idle_threads[i]);
+		if (ret < 0)
+			return ret;
 	}
 
 	return 0;

@@ -2064,8 +2093,8 @@ static struct thread *get_idle_thread(int cpu)
 		idle_threads[cpu] = thread__new(0, 0);
 
 		if (idle_threads[cpu]) {
-			idle_threads[cpu]->tid = 0;
-			thread__set_comm(idle_threads[cpu], idle_comm, 0);
+			if (init_idle_thread(idle_threads[cpu]) < 0)
+				return NULL;
 		}
 	}
 

index e108b0f6a246..dc83b803ca54 100644
@@ -200,6 +200,7 @@ struct perf_sched {
 	/* options for timehist command */
 	bool		summary;
 	bool		summary_only;
+	bool		idle_hist;
 	bool		show_callchain;
 	unsigned int	max_stack;
 	bool		show_cpu_visual;

@@ -2101,6 +2102,15 @@ static struct thread *get_idle_thread(int cpu)
 	return idle_threads[cpu];
 }
 
+static void save_idle_callchain(struct idle_thread_runtime *itr,
+				struct perf_sample *sample)
+{
+	if (!symbol_conf.use_callchain || sample->callchain == NULL)
+		return;
+
+	callchain_cursor__copy(&itr->cursor, &callchain_cursor);
+}
+
 /*
  * handle runtime stats saved per thread
  */

@@ -2154,6 +2164,26 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 		}
 
 		save_task_callchain(sched, sample, evsel, machine);
+		if (sched->idle_hist) {
+			struct thread *idle;
+			struct idle_thread_runtime *itr;
+
+			idle = get_idle_thread(sample->cpu);
+			if (idle == NULL) {
+				pr_err("Failed to get idle thread for cpu %d.\n", sample->cpu);
+				return NULL;
+			}
+
+			itr = thread__priv(idle);
+			if (itr == NULL)
+				return NULL;
+
+			itr->last_thread = thread;
+
+			/* copy task callchain when entering to idle */
+			if (perf_evsel__intval(evsel, sample, "next_pid") == 0)
+				save_idle_callchain(itr, sample);
+		}
 	}
 
 	return thread;

index dc83b803ca54..c8e7848e71a7 100644
@@ -2190,7 +2190,9 @@ static struct thread *timehist_get_thread(struct perf_sched *sched,
 }
 
 static bool timehist_skip_sample(struct perf_sched *sched,
-				 struct thread *thread)
+				 struct thread *thread,
+				 struct perf_evsel *evsel,
+				 struct perf_sample *sample)
 {
 	bool rc = false;
 

@@ -2199,10 +2201,19 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 		sched->skipped_samples++;
 	}
 
+	if (sched->idle_hist) {
+		if (strcmp(perf_evsel__name(evsel), "sched:sched_switch"))
+			rc = true;
+		else if (perf_evsel__intval(evsel, sample, "prev_pid") != 0 &&
+			 perf_evsel__intval(evsel, sample, "next_pid") != 0)
+			rc = true;
+	}
+
 	return rc;
 }
 
 static void timehist_print_wakeup_event(struct perf_sched *sched,
+					struct perf_evsel *evsel,
 					struct perf_sample *sample,
 					struct machine *machine,
 					struct thread *awakened)

@@ -2215,8 +2226,8 @@ static void timehist_print_wakeup_event(struct perf_sched *sched,
 		return;
 
 	/* show wakeup unless both awakee and awaker are filtered */
-	if (timehist_skip_sample(sched, thread) &&
-	    timehist_skip_sample(sched, awakened)) {
+	if (timehist_skip_sample(sched, thread, evsel, sample) &&
+	    timehist_skip_sample(sched, awakened, evsel, sample)) {
 		return;
 	}
 

@@ -2261,7 +2272,7 @@ static int timehist_sched_wakeup_event(struct perf_tool *tool,
 	/* show wakeups if requested */
 	if (sched->show_wakeups &&
 	    !perf_time__skip_sample(&sched->ptime, sample->time))
-		timehist_print_wakeup_event(sched, sample, machine, thread);
+		timehist_print_wakeup_event(sched, evsel, sample, machine, thread);
 
 	return 0;
 }

@@ -2288,8 +2299,8 @@ static void timehist_print_migration_event(struct perf_sched *sched,
 	if (thread == NULL)
 		return;
 
-	if (timehist_skip_sample(sched, thread) &&
-	    timehist_skip_sample(sched, migrated)) {
+	if (timehist_skip_sample(sched, thread, evsel, sample) &&
+	    timehist_skip_sample(sched, migrated, evsel, sample)) {
 		return;
 	}
 

@@ -2374,7 +2385,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 		goto out;
 	}
 
-	if (timehist_skip_sample(sched, thread))
+	if (timehist_skip_sample(sched, thread, evsel, sample))
 		goto out;
 
 	tr = thread__get_runtime(thread);

70 lines not on this page · raw message

index 0b14265432df..c1c07bfe132c 100644
@@ -2448,6 +2448,9 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 			last_tr->dt_wait = 0;
 			last_tr->dt_delay = 0;
 
+			if (itr->cursor.nr)
+				callchain_append(&itr->callchain, &itr->cursor, t - tprev);
+
 			itr->last_thread = NULL;
 		}
 	}

@@ -2557,6 +2560,60 @@ static int show_deadthread_runtime(struct thread *t, void *priv)
 	return __show_thread_runtime(t, priv);
 }
 
+static size_t callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
+{
+	const char *sep = " <- ";
+	struct callchain_list *chain;
+	size_t ret = 0;
+	char bf[1024];
+	bool first;
+
+	if (node == NULL)
+		return 0;
+
+	ret = callchain__fprintf_folded(fp, node->parent);
+	first = (ret == 0);
+
+	list_for_each_entry(chain, &node->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		if (chain->ms.sym && chain->ms.sym->ignore)
+			continue;
+		ret += fprintf(fp, "%s%s", first ? "" : sep,
+			       callchain_list__sym_name(chain, bf, sizeof(bf),
+							false));
+		first = false;
+	}
+
+	return ret;
+}
+
+static size_t timehist_print_idlehist_callchain(struct rb_root *root)
+{
+	size_t ret = 0;
+	FILE *fp = stdout;
+	struct callchain_node *chain;
+	struct rb_node *rb_node = rb_first(root);
+
+	printf("  %16s  %8s  %s\n", "Idle time (msec)", "Count", "Callchains");
+	printf("  %.16s  %.8s  %.50s\n", graph_dotted_line, graph_dotted_line,
+	       graph_dotted_line);
+
+	while (rb_node) {
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+		rb_node = rb_next(rb_node);
+
+		ret += fprintf(fp, "  ");
+		print_sched_time(chain->hit, 12);
+		ret += 16;  /* print_sched_time returns 2nd arg + 4 */
+		ret += fprintf(fp, " %8d  ", chain->count);
+		ret += callchain__fprintf_folded(fp, chain);
+		ret += fprintf(fp, "\n");
+	}
+
+	return ret;
+}
+
 static void timehist_print_summary(struct perf_sched *sched,
 				   struct perf_session *session)
 {

@@ -2615,6 +2672,35 @@ static void timehist_print_summary(struct perf_sched *sched,
 			printf("    CPU %2d idle entire time window\n", i);
 	}
 
+	if (sched->idle_hist && symbol_conf.use_callchain) {
+		callchain_param.mode  = CHAIN_FOLDED;
+		callchain_param.value = CCVAL_PERIOD;
+
+		callchain_register_param(&callchain_param);
+
+		printf("\nIdle stats by callchain:\n");
+		for (i = 0; i < idle_max_cpu; ++i) {
+			struct idle_thread_runtime *itr;
+
+			t = idle_threads[i];
+			if (!t)
+				continue;
+
+			itr = thread__priv(t);
+			if (itr == NULL)
+				continue;
+
+			callchain_param.sort(&itr->sorted_root, &itr->callchain,
+					     0, &callchain_param);
+
+			printf("  CPU %2d:", i);
+			print_sched_time(itr->tr.total_run_time, 6);
+			printf(" msec\n");
+			timehist_print_idlehist_callchain(&itr->sorted_root);
+			printf("\n");
+		}
+	}
+
 	printf("\n"
 	       "    Total number of unique tasks: %" PRIu64 "\n"
 	       "Total number of context switches: %" PRIu64 "\n"

index 9e5fc168c8a3..f09c70b97eca 100644
@@ -95,6 +95,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_SCHED_ACT,
 	BPF_PROG_TYPE_TRACEPOINT,
 	BPF_PROG_TYPE_XDP,
+	BPF_PROG_TYPE_PERF_EVENT,
 };
 
 #define BPF_PSEUDO_MAP_FD	1

@@ -375,6 +376,56 @@ enum bpf_func_id {
 	 */
 	BPF_FUNC_probe_write_user,
 
+	/**
+	 * bpf_current_task_under_cgroup(map, index) - Check cgroup2 membership of current task
+	 * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+	 * @index: index of the cgroup in the bpf_map
+	 * Return:
+	 *   == 0 current failed the cgroup2 descendant test
+	 *   == 1 current succeeded the cgroup2 descendant test
+	 *    < 0 error
+	 */
+	BPF_FUNC_current_task_under_cgroup,
+
+	/**
+	 * bpf_skb_change_tail(skb, len, flags)
+	 * The helper will resize the skb to the given new size,
+	 * to be used f.e. with control messages.
+	 * @skb: pointer to skb
+	 * @len: new skb length
+	 * @flags: reserved
+	 * Return: 0 on success or negative error
+	 */
+	BPF_FUNC_skb_change_tail,
+
+	/**
+	 * bpf_skb_pull_data(skb, len)
+	 * The helper will pull in non-linear data in case the
+	 * skb is non-linear and not all of len are part of the
+	 * linear section. Only needed for read/write with direct
+	 * packet access.
+	 * @skb: pointer to skb
+	 * @len: len to make read/writeable
+	 * Return: 0 on success or negative error
+	 */
+	BPF_FUNC_skb_pull_data,
+
+	/**
+	 * bpf_csum_update(skb, csum)
+	 * Adds csum into skb->csum in case of CHECKSUM_COMPLETE.
+	 * @skb: pointer to skb
+	 * @csum: csum to add
+	 * Return: csum on success or negative error
+	 */
+	BPF_FUNC_csum_update,
+
+	/**
+	 * bpf_set_hash_invalid(skb)
+	 * Invalidate current skb>hash.
+	 * @skb: pointer to skb
+	 */
+	BPF_FUNC_set_hash_invalid,
+
 	__BPF_FUNC_MAX_ID,
 };
 

index 8143536b462a..89e8e8e5b60e 100644
@@ -70,7 +70,7 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
 
 int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		     size_t insns_cnt, char *license,
-		     u32 kern_version, char *log_buf, size_t log_buf_sz)
+		     __u32 kern_version, char *log_buf, size_t log_buf_sz)
 {
 	int fd;
 	union bpf_attr attr;

@@ -98,7 +98,7 @@ int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 }
 
 int bpf_map_update_elem(int fd, void *key, void *value,
-			u64 flags)
+			__u64 flags)
 {
 	union bpf_attr attr;
 

index 253c3dbb06b4..61130170a6ad 100644
@@ -30,11 +30,11 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 #define BPF_LOG_BUF_SIZE 65536
 int bpf_load_program(enum bpf_prog_type type, struct bpf_insn *insns,
 		     size_t insns_cnt, char *license,
-		     u32 kern_version, char *log_buf,
+		     __u32 kern_version, char *log_buf,
 		     size_t log_buf_sz);
 
 int bpf_map_update_elem(int fd, void *key, void *value,
-			u64 flags);
+			__u64 flags);
 
 int bpf_map_lookup_elem(int fd, void *key, void *value);
 int bpf_map_delete_elem(int fd, void *key);

index 89e8e8e5b60e..d0afb26c2e0f 100644
@@ -54,7 +54,7 @@ static int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 }
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size,
-		   int value_size, int max_entries)
+		   int value_size, int max_entries, __u32 map_flags)
 {
 	union bpf_attr attr;
 

@@ -64,6 +64,7 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size,
 	attr.key_size = key_size;
 	attr.value_size = value_size;
 	attr.max_entries = max_entries;
+	attr.map_flags = map_flags;
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }

index 61130170a6ad..7fcdce16fd62 100644
@@ -24,7 +24,7 @@
 #include <linux/bpf.h>
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries);
+		   int max_entries, __u32 map_flags);
 
 /* Recommend log buffer size */
 #define BPF_LOG_BUF_SIZE 65536

index 2e974593f3e8..84e6b35da4bd 100644
@@ -854,7 +854,8 @@ bpf_object__create_maps(struct bpf_object *obj)
 		*pfd = bpf_create_map(def->type,
 				      def->key_size,
 				      def->value_size,
-				      def->max_entries);
+				      def->max_entries,
+				      0);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;

index 97913e109b14..f8e3c58a0897 100644
@@ -18,7 +18,6 @@
 #include <poll.h>
 #include <ctype.h>
 #include "libbpf.h"
-#include "bpf_helpers.h"
 #include "bpf_load.h"
 
 #define DEBUGFS "/sys/kernel/debug/tracing/"

@@ -26,17 +25,26 @@
 static char license[128];
 static int kern_version;
 static bool processed_sec[128];
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 int map_fd[MAX_MAPS];
 int prog_fd[MAX_PROGS];
 int event_fd[MAX_PROGS];
 int prog_cnt;
 int prog_array_fd = -1;
 
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+	unsigned int map_flags;
+};
+
 static int populate_prog_array(const char *event, int prog_fd)
 {
 	int ind = atoi(event), err;
 
-	err = bpf_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
+	err = bpf_map_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY);
 	if (err < 0) {
 		printf("failed to store prog_fd in prog_array\n");
 		return -1;

@@ -77,9 +85,10 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		return -1;
 	}
 
-	fd = bpf_prog_load(prog_type, prog, size, license, kern_version);
+	fd = bpf_load_program(prog_type, prog, size, license, kern_version,
+			      NULL, 0);
 	if (fd < 0) {
-		printf("bpf_prog_load() err=%d\n%s", errno, bpf_log_buf);
+		printf("bpf_load_program() err=%d\n%s", errno, bpf_log_buf);
 		return -1;
 	}
 

index 625e797be6ef..4ffd8f340496 100644
@@ -58,8 +58,9 @@ static int bpf_prog_create(const char *object)
 		assert(!load_bpf_file((char *)object));
 		return prog_fd[0];
 	} else {
-		return bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER,
-				     insns, sizeof(insns), "GPL", 0);
+		return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER,
+					insns, sizeof(insns), "GPL", 0, NULL,
+					0);
 	}
 }
 

@@ -83,12 +84,12 @@ static int bpf_do_map(const char *file, uint32_t flags, uint32_t key,
 	}
 
 	if ((flags & BPF_F_KEY_VAL) == BPF_F_KEY_VAL) {
-		ret = bpf_update_elem(fd, &key, &value, 0);
+		ret = bpf_map_update_elem(fd, &key, &value, 0);
 		printf("bpf: fd:%d u->(%u:%u) ret:(%d,%s)\n", fd, key, value,
 		       ret, strerror(errno));
 		assert(ret == 0);
 	} else if (flags & BPF_F_KEY) {
-		ret = bpf_lookup_elem(fd, &key, &value);
+		ret = bpf_map_lookup_elem(fd, &key, &value);
 		printf("bpf: fd:%d l->(%u):%u ret:(%d,%s)\n", fd, key, value,
 		       ret, strerror(errno));
 		assert(ret == 0);

index 65da8c1576de..bcdee00816b2 100644
@@ -23,6 +23,7 @@ struct cpu_hist {
 };
 
 static struct cpu_hist cpu_hist[MAX_CPU];
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static void stars(char *str, long val, long max, int width)
 {

@@ -73,7 +74,7 @@ static void get_data(int fd)
 	for (c = 0; c < MAX_CPU; c++) {
 		for (i = 0; i < MAX_ENTRIES; i++) {
 			key = c * MAX_ENTRIES + i;
-			bpf_lookup_elem(fd, &key, &value);
+			bpf_map_lookup_elem(fd, &key, &value);
 
 			cpu_hist[c].data[i] = value;
 			if (value > cpu_hist[c].max)

index 9969e35550c3..e5c5a69996fc 100644
@@ -32,7 +32,7 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 	return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
 }
 
-int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags)
+int bpf_map_update_elem(int fd, void *key, void *value, unsigned long long flags)
 {
 	union bpf_attr attr = {
 		.map_fd = fd,

@@ -44,7 +44,7 @@ int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags)
 	return syscall(__NR_bpf, BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
 }
 
-int bpf_lookup_elem(int fd, void *key, void *value)
+int bpf_map_lookup_elem(int fd, void *key, void *value)
 {
 	union bpf_attr attr = {
 		.map_fd = fd,

@@ -55,7 +55,7 @@ int bpf_lookup_elem(int fd, void *key, void *value)
 	return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
 }
 
-int bpf_delete_elem(int fd, void *key)
+int bpf_map_delete_elem(int fd, void *key)
 {
 	union bpf_attr attr = {
 		.map_fd = fd,

@@ -65,7 +65,7 @@ int bpf_delete_elem(int fd, void *key)
 	return syscall(__NR_bpf, BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
 }
 
-int bpf_get_next_key(int fd, void *key, void *next_key)
+int bpf_map_get_next_key(int fd, void *key, void *next_key)
 {
 	union bpf_attr attr = {
 		.map_fd = fd,

@@ -78,19 +78,18 @@ int bpf_get_next_key(int fd, void *key, void *next_key)
 
 #define ROUND_UP(x, n) (((x) + (n) - 1u) & ~((n) - 1u))
 
-char bpf_log_buf[LOG_BUF_SIZE];
-
-int bpf_prog_load(enum bpf_prog_type prog_type,
-		  const struct bpf_insn *insns, int prog_len,
-		  const char *license, int kern_version)
+int bpf_load_program(enum bpf_prog_type prog_type,
+		     const struct bpf_insn *insns, int prog_len,
+		     const char *license, int kern_version,
+		     char *log_buf, size_t log_buf_sz)
 {
 	union bpf_attr attr = {
 		.prog_type = prog_type,
 		.insns = ptr_to_u64((void *) insns),
 		.insn_cnt = prog_len / sizeof(struct bpf_insn),
 		.license = ptr_to_u64((void *) license),
-		.log_buf = ptr_to_u64(bpf_log_buf),
-		.log_size = LOG_BUF_SIZE,
+		.log_buf = ptr_to_u64(log_buf),
+		.log_size = log_buf_sz,
 		.log_level = 1,
 	};
 

@@ -99,7 +98,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	 */
 	attr.kern_version = kern_version;
 
-	bpf_log_buf[0] = 0;
+	log_buf[0] = 0;
 
 	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
 }

index ac6edb61b64a..1325152be4cd 100644
@@ -6,20 +6,20 @@ struct bpf_insn;
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries, int map_flags);
-int bpf_update_elem(int fd, void *key, void *value, unsigned long long flags);
-int bpf_lookup_elem(int fd, void *key, void *value);
-int bpf_delete_elem(int fd, void *key);
-int bpf_get_next_key(int fd, void *key, void *next_key);
+int bpf_map_update_elem(int fd, void *key, void *value, unsigned long long flags);
+int bpf_map_lookup_elem(int fd, void *key, void *value);
+int bpf_map_delete_elem(int fd, void *key);
+int bpf_map_get_next_key(int fd, void *key, void *next_key);
 
-int bpf_prog_load(enum bpf_prog_type prog_type,
-		  const struct bpf_insn *insns, int insn_len,
-		  const char *license, int kern_version);
+int bpf_load_program(enum bpf_prog_type prog_type,
+		     const struct bpf_insn *insns, int insn_len,
+		     const char *license, int kern_version,
+		     char *log_buf, size_t log_buf_sz);
 
 int bpf_obj_pin(int fd, const char *pathname);
 int bpf_obj_get(const char *pathname);
 
-#define LOG_BUF_SIZE 65536
-extern char bpf_log_buf[LOG_BUF_SIZE];
+#define BPF_LOG_BUF_SIZE 65536
 
 /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
 

index 3147377e8fd3..62ed870590cc 100644
@@ -37,6 +37,7 @@ static __u64 time_get_ns(void)
 #define PERCPU_HASH_KMALLOC	(1 << 3)
 
 static int test_flags = ~0;
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static void test_hash_prealloc(int cpu)
 {

index 6f002a9c24fa..dd2598b1fabc 100644
@@ -20,6 +20,8 @@
 
 #define PRINT_RAW_ADDR 0
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static void print_ksym(__u64 addr)
 {
 	struct ksym *sym;

@@ -49,14 +51,14 @@ static void print_stack(struct key_t *key, __u64 count)
 	int i;
 
 	printf("%s;", key->target);
-	if (bpf_lookup_elem(map_fd[3], &key->tret, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[3], &key->tret, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
 			print_ksym(ip[i]);
 	}
 	printf("-;");
-	if (bpf_lookup_elem(map_fd[3], &key->wret, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[3], &key->wret, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = 0; i < PERF_MAX_STACK_DEPTH; i++)

@@ -77,8 +79,8 @@ static void print_stacks(int fd)
 	struct key_t key = {}, next_key;
 	__u64 value;
 
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
-		bpf_lookup_elem(fd, &next_key, &value);
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
 		print_stack(&next_key, value);
 		key = next_key;
 	}

index 260a6bdd6413..09ab620b324c 100644
@@ -28,6 +28,7 @@
 #define PAGE_OFFSET	0xffff880000000000
 
 static int nr_cpus;
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static void usage(void)
 {

@@ -95,8 +96,8 @@ static void print_ip_map(int fd)
 
 	/* fetch IPs and counts */
 	key = 0, i = 0;
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
-		bpf_lookup_elem(fd, &next_key, &value);
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
 		counts[i].ip = next_key;
 		counts[i++].count = value;
 		key = next_key;

index 28b60baa9fa8..7ab636c30154 100644
@@ -55,8 +55,8 @@ static int test_sock(void)
 		BPF_EXIT_INSN(),
 	};
 
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog, sizeof(prog),
-				"GPL", 0);
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, sizeof(prog),
+				   "GPL", 0, NULL, 0);
 	if (prog_fd < 0) {
 		printf("failed to load prog '%s'\n", strerror(errno));
 		goto cleanup;

@@ -72,13 +72,13 @@ static int test_sock(void)
 
 	for (i = 0; i < 10; i++) {
 		key = IPPROTO_TCP;
-		assert(bpf_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
 
 		key = IPPROTO_UDP;
-		assert(bpf_lookup_elem(map_fd, &key, &udp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0);
 
 		key = IPPROTO_ICMP;
-		assert(bpf_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
 
 		printf("TCP %lld UDP %lld ICMP %lld packets\n",
 		       tcp_cnt, udp_cnt, icmp_cnt);

index 678ce4693551..2956d893d732 100644
@@ -6,6 +6,8 @@
 #include <unistd.h>
 #include <arpa/inet.h>
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 int main(int ac, char **argv)
 {
 	char filename[256];

@@ -32,13 +34,13 @@ int main(int ac, char **argv)
 		int key;
 
 		key = IPPROTO_TCP;
-		assert(bpf_lookup_elem(map_fd[0], &key, &tcp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd[0], &key, &tcp_cnt) == 0);
 
 		key = IPPROTO_UDP;
-		assert(bpf_lookup_elem(map_fd[0], &key, &udp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd[0], &key, &udp_cnt) == 0);
 
 		key = IPPROTO_ICMP;
-		assert(bpf_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0);
+		assert(bpf_map_lookup_elem(map_fd[0], &key, &icmp_cnt) == 0);
 
 		printf("TCP %lld UDP %lld ICMP %lld bytes\n",
 		       tcp_cnt, udp_cnt, icmp_cnt);

index 8a4085c2d117..c43958a67cca 100644
@@ -7,6 +7,8 @@
 #include <arpa/inet.h>
 #include <sys/resource.h>
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 struct pair {
 	__u64 packets;
 	__u64 bytes;

@@ -39,8 +41,8 @@ int main(int ac, char **argv)
 		int key = 0, next_key;
 		struct pair value;
 
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[0], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
 			printf("ip %s bytes %lld packets %lld\n",
 			       inet_ntoa((struct in_addr){htonl(next_key)}),
 			       value.bytes, value.packets);

index 3fcfd8c4b2a3..2cb9011ea440 100644
@@ -7,6 +7,8 @@
 #include <arpa/inet.h>
 #include <sys/resource.h>
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 struct bpf_flow_keys {
 	__be32 src;
 	__be32 dst;

@@ -54,8 +56,8 @@ int main(int argc, char **argv)
 
 		sleep(1);
 		printf("IP     src.port -> dst.port               bytes      packets\n");
-		while (bpf_get_next_key(map_fd[2], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[2], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[2], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[2], &next_key, &value);
 			printf("%s.%05d -> %s.%05d %12lld %12lld\n",
 			       inet_ntoa((struct in_addr){htonl(next_key.src)}),
 			       next_key.port16[0],

index 311ede532230..8950a3d27a92 100644
@@ -7,6 +7,8 @@
 #include "libbpf.h"
 #include "bpf_load.h"
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 int main(int ac, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};

@@ -31,8 +33,8 @@ int main(int ac, char **argv)
 	for (i = 0; i < 5; i++) {
 		key = 0;
 		printf("kprobing funcs:");
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[0], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
 			assert(next_key == value);
 			sym = ksym_search(value);
 			printf(" %s", sym->name);

@@ -41,8 +43,8 @@ int main(int ac, char **argv)
 		if (key)
 			printf("\n");
 		key = 0;
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0)
-			bpf_delete_elem(map_fd[0], &next_key);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0)
+			bpf_map_delete_elem(map_fd[0], &next_key);
 		sleep(1);
 	}
 

index 4013c5337b91..28995a776560 100644
@@ -60,9 +60,9 @@ int main(int argc, char **argv)
 	}
 
 	/* bpf_tunnel_key.remote_ipv4 expects host byte orders */
-	ret = bpf_update_elem(array_fd, &array_key, &ifindex, 0);
+	ret = bpf_map_update_elem(array_fd, &array_key, &ifindex, 0);
 	if (ret) {
-		perror("bpf_update_elem");
+		perror("bpf_map_update_elem");
 		goto out;
 	}
 

index 70e86f7be69d..8a1b8b5d8def 100644
@@ -85,9 +85,9 @@ int main(int argc, char **argv)
 		}
 	}
 
-	ret = bpf_update_elem(array_fd, &array_key, &cg2_fd, 0);
+	ret = bpf_map_update_elem(array_fd, &array_key, &cg2_fd, 0);
 	if (ret) {
-		perror("bpf_update_elem");
+		perror("bpf_map_update_elem");
 		goto out;
 	}
 

index 30b0bce884f9..054915324aeb 100644
@@ -28,6 +28,8 @@
 #define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
 	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static int join_cgroup(char *path)
 {
 	int fd, rc = 0;

@@ -94,7 +96,7 @@ int main(int argc, char **argv)
 		goto cleanup_cgroup_err;
 	}
 
-	if (bpf_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) {
+	if (bpf_map_update_elem(map_fd[0], &idx, &cg2, BPF_ANY)) {
 		log_err("Adding target cgroup to map");
 		goto cleanup_cgroup_err;
 	}

@@ -109,7 +111,7 @@ int main(int argc, char **argv)
 	 */
 
 	sync();
-	bpf_lookup_elem(map_fd[1], &idx, &remote_pid);
+	bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid);
 
 	if (local_pid != remote_pid) {
 		fprintf(stderr,

@@ -123,10 +125,10 @@ int main(int argc, char **argv)
 		goto leave_cgroup_err;
 
 	remote_pid = 0;
-	bpf_update_elem(map_fd[1], &idx, &remote_pid, BPF_ANY);
+	bpf_map_update_elem(map_fd[1], &idx, &remote_pid, BPF_ANY);
 
 	sync();
-	bpf_lookup_elem(map_fd[1], &idx, &remote_pid);
+	bpf_map_lookup_elem(map_fd[1], &idx, &remote_pid);
 
 	if (local_pid == remote_pid) {
 		fprintf(stderr, "BPF cgroup negative test did not work\n");

361 lines not on this page · raw message

index d291167fd3c7..74b79af98ba2 100644
@@ -24,6 +24,8 @@
 
 #define MAX_CNT 1000000
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static __u64 time_get_ns(void)
 {
 	struct timespec ts;

index a44bf347bedd..29af2160e4e2 100644
@@ -9,6 +9,8 @@
 #include <netinet/in.h>
 #include <arpa/inet.h>
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 int main(int ac, char **argv)
 {
 	int serverfd, serverconnfd, clientfd;

@@ -50,7 +52,7 @@ int main(int ac, char **argv)
 	mapped_addr_in->sin_port = htons(5555);
 	mapped_addr_in->sin_addr.s_addr = inet_addr("255.255.255.255");
 
-	assert(!bpf_update_elem(map_fd[0], &mapped_addr, &serv_addr, BPF_ANY));
+	assert(!bpf_map_update_elem(map_fd[0], &mapped_addr, &serv_addr, BPF_ANY));
 
 	assert(listen(serverfd, 5) == 0);
 

index 369ffaad3799..2e85a8e2d696 100644
@@ -24,6 +24,8 @@
 
 #define MAX_FIXUPS 8
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];

@@ -2466,9 +2468,9 @@ static int test(void)
 
 		printf("#%d %s ", i, tests[i].descr);
 
-		prog_fd = bpf_prog_load(prog_type ?: BPF_PROG_TYPE_SOCKET_FILTER,
-					prog, prog_len * sizeof(struct bpf_insn),
-					"GPL", 0);
+		prog_fd = bpf_load_program(prog_type ?: BPF_PROG_TYPE_SOCKET_FILTER,
+					   prog, prog_len * sizeof(struct bpf_insn),
+					   "GPL", 0, NULL, 0);
 
 		if (unpriv && tests[i].result_unpriv != UNDEF)
 			expected_result = tests[i].result_unpriv;

index 9a130d31ecf2..de8fd0266d78 100644
@@ -24,6 +24,7 @@
 #define SAMPLE_FREQ 50
 
 static bool sys_read_seen, sys_write_seen;
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 static void print_ksym(__u64 addr)
 {

@@ -61,14 +62,14 @@ static void print_stack(struct key_t *key, __u64 count)
 	int i;
 
 	printf("%3lld %s;", count, key->comm);
-	if (bpf_lookup_elem(map_fd[1], &key->kernstack, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[1], &key->kernstack, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
 			print_ksym(ip[i]);
 	}
 	printf("-;");
-	if (bpf_lookup_elem(map_fd[1], &key->userstack, ip) != 0) {
+	if (bpf_map_lookup_elem(map_fd[1], &key->userstack, ip) != 0) {
 		printf("---;");
 	} else {
 		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)

@@ -98,10 +99,10 @@ static void print_stacks(void)
 	int fd = map_fd[0], stack_map = map_fd[1];
 
 	sys_read_seen = sys_write_seen = false;
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
-		bpf_lookup_elem(fd, &next_key, &value);
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
 		print_stack(&next_key, value);
-		bpf_delete_elem(fd, &next_key);
+		bpf_map_delete_elem(fd, &next_key);
 		key = next_key;
 	}
 

@@ -111,8 +112,8 @@ static void print_stacks(void)
 	}
 
 	/* clear stack map */
-	while (bpf_get_next_key(stack_map, &stackid, &next_id) == 0) {
-		bpf_delete_elem(stack_map, &next_id);
+	while (bpf_map_get_next_key(stack_map, &stackid, &next_id) == 0) {
+		bpf_map_delete_elem(stack_map, &next_id);
 		stackid = next_id;
 	}
 }

index 661a7d052f2c..9c38f7aa4515 100644
@@ -27,6 +27,7 @@ static int pmu_fd;
 int page_size;
 int page_cnt = 8;
 volatile struct perf_event_mmap_page *header;
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
 
 typedef void (*print_fn)(void *data, int size);
 

@@ -162,7 +163,7 @@ static void test_bpf_perf_event(void)
 	pmu_fd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
 
 	assert(pmu_fd >= 0);
-	assert(bpf_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
+	assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);
 	ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
 }
 

index 31a48183beea..aa60cc3ef38c 100644
@@ -4,6 +4,8 @@
 #include "libbpf.h"
 #include "bpf_load.h"
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 int main(int ac, char **argv)
 {
 	FILE *f;

index ab5b19e68acf..5dd128cc5785 100644
@@ -10,6 +10,8 @@
 #define MAX_INDEX	64
 #define MAX_STARS	38
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static void stars(char *str, long val, long max, int width)
 {
 	int i;

@@ -46,12 +48,12 @@ static void print_hist_for_pid(int fd, void *task)
 	long max_value = 0;
 	int i, ind;
 
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
 		if (memcmp(&next_key, task, SIZE)) {
 			key = next_key;
 			continue;
 		}
-		bpf_lookup_elem(fd, &next_key, values);
+		bpf_map_lookup_elem(fd, &next_key, values);
 		value = 0;
 		for (i = 0; i < nr_cpus; i++)
 			value += values[i];

@@ -81,7 +83,7 @@ static void print_hist(int fd)
 	int task_cnt = 0;
 	int i;
 
-	while (bpf_get_next_key(fd, &key, &next_key) == 0) {
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
 		int found = 0;
 
 		for (i = 0; i < task_cnt; i++)

@@ -134,8 +136,8 @@ int main(int ac, char **argv)
 
 	for (i = 0; i < 5; i++) {
 		key = 0;
-		while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-			bpf_lookup_elem(map_fd[0], &next_key, &value);
+		while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
 			printf("location 0x%lx count %ld\n", next_key, value);
 			key = next_key;
 		}

index 48716f7f0d8b..9c6ee595a882 100644
@@ -18,6 +18,8 @@
 
 #define SLOTS 100
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static void clear_stats(int fd)
 {
 	unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);

@@ -26,7 +28,7 @@ static void clear_stats(int fd)
 
 	memset(values, 0, sizeof(values));
 	for (key = 0; key < SLOTS; key++)
-		bpf_update_elem(fd, &key, values, BPF_ANY);
+		bpf_map_update_elem(fd, &key, values, BPF_ANY);
 }
 
 const char *color[] = {

@@ -87,7 +89,7 @@ static void print_hist(int fd)
 	int i;
 
 	for (key = 0; key < SLOTS; key++) {
-		bpf_lookup_elem(fd, &key, values);
+		bpf_map_lookup_elem(fd, &key, values);
 		value = 0;
 		for (i = 0; i < nr_cpus; i++)
 			value += values[i];

index bc4a3bdea6ed..8b2f98c6c99a 100644
@@ -15,6 +15,8 @@
 #include "libbpf.h"
 #include "bpf_load.h"
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 struct pair {
 	long long val;
 	__u64 ip;

@@ -37,8 +39,8 @@ static void print_old_objects(int fd)
 	key = write(1, "\e[1;1H\e[2J", 12); /* clear screen */
 
 	key = -1;
-	while (bpf_get_next_key(map_fd[0], &key, &next_key) == 0) {
-		bpf_lookup_elem(map_fd[0], &next_key, &v);
+	while (bpf_map_get_next_key(map_fd[0], &key, &next_key) == 0) {
+		bpf_map_lookup_elem(map_fd[0], &next_key, &v);
 		key = next_key;
 		if (val - v.val < 1000000000ll)
 			/* object was allocated more then 1 sec ago */

index 36b5925bb137..035beea6b31c 100644
@@ -8,6 +8,8 @@
 #include "bpf_load.h"
 #include <sys/resource.h>
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 /* install fake seccomp program to enable seccomp code path inside the kernel,
  * so that our kprobe attached to seccomp_phase1() can be triggered
  */

index 8ea4976cfcf1..7a3b4a4b19f3 100644
@@ -13,6 +13,8 @@
 
 #define SAMPLE_PERIOD  0x7fffffffffffffffULL
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static void test_bpf_perf_event(void)
 {
 	int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);

@@ -36,7 +38,7 @@ static void test_bpf_perf_event(void)
 			goto exit;
 		}
 
-		bpf_update_elem(map_fd[0], &i, &pmu_fd[i], BPF_ANY);
+		bpf_map_update_elem(map_fd[0], &i, &pmu_fd[i], BPF_ANY);
 		ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE, 0);
 	}
 

index a5e109e398a1..7302322f26ff 100644
@@ -18,6 +18,8 @@
 #include "bpf_load.h"
 #include "libbpf.h"
 
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
 static int set_link_xdp_fd(int ifindex, int fd)
 {
 	struct sockaddr_nl sa;

@@ -134,7 +136,7 @@ static void poll_stats(int interval)
 		for (key = 0; key < nr_keys; key++) {
 			__u64 sum = 0;
 
-			assert(bpf_lookup_elem(map_fd[0], &key, values) == 0);
+			assert(bpf_map_lookup_elem(map_fd[0], &key, values) == 0);
 			for (i = 0; i < nr_cpus; i++)
 				sum += (values[i] - prev[key][i]);
 			if (sum)

123 lines not on this page · raw message

index 1325152be4cd..cc815624aacf 100644
@@ -2,24 +2,9 @@
 #ifndef __LIBBPF_H
 #define __LIBBPF_H
 
-struct bpf_insn;
-
-int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
-		   int max_entries, int map_flags);
-int bpf_map_update_elem(int fd, void *key, void *value, unsigned long long flags);
-int bpf_map_lookup_elem(int fd, void *key, void *value);
-int bpf_map_delete_elem(int fd, void *key);
-int bpf_map_get_next_key(int fd, void *key, void *next_key);
-
-int bpf_load_program(enum bpf_prog_type prog_type,
-		     const struct bpf_insn *insns, int insn_len,
-		     const char *license, int kern_version,
-		     char *log_buf, size_t log_buf_sz);
+#include <bpf/bpf.h>
 
-int bpf_obj_pin(int fd, const char *pathname);
-int bpf_obj_get(const char *pathname);
-
-#define BPF_LOG_BUF_SIZE 65536
+struct bpf_insn;
 
 /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
 

index f8e3c58a0897..d683bd278171 100644
@@ -19,6 +19,7 @@
 #include <ctype.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define DEBUGFS "/sys/kernel/debug/tracing/"
 

@@ -168,7 +169,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	id = atoi(buf);
 	attr.config = id;
 
-	efd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
+	efd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
 	if (efd < 0) {
 		printf("event %d fd %d err %s\n", id, efd, strerror(errno));
 		return -1;

index d9af876b4a2c..bee473a494f1 100644
@@ -34,10 +34,3 @@ int open_raw_sock(const char *name)
 
 	return sock;
 }
-
-int perf_event_open(struct perf_event_attr *attr, int pid, int cpu,
-		    int group_fd, unsigned long flags)
-{
-	return syscall(__NR_perf_event_open, attr, pid, cpu,
-		       group_fd, flags);
-}

index cc815624aacf..09aedc320009 100644
@@ -188,7 +188,4 @@ struct bpf_insn;
 /* create RAW socket and bind to interface 'name' */
 int open_raw_sock(const char *name);
 
-struct perf_event_attr;
-int perf_event_open(struct perf_event_attr *attr, int pid, int cpu,
-		    int group_fd, unsigned long flags);
 #endif

index 09ab620b324c..476a11947180 100644
@@ -21,6 +21,7 @@
 #include <sys/ioctl.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define DEFAULT_FREQ	99
 #define DEFAULT_SECS	5

@@ -50,7 +51,7 @@ static int sampling_start(int *pmu_fd, int freq)
 	};
 
 	for (i = 0; i < nr_cpus; i++) {
-		pmu_fd[i] = perf_event_open(&pe_sample_attr, -1 /* pid */, i,
+		pmu_fd[i] = sys_perf_event_open(&pe_sample_attr, -1 /* pid */, i,
 					    -1 /* group_fd */, 0 /* flags */);
 		if (pmu_fd[i] < 0) {
 			fprintf(stderr, "ERROR: Initializing perf sampling\n");

index de8fd0266d78..ccb0cba8324a 100644
@@ -20,6 +20,7 @@
 #include <sys/resource.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define SAMPLE_FREQ 50
 

@@ -126,9 +127,9 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 
 	/* open perf_event on all cpus */
 	for (i = 0; i < nr_cpus; i++) {
-		pmu_fd[i] = perf_event_open(attr, -1, i, -1, 0);
+		pmu_fd[i] = sys_perf_event_open(attr, -1, i, -1, 0);
 		if (pmu_fd[i] < 0) {
-			printf("perf_event_open failed\n");
+			printf("sys_perf_event_open failed\n");
 			goto all_cpu_err;
 		}
 		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);

@@ -147,9 +148,9 @@ static void test_perf_event_task(struct perf_event_attr *attr)
 	int pmu_fd;
 
 	/* open task bound event */
-	pmu_fd = perf_event_open(attr, 0, -1, -1, 0);
+	pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0);
 	if (pmu_fd < 0) {
-		printf("perf_event_open failed\n");
+		printf("sys_perf_event_open failed\n");
 		return;
 	}
 	assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);

index 9c38f7aa4515..64e692fd7d51 100644
@@ -21,6 +21,7 @@
 #include <signal.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 static int pmu_fd;
 

@@ -160,7 +161,7 @@ static void test_bpf_perf_event(void)
 	};
 	int key = 0;
 
-	pmu_fd = perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
+	pmu_fd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
 
 	assert(pmu_fd >= 0);
 	assert(bpf_map_update_elem(map_fd[0], &key, &pmu_fd, BPF_ANY) == 0);

index 7a3b4a4b19f3..1681cb7cd713 100644
@@ -10,6 +10,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "perf-sys.h"
 
 #define SAMPLE_PERIOD  0x7fffffffffffffffULL
 

@@ -32,7 +33,7 @@ static void test_bpf_perf_event(void)
 	};
 
 	for (i = 0; i < nr_cpus; i++) {
-		pmu_fd[i] = perf_event_open(&attr_insn_pmu, -1/*pid*/, i/*cpu*/, -1/*group_fd*/, 0);
+		pmu_fd[i] = sys_perf_event_open(&attr_insn_pmu, -1/*pid*/, i/*cpu*/, -1/*group_fd*/, 0);
 		if (pmu_fd[i] < 0) {
 			printf("event syscall failed\n");
 			goto exit;

index 4ffd8f340496..7ae3b19f5c42 100644
@@ -14,6 +14,7 @@
 
 #include "bpf_load.h"
 #include "libbpf.h"
+#include "sock_example.h"
 
 #define BPF_F_PIN	(1 << 0)
 #define BPF_F_GET	(1 << 1)

index 09aedc320009..3705fba453a0 100644
@@ -185,7 +185,4 @@ struct bpf_insn;
 		.off   = 0,					\
 		.imm   = 0 })
 
-/* create RAW socket and bind to interface 'name' */
-int open_raw_sock(const char *name);
-
 #endif

index 7ab636c30154..bb418fd0a1f2 100644
@@ -27,6 +27,7 @@
 #include <linux/ip.h>
 #include <stddef.h>
 #include "libbpf.h"
+#include "sock_example.h"
 
 static int test_sock(void)
 {

similarity index 92%
rename from samples/bpf/libbpf.c
rename to samples/bpf/sock_example.h
index bee473a494f1..09f7fe7e5fd7 100644
@@ -1,4 +1,3 @@
-/* eBPF mini library */
 #include <stdlib.h>
 #include <stdio.h>
 #include <linux/unistd.h>

@@ -11,7 +10,7 @@
 #include <arpa/inet.h>
 #include "libbpf.h"
 
-int open_raw_sock(const char *name)
+static inline int open_raw_sock(const char *name)
 {
 	struct sockaddr_ll sll;
 	int sock;

index 2956d893d732..5cdddc5c9015 100644
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
 

index c43958a67cca..7ae4e2e5cf3a 100644
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
 #include <sys/resource.h>

index 2cb9011ea440..a100cf6c95bb 100644
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include "libbpf.h"
 #include "bpf_load.h"
+#include "sock_example.h"
 #include <unistd.h>
 #include <arpa/inet.h>
 #include <sys/resource.h>

index 99400b0e8f2a..7725c3f9d6a2 100644
@@ -1822,7 +1822,7 @@ void kcore_extract__delete(struct kcore_extract *kce)
 static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 			     struct list_head *sdt_notes)
 {
-	const char *provider, *name;
+	const char *provider, *name, *args;
 	struct sdt_note *tmp = NULL;
 	GElf_Ehdr ehdr;
 	GElf_Addr base_off = 0;

@@ -1881,6 +1881,25 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 		goto out_free_prov;
 	}
 
+	args = memchr(name, '\0', data + len - name);
+
+	/*
+	 * There is no argument if:
+	 * - We reached the end of the note;
+	 * - There is not enough room to hold a potential string;
+	 * - The argument string is empty or just contains ':'.
+	 */
+	if (args == NULL || data + len - args < 2 ||
+		args[1] == ':' || args[1] == '\0')
+		tmp->args = NULL;
+	else {
+		tmp->args = strdup(++args);
+		if (!tmp->args) {
+			ret = -ENOMEM;
+			goto out_free_name;
+		}
+	}
+
 	if (gelf_getclass(*elf) == ELFCLASS32) {
 		memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
 		tmp->bit32 = true;

@@ -1892,7 +1911,7 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	if (!gelf_getehdr(*elf, &ehdr)) {
 		pr_debug("%s : cannot get elf header.\n", __func__);
 		ret = -EBADF;
-		goto out_free_name;
+		goto out_free_args;
 	}
 
 	/* Adjust the prelink effect :

@@ -1917,6 +1936,8 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
 	list_add_tail(&tmp->note_list, sdt_notes);
 	return 0;
 
+out_free_args:
+	free(tmp->args);
 out_free_name:
 	free(tmp->name);
 out_free_prov:

index 6c358b7ed336..9222c7e702f3 100644
@@ -351,6 +351,7 @@ int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
 struct sdt_note {
 	char *name;			/* name of the note*/
 	char *provider;			/* provider name */
+	char *args;
 	bool bit32;			/* whether the location is 32 bits? */
 	union {				/* location, base and semaphore addrs */
 		Elf64_Addr a64[3];

index 4b419631753d..f8ca7a4ebabc 100644
@@ -208,7 +208,7 @@ static void compute_stats(struct c2c_hist_entry *c2c_he,
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event,
 				struct perf_sample *sample,
-				struct perf_evsel *evsel __maybe_unused,
+				struct perf_evsel *evsel,
 				struct machine *machine)
 {
 	struct c2c_hists *c2c_hists = &c2c.hists;

@@ -379,7 +379,7 @@ static int symbol_width(struct hists *hists, struct sort_entry *se)
 
 static int c2c_width(struct perf_hpp_fmt *fmt,
 		     struct perf_hpp *hpp __maybe_unused,
-		     struct hists *hists __maybe_unused)
+		     struct hists *hists)
 {
 	struct c2c_fmt *c2c_fmt;
 	struct c2c_dimension *dim;

@@ -1127,7 +1127,7 @@ MEAN_ENTRY(mean_lcl_entry,  lcl_hitm);
 MEAN_ENTRY(mean_load_entry, load);
 
 static int
-cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cpucnt_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he)
 {
 	struct c2c_hist_entry *c2c_he;

@@ -1141,7 +1141,7 @@ cpucnt_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 }
 
 static int
-cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cl_idx_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he)
 {
 	struct c2c_hist_entry *c2c_he;

@@ -1155,7 +1155,7 @@ cl_idx_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
 }
 
 static int
-cl_idx_empty_entry(struct perf_hpp_fmt *fmt __maybe_unused, struct perf_hpp *hpp,
+cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		   struct hist_entry *he)
 {
 	int width = c2c_width(fmt, hpp, he->hists);

@@ -1779,7 +1779,6 @@ static int c2c_hists__init(struct c2c_hists *hists,
 	return hpp_list__parse(&hists->list, NULL, sort);
 }
 
-__maybe_unused
 static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
 			     const char *output,
 			     const char *sort)

@@ -2658,7 +2657,7 @@ static int perf_c2c__report(int argc, const char **argv)
 	return err;
 }
 
-static int parse_record_events(const struct option *opt __maybe_unused,
+static int parse_record_events(const struct option *opt,
 			       const char *str, int unset __maybe_unused)
 {
 	bool *event_set = (bool *) opt->value;

index d2afbe4a240d..06cc759a4597 100644
@@ -648,7 +648,7 @@ report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
 }
 
 static int
-parse_branch_mode(const struct option *opt __maybe_unused,
+parse_branch_mode(const struct option *opt,
 		  const char *str __maybe_unused, int unset)
 {
 	int *branch_mode = opt->value;

index 688dea7cb08f..a02f2e965628 100644
@@ -2195,7 +2195,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+int process_stat_config_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_session *session __maybe_unused)
 {

@@ -2238,7 +2238,7 @@ static int set_maps(struct perf_stat *st)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool __maybe_unused,
+int process_thread_map_event(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_session *session __maybe_unused)
 {

@@ -2257,7 +2257,7 @@ int process_thread_map_event(struct perf_tool *tool __maybe_unused,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+int process_cpu_map_event(struct perf_tool *tool,
 			  union perf_event *event,
 			  struct perf_session *session __maybe_unused)
 {

index d1ce29be560e..cd7bc4d104e2 100644
@@ -70,8 +70,8 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_UINTEGER(0, "ldlat", &perf_mem_events__loads_ldlat, "mem-loads latency"),
 	OPT_INCR('v', "verbose", &verbose,
 		 "be more verbose (show counter open errors, etc)"),
-	OPT_BOOLEAN('U', "--all-user", &all_user, "collect only user level data"),
-	OPT_BOOLEAN('K', "--all-kernel", &all_kernel, "collect only kernel level data"),
+	OPT_BOOLEAN('U', "all-user", &all_user, "collect only user level data"),
+	OPT_BOOLEAN('K', "all-kernel", &all_kernel, "collect only kernel level data"),
 	OPT_END()
 	};
 

index b2365a63db45..fd61ebd77c26 100644
@@ -1474,7 +1474,7 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
-			int group_fd;
+			int fd, group_fd;
 
 			if (!evsel->cgrp && !evsel->system_wide)
 				pid = thread_map__pid(threads, thread);

@@ -1484,21 +1484,22 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
 				  pid, cpus->map[cpu], group_fd, flags);
 
-			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
-								     pid,
-								     cpus->map[cpu],
-								     group_fd, flags);
-			if (FD(evsel, cpu, thread) < 0) {
+			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
+						 group_fd, flags);
+
+			FD(evsel, cpu, thread) = fd;
+
+			if (fd < 0) {
 				err = -errno;
 				pr_debug2("\nsys_perf_event_open failed, error %d\n",
 					  err);
 				goto try_fallback;
 			}
 
-			pr_debug2(" = %d\n", FD(evsel, cpu, thread));
+			pr_debug2(" = %d\n", fd);
 
 			if (evsel->bpf_fd >= 0) {
-				int evt_fd = FD(evsel, cpu, thread);
+				int evt_fd = fd;
 				int bpf_fd = evsel->bpf_fd;
 
 				err = ioctl(evt_fd,

index 23605202d4a1..a77dcc0d24e3 100644
@@ -186,6 +186,10 @@ static struct test generic_tests[] = {
 		.func = test__thread_map_synthesize,
 	},
 	{
+		.desc = "Remove thread map",
+		.func = test__thread_map_remove,
+	},
+	{
 		.desc = "Synthesize cpu map",
 		.func = test__cpu_map_synthesize,
 	},

index 0d7b251305af..a512f0c8ff5b 100644
@@ -80,6 +80,7 @@ const char *test__bpf_subtest_get_desc(int subtest);
 int test__bpf_subtest_get_nr(void);
 int test_session_topology(int subtest);
 int test__thread_map_synthesize(int subtest);
+int test__thread_map_remove(int subtest);
 int test__cpu_map_synthesize(int subtest);
 int test__synthesize_stat_config(int subtest);
 int test__synthesize_stat(int subtest);

50 lines not on this page · raw message

index 40585f5b7027..f9eab200fd75 100644
@@ -448,3 +448,25 @@ bool thread_map__has(struct thread_map *threads, pid_t pid)
 
 	return false;
 }
+
+int thread_map__remove(struct thread_map *threads, int idx)
+{
+	int i;
+
+	if (threads->nr < 1)
+		return -EINVAL;
+
+	if (idx >= threads->nr)
+		return -EINVAL;
+
+	/*
+	 * Free the 'idx' item and shift the rest up.
+	 */
+	free(threads->map[idx].comm);
+
+	for (i = idx; i < threads->nr - 1; i++)
+		threads->map[i] = threads->map[i + 1];
+
+	threads->nr--;
+	return 0;
+}

index bd3b971588da..ea0ef08c6303 100644
@@ -58,4 +58,5 @@ static inline char *thread_map__comm(struct thread_map *map, int thread)
 
 void thread_map__read_comms(struct thread_map *threads);
 bool thread_map__has(struct thread_map *threads, pid_t pid);
+int thread_map__remove(struct thread_map *threads, int idx);
 #endif	/* __PERF_THREAD_MAP_H */

index 9a0236a4cf95..1c27d947c2fe 100644
@@ -55,6 +55,7 @@ struct record_opts {
 	bool	     all_user;
 	bool	     tail_synthesize;
 	bool	     overwrite;
+	bool	     ignore_missing_thread;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;

62 lines not on this page · raw message

index 6abb89cd27f9..06ef6f29efa1 100644
@@ -120,6 +120,7 @@ struct perf_evsel {
 	bool			tracking;
 	bool			per_pkg;
 	bool			precise_max;
+	bool			ignore_missing_thread;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;

index fa26865364b6..74d6a035133a 100644
@@ -1687,6 +1687,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out;
 	}
 
+	/* Enable ignoring missing threads when -u option is defined. */
+	rec->opts.ignore_missing_thread = rec->opts.target.uid != UINT_MAX;
+
 	err = -ENOMEM;
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);