Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "On the kernel side the main changes in this cycle were:

   - Add Intel Kaby Lake CPU support (Srinivas Pandruvada)

   - AMD uncore driver updates for fam17 (Janakarajan Natarajan)

   - Intel/PT updates and core events optimizations and cleanups
     (Alexander Shishkin)

   - cgroups events fixes (David Carrillo-Cisneros)

   - kprobes improvements (Masami Hiramatsu)

   - ... plus misc fixes and updates.

  On the tooling side the main changes were:

   - Support clang build in tools/{perf,lib/{bpf,traceevent,api}} with
     CC=clang, to, for instance, take advantage of better warnings
     (Arnaldo Carvalho de Melo):

   - Introduce the 'delta-abs' 'perf diff' compute method, that orders
     the histogram entries by the absolute value of the percentage delta
     for a function in two perf.data files, i.e. the functions that
     changed the most (increase or decrease in samples) comes first
     (Namhyung Kim)

   - Add support for parsing Intel uncore vendor event files and add
     uncore vendor events for the Intel server processors (Haswell,
     Broadwell, IvyBridge), Xeon Phi (Knights Landing) and Broadwell DE
     (Andi Kleen)

   - Introduce 'perf ftrace' a perf front end to the kernel's ftrace
     function and function_graph tracer, defaulting to the
     "function_graph" tracer, more work will be done in reviving this
     effort, forward porting it from its initial patch submission
     (Namhyung Kim)

   - Add 'e' and 'c' hotkeys to expand/collapse call chains for a single
     hist entry in the 'perf report' and 'perf top' TUI (Jiri Olsa)

   - Account thread wait time (off CPU time) separately: sleep, iowait
     and preempt, based on the prev_state of the last event, show the
     breakdown when using "perf sched timehist --state" (Namhyumg Kim)

   - Add more triggers to switch the output file (perf.data.TIMESTAMP).

     Now, in addition to switching to a different output file when
     receiving a SIGUSR2, one can also specify file size and time based
     triggers:

           perf record -a --switch-output=signal

     is equivalent to what we had before:

           perf record -a --switch-output

     While we can also ask for the file to be "sliced" by size, taking
     into account that that will happen only when we get woken up by the
     kernel, i.e. one has to take into account the --mmap-pages (the
     size of the perf mmap ring buffer):

           perf record -a --switch-output=2G

     will break the perf.data output into multiple files limited to 2GB
     of samples, right when generating the output.

     For time based samples, alert() will be used, so to have 1 minute
     limited perf.data output files:

          perf record -a --switch-output=1m

     (Jiri Olsa)

   - Improve 'perf trace' (Arnaldo Carvalho de Melo)

   - 'perf kallsyms' toy tool to look for extended symbol information on
     the running kernel and demonstrate the machine/thread/symbol APIs
     for use in other tools, such as 'perf probe' (Arnaldo Carvalho de
     Melo)

   - ... plus tons of other changes, see the shortlog and Git log for
     details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (131 commits)
  perf tools: Add missing parse_events_error() prototype
  perf pmu: Fix check for unset alias->unit array
  perf tools: Be consistent on the type of map->symbols[] interator
  perf intel pt decoder: clang has no -Wno-override-init
  perf evsel: Do not put a variable sized type not at the end of a struct
  perf probe: Avoid accessing uninitialized 'map' variable
  perf tools: Do not put a variable sized type not at the end of a struct
  perf record: Do not put a variable sized type not at the end of a struct
  perf tests: Synthesize struct instead of using field after variable sized type
  perf bench numa: Make sure dprintf() is not defined
  Revert "perf bench futex: Sanitize numeric parameters"
  tools lib subcmd: Make it an error to pass a signed value to OPTION_UINTEGER
  tools: Set the maximum optimization level according to the compiler being used
  tools: Suppress request for warning options not existent in clang
  samples/bpf: Reset global variables
  samples/bpf: Ignore already processed ELF sections
  samples/bpf: Add missing header
  perf symbols: dso->name is an array, no need to check it against NULL
  perf tests record: No need to test an array against NULL
  perf symbols: No need to check if sym->name is NULL
  ...

3 files changed, 255 insertions, 29 deletions

diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 4ac6c4b84100..44fb7c5f8ae6 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -22,6 +22,7 @@
 #define __BPF_BPF_H
 
 #include <linux/bpf.h>
+#include <stddef.h>
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries, __u32 map_flags);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 84e6b35da4bd..ac6eb863b2a4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Lesser General Public
@@ -22,15 +23,21 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
+#include <libgen.h>
 #include <inttypes.h>
 #include <string.h>
 #include <unistd.h>
 #include <fcntl.h>
 #include <errno.h>
 #include <asm/unistd.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/list.h>
+#include <linux/limits.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
 #include <libelf.h>
 #include <gelf.h>
 
@@ -41,6 +48,10 @@
 #define EM_BPF 247
 #endif
 
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC		0xcafe4a11
+#endif
+
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 __printf(1, 2)
@@ -779,7 +790,7 @@ static int
 bpf_program__collect_reloc(struct bpf_program *prog,
 			   size_t nr_maps, GElf_Shdr *shdr,
 			   Elf_Data *data, Elf_Data *symbols,
-			   int maps_shndx)
+			   int maps_shndx, struct bpf_map *maps)
 {
 	int i, nrels;
 
@@ -829,7 +840,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		map_idx = sym.st_value / sizeof(struct bpf_map_def);
+		/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
+		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+			if (maps[map_idx].offset == sym.st_value) {
+				pr_debug("relocation: find map %zd (%s) for insn %u\n",
+					 map_idx, maps[map_idx].name, insn_idx);
+				break;
+			}
+		}
+
 		if (map_idx >= nr_maps) {
 			pr_warning("bpf relocation: map_idx %d large than %d\n",
 				   (int)map_idx, (int)nr_maps - 1);
@@ -953,7 +972,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
 						 obj->efile.symbols,
-						 obj->efile.maps_shndx);
+						 obj->efile.maps_shndx,
+						 obj->maps);
 		if (err)
 			return err;
 	}
@@ -1227,6 +1247,191 @@ out:
 	return err;
 }
 
+static int check_path(const char *path)
+{
+	struct statfs st_fs;
+	char *dname, *dir;
+	int err = 0;
+
+	if (path == NULL)
+		return -EINVAL;
+
+	dname = strdup(path);
+	if (dname == NULL)
+		return -ENOMEM;
+
+	dir = dirname(dname);
+	if (statfs(dir, &st_fs)) {
+		pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
+		err = -errno;
+	}
+	free(dname);
+
+	if (!err && st_fs.f_type != BPF_FS_MAGIC) {
+		pr_warning("specified path %s is not on BPF FS\n", path);
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+			      int instance)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (instance < 0 || instance >= prog->instances.nr) {
+		pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+			   instance, prog->section_name, prog->instances.nr);
+		return -EINVAL;
+	}
+
+	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
+		pr_warning("failed to pin program: %s\n", strerror(errno));
+		return -errno;
+	}
+	pr_debug("pinned program '%s'\n", path);
+
+	return 0;
+}
+
+static int make_dir(const char *path)
+{
+	int err = 0;
+
+	if (mkdir(path, 0700) && errno != EEXIST)
+		err = -errno;
+
+	if (err)
+		pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
+	return err;
+}
+
+int bpf_program__pin(struct bpf_program *prog, const char *path)
+{
+	int i, err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (prog->instances.nr <= 0) {
+		pr_warning("no instances of prog %s to pin\n",
+			   prog->section_name);
+		return -EINVAL;
+	}
+
+	err = make_dir(path);
+	if (err)
+		return err;
+
+	for (i = 0; i < prog->instances.nr; i++) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0)
+			return -EINVAL;
+		else if (len >= PATH_MAX)
+			return -ENAMETOOLONG;
+
+		err = bpf_program__pin_instance(prog, buf, i);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int bpf_map__pin(struct bpf_map *map, const char *path)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (map == NULL) {
+		pr_warning("invalid map pointer\n");
+		return -EINVAL;
+	}
+
+	if (bpf_obj_pin(map->fd, path)) {
+		pr_warning("failed to pin map: %s\n", strerror(errno));
+		return -errno;
+	}
+
+	pr_debug("pinned map '%s'\n", path);
+	return 0;
+}
+
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	struct bpf_map *map;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->loaded) {
+		pr_warning("object not yet loaded; load it first\n");
+		return -ENOENT;
+	}
+
+	err = make_dir(path);
+	if (err)
+		return err;
+
+	bpf_map__for_each(map, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
+		if (len < 0)
+			return -EINVAL;
+		else if (len >= PATH_MAX)
+			return -ENAMETOOLONG;
+
+		err = bpf_map__pin(map, buf);
+		if (err)
+			return err;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->section_name);
+		if (len < 0)
+			return -EINVAL;
+		else if (len >= PATH_MAX)
+			return -ENAMETOOLONG;
+
+		err = bpf_program__pin(prog, buf);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 void bpf_object__close(struct bpf_object *obj)
 {
 	size_t i;
@@ -1419,37 +1624,33 @@ static void bpf_program__set_type(struct bpf_program *prog,
 	prog->type = type;
 }
 
-int bpf_program__set_tracepoint(struct bpf_program *prog)
-{
-	if (!prog)
-		return -EINVAL;
-	bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-	return 0;
-}
-
-int bpf_program__set_kprobe(struct bpf_program *prog)
-{
-	if (!prog)
-		return -EINVAL;
-	bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
-	return 0;
-}
-
 static bool bpf_program__is_type(struct bpf_program *prog,
 				 enum bpf_prog_type type)
 {
 	return prog ? (prog->type == type) : false;
 }
 
-bool bpf_program__is_tracepoint(struct bpf_program *prog)
-{
-	return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-}
-
-bool bpf_program__is_kprobe(struct bpf_program *prog)
-{
-	return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
-}
+#define BPF_PROG_TYPE_FNS(NAME, TYPE)			\
+int bpf_program__set_##NAME(struct bpf_program *prog)	\
+{							\
+	if (!prog)					\
+		return -EINVAL;				\
+	bpf_program__set_type(prog, TYPE);		\
+	return 0;					\
+}							\
+							\
+bool bpf_program__is_##NAME(struct bpf_program *prog)	\
+{							\
+	return bpf_program__is_type(prog, TYPE);	\
+}							\
+
+BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
+BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
+BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
+BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
+BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
+BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
 
 int bpf_map__fd(struct bpf_map *map)
 {
@@ -1537,3 +1738,10 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
 	}
 	return ERR_PTR(-ENOENT);
 }
+
+long libbpf_get_error(const void *ptr)
+{
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+	return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a5a8b86a06fe..b30394f9947a 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -22,8 +22,8 @@
 #define __BPF_LIBBPF_H
 
 #include <stdio.h>
+#include <stdint.h>
 #include <stdbool.h>
-#include <linux/err.h>
 #include <sys/types.h>  // for size_t
 
 enum libbpf_errno {
@@ -65,6 +65,7 @@ struct bpf_object *bpf_object__open(const char *path);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 					   size_t obj_buf_sz,
 					   const char *name);
+int bpf_object__pin(struct bpf_object *object, const char *path);
 void bpf_object__close(struct bpf_object *object);
 
 /* Load/unload object into/from kernel */
@@ -106,6 +107,9 @@ void *bpf_program__priv(struct bpf_program *prog);
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
 int bpf_program__fd(struct bpf_program *prog);
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+			      int instance);
+int bpf_program__pin(struct bpf_program *prog, const char *path);
 
 struct bpf_insn;
 
@@ -174,11 +178,21 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n);
 /*
  * Adjust type of bpf program. Default is kprobe.
  */
+int bpf_program__set_socket_filter(struct bpf_program *prog);
 int bpf_program__set_tracepoint(struct bpf_program *prog);
 int bpf_program__set_kprobe(struct bpf_program *prog);
+int bpf_program__set_sched_cls(struct bpf_program *prog);
+int bpf_program__set_sched_act(struct bpf_program *prog);
+int bpf_program__set_xdp(struct bpf_program *prog);
+int bpf_program__set_perf_event(struct bpf_program *prog);
 
+bool bpf_program__is_socket_filter(struct bpf_program *prog);
 bool bpf_program__is_tracepoint(struct bpf_program *prog);
 bool bpf_program__is_kprobe(struct bpf_program *prog);
+bool bpf_program__is_sched_cls(struct bpf_program *prog);
+bool bpf_program__is_sched_act(struct bpf_program *prog);
+bool bpf_program__is_xdp(struct bpf_program *prog);
+bool bpf_program__is_perf_event(struct bpf_program *prog);
 
 /*
  * We don't need __attribute__((packed)) now since it is
@@ -223,5 +237,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		      bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__pin(struct bpf_map *map, const char *path);
+
+long libbpf_get_error(const void *ptr);
 
 #endif