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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - Intel Knights Landing support.  (Harish Chegondi)

   - Intel Broadwell-EP uncore PMU support.  (Kan Liang)

   - Core code improvements.  (Peter Zijlstra.)

   - Event filter, LBR and PEBS fixes.  (Stephane Eranian)

   - Enable cycles:pp on Intel Atom.  (Stephane Eranian)

   - Add cycles:ppp support for Skylake.  (Andi Kleen)

   - Various x86 NMI overhead optimizations.  (Andi Kleen)

   - Intel PT enhancements.  (Takao Indoh)

   - AMD cache events fix.  (Vince Weaver)

  Tons of tooling changes:

   - Show random perf tool tips in the 'perf report' bottom line
     (Namhyung Kim)

   - perf report now defaults to --group if the perf.data file has
     grouped events, try it with:

      # perf record -e '{cycles,instructions}' -a sleep 1
      [ perf record: Woken up 1 times to write data ]
      [ perf record: Captured and wrote 1.093 MB perf.data (1247 samples) ]
      # perf report
      # Samples: 1K of event 'anon group { cycles, instructions }'
      # Event count (approx.): 1955219195
      #
      #       Overhead  Command     Shared Object      Symbol

         2.86%   0.22%  swapper     [kernel.kallsyms]  [k] intel_idle
         1.05%   0.33%  firefox     libxul.so          [.] js::SetObjectElement
         1.05%   0.00%  kworker/0:3 [kernel.kallsyms]  [k] gen6_ring_get_seqno
         0.88%   0.17%  chrome      chrome             [.] 0x0000000000ee27ab
         0.65%   0.86%  firefox     libxul.so          [.] js::ValueToId<(js::AllowGC)1>
         0.64%   0.23%  JS Helper   libxul.so          [.] js::SplayTree<js::jit::LiveRange*, js::jit::LiveRange>::splay
         0.62%   1.27%  firefox     libxul.so          [.] js::GetIterator
         0.61%   1.74%  firefox     libxul.so          [.] js::NativeSetProperty
         0.61%   0.31%  firefox     libxul.so          [.] js::SetPropertyByDefining

   - Introduce the 'perf stat record/report' workflow:

     Generate perf.data files from 'perf stat', to tap into the
     scripting capabilities perf has instead of defining a 'perf stat'
     specific scripting support to calculate event ratios, etc.

     Simple example:

        $ perf stat record -e cycles usleep 1

         Performance counter stats for 'usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $ perf stat report

         Performance counter stats for '/home/acme/bin/perf stat record -e cycles usleep 1':

               1,134,996      cycles

             0.000670644 seconds time elapsed

        $

     It generates PERF_RECORD_ userspace records to store the details:

        $ perf report -D | grep PERF_RECORD
        0xf0 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27637
        0x118 [0x12]: PERF_RECORD_CPU_MAP nr: 1 cpu: 65535
        0x12a [0x40]: PERF_RECORD_STAT_CONFIG
        0x16a [0x30]: PERF_RECORD_STAT
        -1 -1 0x19a [0x40]: PERF_RECORD_MMAP -1/0: [0xffffffff81000000(0x1f000000) @ 0xffffffff81000000]: x [kernel.kallsyms]_text
        0x1da [0x18]: PERF_RECORD_STAT_ROUND
        [acme@ssdandy linux]$

     An effort was made to make perf.data files generated like this to
     not generate cryptic messages when processed by older tools.

     The 'perf script' bits need rebasing, will go up later.

   - Make command line options always available, even when they depend
     on some feature being enabled, warning the user about use of such
     options (Wang Nan)

   - Support hw breakpoint events (mem:0xAddress) in the default output
     mode in 'perf script' (Wang Nan)

   - Fixes and improvements for supporting annotating ARM binaries,
     support ARM call and jump instructions, more work needed to have
     arch specific stuff separated into tools/perf/arch/*/annotate/
     (Russell King)

   - Add initial 'perf config' command, for now just with a --list
     command to the contents of the configuration file in use and a
     basic man page describing its format, commands for doing edits and
     detailed documentation are being reviewed and proof-read.  (Taeung
     Song)

   - Allows BPF scriptlets specify arguments to be fetched using DWARF
     info, using a prologue generated at compile/build time (He Kuang,
     Wang Nan)

   - Allow attaching BPF scriptlets to module symbols (Wang Nan)

   - Allow attaching BPF scriptlets to userspace code using uprobe (Wang
     Nan)

   - BPF programs now can specify 'perf probe' tunables via its section
     name, separating key=val values using semicolons (Wang Nan)

     Testing some of these new BPF features:

        Use case: get callchains when receiving SSL packets, filter then in the
                  kernel, at arbitrary place.

        # cat ssl.bpf.c
        #define SEC(NAME) __attribute__((section(NAME), used))

        struct pt_regs;

        SEC("func=__inet_lookup_established hnum")
        int func(struct pt_regs *ctx, int err, unsigned short port)
        {
                return err == 0 && port == 443;
        }

        char _license[] SEC("license") = "GPL";
        int  _version   SEC("version") = LINUX_VERSION_CODE;
        #
        # perf record -a -g -e ssl.bpf.c
        ^C[ perf record: Woken up 1 times to write data ]
        [ perf record: Captured and wrote 0.787 MB perf.data (3 samples) ]
        # perf script | head -30
        swapper     0 [000] 58783.268118: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           8572a8 process_backlog (/lib/modules/4.3.0+/build/vmlinux)
           856b11 net_rx_action (/lib/modules/4.3.0+/build/vmlinux)
           2a284b __do_softirq (/lib/modules/4.3.0+/build/vmlinux)
           2a2ba3 irq_exit (/lib/modules/4.3.0+/build/vmlinux)
           96b7a4 do_IRQ (/lib/modules/4.3.0+/build/vmlinux)
           969807 ret_from_intr (/lib/modules/4.3.0+/build/vmlinux)
           2dede5 cpu_startup_entry (/lib/modules/4.3.0+/build/vmlinux)
           95d5bc rest_init (/lib/modules/4.3.0+/build/vmlinux)
          1163ffa start_kernel ([kernel.vmlinux].init.text)
          11634d7 x86_64_start_reservations ([kernel.vmlinux].init.text)
          1163623 x86_64_start_kernel ([kernel.vmlinux].init.text)

        qemu-system-x86  9178 [003] 58785.792417: perf_bpf_probe:func: (ffffffff816a0f60) hnum=0x1bb
           8a0f61 __inet_lookup_established (/lib/modules/4.3.0+/build/vmlinux)
           896def ip_rcv_finish (/lib/modules/4.3.0+/build/vmlinux)
           8976c2 ip_rcv (/lib/modules/4.3.0+/build/vmlinux)
           855eba __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
           856660 netif_receive_skb_internal (/lib/modules/4.3.0+/build/vmlinux)
           8566ec netif_receive_skb_sk (/lib/modules/4.3.0+/build/vmlinux)
             430a br_handle_frame_finish ([bridge])
             48bc br_handle_frame ([bridge])
           855f44 __netif_receive_skb_core (/lib/modules/4.3.0+/build/vmlinux)
           8565d8 __netif_receive_skb (/lib/modules/4.3.0+/build/vmlinux)
        #

   - Use 'perf probe' various options to list functions, see what
     variables can be collected at any given point, experiment first
     collecting without a filter, then filter, use it together with
     'perf trace', 'perf top', with or without callchains, if it
     explodes, please tell us!

   - Introduce a new callchain mode: "folded", that will list per line
     representations of all callchains for a give histogram entry,
     facilitating 'perf report' output processing by other tools, such
     as Brendan Gregg's flamegraph tools (Namhyung Kim)

     E.g:

        # perf report | grep -v ^# | head
           18.37%     0.00%  swapper  [kernel.kallsyms]   [k] cpu_startup_entry
                           |
                           ---cpu_startup_entry
                              |
                              |--12.07%--start_secondary
                              |
                               --6.30%--rest_init
                                         start_kernel
                                         x86_64_start_reservations
                                         x86_64_start_kernel
         #

     Becomes, in "folded" mode:

        # perf report -g folded | grep -v ^# | head -5
            18.37%     0.00%  swapper [kernel.kallsyms]   [k] cpu_startup_entry
          12.07% cpu_startup_entry;start_secondary
           6.30% cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] call_cpuidle
          11.23% call_cpuidle;cpu_startup_entry;start_secondary
           5.67% call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            16.90%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter
          11.23% cpuidle_enter;call_cpuidle;cpu_startup_entry;start_secondary
           5.67% cpuidle_enter;call_cpuidle;cpu_startup_entry;rest_init;start_kernel;x86_64_start_reservations;x86_64_start_kernel
            15.12%     0.00%  swapper [kernel.kallsyms]   [k] cpuidle_enter_state
         #

     The user can also select one of "count", "period" or "percent" as
     the first column.

  ... and lots of infrastructure enhancements, plus fixes and other
  changes, features I failed to list - see the shortlog and the git log
  for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (271 commits)
  perf evlist: Add --trace-fields option to show trace fields
  perf record: Store data mmaps for dwarf unwind
  perf libdw: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Check for mmaps also in MAP__VARIABLE tree
  perf unwind: Use find_map function in access_dso_mem
  perf evlist: Remove perf_evlist__(enable|disable)_event functions
  perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does)
  perf report: Show random usage tip on the help line
  perf hists: Export a couple of hist functions
  perf diff: Use perf_hpp__register_sort_field interface
  perf tools: Add overhead/overhead_children keys defaults via string
  perf tools: Remove list entry from struct sort_entry
  perf tools: Include all tools/lib directory for tags/cscope/TAGS targets
  perf script: Align event name properly
  perf tools: Add missing headers in perf's MANIFEST
  perf tools: Do not show trace command if it's not compiled in
  perf report: Change default to use event group view
  perf top: Decay periods in callchains
  tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/
  tools lib: Sync tools/lib/find_bit.c with the kernel
  ...

1 files changed, 339 insertions, 73 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e176bad19bcb..8334a5a9d5d7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -152,29 +152,36 @@ struct bpf_program {
 	} *reloc_desc;
 	int nr_reloc;
 
-	int fd;
+	struct {
+		int nr;
+		int *fds;
+	} instances;
+	bpf_program_prep_t preprocessor;
 
 	struct bpf_object *obj;
 	void *priv;
 	bpf_program_clear_priv_t clear_priv;
 };
 
+struct bpf_map {
+	int fd;
+	char *name;
+	struct bpf_map_def def;
+	void *priv;
+	bpf_map_clear_priv_t clear_priv;
+};
+
 static LIST_HEAD(bpf_objects_list);
 
 struct bpf_object {
 	char license[64];
 	u32 kern_version;
-	void *maps_buf;
-	size_t maps_buf_sz;
 
 	struct bpf_program *programs;
 	size_t nr_programs;
-	int *map_fds;
-	/*
-	 * This field is required because maps_buf will be freed and
-	 * maps_buf_sz will be set to 0 after loaded.
-	 */
-	size_t nr_map_fds;
+	struct bpf_map *maps;
+	size_t nr_maps;
+
 	bool loaded;
 
 	/*
@@ -188,6 +195,7 @@ struct bpf_object {
 		Elf *elf;
 		GElf_Ehdr ehdr;
 		Elf_Data *symbols;
+		size_t strtabidx;
 		struct {
 			GElf_Shdr shdr;
 			Elf_Data *data;
@@ -206,10 +214,25 @@ struct bpf_object {
 
 static void bpf_program__unload(struct bpf_program *prog)
 {
+	int i;
+
 	if (!prog)
 		return;
 
-	zclose(prog->fd);
+	/*
+	 * If the object is opened but the program was never loaded,
+	 * it is possible that prog->instances.nr == -1.
+	 */
+	if (prog->instances.nr > 0) {
+		for (i = 0; i < prog->instances.nr; i++)
+			zclose(prog->instances.fds[i]);
+	} else if (prog->instances.nr != -1) {
+		pr_warning("Internal error: instances.nr is %d\n",
+			   prog->instances.nr);
+	}
+
+	prog->instances.nr = -1;
+	zfree(&prog->instances.fds);
 }
 
 static void bpf_program__exit(struct bpf_program *prog)
@@ -260,7 +283,8 @@ bpf_program__init(void *data, size_t size, char *name, int idx,
 	memcpy(prog->insns, data,
 	       prog->insns_cnt * sizeof(struct bpf_insn));
 	prog->idx = idx;
-	prog->fd = -1;
+	prog->instances.fds = NULL;
+	prog->instances.nr = -1;
 
 	return 0;
 errout:
@@ -469,21 +493,77 @@ static int
 bpf_object__init_maps(struct bpf_object *obj, void *data,
 		      size_t size)
 {
-	if (size == 0) {
+	size_t nr_maps;
+	int i;
+
+	nr_maps = size / sizeof(struct bpf_map_def);
+	if (!data || !nr_maps) {
 		pr_debug("%s doesn't need map definition\n",
 			 obj->path);
 		return 0;
 	}
 
-	obj->maps_buf = malloc(size);
-	if (!obj->maps_buf) {
-		pr_warning("malloc maps failed: %s\n", obj->path);
+	pr_debug("maps in %s: %zd bytes\n", obj->path, size);
+
+	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
+	if (!obj->maps) {
+		pr_warning("alloc maps for object failed\n");
 		return -ENOMEM;
 	}
+	obj->nr_maps = nr_maps;
 
-	obj->maps_buf_sz = size;
-	memcpy(obj->maps_buf, data, size);
-	pr_debug("maps in %s: %ld bytes\n", obj->path, (long)size);
+	for (i = 0; i < nr_maps; i++) {
+		struct bpf_map_def *def = &obj->maps[i].def;
+
+		/*
+		 * fill all fd with -1 so won't close incorrect
+		 * fd (fd=0 is stdin) when failure (zclose won't close
+		 * negative fd)).
+		 */
+		obj->maps[i].fd = -1;
+
+		/* Save map definition into obj->maps */
+		*def = ((struct bpf_map_def *)data)[i];
+	}
+	return 0;
+}
+
+static int
+bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+{
+	int i;
+	Elf_Data *symbols = obj->efile.symbols;
+
+	if (!symbols || maps_shndx < 0)
+		return -EINVAL;
+
+	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+		GElf_Sym sym;
+		size_t map_idx;
+		const char *map_name;
+
+		if (!gelf_getsym(symbols, i, &sym))
+			continue;
+		if (sym.st_shndx != maps_shndx)
+			continue;
+
+		map_name = elf_strptr(obj->efile.elf,
+				      obj->efile.strtabidx,
+				      sym.st_name);
+		map_idx = sym.st_value / sizeof(struct bpf_map_def);
+		if (map_idx >= obj->nr_maps) {
+			pr_warning("index of map \"%s\" is buggy: %zu > %zu\n",
+				   map_name, map_idx, obj->nr_maps);
+			continue;
+		}
+		obj->maps[map_idx].name = strdup(map_name);
+		if (!obj->maps[map_idx].name) {
+			pr_warning("failed to alloc map name\n");
+			return -ENOMEM;
+		}
+		pr_debug("map %zu is \"%s\"\n", map_idx,
+			 obj->maps[map_idx].name);
+	}
 	return 0;
 }
 
@@ -492,7 +572,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
 	Elf_Scn *scn = NULL;
-	int idx = 0, err = 0;
+	int idx = 0, err = 0, maps_shndx = -1;
 
 	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
 	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -542,16 +622,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			err = bpf_object__init_kversion(obj,
 							data->d_buf,
 							data->d_size);
-		else if (strcmp(name, "maps") == 0)
+		else if (strcmp(name, "maps") == 0) {
 			err = bpf_object__init_maps(obj, data->d_buf,
 						    data->d_size);
-		else if (sh.sh_type == SHT_SYMTAB) {
+			maps_shndx = idx;
+		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
 					   obj->path);
 				err = -LIBBPF_ERRNO__FORMAT;
-			} else
+			} else {
 				obj->efile.symbols = data;
+				obj->efile.strtabidx = sh.sh_link;
+			}
 		} else if ((sh.sh_type == SHT_PROGBITS) &&
 			   (sh.sh_flags & SHF_EXECINSTR) &&
 			   (data->d_size > 0)) {
@@ -586,6 +669,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		if (err)
 			goto out;
 	}
+
+	if (!obj->efile.strtabidx || obj->efile.strtabidx >= idx) {
+		pr_warning("Corrupted ELF file: index of strtab invalid\n");
+		return LIBBPF_ERRNO__FORMAT;
+	}
+	if (maps_shndx >= 0)
+		err = bpf_object__init_maps_name(obj, maps_shndx);
 out:
 	return err;
 }
@@ -668,37 +758,15 @@ static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
 	unsigned int i;
-	size_t nr_maps;
-	int *pfd;
-
-	nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def);
-	if (!obj->maps_buf || !nr_maps) {
-		pr_debug("don't need create maps for %s\n",
-			 obj->path);
-		return 0;
-	}
-
-	obj->map_fds = malloc(sizeof(int) * nr_maps);
-	if (!obj->map_fds) {
-		pr_warning("realloc perf_bpf_map_fds failed\n");
-		return -ENOMEM;
-	}
-	obj->nr_map_fds = nr_maps;
 
-	/* fill all fd with -1 */
-	memset(obj->map_fds, -1, sizeof(int) * nr_maps);
-
-	pfd = obj->map_fds;
-	for (i = 0; i < nr_maps; i++) {
-		struct bpf_map_def def;
+	for (i = 0; i < obj->nr_maps; i++) {
+		struct bpf_map_def *def = &obj->maps[i].def;
+		int *pfd = &obj->maps[i].fd;
 
-		def = *(struct bpf_map_def *)(obj->maps_buf +
-				i * sizeof(struct bpf_map_def));
-
-		*pfd = bpf_create_map(def.type,
-				      def.key_size,
-				      def.value_size,
-				      def.max_entries);
+		*pfd = bpf_create_map(def->type,
+				      def->key_size,
+				      def->value_size,
+				      def->max_entries);
 		if (*pfd < 0) {
 			size_t j;
 			int err = *pfd;
@@ -706,22 +774,17 @@ bpf_object__create_maps(struct bpf_object *obj)
 			pr_warning("failed to create map: %s\n",
 				   strerror(errno));
 			for (j = 0; j < i; j++)
-				zclose(obj->map_fds[j]);
-			obj->nr_map_fds = 0;
-			zfree(&obj->map_fds);
+				zclose(obj->maps[j].fd);
 			return err;
 		}
 		pr_debug("create map: fd=%d\n", *pfd);
-		pfd++;
 	}
 
-	zfree(&obj->maps_buf);
-	obj->maps_buf_sz = 0;
 	return 0;
 }
 
 static int
-bpf_program__relocate(struct bpf_program *prog, int *map_fds)
+bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 {
 	int i;
 
@@ -741,7 +804,7 @@ bpf_program__relocate(struct bpf_program *prog, int *map_fds)
 			return -LIBBPF_ERRNO__RELOC;
 		}
 		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
-		insns[insn_idx].imm = map_fds[map_idx];
+		insns[insn_idx].imm = obj->maps[map_idx].fd;
 	}
 
 	zfree(&prog->reloc_desc);
@@ -760,7 +823,7 @@ bpf_object__relocate(struct bpf_object *obj)
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
 
-		err = bpf_program__relocate(prog, obj->map_fds);
+		err = bpf_program__relocate(prog, obj);
 		if (err) {
 			pr_warning("failed to relocate '%s'\n",
 				   prog->section_name);
@@ -784,8 +847,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 		Elf_Data *data = obj->efile.reloc[i].data;
 		int idx = shdr->sh_info;
 		struct bpf_program *prog;
-		size_t nr_maps = obj->maps_buf_sz /
-				 sizeof(struct bpf_map_def);
+		size_t nr_maps = obj->nr_maps;
 
 		if (shdr->sh_type != SHT_REL) {
 			pr_warning("internal error at %d\n", __LINE__);
@@ -860,13 +922,73 @@ static int
 bpf_program__load(struct bpf_program *prog,
 		  char *license, u32 kern_version)
 {
-	int err, fd;
+	int err = 0, fd, i;
 
-	err = load_program(prog->insns, prog->insns_cnt,
-			   license, kern_version, &fd);
-	if (!err)
-		prog->fd = fd;
+	if (prog->instances.nr < 0 || !prog->instances.fds) {
+		if (prog->preprocessor) {
+			pr_warning("Internal error: can't load program '%s'\n",
+				   prog->section_name);
+			return -LIBBPF_ERRNO__INTERNAL;
+		}
+
+		prog->instances.fds = malloc(sizeof(int));
+		if (!prog->instances.fds) {
+			pr_warning("Not enough memory for BPF fds\n");
+			return -ENOMEM;
+		}
+		prog->instances.nr = 1;
+		prog->instances.fds[0] = -1;
+	}
+
+	if (!prog->preprocessor) {
+		if (prog->instances.nr != 1) {
+			pr_warning("Program '%s' is inconsistent: nr(%d) != 1\n",
+				   prog->section_name, prog->instances.nr);
+		}
+		err = load_program(prog->insns, prog->insns_cnt,
+				   license, kern_version, &fd);
+		if (!err)
+			prog->instances.fds[0] = fd;
+		goto out;
+	}
+
+	for (i = 0; i < prog->instances.nr; i++) {
+		struct bpf_prog_prep_result result;
+		bpf_program_prep_t preprocessor = prog->preprocessor;
+
+		bzero(&result, sizeof(result));
+		err = preprocessor(prog, i, prog->insns,
+				   prog->insns_cnt, &result);
+		if (err) {
+			pr_warning("Preprocessing the %dth instance of program '%s' failed\n",
+				   i, prog->section_name);
+			goto out;
+		}
+
+		if (!result.new_insn_ptr || !result.new_insn_cnt) {
+			pr_debug("Skip loading the %dth instance of program '%s'\n",
+				 i, prog->section_name);
+			prog->instances.fds[i] = -1;
+			if (result.pfd)
+				*result.pfd = -1;
+			continue;
+		}
+
+		err = load_program(result.new_insn_ptr,
+				   result.new_insn_cnt,
+				   license, kern_version, &fd);
+
+		if (err) {
+			pr_warning("Loading the %dth instance of program '%s' failed\n",
+					i, prog->section_name);
+			goto out;
+		}
 
+		if (result.pfd)
+			*result.pfd = fd;
+		prog->instances.fds[i] = fd;
+	}
+out:
 	if (err)
 		pr_warning("failed to load program '%s'\n",
 			   prog->section_name);
@@ -970,10 +1092,8 @@ int bpf_object__unload(struct bpf_object *obj)
 	if (!obj)
 		return -EINVAL;
 
-	for (i = 0; i < obj->nr_map_fds; i++)
-		zclose(obj->map_fds[i]);
-	zfree(&obj->map_fds);
-	obj->nr_map_fds = 0;
+	for (i = 0; i < obj->nr_maps; i++)
+		zclose(obj->maps[i].fd);
 
 	for (i = 0; i < obj->nr_programs; i++)
 		bpf_program__unload(&obj->programs[i]);
@@ -1016,7 +1136,16 @@ void bpf_object__close(struct bpf_object *obj)
 	bpf_object__elf_finish(obj);
 	bpf_object__unload(obj);
 
-	zfree(&obj->maps_buf);
+	for (i = 0; i < obj->nr_maps; i++) {
+		zfree(&obj->maps[i].name);
+		if (obj->maps[i].clear_priv)
+			obj->maps[i].clear_priv(&obj->maps[i],
+						obj->maps[i].priv);
+		obj->maps[i].priv = NULL;
+		obj->maps[i].clear_priv = NULL;
+	}
+	zfree(&obj->maps);
+	obj->nr_maps = 0;
 
 	if (obj->programs && obj->nr_programs) {
 		for (i = 0; i < obj->nr_programs; i++)
@@ -1121,5 +1250,142 @@ const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
 
 int bpf_program__fd(struct bpf_program *prog)
 {
-	return prog->fd;
+	return bpf_program__nth_fd(prog, 0);
+}
+
+int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
+			  bpf_program_prep_t prep)
+{
+	int *instances_fds;
+
+	if (nr_instances <= 0 || !prep)
+		return -EINVAL;
+
+	if (prog->instances.nr > 0 || prog->instances.fds) {
+		pr_warning("Can't set pre-processor after loading\n");
+		return -EINVAL;
+	}
+
+	instances_fds = malloc(sizeof(int) * nr_instances);
+	if (!instances_fds) {
+		pr_warning("alloc memory failed for fds\n");
+		return -ENOMEM;
+	}
+
+	/* fill all fd with -1 */
+	memset(instances_fds, -1, sizeof(int) * nr_instances);
+
+	prog->instances.nr = nr_instances;
+	prog->instances.fds = instances_fds;
+	prog->preprocessor = prep;
+	return 0;
+}
+
+int bpf_program__nth_fd(struct bpf_program *prog, int n)
+{
+	int fd;
+
+	if (n >= prog->instances.nr || n < 0) {
+		pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
+			   n, prog->section_name, prog->instances.nr);
+		return -EINVAL;
+	}
+
+	fd = prog->instances.fds[n];
+	if (fd < 0) {
+		pr_warning("%dth instance of program '%s' is invalid\n",
+			   n, prog->section_name);
+		return -ENOENT;
+	}
+
+	return fd;
+}
+
+int bpf_map__get_fd(struct bpf_map *map)
+{
+	if (!map)
+		return -EINVAL;
+
+	return map->fd;
+}
+
+int bpf_map__get_def(struct bpf_map *map, struct bpf_map_def *pdef)
+{
+	if (!map || !pdef)
+		return -EINVAL;
+
+	*pdef = map->def;
+	return 0;
+}
+
+const char *bpf_map__get_name(struct bpf_map *map)
+{
+	if (!map)
+		return NULL;
+	return map->name;
+}
+
+int bpf_map__set_private(struct bpf_map *map, void *priv,
+			 bpf_map_clear_priv_t clear_priv)
+{
+	if (!map)
+		return -EINVAL;
+
+	if (map->priv) {
+		if (map->clear_priv)
+			map->clear_priv(map, map->priv);
+	}
+
+	map->priv = priv;
+	map->clear_priv = clear_priv;
+	return 0;
+}
+
+int bpf_map__get_private(struct bpf_map *map, void **ppriv)
+{
+	if (!map)
+		return -EINVAL;
+
+	if (ppriv)
+		*ppriv = map->priv;
+	return 0;
+}
+
+struct bpf_map *
+bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
+{
+	size_t idx;
+	struct bpf_map *s, *e;
+
+	if (!obj || !obj->maps)
+		return NULL;
+
+	s = obj->maps;
+	e = obj->maps + obj->nr_maps;
+
+	if (prev == NULL)
+		return s;
+
+	if ((prev < s) || (prev >= e)) {
+		pr_warning("error in %s: map handler doesn't belong to object\n",
+			   __func__);
+		return NULL;
+	}
+
+	idx = (prev - obj->maps) + 1;
+	if (idx >= obj->nr_maps)
+		return NULL;
+	return &obj->maps[idx];
+}
+
+struct bpf_map *
+bpf_object__get_map_by_name(struct bpf_object *obj, const char *name)
+{
+	struct bpf_map *pos;
+
+	bpf_map__for_each(pos, obj) {
+		if (pos->name && !strcmp(pos->name, name))
+			return pos;
+	}
+	return NULL;
 }