[PATCH 05/16] perf sdt: ELF support for SDT

[Arnaldo Carvalho de Melo]

From: Hemant Kumar <hemant@xxxxxxxxxxxxxxxxxx>

This patch serves the initial support to identify and list SDT events in
binaries.  When programs containing SDT markers are compiled, gcc with
the help of assembler directives identifies them and places them in the
section ".note.stapsdt".

To find these markers from the binaries, one needs to traverse through
this section and parse the relevant details like the name, type and
location of the marker. Also, the original location could be skewed due
to the effect of prelinking. If that is the case, the locations need to
be adjusted.

The functions in this patch open a given ELF, find out the SDT section,
parse the relevant details, adjust the location (if necessary) and
populate them in a list.

A typical note entry in ".note.stapsdt" section is as follows :

                                 |--nhdr.n_namesz--|
                ------------------------------------
                |      nhdr      |     "stapsdt"   |
        -----   |----------------------------------|
         |      |  <location>       <base_address> |
         |      |  <semaphore>                     |
nhdr.n_descsize |  "provider_name"   "note_name"   |
         |      |   <args>                         |
        -----   |----------------------------------|
                |      nhdr      |     "stapsdt"   |
                |...

The above shows an excerpt from the section ".note.stapsdt".  'nhdr' is
a structure which has the note name size (n_namesz), note description
size (n_desc_sz) and note type (n_type).

So, in order to parse the note note info, we need nhdr to tell us where
to start from.  As can be seen from <sys/sdt.h>, the name of the SDT
notes given is "stapsdt".  But this is not the identifier of the note.

After that, we go to description of the note to find out its location, the
address of the ".stapsdt.base" section and the semaphore address.
Then, we find the provider name and the SDT marker name and then follow the
arguments.

Signed-off-by: Hemant Kumar <hemant@xxxxxxxxxxxxxxxxxx>
Reviewed-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Acked-by: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Ananth N Mavinakayanahalli <ananth@xxxxxxxxxxxxxxxxxx>
Cc: Brendan Gregg <brendan.d.gregg@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: 146736022628.27797.1201368329092908163.stgit@devbox">http://lkml.kernel.org/r/146736022628.27797.1201368329092908163.stgit@devbox
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/symbol-elf.c | 252 +++++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/symbol.h     |  22 ++++
 2 files changed, 274 insertions(+)

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index b222552c7159..6f15b92cbf70 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1789,6 +1789,258 @@ void kcore_extract__delete(struct kcore_extract *kce)
 	unlink(kce->extract_filename);
 }
 
+/**
+ * populate_sdt_note : Parse raw data and identify SDT note
+ * @elf: elf of the opened file
+ * @data: raw data of a section with description offset applied
+ * @len: note description size
+ * @type: type of the note
+ * @sdt_notes: List to add the SDT note
+ *
+ * Responsible for parsing the @data in section .note.stapsdt in @elf and
+ * if its an SDT note, it appends to @sdt_notes list.
+ */
+static int populate_sdt_note(Elf **elf, const char *data, size_t len,
+			     struct list_head *sdt_notes)
+{
+	const char *provider, *name;
+	struct sdt_note *tmp = NULL;
+	GElf_Ehdr ehdr;
+	GElf_Addr base_off = 0;
+	GElf_Shdr shdr;
+	int ret = -EINVAL;
+
+	union {
+		Elf64_Addr a64[NR_ADDR];
+		Elf32_Addr a32[NR_ADDR];
+	} buf;
+
+	Elf_Data dst = {
+		.d_buf = &buf, .d_type = ELF_T_ADDR, .d_version = EV_CURRENT,
+		.d_size = gelf_fsize((*elf), ELF_T_ADDR, NR_ADDR, EV_CURRENT),
+		.d_off = 0, .d_align = 0
+	};
+	Elf_Data src = {
+		.d_buf = (void *) data, .d_type = ELF_T_ADDR,
+		.d_version = EV_CURRENT, .d_size = dst.d_size, .d_off = 0,
+		.d_align = 0
+	};
+
+	tmp = (struct sdt_note *)calloc(1, sizeof(struct sdt_note));
+	if (!tmp) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	INIT_LIST_HEAD(&tmp->note_list);
+
+	if (len < dst.d_size + 3)
+		goto out_free_note;
+
+	/* Translation from file representation to memory representation */
+	if (gelf_xlatetom(*elf, &dst, &src,
+			  elf_getident(*elf, NULL)[EI_DATA]) == NULL) {
+		pr_err("gelf_xlatetom : %s\n", elf_errmsg(-1));
+		goto out_free_note;
+	}
+
+	/* Populate the fields of sdt_note */
+	provider = data + dst.d_size;
+
+	name = (const char *)memchr(provider, '\0', data + len - provider);
+	if (name++ == NULL)
+		goto out_free_note;
+
+	tmp->provider = strdup(provider);
+	if (!tmp->provider) {
+		ret = -ENOMEM;
+		goto out_free_note;
+	}
+	tmp->name = strdup(name);
+	if (!tmp->name) {
+		ret = -ENOMEM;
+		goto out_free_prov;
+	}
+
+	if (gelf_getclass(*elf) == ELFCLASS32) {
+		memcpy(&tmp->addr, &buf, 3 * sizeof(Elf32_Addr));
+		tmp->bit32 = true;
+	} else {
+		memcpy(&tmp->addr, &buf, 3 * sizeof(Elf64_Addr));
+		tmp->bit32 = false;
+	}
+
+	if (!gelf_getehdr(*elf, &ehdr)) {
+		pr_debug("%s : cannot get elf header.\n", __func__);
+		ret = -EBADF;
+		goto out_free_name;
+	}
+
+	/* Adjust the prelink effect :
+	 * Find out the .stapsdt.base section.
+	 * This scn will help us to handle prelinking (if present).
+	 * Compare the retrieved file offset of the base section with the
+	 * base address in the description of the SDT note. If its different,
+	 * then accordingly, adjust the note location.
+	 */
+	if (elf_section_by_name(*elf, &ehdr, &shdr, SDT_BASE_SCN, NULL)) {
+		base_off = shdr.sh_offset;
+		if (base_off) {
+			if (tmp->bit32)
+				tmp->addr.a32[0] = tmp->addr.a32[0] + base_off -
+					tmp->addr.a32[1];
+			else
+				tmp->addr.a64[0] = tmp->addr.a64[0] + base_off -
+					tmp->addr.a64[1];
+		}
+	}
+
+	list_add_tail(&tmp->note_list, sdt_notes);
+	return 0;
+
+out_free_name:
+	free(tmp->name);
+out_free_prov:
+	free(tmp->provider);
+out_free_note:
+	free(tmp);
+out_err:
+	return ret;
+}
+
+/**
+ * construct_sdt_notes_list : constructs a list of SDT notes
+ * @elf : elf to look into
+ * @sdt_notes : empty list_head
+ *
+ * Scans the sections in 'elf' for the section
+ * .note.stapsdt. It, then calls populate_sdt_note to find
+ * out the SDT events and populates the 'sdt_notes'.
+ */
+static int construct_sdt_notes_list(Elf *elf, struct list_head *sdt_notes)
+{
+	GElf_Ehdr ehdr;
+	Elf_Scn *scn = NULL;
+	Elf_Data *data;
+	GElf_Shdr shdr;
+	size_t shstrndx, next;
+	GElf_Nhdr nhdr;
+	size_t name_off, desc_off, offset;
+	int ret = 0;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL) {
+		ret = -EBADF;
+		goto out_ret;
+	}
+	if (elf_getshdrstrndx(elf, &shstrndx) != 0) {
+		ret = -EBADF;
+		goto out_ret;
+	}
+
+	/* Look for the required section */
+	scn = elf_section_by_name(elf, &ehdr, &shdr, SDT_NOTE_SCN, NULL);
+	if (!scn) {
+		ret = -ENOENT;
+		goto out_ret;
+	}
+
+	if ((shdr.sh_type != SHT_NOTE) || (shdr.sh_flags & SHF_ALLOC)) {
+		ret = -ENOENT;
+		goto out_ret;
+	}
+
+	data = elf_getdata(scn, NULL);
+
+	/* Get the SDT notes */
+	for (offset = 0; (next = gelf_getnote(data, offset, &nhdr, &name_off,
+					      &desc_off)) > 0; offset = next) {
+		if (nhdr.n_namesz == sizeof(SDT_NOTE_NAME) &&
+		    !memcmp(data->d_buf + name_off, SDT_NOTE_NAME,
+			    sizeof(SDT_NOTE_NAME))) {
+			/* Check the type of the note */
+			if (nhdr.n_type != SDT_NOTE_TYPE)
+				goto out_ret;
+
+			ret = populate_sdt_note(&elf, ((data->d_buf) + desc_off),
+						nhdr.n_descsz, sdt_notes);
+			if (ret < 0)
+				goto out_ret;
+		}
+	}
+	if (list_empty(sdt_notes))
+		ret = -ENOENT;
+
+out_ret:
+	return ret;
+}
+
+/**
+ * get_sdt_note_list : Wrapper to construct a list of sdt notes
+ * @head : empty list_head
+ * @target : file to find SDT notes from
+ *
+ * This opens the file, initializes
+ * the ELF and then calls construct_sdt_notes_list.
+ */
+int get_sdt_note_list(struct list_head *head, const char *target)
+{
+	Elf *elf;
+	int fd, ret;
+
+	fd = open(target, O_RDONLY);
+	if (fd < 0)
+		return -EBADF;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (!elf) {
+		ret = -EBADF;
+		goto out_close;
+	}
+	ret = construct_sdt_notes_list(elf, head);
+	elf_end(elf);
+out_close:
+	close(fd);
+	return ret;
+}
+
+/**
+ * cleanup_sdt_note_list : free the sdt notes' list
+ * @sdt_notes: sdt notes' list
+ *
+ * Free up the SDT notes in @sdt_notes.
+ * Returns the number of SDT notes free'd.
+ */
+int cleanup_sdt_note_list(struct list_head *sdt_notes)
+{
+	struct sdt_note *tmp, *pos;
+	int nr_free = 0;
+
+	list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) {
+		list_del(&pos->note_list);
+		free(pos->name);
+		free(pos->provider);
+		free(pos);
+		nr_free++;
+	}
+	return nr_free;
+}
+
+/**
+ * sdt_notes__get_count: Counts the number of sdt events
+ * @start: list_head to sdt_notes list
+ *
+ * Returns the number of SDT notes in a list
+ */
+int sdt_notes__get_count(struct list_head *start)
+{
+	struct sdt_note *sdt_ptr;
+	int count = 0;
+
+	list_for_each_entry(sdt_ptr, start, note_list)
+		count++;
+	return count;
+}
+
 void symbol__elf_init(void)
 {
 	elf_version(EV_CURRENT);
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index b10d558a8803..699f7cbcfe72 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -342,4 +342,26 @@ void arch__sym_update(struct symbol *s, GElf_Sym *sym);
 
 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
 
+/* structure containing an SDT note's info */
+struct sdt_note {
+	char *name;			/* name of the note*/
+	char *provider;			/* provider name */
+	bool bit32;			/* whether the location is 32 bits? */
+	union {				/* location, base and semaphore addrs */
+		Elf64_Addr a64[3];
+		Elf32_Addr a32[3];
+	} addr;
+	struct list_head note_list;	/* SDT notes' list */
+};
+
+int get_sdt_note_list(struct list_head *head, const char *target);
+int cleanup_sdt_note_list(struct list_head *sdt_notes);
+int sdt_notes__get_count(struct list_head *start);
+
+#define SDT_BASE_SCN ".stapsdt.base"
+#define SDT_NOTE_SCN  ".note.stapsdt"
+#define SDT_NOTE_TYPE 3
+#define SDT_NOTE_NAME "stapsdt"
+#define NR_ADDR 3
+
 #endif /* __PERF_SYMBOL */
-- 
2.7.4