perf buildid-cache: Add ability to add kcore to the cache

kcore can be used to view the running kernel object code.  However,
kcore changes as modules are loaded and unloaded, and when the kernel
decides to modify its own code.  Consequently it is useful to create a
copy of kcore at a particular time.  Unlike vmlinux, kcore is not unique
for a given build-id.  And in addition, the kallsyms and modules files
are also needed.  The tool therefore creates a directory:

	~/.debug/[kernel.kcore]/<build-id>/<YYYYmmddHHMMSShh>

which contains: kcore, kallsyms and modules.

Note that the copied kcore contains only code sections.  See the
kcore_copy() function for how that is determined.

The tool will not make additional copies of kcore if there is already
one with the same modules at the same addresses.

Currently, perf tools will not look for kcore in the cache.  That is
addressed in another patch.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/525BF849.5030405@intel.com
[ renamed 'index' to 'idx' to avoid shadowing string.h symbol in f12,
  use at least one member initializer when initializing a struct to
  zeros, also to fix the build on f12 ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 366 insertions, 0 deletions

diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 499c71d30225..d6b8af3ce344 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1202,6 +1202,372 @@ static off_t kcore__write(struct kcore *kcore)
 	return elf_update(kcore->elf, ELF_C_WRITE);
 }
 
+struct phdr_data {
+	off_t offset;
+	u64 addr;
+	u64 len;
+};
+
+struct kcore_copy_info {
+	u64 stext;
+	u64 etext;
+	u64 first_symbol;
+	u64 last_symbol;
+	u64 first_module;
+	u64 last_module_symbol;
+	struct phdr_data kernel_map;
+	struct phdr_data modules_map;
+};
+
+static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
+					u64 start)
+{
+	struct kcore_copy_info *kci = arg;
+
+	if (!symbol_type__is_a(type, MAP__FUNCTION))
+		return 0;
+
+	if (strchr(name, '[')) {
+		if (start > kci->last_module_symbol)
+			kci->last_module_symbol = start;
+		return 0;
+	}
+
+	if (!kci->first_symbol || start < kci->first_symbol)
+		kci->first_symbol = start;
+
+	if (!kci->last_symbol || start > kci->last_symbol)
+		kci->last_symbol = start;
+
+	if (!strcmp(name, "_stext")) {
+		kci->stext = start;
+		return 0;
+	}
+
+	if (!strcmp(name, "_etext")) {
+		kci->etext = start;
+		return 0;
+	}
+
+	return 0;
+}
+
+static int kcore_copy__parse_kallsyms(struct kcore_copy_info *kci,
+				      const char *dir)
+{
+	char kallsyms_filename[PATH_MAX];
+
+	scnprintf(kallsyms_filename, PATH_MAX, "%s/kallsyms", dir);
+
+	if (symbol__restricted_filename(kallsyms_filename, "/proc/kallsyms"))
+		return -1;
+
+	if (kallsyms__parse(kallsyms_filename, kci,
+			    kcore_copy__process_kallsyms) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int kcore_copy__process_modules(void *arg,
+				       const char *name __maybe_unused,
+				       u64 start)
+{
+	struct kcore_copy_info *kci = arg;
+
+	if (!kci->first_module || start < kci->first_module)
+		kci->first_module = start;
+
+	return 0;
+}
+
+static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
+				     const char *dir)
+{
+	char modules_filename[PATH_MAX];
+
+	scnprintf(modules_filename, PATH_MAX, "%s/modules", dir);
+
+	if (symbol__restricted_filename(modules_filename, "/proc/modules"))
+		return -1;
+
+	if (modules__parse(modules_filename, kci,
+			   kcore_copy__process_modules) < 0)
+		return -1;
+
+	return 0;
+}
+
+static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
+			    u64 s, u64 e)
+{
+	if (p->addr || s < start || s >= end)
+		return;
+
+	p->addr = s;
+	p->offset = (s - start) + pgoff;
+	p->len = e < end ? e - s : end - s;
+}
+
+static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
+{
+	struct kcore_copy_info *kci = data;
+	u64 end = start + len;
+
+	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
+			kci->etext);
+
+	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
+			kci->last_module_symbol);
+
+	return 0;
+}
+
+static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
+{
+	if (elf_read_maps(elf, true, kcore_copy__read_map, kci) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
+				 Elf *elf)
+{
+	if (kcore_copy__parse_kallsyms(kci, dir))
+		return -1;
+
+	if (kcore_copy__parse_modules(kci, dir))
+		return -1;
+
+	if (kci->stext)
+		kci->stext = round_down(kci->stext, page_size);
+	else
+		kci->stext = round_down(kci->first_symbol, page_size);
+
+	if (kci->etext) {
+		kci->etext = round_up(kci->etext, page_size);
+	} else if (kci->last_symbol) {
+		kci->etext = round_up(kci->last_symbol, page_size);
+		kci->etext += page_size;
+	}
+
+	kci->first_module = round_down(kci->first_module, page_size);
+
+	if (kci->last_module_symbol) {
+		kci->last_module_symbol = round_up(kci->last_module_symbol,
+						   page_size);
+		kci->last_module_symbol += page_size;
+	}
+
+	if (!kci->stext || !kci->etext)
+		return -1;
+
+	if (kci->first_module && !kci->last_module_symbol)
+		return -1;
+
+	return kcore_copy__read_maps(kci, elf);
+}
+
+static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
+				 const char *name)
+{
+	char from_filename[PATH_MAX];
+	char to_filename[PATH_MAX];
+
+	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+	return copyfile_mode(from_filename, to_filename, 0400);
+}
+
+static int kcore_copy__unlink(const char *dir, const char *name)
+{
+	char filename[PATH_MAX];
+
+	scnprintf(filename, PATH_MAX, "%s/%s", dir, name);
+
+	return unlink(filename);
+}
+
+static int kcore_copy__compare_fds(int from, int to)
+{
+	char *buf_from;
+	char *buf_to;
+	ssize_t ret;
+	size_t len;
+	int err = -1;
+
+	buf_from = malloc(page_size);
+	buf_to = malloc(page_size);
+	if (!buf_from || !buf_to)
+		goto out;
+
+	while (1) {
+		/* Use read because mmap won't work on proc files */
+		ret = read(from, buf_from, page_size);
+		if (ret < 0)
+			goto out;
+
+		if (!ret)
+			break;
+
+		len = ret;
+
+		if (readn(to, buf_to, len) != (int)len)
+			goto out;
+
+		if (memcmp(buf_from, buf_to, len))
+			goto out;
+	}
+
+	err = 0;
+out:
+	free(buf_to);
+	free(buf_from);
+	return err;
+}
+
+static int kcore_copy__compare_files(const char *from_filename,
+				     const char *to_filename)
+{
+	int from, to, err = -1;
+
+	from = open(from_filename, O_RDONLY);
+	if (from < 0)
+		return -1;
+
+	to = open(to_filename, O_RDONLY);
+	if (to < 0)
+		goto out_close_from;
+
+	err = kcore_copy__compare_fds(from, to);
+
+	close(to);
+out_close_from:
+	close(from);
+	return err;
+}
+
+static int kcore_copy__compare_file(const char *from_dir, const char *to_dir,
+				    const char *name)
+{
+	char from_filename[PATH_MAX];
+	char to_filename[PATH_MAX];
+
+	scnprintf(from_filename, PATH_MAX, "%s/%s", from_dir, name);
+	scnprintf(to_filename, PATH_MAX, "%s/%s", to_dir, name);
+
+	return kcore_copy__compare_files(from_filename, to_filename);
+}
+
+/**
+ * kcore_copy - copy kallsyms, modules and kcore from one directory to another.
+ * @from_dir: from directory
+ * @to_dir: to directory
+ *
+ * This function copies kallsyms, modules and kcore files from one directory to
+ * another.  kallsyms and modules are copied entirely.  Only code segments are
+ * copied from kcore.  It is assumed that two segments suffice: one for the
+ * kernel proper and one for all the modules.  The code segments are determined
+ * from kallsyms and modules files.  The kernel map starts at _stext or the
+ * lowest function symbol, and ends at _etext or the highest function symbol.
+ * The module map starts at the lowest module address and ends at the highest
+ * module symbol.  Start addresses are rounded down to the nearest page.  End
+ * addresses are rounded up to the nearest page.  An extra page is added to the
+ * highest kernel symbol and highest module symbol to, hopefully, encompass that
+ * symbol too.  Because it contains only code sections, the resulting kcore is
+ * unusual.  One significant peculiarity is that the mapping (start -> pgoff)
+ * is not the same for the kernel map and the modules map.  That happens because
+ * the data is copied adjacently whereas the original kcore has gaps.  Finally,
+ * kallsyms and modules files are compared with their copies to check that
+ * modules have not been loaded or unloaded while the copies were taking place.
+ *
+ * Return: %0 on success, %-1 on failure.
+ */
+int kcore_copy(const char *from_dir, const char *to_dir)
+{
+	struct kcore kcore;
+	struct kcore extract;
+	size_t count = 2;
+	int idx = 0, err = -1;
+	off_t offset = page_size, sz, modules_offset = 0;
+	struct kcore_copy_info kci = { .stext = 0, };
+	char kcore_filename[PATH_MAX];
+	char extract_filename[PATH_MAX];
+
+	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
+		return -1;
+
+	if (kcore_copy__copy_file(from_dir, to_dir, "modules"))
+		goto out_unlink_kallsyms;
+
+	scnprintf(kcore_filename, PATH_MAX, "%s/kcore", from_dir);
+	scnprintf(extract_filename, PATH_MAX, "%s/kcore", to_dir);
+
+	if (kcore__open(&kcore, kcore_filename))
+		goto out_unlink_modules;
+
+	if (kcore_copy__calc_maps(&kci, from_dir, kcore.elf))
+		goto out_kcore_close;
+
+	if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
+		goto out_kcore_close;
+
+	if (!kci.modules_map.addr)
+		count -= 1;
+
+	if (kcore__copy_hdr(&kcore, &extract, count))
+		goto out_extract_close;
+
+	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
+			    kci.kernel_map.len))
+		goto out_extract_close;
+
+	if (kci.modules_map.addr) {
+		modules_offset = offset + kci.kernel_map.len;
+		if (kcore__add_phdr(&extract, idx, modules_offset,
+				    kci.modules_map.addr, kci.modules_map.len))
+			goto out_extract_close;
+	}
+
+	sz = kcore__write(&extract);
+	if (sz < 0 || sz > offset)
+		goto out_extract_close;
+
+	if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
+		       kci.kernel_map.len))
+		goto out_extract_close;
+
+	if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
+					 extract.fd, modules_offset,
+					 kci.modules_map.len))
+		goto out_extract_close;
+
+	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
+		goto out_extract_close;
+
+	if (kcore_copy__compare_file(from_dir, to_dir, "kallsyms"))
+		goto out_extract_close;
+
+	err = 0;
+
+out_extract_close:
+	kcore__close(&extract);
+	if (err)
+		unlink(extract_filename);
+out_kcore_close:
+	kcore__close(&kcore);
+out_unlink_modules:
+	if (err)
+		kcore_copy__unlink(to_dir, "modules");
+out_unlink_kallsyms:
+	if (err)
+		kcore_copy__unlink(to_dir, "kallsyms");
+
+	return err;
+}
+
 int kcore_extract__create(struct kcore_extract *kce)
 {
 	struct kcore kcore;