perf record: Put a copy of kcore into the perf.data directory

Add a new 'perf record' option '--kcore' which will put a copy of
/proc/kcore, kallsyms and modules into a perf.data directory. Note, that
without the --kcore option, output goes to a file as previously. The
tools' -o and -i options work with either a file name or directory name.

Example:

$ sudo perf record --kcore uname

$ sudo tree perf.data
perf.data
├── kcore_dir
│   ├── kallsyms
│   ├── kcore
│   └── modules
└── data

$ sudo perf script -v
build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de
build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541
Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field.
Using CPUID GenuineIntel-6-8E-A
Using perf.data/kcore_dir/kcore for kernel data
Using perf.data/kcore_dir/kallsyms for symbols
perf 19058 506778.423729: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux)
perf 19058 506778.423733: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux)
perf 19058 506778.423734: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux)
perf 19058 506778.423736: 117 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux)
perf 19058 506778.423738: 2092 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux)
perf 19058 506778.423740: 37380 cycles: ffffffffa2f121d0 perf_event_addr_filters_exec+0x0 (vmlinux)
uname 19058 506778.423751: 582673 cycles: ffffffffa303a407 propagate_protected_usage+0x147 (vmlinux)
uname 19058 506778.423892: 2241841 cycles: ffffffffa2cae0c9 unwind_next_frame.part.5+0x79 (vmlinux)
uname 19058 506778.424430: 2457397 cycles: ffffffffa3019232 check_memory_region+0x52 (vmlinux)

Committer testing:

# rm -rf perf.data*
# perf record sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.024 MB perf.data (7 samples) ]
# ls -l perf.data
-rw-------. 1 root root 34772 Oct 21 11:08 perf.data
# perf record --kcore uname
Linux
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.024 MB perf.data (7 samples) ]
ls[root@quaco ~]# ls -lad perf.data*
drwx------. 3 root root 4096 Oct 21 11:08 perf.data
-rw-------. 1 root root 34772 Oct 21 11:08 perf.data.old
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1
# perf evlist -v -i perf.data/data
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1
#

Signed-off-by: Adrian Hunter <[e-mail]>
Reviewed-by: Jiri Olsa <[e-mail]>
Tested-by: Arnaldo Carvalho de Melo <[e-mail]>
Link: http://lore.kernel.org/lkml/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/Documentation/perf-record.txt

···
 
 Implies --tail-synthesize.
 
+--kcore::
+Make a copy of /proc/kcore and place it into a directory with the perf data file.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]

tools/perf/Documentation/perf.data-directory-format.txt

···
 
 Future versions are expected to describe different data files
 layout according to special needs.
+
+Currently the only 'perf record' option to output to a directory is
+the --kcore option which puts a copy of /proc/kcore into the directory.
+e.g.
+
+  $ sudo perf record --kcore uname
+  Linux
+  [ perf record: Woken up 1 times to write data ]
+  [ perf record: Captured and wrote 0.015 MB perf.data (9 samples) ]
+  $ sudo tree -ps perf.data
+  perf.data
+  ├── [-rw-------       23744]  data
+  └── [drwx------        4096]  kcore_dir
+      ├── [-r--------     6731125]  kallsyms
+      ├── [-r--------    40230912]  kcore
+      └── [-r--------        5419]  modules
+
+  1 directory, 4 files
+  $ sudo perf script -v
+  build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de
+  build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541
+  build id event received for /lib/x86_64-linux-gnu/libc-2.28.so: 5b157f49586a3ca84d55837f97ff466767dd3445
+  Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field.
+  Using CPUID GenuineIntel-6-8E-A
+  Using perf.data/kcore_dir/kcore for kernel data
+  Using perf.data/kcore_dir/kallsyms for symbols
+              perf 15316 2060795.480902:          1 cycles:  ffffffffa2caa548 native_write_msr+0x8 (vmlinux)
+              perf 15316 2060795.480906:          1 cycles:  ffffffffa2caa548 native_write_msr+0x8 (vmlinux)
+              perf 15316 2060795.480908:          7 cycles:  ffffffffa2caa548 native_write_msr+0x8 (vmlinux)
+              perf 15316 2060795.480910:        119 cycles:  ffffffffa2caa54a native_write_msr+0xa (vmlinux)
+              perf 15316 2060795.480912:       2109 cycles:  ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux)
+              perf 15316 2060795.480914:      37606 cycles:  ffffffffa2f121fe perf_event_addr_filters_exec+0x2e (vmlinux)
+             uname 15316 2060795.480924:     588287 cycles:  ffffffffa303a56d page_counter_try_charge+0x6d (vmlinux)
+             uname 15316 2060795.481067:    2261945 cycles:  ffffffffa301438f kmem_cache_free+0x4f (vmlinux)
+             uname 15316 2060795.481643:    2172167 cycles:      7f1a48c393c0 _IO_un_link+0x0 (/lib/x86_64-linux-gnu/libc-2.28.so)

tools/perf/builtin-record.c

···
 #include <signal.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include <linux/time64.h>
···
 }
 
 #endif
+
+static bool record__kcore_readable(struct machine *machine)
+{
+	char kcore[PATH_MAX];
+	int fd;
+
+	scnprintf(kcore, sizeof(kcore), "%s/proc/kcore", machine->root_dir);
+
+	fd = open(kcore, O_RDONLY);
+	if (fd < 0)
+		return false;
+
+	close(fd);
+
+	return true;
+}
+
+static int record__kcore_copy(struct machine *machine, struct perf_data *data)
+{
+	char from_dir[PATH_MAX];
+	char kcore_dir[PATH_MAX];
+	int ret;
+
+	snprintf(from_dir, sizeof(from_dir), "%s/proc", machine->root_dir);
+
+	ret = perf_data__make_kcore_dir(data, kcore_dir, sizeof(kcore_dir));
+	if (ret)
+		return ret;
+
+	return kcore_copy(from_dir, kcore_dir);
+}
 
 static int record__mmap_evlist(struct record *rec,
 			       struct evlist *evlist)
···
 	session->header.env.comp_type  = PERF_COMP_ZSTD;
 	session->header.env.comp_level = rec->opts.comp_level;
 
+	if (rec->opts.kcore &&
+	    !record__kcore_readable(&session->machines.host)) {
+		pr_err("ERROR: kcore is not readable.\n");
+		return -1;
+	}
+
 	record__init_features(rec);
 
 	if (rec->opts.use_clockid && rec->opts.clockid_res_ns)
···
 		goto out_child;
 	}
 	session->header.env.comp_mmap_len = session->evlist->core.mmap_len;
+
+	if (rec->opts.kcore) {
+		err = record__kcore_copy(&session->machines.host, data);
+		if (err) {
+			pr_err("ERROR: Failed to copy kcore\n");
+			goto out_child;
+		}
+	}
 
 	err = bpf__apply_obj_config();
 	if (err) {
···
 		     parse_cgroups),
 	OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
 		  "ms to wait before starting measurement after program start"),
+	OPT_BOOLEAN(0, "kcore", &record.opts.kcore, "copy /proc/kcore"),
 	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
 		   "user to profile"),
 
···
 			"cgroup monitoring only available in system-wide mode");
 
 	}
+
+	if (rec->opts.kcore)
+		rec->data.is_dir = true;
 
 	if (rec->opts.comp_level != 0) {
 		pr_debug("Compression enabled, disabling build id collection at the end of the session.\n");

tools/perf/util/data.c

···
 
 	return size;
 }
+
+int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz)
+{
+	int ret;
+
+	if (!data->is_dir)
+		return -1;
+
+	ret = snprintf(buf, buf_sz, "%s/kcore_dir", data->path);
+	if (ret < 0 || (size_t)ret >= buf_sz)
+		return -1;
+
+	return mkdir(buf, S_IRWXU);
+}
+
+char *perf_data__kallsyms_name(struct perf_data *data)
+{
+	char *kallsyms_name;
+	struct stat st;
+
+	if (!data->is_dir)
+		return NULL;
+
+	if (asprintf(&kallsyms_name, "%s/kcore_dir/kallsyms", data->path) < 0)
+		return NULL;
+
+	if (stat(kallsyms_name, &st)) {
+		free(kallsyms_name);
+		return NULL;
+	}
+
+	return kallsyms_name;
+}

tools/perf/util/data.h

···
 void perf_data__close_dir(struct perf_data *data);
 int perf_data__update_dir(struct perf_data *data);
 unsigned long perf_data__size(struct perf_data *data);
+int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz);
+char *perf_data__kallsyms_name(struct perf_data *data);
 #endif /* __PERF_DATA_H */

tools/perf/util/record.h

···
 	bool	      strict_freq;
 	bool	      sample_id;
 	bool	      no_bpf_event;
+	bool	      kcore;
 	unsigned int  freq;
 	unsigned int  mmap_pages;
 	unsigned int  auxtrace_mmap_pages;

tools/perf/util/session.c

···
 				if (ret)
 					goto out_delete;
 			}
+
+			if (!symbol_conf.kallsyms_name &&
+			    !symbol_conf.vmlinux_name)
+				symbol_conf.kallsyms_name = perf_data__kallsyms_name(data);
 		}
 	} else  {
 		session->machines.host.env = &perf_env;

tools/perf/util/util.c

···
 	return rmdir(path);
 }
 
+static int rm_rf_kcore_dir(const char *path)
+{
+	char kcore_dir_path[PATH_MAX];
+	const char *pat[] = {
+		"kcore",
+		"kallsyms",
+		"modules",
+		NULL,
+	};
+
+	snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/kcore_dir", path);
+
+	return rm_rf_depth_pat(kcore_dir_path, 0, pat);
+}
+
 int rm_rf_perf_data(const char *path)
 {
 	const char *pat[] = {
···
 		"data.*",
 		NULL,
 	};
+
+	rm_rf_kcore_dir(path);
 
 	return rm_rf_depth_pat(path, 0, pat);
 }