[PATCH v4 11/29] trace-cmd library: Read compressed trace file

["Tzvetomir Stoyanov (VMware)" <tz.stoyanov@gmail.com>]

If a trace file version 7 is detected, read compressed sections of it.
Read the compression header, check if the compression algorithm and
version, used to compress the file, are supported and use it to
uncompress these sections of the file:
 - ftrace events format
 - format of recorded events
 - information of the mapping of function addresses to the function names
 - trace_printk() format strings
 - information of the mapping a PID to a process name

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/include/trace-cmd-local.h |   3 +
 lib/trace-cmd/trace-input.c             | 257 ++++++++++++++++--------
 2 files changed, 178 insertions(+), 82 deletions(-)

diff --git a/lib/trace-cmd/include/trace-cmd-local.h b/lib/trace-cmd/include/trace-cmd-local.h
index bf90eae8..24228d8f 100644
--- a/lib/trace-cmd/include/trace-cmd-local.h
+++ b/lib/trace-cmd/include/trace-cmd-local.h
@@ -38,4 +38,7 @@ int out_compression_start(struct tracecmd_output *handle);
 int out_compression_end(struct tracecmd_output *handle);
 void out_compression_reset(struct tracecmd_output *handle);
 
+void in_uncompress_reset(struct tracecmd_input *handle);
+int in_uncompress_block(struct tracecmd_input *handle);
+
 #endif /* _TRACE_CMD_LOCAL_H */
diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 67e73c4c..1bfa26d7 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -136,6 +136,9 @@ struct tracecmd_input {
 	long long		ts_offset;
 	struct tsc2nsec		tsc_calc;
 
+	bool			read_compress;
+	struct tracecmd_compression *compress;
+
 	struct host_trace_info	host;
 	double			ts2secs;
 	char *			cpustats;
@@ -255,12 +258,28 @@ static ssize_t do_read(struct tracecmd_input *handle, void *data, size_t size)
 	return tot;
 }
 
+static inline int do_lseek(struct tracecmd_input *handle, int offset, int whence)
+{
+	if (handle->read_compress)
+		return tracecmd_compress_lseek(handle->compress, offset, whence);
+	else
+		return lseek(handle->fd, offset, whence);
+}
+
+static inline ssize_t do_read_compressed(struct tracecmd_input *handle, void *data, size_t size)
+{
+	if (handle->read_compress)
+		return tracecmd_compress_read(handle->compress, data, size);
+	else
+		return do_read(handle, data, size);
+}
+
 static ssize_t
 do_read_check(struct tracecmd_input *handle, void *data, size_t size)
 {
 	ssize_t ret;
 
-	ret = do_read(handle, data, size);
+	ret = do_read_compressed(handle, data, size);
 	if (ret < 0)
 		return ret;
 	if (ret != size)
@@ -278,10 +297,8 @@ static char *read_string(struct tracecmd_input *handle)
 	ssize_t r;
 
 	for (;;) {
-		r = do_read(handle, buf, BUFSIZ);
-		if (r < 0)
-			goto fail;
-		if (!r)
+		r = do_read_compressed(handle, buf, BUFSIZ);
+		if (r <= 0)
 			goto fail;
 
 		for (i = 0; i < r; i++) {
@@ -307,7 +324,7 @@ static char *read_string(struct tracecmd_input *handle)
 	}
 
 	/* move the file descriptor to the end of the string */
-	r = lseek(handle->fd, -(r - (i+1)), SEEK_CUR);
+	r = do_lseek(handle, -(r - (i+1)), SEEK_CUR);
 	if (r < 0)
 		goto fail;
 
@@ -359,6 +376,26 @@ static int read8(struct tracecmd_input *handle, unsigned long long *size)
 	return 0;
 }
 
+__hidden void in_uncompress_reset(struct tracecmd_input *handle)
+{
+	if (handle->compress && handle->file_version >= 7) {
+		handle->read_compress = false;
+		tracecmd_compress_reset(handle->compress);
+	}
+}
+
+__hidden int in_uncompress_block(struct tracecmd_input *handle)
+{
+	int ret = 0;
+
+	if (handle->compress && handle->file_version >= 7) {
+		ret = tracecmd_uncompress_block(handle->compress);
+		if (!ret)
+			handle->read_compress = true;
+	}
+	return ret;
+}
+
 static int read_header_files(struct tracecmd_input *handle)
 {
 	struct tep_handle *pevent = handle->pevent;
@@ -602,34 +639,40 @@ static int read_ftrace_files(struct tracecmd_input *handle, const char *regex)
 		}
 	}
 
-	if (read4(handle, &count) < 0)
+	if (in_uncompress_block(handle))
 		return -1;
 
+	ret = read4(handle, &count);
+	if (ret < 0)
+		goto out;
+
 	for (i = 0; i < count; i++) {
-		if (read8(handle, &size) < 0)
-			return -1;
+		ret = read8(handle, &size);
+		if (ret < 0)
+			goto out;
 		ret = read_ftrace_file(handle, size, print_all, ereg);
 		if (ret < 0)
-			return -1;
+			goto out;
 	}
 
 	handle->event_files_start =
 		lseek64(handle->fd, 0, SEEK_CUR);
+	handle->file_state = TRACECMD_FILE_FTRACE_EVENTS;
 
+	ret = 0;
+out:
 	if (sreg) {
 		regfree(sreg);
 		regfree(ereg);
 	}
-
-	handle->file_state = TRACECMD_FILE_FTRACE_EVENTS;
-
-	return 0;
+	in_uncompress_reset(handle);
+	return ret;
 }
 
 static int read_event_files(struct tracecmd_input *handle, const char *regex)
 {
 	unsigned long long size;
-	char *system;
+	char *system = NULL;
 	regex_t spreg;
 	regex_t epreg;
 	regex_t *sreg = NULL;
@@ -654,13 +697,19 @@ static int read_event_files(struct tracecmd_input *handle, const char *regex)
 			return -1;
 	}
 
-	if (read4(handle, &systems) < 0)
+	if (in_uncompress_block(handle))
 		return -1;
 
+	ret = read4(handle, &systems);
+	if (ret < 0)
+		goto out;
+
 	for (i = 0; i < systems; i++) {
 		system = read_string(handle);
-		if (!system)
-			return -1;
+		if (!system) {
+			ret = -1;
+			goto out;
+		}
 
 		sys_printed = 0;
 		print_all = 0;
@@ -687,103 +736,117 @@ static int read_event_files(struct tracecmd_input *handle, const char *regex)
 			}
 		}
 
-		if (read4(handle, &count) < 0)
-			goto failed;
+		ret = read4(handle, &count);
+		if (ret < 0)
+			goto out;
 
 		for (x=0; x < count; x++) {
-			if (read8(handle, &size) < 0)
-				goto failed;
+			ret = read8(handle, &size);
+			if (ret < 0)
+				goto out;
 
 			ret = read_event_file(handle, system, size,
 					      print_all, &sys_printed,
 					      reg);
 			if (ret < 0)
-				goto failed;
+				goto out;
 		}
 		free(system);
-	}
-
-	if (sreg) {
-		regfree(sreg);
-		regfree(ereg);
+		system = NULL;
 	}
 
 	handle->file_state = TRACECMD_FILE_ALL_EVENTS;
-
-	return 0;
-
- failed:
+	ret = 0;
+ out:
+	in_uncompress_reset(handle);
 	if (sreg) {
 		regfree(sreg);
 		regfree(ereg);
 	}
 
 	free(system);
-	return -1;
+	return ret;
 }
 
 static int read_proc_kallsyms(struct tracecmd_input *handle)
 {
-	struct tep_handle *pevent = handle->pevent;
+	struct tep_handle *tep = handle->pevent;
 	unsigned int size;
-	char *buf;
+	char *buf = NULL;
+	int ret;
 
 	if (handle->file_state >= TRACECMD_FILE_KALLSYMS)
 		return 0;
 
-	if (read4(handle, &size) < 0)
+	if (in_uncompress_block(handle))
 		return -1;
-	if (!size)
-		return 0; /* OK? */
 
-	buf = malloc(size+1);
-	if (!buf)
-		return -1;
-	if (do_read_check(handle, buf, size)){
-		free(buf);
-		return -1;
+	ret = read4(handle, &size);
+	if (ret < 0)
+		goto out;
+	if (!size) {
+		handle->file_state = TRACECMD_FILE_KALLSYMS;
+		goto out; /* OK? */
 	}
-	buf[size] = 0;
-
-	tep_parse_kallsyms(pevent, buf);
 
-	free(buf);
+	buf = malloc(size+1);
+	if (!buf) {
+		ret = -1;
+		goto out;
+	}
+	ret = do_read_check(handle, buf, size);
+	if (ret < 0)
+		goto out;
 
+	buf[size] = 0;
+	tep_parse_kallsyms(tep, buf);
 	handle->file_state = TRACECMD_FILE_KALLSYMS;
-
-	return 0;
+	ret = 0;
+out:
+	free(buf);
+	in_uncompress_reset(handle);
+	return ret;
 }
 
 static int read_ftrace_printk(struct tracecmd_input *handle)
 {
 	unsigned int size;
-	char *buf;
+	char *buf = NULL;
+	int ret;
 
 	if (handle->file_state >= TRACECMD_FILE_PRINTK)
 		return 0;
 
-	if (read4(handle, &size) < 0)
+	if (in_uncompress_block(handle))
 		return -1;
-	if (!size)
-		return 0; /* OK? */
+
+	ret = read4(handle, &size);
+	if (ret < 0)
+		goto out;
+	if (!size) {
+		handle->file_state = TRACECMD_FILE_PRINTK;
+		goto out; /* OK? */
+	}
 
 	buf = malloc(size + 1);
-	if (!buf)
-		return -1;
-	if (do_read_check(handle, buf, size)) {
-		free(buf);
-		return -1;
+	if (!buf) {
+		ret = -1;
+		goto out;
 	}
+	ret = do_read_check(handle, buf, size);
+	if (ret < 0)
+		goto out;
 
 	buf[size] = 0;
 
 	tep_parse_printk_formats(handle->pevent, buf);
-
-	free(buf);
-
 	handle->file_state = TRACECMD_FILE_PRINTK;
+	ret = 0;
 
-	return 0;
+out:
+	free(buf);
+	in_uncompress_reset(handle);
+	return ret;
 }
 
 static int read_and_parse_cmdlines(struct tracecmd_input *handle);
@@ -2974,20 +3037,30 @@ static int read_and_parse_cmdlines(struct tracecmd_input *handle)
 {
 	struct tep_handle *pevent = handle->pevent;
 	unsigned long long size;
-	char *cmdlines;
+	char *cmdlines = NULL;
+	int ret;
 
 	if (handle->file_state >= TRACECMD_FILE_CMD_LINES)
 		return 0;
 
-	if (read_data_and_size(handle, &cmdlines, &size) < 0)
+	if (in_uncompress_block(handle))
 		return -1;
+
+	ret = read_data_and_size(handle, &cmdlines, &size);
+	if (ret < 0)
+		goto out;
+	if (!size) {
+		handle->file_state = TRACECMD_FILE_CMD_LINES;
+		goto out;
+	}
 	cmdlines[size] = 0;
 	tep_parse_saved_cmdlines(pevent, cmdlines);
-	free(cmdlines);
-
 	handle->file_state = TRACECMD_FILE_CMD_LINES;
-
-	return 0;
+	ret = 0;
+out:
+	free(cmdlines);
+	in_uncompress_reset(handle);
+	return ret;
 }
 
 static void extract_trace_clock(struct tracecmd_input *handle, char *line)
@@ -3268,7 +3341,9 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 	struct tracecmd_input *handle;
 	char test[] = TRACECMD_MAGIC;
 	unsigned int page_size;
-	char *version;
+	size_t offset;
+	char *str = NULL;
+	char *zver;
 	char buf[BUFSIZ];
 	unsigned long ver;
 
@@ -3291,11 +3366,11 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 	if (memcmp(buf, "tracing", 7) != 0)
 		goto failed_read;
 
-	version = read_string(handle);
-	if (!version)
+	str = read_string(handle);
+	if (!str)
 		goto failed_read;
-	tracecmd_info("version = %s\n", version);
-	ver = strtol(version, NULL, 10);
+	tracecmd_info("version = %s\n", str);
+	ver = strtol(str, NULL, 10);
 	if (!ver && errno)
 		goto failed_read;
 	if (!tracecmd_is_version_supported(ver)) {
@@ -3303,7 +3378,8 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 		goto failed_read;
 	}
 	handle->file_version = ver;
-	free(version);
+	free(str);
+	str = NULL;
 
 	if (do_read_check(handle, buf, 1))
 		goto failed_read;
@@ -3328,20 +3404,36 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 	read4(handle, &page_size);
 	handle->page_size = page_size;
 
-	handle->header_files_start =
-		lseek64(handle->fd, 0, SEEK_CUR);
+	offset = lseek64(handle->fd, 0, SEEK_CUR);
+	handle->total_file_size = lseek64(handle->fd, 0, SEEK_END);
+	lseek64(handle->fd, offset, SEEK_SET);
 
-	handle->total_file_size =
-		lseek64(handle->fd, 0, SEEK_END);
+	if (handle->file_version >= 7) {
+		str = read_string(handle);
+		if (!str)
+			goto failed_read;
+		zver = strchr(str, ' ');
+		if (!zver)
+			goto failed_read;
+		*zver = '\0';
+		handle->compress = tracecmd_compress_alloc(str, zver + 1,
+							   handle->fd, handle->pevent, NULL);
+		if (!handle->compress) {
+			tracecmd_warning("Unsupported file compression %s %s", str, zver + 1);
+			goto failed_read;
+		}
+		free(str);
+		str = NULL;
+	}
 
 	handle->header_files_start =
-		lseek64(handle->fd, handle->header_files_start, SEEK_SET);
-
+		lseek64(handle->fd, 0, SEEK_CUR);
 	handle->file_state = TRACECMD_FILE_INIT;
 
 	return handle;
 
  failed_read:
+	free(str);
 	free(handle);
 
 	return NULL;
@@ -3519,7 +3611,8 @@ void tracecmd_close(struct tracecmd_input *handle)
 	if (handle->flags & TRACECMD_FL_BUFFER_INSTANCE)
 		tracecmd_close(handle->parent);
 	else {
-		/* Only main handle frees plugins and pevent */
+		/* Only main handle frees plugins, pevent and compression context */
+		tracecmd_compress_destroy(handle->compress);
 		tep_unload_plugins(handle->plugin_list, handle->pevent);
 		tep_free(handle->pevent);
 	}
-- 
2.31.1