[PoC PATCH v3 00/25] Add trace file compression

[PoC PATCH v3 00/25] Add trace file compression

[Tzvetomir Stoyanov (VMware)]

A new PoC implementation, adding a compression to trace file.
A basic infrastructure for compression support is added into the trace-cmd
library. The zlib is used for compression, but more libraries and algorithms
can be added. Trace data is commpressed and part of the trace file metadata: 
 - ftrace events format
 - format of recorded events
 - information about the mapping of function addresses to the function names
 - trace_printk() format strings
 - information of the mapping a PID to a process name
 - options

Note: not all trace-cmd commands are tested with these changes. These are
verified to work with compressed trace files:
 trace-cmd record
 trace-cmd report
 trace-cmd dump
 trace-cmd agent

Todo list, in order to have complete trace file compression:
 - Add support for more compression libraries.
 - Add new trace-cmd command to convert trace files from version 6 to
   version 7 and vise versa.
 - Test all trace-cmd commands with trace file v7.
 - Update trace-cmd documentation.

v3 changes:
 - Compress the trace data.
 - Added documentation to all compression APIs.
 - A few minor fixes.
v2 changes:
 - Refactored compression APIs.
 - Moved the trace buffers description out of the trace options section.
 - Added compression of "options" section of the trace file.
 - Updated "trace-cmd list" to show available compression algorithms.
 - Tested with host-guest tracing.
 - Merged with the patchset that bumps the trace file version.

Tzvetomir Stoyanov (VMware) (25):
  trace-cmd library: Remove unused private APIs for creating trace files
  trace-cmd library: Remove unused API tracecmd_update_option
  trace-cmd: Check if file version is supported
  trace-cmd library: Add new API to get file version of input handler
  trace-cmd library: Select the file version when writing trace file
  trace-cmd: Add APIs for library initialization and free
  trace-cmd library: Add support for compression algorithms
  trace-cmd list: Show supported compression algorithms
  trace-cmd library: Bump the trace file version to 7
  trace-cmd library: Compress part of the trace file
  trace-cmd library: Read compressed trace file
  trace-cmd library: Add new API to get compression of input handler
  trace-cmd library: Inherit compression algorithm from input file
  trace-cmd library: Extend the create file APIs to support different
    compression
  trace-cmd record: Add new parameter --compression
  trace-cmd dump: Add support for trace files version 7
  trace-cmd library: Add support for zlib compression library
  trace-cmd library: Hide the logic for updating buffer offset
  trace-cmd: Move buffers description outside of options
  trace-cmd library: Track the offset in the option section in the trace
    file
  trace-cmd library: Add compression of the option section of the trace
    file
  trace-cmd library: Refactor the logic for writing trace data in the
    file
  trace-cmd library: Add APIs for read and write compressed data in
    chunks
  trace-cmd: Compress trace data
  trace-cmd: Read compressed trace data

 lib/trace-cmd/Makefile                        |  11 +
 .../include/private/trace-cmd-private.h       |  74 +-
 lib/trace-cmd/include/trace-cmd-local.h       |   9 +-
 lib/trace-cmd/trace-compress-zlib.c           | 172 ++++
 lib/trace-cmd/trace-compress.c                | 787 ++++++++++++++++++
 lib/trace-cmd/trace-input.c                   | 451 +++++++---
 lib/trace-cmd/trace-output.c                  | 676 ++++++++++-----
 lib/trace-cmd/trace-util.c                    |  19 +
 tracecmd/trace-cmd.c                          |  11 +-
 tracecmd/trace-dump.c                         | 162 +++-
 tracecmd/trace-list.c                         |  26 +
 tracecmd/trace-listen.c                       |   3 +
 tracecmd/trace-read.c                         |   8 +
 tracecmd/trace-record.c                       |  42 +-
 tracecmd/trace-restore.c                      |   4 +-
 tracecmd/trace-usage.c                        |   6 +
 16 files changed, 2101 insertions(+), 360 deletions(-)
 create mode 100644 lib/trace-cmd/trace-compress-zlib.c
 create mode 100644 lib/trace-cmd/trace-compress.c

-- 
2.31.1

[PATCH v3 01/25] trace-cmd library: Remove unused private APIs for creating trace files

[Tzvetomir Stoyanov (VMware)]

Remove these unused private trace-cmd library APIs:
  tracecmd_create_file()
  tracecmd_create_file_glob()

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 .../include/private/trace-cmd-private.h       |  6 ----
 lib/trace-cmd/trace-output.c                  | 29 -------------------
 2 files changed, 35 deletions(-)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 42e739fa..8ec33ea2 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -263,12 +263,6 @@ struct tracecmd_option;
 struct tracecmd_msg_handle;
 
 struct tracecmd_output *tracecmd_create_file_latency(const char *output_file, int cpus);
-struct tracecmd_output *tracecmd_create_file(const char *output_file,
-					     int cpus, char * const *cpu_data_files);
-struct tracecmd_output *
-tracecmd_create_file_glob(const char *output_file,
-			  int cpus, char * const *cpu_data_files,
-			  struct tracecmd_event_list *event_globs);
 struct tracecmd_output *
 tracecmd_create_init_file_glob(const char *output_file,
 			       struct tracecmd_event_list *list);
diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index a4a1eecc..9231c319 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -1614,35 +1614,6 @@ struct tracecmd_output *tracecmd_get_output_handle_fd(int fd)
 	return NULL;
 }
 
-struct tracecmd_output *
-tracecmd_create_file_glob(const char *output_file,
-			  int cpus, char * const *cpu_data_files,
-			  struct tracecmd_event_list *list)
-{
-	struct tracecmd_output *handle;
-
-	handle = create_file(output_file, NULL, NULL, NULL, list);
-	if (!handle)
-		return NULL;
-
-	if (tracecmd_write_cmdlines(handle))
-		return NULL;
-
-	if (tracecmd_append_cpu_data(handle, cpus, cpu_data_files) < 0) {
-		tracecmd_output_close(handle);
-		return NULL;
-	}
-
-	return handle;
-}
-
-struct tracecmd_output *tracecmd_create_file(const char *output_file,
-					     int cpus, char * const *cpu_data_files)
-{
-	return tracecmd_create_file_glob(output_file, cpus,
-					 cpu_data_files, &all_event_list);
-}
-
 struct tracecmd_output *tracecmd_create_init_fd(int fd)
 {
 	return create_file_fd(fd, NULL, NULL, NULL, &all_event_list, NULL);
-- 
2.31.1

[PATCH v3 02/25] trace-cmd library: Remove unused API tracecmd_update_option

[Tzvetomir Stoyanov (VMware)]

Removed not used trace-cmd library API for updating the options section
of already written trace file:
 tracecmd_update_option()

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 .../include/private/trace-cmd-private.h       |  3 --
 lib/trace-cmd/trace-output.c                  | 40 -------------------
 2 files changed, 43 deletions(-)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 8ec33ea2..ecd172ca 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -290,9 +290,6 @@ int tracecmd_write_cpus(struct tracecmd_output *handle, int cpus);
 int tracecmd_write_cmdlines(struct tracecmd_output *handle);
 int tracecmd_write_options(struct tracecmd_output *handle);
 int tracecmd_append_options(struct tracecmd_output *handle);
-int tracecmd_update_option(struct tracecmd_output *handle,
-			   struct tracecmd_option *option, int size,
-			   const void *data);
 void tracecmd_output_close(struct tracecmd_output *handle);
 void tracecmd_output_free(struct tracecmd_output *handle);
 struct tracecmd_output *tracecmd_copy(struct tracecmd_input *ihandle,
diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index 9231c319..c0aa58cf 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -1229,46 +1229,6 @@ int tracecmd_append_options(struct tracecmd_output *handle)
 	return 0;
 }
 
-int tracecmd_update_option(struct tracecmd_output *handle,
-			   struct tracecmd_option *option, int size,
-			   const void *data)
-{
-	tsize_t offset;
-	stsize_t ret;
-
-	if (size > option->size) {
-		tracecmd_warning("Can't update option with more data than allocated");
-		return -1;
-	}
-
-	if (handle->file_state < TRACECMD_FILE_OPTIONS) {
-		/* Hasn't been written yet. Just update current pointer */
-		option->size = size;
-		memcpy(option->data, data, size);
-		return 0;
-	}
-
-	/* Save current offset */
-	offset = lseek64(handle->fd, 0, SEEK_CUR);
-
-	ret = lseek64(handle->fd, option->offset, SEEK_SET);
-	if (ret == (off64_t)-1) {
-		tracecmd_warning("could not seek to %lld\n", option->offset);
-		return -1;
-	}
-
-	if (do_write_check(handle, data, size))
-		return -1;
-
-	ret = lseek64(handle->fd, offset, SEEK_SET);
-	if (ret == (off64_t)-1) {
-		tracecmd_warning("could not seek to %lld\n", offset);
-		return -1;
-	}
-
-	return 0;
-}
-
 struct tracecmd_option *
 tracecmd_add_buffer_option(struct tracecmd_output *handle, const char *name,
 			   int cpus)
-- 
2.31.1

[PATCH v3 03/25] trace-cmd: Check if file version is supported

[Tzvetomir Stoyanov (VMware)]

When reading a trace file, version of the file is ignored. This could
case problems when bumping the version number because of changes in
in the structure of the file. The old code should detect unsupported
file version and should not try to read it.
A new trace-cmd library API is added to check if version is supported:
 tracecmd_is_version_supported()
Checks are added in the code to ensure not trying to read trace file
from unsupported version.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/include/private/trace-cmd-private.h |  2 ++
 lib/trace-cmd/trace-input.c                       | 10 ++++++++++
 lib/trace-cmd/trace-util.c                        |  7 +++++++
 tracecmd/trace-dump.c                             |  7 +++++++
 4 files changed, 26 insertions(+)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index ecd172ca..136057b4 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -42,6 +42,8 @@ void tracecmd_record_ref(struct tep_record *record);
 void tracecmd_set_debug(bool set_debug);
 bool tracecmd_get_debug(void);
 
+bool tracecmd_is_version_supported(unsigned int version);
+
 struct tracecmd_output;
 struct tracecmd_recorder;
 struct hook_list;
diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 9726e994..b095004d 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -131,6 +131,7 @@ struct tracecmd_input {
 	bool			use_trace_clock;
 	bool			read_page;
 	bool			use_pipe;
+	int			file_version;
 	struct cpu_data 	*cpu_data;
 	long long		ts_offset;
 	struct tsc2nsec		tsc_calc;
@@ -3269,6 +3270,7 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 	unsigned int page_size;
 	char *version;
 	char buf[BUFSIZ];
+	unsigned long ver;
 
 	handle = malloc(sizeof(*handle));
 	if (!handle)
@@ -3293,6 +3295,14 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 	if (!version)
 		goto failed_read;
 	pr_stat("version = %s\n", version);
+	ver = strtol(version, NULL, 10);
+	if (!ver && errno)
+		goto failed_read;
+	if (!tracecmd_is_version_supported(ver)) {
+		tracecmd_warning("Unsupported file version %lu", ver);
+		goto failed_read;
+	}
+	handle->file_version = ver;
 	free(version);
 
 	if (do_read_check(handle, buf, 1))
diff --git a/lib/trace-cmd/trace-util.c b/lib/trace-cmd/trace-util.c
index 2d3bc741..a6fc64c8 100644
--- a/lib/trace-cmd/trace-util.c
+++ b/lib/trace-cmd/trace-util.c
@@ -582,3 +582,10 @@ unsigned long long tracecmd_generate_traceid(void)
 	free(str);
 	return hash;
 }
+
+bool tracecmd_is_version_supported(unsigned int version)
+{
+	if (version <= FILE_VERSION)
+		return true;
+	return false;
+}
diff --git a/tracecmd/trace-dump.c b/tracecmd/trace-dump.c
index 98425b98..03cc82b4 100644
--- a/tracecmd/trace-dump.c
+++ b/tracecmd/trace-dump.c
@@ -10,6 +10,7 @@
 #include <getopt.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <errno.h>
 
 #include "trace-local.h"
 
@@ -145,6 +146,7 @@ static void dump_initial_format(int fd)
 	char magic[] = TRACECMD_MAGIC;
 	char buf[DUMP_SIZE];
 	int val4;
+	unsigned long ver;
 
 	do_print(SUMMARY, "\t[Initial format]\n");
 
@@ -166,6 +168,11 @@ static void dump_initial_format(int fd)
 		die("no version string");
 
 	do_print(SUMMARY, "\t\t%s\t[Version]\n", buf);
+	ver = strtol(buf, NULL, 10);
+	if (!ver && errno)
+		die("Invalid file version string %s", buf);
+	if (!tracecmd_is_version_supported(ver))
+		die("Unsupported file version %lu", ver);
 
 	/* get file endianness*/
 	if (read_file_bytes(fd, buf, 1))
-- 
2.31.1

[PATCH v3 04/25] trace-cmd library: Add new API to get file version of input handler

[Tzvetomir Stoyanov (VMware)]

Added an API to get the version of the trace file, associated with given
input file handler.
  tracecmd_get_file_version()

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/include/private/trace-cmd-private.h | 2 ++
 lib/trace-cmd/trace-input.c                       | 9 +++++++++
 2 files changed, 11 insertions(+)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 136057b4..6a211333 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -232,6 +232,8 @@ int tracecmd_set_cursor(struct tracecmd_input *handle,
 unsigned long long
 tracecmd_get_cursor(struct tracecmd_input *handle, int cpu);
 
+unsigned long tracecmd_get_file_version(struct tracecmd_input *handle);
+
 int tracecmd_ftrace_overrides(struct tracecmd_input *handle, struct tracecmd_ftrace *finfo);
 bool tracecmd_get_use_trace_clock(struct tracecmd_input *handle);
 tracecmd_show_data_func
diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index b095004d..9c9180d6 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -4046,6 +4046,15 @@ struct tep_handle *tracecmd_get_tep(struct tracecmd_input *handle)
 	return handle->pevent;
 }
 
+/**
+ * tracecmd_get_file_version - return the trace.dat file version
+ * @handle: input handle for the trace.dat file
+ */
+unsigned long tracecmd_get_file_version(struct tracecmd_input *handle)
+{
+	return handle->file_version;
+}
+
 /**
  * tracecmd_get_use_trace_clock - return use_trace_clock
  * @handle: input handle for the trace.dat file
-- 
2.31.1

[PATCH v3 05/25] trace-cmd library: Select the file version when writing trace file

[Tzvetomir Stoyanov (VMware)]

When a new output handler to trace file is allocated, select the proper
file version. If this output handler is based on an existing input trace
file handler, inherit the trace file version.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/trace-output.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index c0aa58cf..3c30edc1 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -57,6 +57,7 @@ struct tracecmd_output {
 	int			nr_options;
 	bool			quiet;
 	unsigned long		file_state;
+	unsigned long		file_version;
 	struct list_head	options;
 	struct tracecmd_msg_handle *msg_handle;
 	char			*trace_clock;
@@ -907,6 +908,17 @@ out_free:
 	return ret;
 }
 
+static int select_file_version(struct tracecmd_output *handle,
+				struct tracecmd_input *ihandle)
+{
+	if (ihandle)
+		handle->file_version = tracecmd_get_file_version(ihandle);
+	else
+		handle->file_version = FILE_VERSION;
+
+	return 0;
+}
+
 static struct tracecmd_output *
 create_file_fd(int fd, struct tracecmd_input *ihandle,
 	       const char *tracing_dir,
@@ -933,6 +945,9 @@ create_file_fd(int fd, struct tracecmd_input *ihandle,
 
 	handle->msg_handle = msg_handle;
 
+	if (select_file_version(handle, ihandle))
+		goto out_free;
+
 	list_head_init(&handle->options);
 
 	buf[0] = 23;
@@ -943,7 +958,8 @@ create_file_fd(int fd, struct tracecmd_input *ihandle,
 	if (do_write_check(handle, buf, 10))
 		goto out_free;
 
-	if (do_write_check(handle, FILE_VERSION_STRING, strlen(FILE_VERSION_STRING) + 1))
+	sprintf(buf, "%lu", handle->file_version);
+	if (do_write_check(handle, buf, strlen(buf) + 1))
 		goto out_free;
 
 	/* get endian and page size */
@@ -1562,6 +1578,7 @@ struct tracecmd_output *tracecmd_get_output_handle_fd(int fd)
 	handle->pevent = tracecmd_get_tep(ihandle);
 	tep_ref(handle->pevent);
 	handle->page_size = tracecmd_page_size(ihandle);
+	handle->file_version = tracecmd_get_file_version(ihandle);
 	list_head_init(&handle->options);
 
 	tracecmd_close(ihandle);
-- 
2.31.1

[PATCH v3 06/25] trace-cmd: Add APIs for library initialization and free

[Tzvetomir Stoyanov (VMware)]

The trace-cmd library has no APIs for initialization and free of the
whole library. Added these new APIs:
 tracecmd_lib_init()
 tracecmd_lib_free()
and call them in trace-cmd main function.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/include/private/trace-cmd-private.h |  3 +++
 lib/trace-cmd/trace-util.c                        |  9 +++++++++
 tracecmd/trace-cmd.c                              | 11 ++++++++---
 3 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 6a211333..e410a6f1 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -29,6 +29,9 @@
 
 struct tep_plugin_list *trace_load_plugins(struct tep_handle *tep, int flags);
 
+int tracecmd_lib_init(void);
+void tracecmd_lib_free(void);
+
 int *tracecmd_add_id(int *list, int id, int len);
 
 enum {
diff --git a/lib/trace-cmd/trace-util.c b/lib/trace-cmd/trace-util.c
index a6fc64c8..3ef10eae 100644
--- a/lib/trace-cmd/trace-util.c
+++ b/lib/trace-cmd/trace-util.c
@@ -589,3 +589,12 @@ bool tracecmd_is_version_supported(unsigned int version)
 		return true;
 	return false;
 }
+
+int tracecmd_lib_init(void)
+{
+	return 0;
+}
+
+void tracecmd_lib_free(void)
+{
+}
diff --git a/tracecmd/trace-cmd.c b/tracecmd/trace-cmd.c
index 7376c5a5..aad8e0a7 100644
--- a/tracecmd/trace-cmd.c
+++ b/tracecmd/trace-cmd.c
@@ -116,15 +116,20 @@ int main (int argc, char **argv)
 	if (argc < 2)
 		trace_usage(argc, argv);
 
+	tracecmd_lib_init();
+
 	for (i = 0; i < ARRAY_SIZE(commands); ++i) {
 		if (strcmp(argv[1], commands[i].name) == 0 ){
 			commands[i].run(argc, argv);
-			goto out;
+			break;
 		}
 	}
 
+	tracecmd_lib_free();
+
 	/* No valid command found, show help */
-	trace_usage(argc, argv);
-out:
+	if (i == ARRAY_SIZE(commands))
+		trace_usage(argc, argv);
+
 	exit(0);
 }
-- 
2.31.1

[PATCH v3 07/25] trace-cmd library: Add support for compression algorithms

[Tzvetomir Stoyanov (VMware)]

Added infrastructure to trace-cmd library for compression. Introduced
various new APIs to work with this new functionality:
 struct tracecmd_compression
 tracecmd_compress_init()
 tracecmd_compress_free()
 tracecmd_compress_alloc()
 tracecmd_compress_destroy()
 tracecmd_compress_block()
 tracecmd_uncompress_block()
 tracecmd_compress_reset()
 tracecmd_compress_read()
 tracecmd_compress_pread()
 tracecmd_compress_write()
 tracecmd_compress_lseek()
 tracecmd_compress_proto_get_name()
 tracecmd_compress_is_supported()
 tracecmd_compress_protos_get()
 tracecmd_compress_proto_register()
The compression algorithms are not part of this patch.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/Makefile                        |   1 +
 .../include/private/trace-cmd-private.h       |  26 +
 lib/trace-cmd/include/trace-cmd-local.h       |   2 +
 lib/trace-cmd/trace-compress.c                | 588 ++++++++++++++++++
 lib/trace-cmd/trace-util.c                    |   3 +
 5 files changed, 620 insertions(+)
 create mode 100644 lib/trace-cmd/trace-compress.c

diff --git a/lib/trace-cmd/Makefile b/lib/trace-cmd/Makefile
index 17600318..bab4322d 100644
--- a/lib/trace-cmd/Makefile
+++ b/lib/trace-cmd/Makefile
@@ -25,6 +25,7 @@ ifeq ($(VSOCK_DEFINED), 1)
 OBJS += trace-timesync-ptp.o
 OBJS += trace-timesync-kvm.o
 endif
+OBJS += trace-compress.o
 
 # Additional util objects
 OBJS += trace-blk-hack.o
diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index e410a6f1..602817cb 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -463,6 +463,32 @@ void tracecmd_tsync_free(struct tracecmd_time_sync *tsync);
 int tracecmd_write_guest_time_shift(struct tracecmd_output *handle,
 				    struct tracecmd_time_sync *tsync);
 
+/* --- Compression --- */
+struct tracecmd_compression;
+struct tracecmd_compression *tracecmd_compress_alloc(const char *name, const char *version,
+						     int fd, struct tep_handle *tep,
+						     struct tracecmd_msg_handle *msg_handle);
+void tracecmd_compress_destroy(struct tracecmd_compression *handle);
+int tracecmd_compress_block(struct tracecmd_compression *handle);
+int tracecmd_uncompress_block(struct tracecmd_compression *handle);
+void tracecmd_compress_reset(struct tracecmd_compression *handle);
+int tracecmd_compress_read(struct tracecmd_compression *handle, char *dst, int len);
+int tracecmd_compress_pread(struct tracecmd_compression *handle, char *dst, int len, off_t offset);
+int tracecmd_compress_write(struct tracecmd_compression *handle,
+			    const void *data, unsigned long long size);
+off_t tracecmd_compress_lseek(struct tracecmd_compression *handle, off_t offset, int whence);
+int tracecmd_compress_proto_get_name(struct tracecmd_compression *compress,
+				     const char **name, const char **version);
+bool tracecmd_compress_is_supported(const char *name, const char *version);
+int tracecmd_compress_protos_get(char ***names, char ***versions);
+int tracecmd_compress_proto_register(const char *name, const char *version, int weight,
+				     int (*compress)(char *in, unsigned int in_bytes,
+						     char *out, unsigned int *out_bytes),
+				     int (*uncompress)(char *in, unsigned int in_bytes,
+						       char *out, unsigned int *out_bytes),
+				     unsigned int (*comress_size)(unsigned int bytes),
+				     bool (*is_supported)(const char *name, const char *version));
+
 /* --- Plugin handling --- */
 extern struct tep_plugin_option trace_ftrace_options[];
 
diff --git a/lib/trace-cmd/include/trace-cmd-local.h b/lib/trace-cmd/include/trace-cmd-local.h
index e8533b22..862283fc 100644
--- a/lib/trace-cmd/include/trace-cmd-local.h
+++ b/lib/trace-cmd/include/trace-cmd-local.h
@@ -30,5 +30,7 @@ void tracecmd_fatal(const char *fmt, ...);
 #endif
 #endif
 
+int tracecmd_compress_init(void);
+void tracecmd_compress_free(void);
 
 #endif /* _TRACE_CMD_LOCAL_H */
diff --git a/lib/trace-cmd/trace-compress.c b/lib/trace-cmd/trace-compress.c
new file mode 100644
index 00000000..ff742226
--- /dev/null
+++ b/lib/trace-cmd/trace-compress.c
@@ -0,0 +1,588 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2021, VMware, Tzvetomir Stoyanov tz.stoyanov@gmail.com>
+ *
+ */
+#include <stdlib.h>
+#include <sys/time.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <unistd.h>
+
+#include "trace-cmd-private.h"
+#include "trace-cmd-local.h"
+
+struct compress_proto {
+	struct compress_proto *next;
+	char *proto_name;
+	char *proto_version;
+	int weight;
+
+	int (*comress_block)(char *in, unsigned int in_bytes,
+			     char *out, unsigned int *out_bytes);
+	int (*uncompress_block)(char *in, unsigned int in_bytes,
+				char *out, unsigned int *out_bytes);
+	unsigned int (*comress_size)(unsigned int bytes);
+	bool (*is_supported)(const char *name, const char *version);
+};
+
+static struct compress_proto *proto_list;
+
+struct tracecmd_compression {
+	int				fd;
+	unsigned int			capacity;
+	unsigned long			pointer;
+	char				*buffer;
+	struct compress_proto		*proto;
+	struct tep_handle		*tep;
+	struct tracecmd_msg_handle	*msg_handle;
+};
+
+static int read_fd(int fd, char *dst, int len)
+{
+	size_t size = 0;
+	int r;
+
+	do {
+		r = read(fd, dst+size, len);
+		if (r > 0) {
+			size += r;
+			len -= r;
+		} else
+			break;
+	} while (r > 0);
+
+	if (len)
+		return -1;
+	return size;
+}
+
+static long long write_fd(int fd, const void *data, size_t size)
+{
+	long long tot = 0;
+	long long w;
+
+	do {
+		w = write(fd, data + tot, size - tot);
+		tot += w;
+
+		if (!w)
+			break;
+		if (w < 0)
+			return w;
+	} while (tot != size);
+
+	return tot;
+}
+
+static long long do_write(struct tracecmd_compression *handle,
+			  const void *data, unsigned long long size)
+{
+	int ret;
+
+	if (handle->msg_handle) {
+		ret = tracecmd_msg_data_send(handle->msg_handle, data, size);
+		if (ret)
+			return -1;
+		return size;
+	}
+	return write_fd(handle->fd, data, size);
+}
+
+/**
+ * tracecmd_compress_lseek - Move the read/write pointer into the compression buffer
+ * @handle: compression handler
+ * @offset: number of bytes to move the pointer, can be negative or positive
+ * @whence: the starting position of the pointer movement,
+ *
+ * Read compressed memory block from the file and uncompress it into internal buffer.
+ * The tracecmd_compress_read() can be used to read the uncompressed data from the buffer
+ *
+ * Returns the new file pointer on success, or -1 in case of an error.
+ */
+off_t tracecmd_compress_lseek(struct tracecmd_compression *handle, off_t offset, int whence)
+{
+	unsigned long p, extend;
+	char *buf;
+
+	if (!handle || !handle->buffer)
+		return (off_t)-1;
+
+	switch (whence) {
+	case SEEK_CUR:
+		p = handle->pointer + offset;
+		break;
+	case SEEK_END:
+		p = handle->capacity + offset;
+		break;
+	case SEEK_SET:
+		p = offset;
+		break;
+	default:
+		return (off_t)-1;
+	}
+
+	if (p <= handle->capacity) {
+		handle->pointer = p;
+	} else {
+		extend = p - handle->capacity;
+		extend = extend < BUFSIZ ? BUFSIZ : extend;
+		buf = realloc(handle->buffer, handle->capacity + extend);
+		if (!buf)
+			return (off_t)-1;
+		handle->buffer = buf;
+		handle->capacity += extend;
+		handle->pointer = p;
+	}
+
+	return p;
+}
+
+static int compress_read(struct tracecmd_compression *handle, char *dst, int len)
+{
+	int s;
+
+	if (handle->pointer + len > handle->capacity)
+		s = handle->capacity - handle->pointer;
+	else
+		s = len;
+	memcpy(dst, handle->buffer + handle->pointer, s);
+
+	return s;
+}
+
+/**
+ * tracecmd_compress_pread - pread() on compression buffer
+ * @handle: compression handler
+ * @dst: return, store the read data
+ * @len: length of data to be read
+ * @offset: offset in the buffer of data to be read
+ *
+ * Read a @len of data from the compression buffer at given @offset,
+ * without updating the buffer pointer.
+ *
+ * On success returns the number of bytes read, or -1 on failure.
+ */
+int tracecmd_compress_pread(struct tracecmd_compression *handle, char *dst, int len, off_t offset)
+{
+	int ret;
+
+	if (!handle || !handle->buffer || offset > handle->capacity)
+		return -1;
+
+	ret = tracecmd_compress_lseek(handle, offset, SEEK_SET);
+	if (ret < 0)
+		return ret;
+	return compress_read(handle, dst, len);
+}
+
+/**
+ * tracecmd_compress_read - read() from compression buffer
+ * @handle: compression handler
+ * @dst: return, store the read data
+ * @len: length of data to be read
+ *
+ * Read a @len of data from the compression buffer
+ *
+ * On success returns the number of bytes read, or -1 on failure.
+ */
+int tracecmd_compress_read(struct tracecmd_compression *handle, char *dst, int len)
+{
+	int ret;
+
+	if (!handle || !handle->buffer)
+		return -1;
+
+	ret = compress_read(handle, dst, len);
+	if (ret > 0)
+		handle->pointer += ret;
+
+	return ret;
+}
+
+/**
+ * tracecmd_compress_reset - Reset the compression buffer
+ * @handle: compression handler
+ *
+ * Reset the compression buffer, any data currently in the buffer will be destroyed.
+ *
+ */
+void tracecmd_compress_reset(struct tracecmd_compression *handle)
+{
+	if (handle) {
+		free(handle->buffer);
+		handle->buffer = NULL;
+		handle->pointer = 0;
+		handle->capacity = 0;
+	}
+}
+
+/**
+ * tracecmd_uncompress_block - uncompress a memory block
+ * @handle: compression handler
+ *
+ * Read compressed memory block from the file and uncompress it into internal buffer.
+ * The tracecmd_compress_read() can be used to read the uncompressed data from the buffer
+ *
+ * Returns 0 on success, or -1 in case of an error.
+ */
+int tracecmd_uncompress_block(struct tracecmd_compression *handle)
+{
+	unsigned int s_uncompressed;
+	unsigned int s_compressed;
+	char buf[4];
+	char *bytes = NULL;
+	int ret;
+
+	if (!handle || !handle->proto || !handle->proto->uncompress_block)
+		return -1;
+	tracecmd_compress_reset(handle);
+
+	if (read(handle->fd, buf, 4) != 4)
+		return -1;
+	s_compressed = tep_read_number(handle->tep, buf, 4);
+	if (read(handle->fd, buf, 4) != 4)
+		return -1;
+	s_uncompressed = tep_read_number(handle->tep, buf, 4);
+
+	handle->buffer = malloc(s_uncompressed);
+	if (!handle->buffer)
+		return -1;
+	bytes = malloc(s_compressed);
+	if (!bytes)
+		goto error;
+
+	if (read_fd(handle->fd, bytes, s_compressed) < 0)
+		goto error;
+	ret = handle->proto->uncompress_block(bytes, s_compressed,
+					      handle->buffer, &s_uncompressed);
+	if (ret)
+		goto error;
+	free(bytes);
+	handle->pointer = 0;
+	handle->capacity = s_uncompressed;
+	return 0;
+error:
+	tracecmd_compress_reset(handle);
+	free(bytes);
+	return -1;
+}
+
+/**
+ * tracecmd_compress_block - compress a memory block
+ * @handle: compression handler
+ *
+ * Compress the content of the internal memory buffer and write the compressed data in the file
+ * The tracecmd_compress_write() can be used to write data into the internal memory buffer, before
+ * calling this API.
+ *
+ * Returns 0 on success, or -1 in case of an error.
+ */
+int tracecmd_compress_block(struct tracecmd_compression *handle)
+{
+	unsigned int size;
+	char *buf;
+	int endian4;
+	int ret;
+
+	size = handle->proto->comress_size(handle->pointer);
+	buf = malloc(size);
+	if (!buf)
+		return -1;
+	ret = handle->proto->comress_block(handle->buffer, handle->pointer, buf, &size);
+	if (ret < 0)
+		goto out;
+	/* Write compressed data size */
+	endian4 = tep_read_number(handle->tep, &size, 4);
+	ret = do_write(handle, &endian4, 4);
+	if (ret != 4)
+		goto out;
+	/* Write uncompressed data size */
+	endian4 = tep_read_number(handle->tep, &handle->pointer, 4);
+	ret = do_write(handle, &endian4, 4);
+	if (ret != 4)
+		goto out;
+	/* Write the uncompressed data */
+	ret = do_write(handle, buf, size);
+	ret = ((ret == size) ? 0 : -1);
+out:
+	tracecmd_compress_reset(handle);
+	free(buf);
+	return ret;
+}
+
+/**
+ * tracecmd_compress_write - write() to compression buffer
+ * @handle: compression handler
+ * @data: data to be written
+ * @size: size of @data
+ *
+ * Write @data of @size in the compression buffer
+ *
+ * Returns 0 on success, or -1 on failure.
+ */
+int tracecmd_compress_write(struct tracecmd_compression *handle,
+			    const void *data, unsigned long long size)
+{
+	char *buf;
+	int extend;
+
+	if (handle->capacity < handle->pointer + size) {
+		extend = (handle->pointer + size) - handle->capacity;
+		extend = extend < BUFSIZ ? BUFSIZ : extend;
+		buf = realloc(handle->buffer, handle->capacity + extend);
+		if (!buf)
+			return -1;
+		handle->buffer = buf;
+		handle->capacity += extend;
+	}
+	memcpy(&handle->buffer[handle->pointer], data, size);
+	handle->pointer += size;
+	return 0;
+}
+
+/**
+ * tracecmd_compress_init - initialize the library with available compression algorithms
+ *
+ * Returns 0. If no compression algorithms are available, a warning is printed.
+ */
+int tracecmd_compress_init(void)
+{
+	struct timeval time;
+
+	gettimeofday(&time, NULL);
+	srand((time.tv_sec * 1000) + (time.tv_usec / 1000));
+
+	return 0;
+}
+
+static struct compress_proto *compress_proto_select(void)
+{
+	struct compress_proto *proto = proto_list;
+	struct compress_proto *selected = NULL;
+
+	while (proto) {
+		if (!selected || selected->weight > proto->weight)
+			selected = proto;
+		proto = proto->next;
+	}
+
+	return selected;
+}
+
+/**
+ * tracecmd_compress_alloc - Allocate a new compression context
+ * @name: name of the compression algorithm
+ * @version: version of the compression algorithm
+ * @fd: file descriptor for reading / writing data
+ * @tep: tep handler, used to encode the data
+ * @msg_handle: message handler, use it for reading / writing data instead of @fd
+ *
+ * Returns NULL on failure or pointer to allocated compression context.
+ * The returned context must be freed by tracecmd_compress_destroy()
+ */
+struct tracecmd_compression *tracecmd_compress_alloc(const char *name, const char *version,
+						     int fd, struct tep_handle *tep,
+						     struct tracecmd_msg_handle *msg_handle)
+{
+	struct compress_proto *proto;
+	struct tracecmd_compression *new;
+
+	if (name) {
+		proto = proto_list;
+		while (proto) {
+			if (proto->is_supported && proto->is_supported(name, version))
+				break;
+			proto = proto->next;
+		}
+	} else {
+		proto = compress_proto_select();
+	}
+	if (!proto)
+		return NULL;
+
+	new = calloc(1, sizeof(*new));
+	if (!new)
+		return NULL;
+	new->fd = fd;
+	new->tep = tep;
+	new->msg_handle = msg_handle;
+	new->proto = proto;
+	return new;
+}
+
+/**
+ * tracecmd_compress_destroy - Free a compression context
+ * @handle: handle to the compression context that will be freed
+ */
+void tracecmd_compress_destroy(struct tracecmd_compression *handle)
+{
+	tracecmd_compress_reset(handle);
+	free(handle);
+}
+
+/**
+ * tracecmd_compress_is_supported - check if compression algorithm with given name and
+ *				    version is supported
+ * @name: name of the compression algorithm.
+ * @version: version of the compression algorithm.
+ *
+ * Returns true if the algorithm with given name and version is supported or false if it is not.
+ */
+bool tracecmd_compress_is_supported(const char *name, const char *version)
+{
+	struct compress_proto *proto = proto_list;
+
+	if (!name)
+		return NULL;
+
+	while (proto) {
+		if (proto->is_supported && proto->is_supported(name, version))
+			return true;
+		proto = proto->next;
+	}
+	return false;
+}
+
+/**
+ * tracecmd_compress_proto_get_name - get name and version of compression algorithm
+ * @compress: compression handler.
+ * @name: return, name of the compression algorithm.
+ * @version: return, version of the compression algorithm.
+ *
+ * Returns 0 on success, or -1 in case of an error. If 0 is returned, the name and version of the
+ * algorithm are stored in @name and @version. The returned strings must *not* be freed.
+ */
+int tracecmd_compress_proto_get_name(struct tracecmd_compression *compress,
+				     const char **name, const char **version)
+{
+	if (!compress || !compress->proto)
+		return -1;
+	if (name)
+		*name = compress->proto->proto_name;
+	if (version)
+		*version = compress->proto->proto_version;
+	return 0;
+}
+
+/**
+ * tracecmd_compress_proto_register - register a new compression algorithm
+ * @name: name of the compression algorithm.
+ * @version: version of the compression algorithm.
+ * @weight: weight of the compression algorithm, lower is better.
+ * @compress: compression hook, called to compress a memory block.
+ * @uncompress: uncompression hook, called to uncompress a memory block.
+ * @comress_size: hook, called to get the required minimum size of the buffer for compression
+ *		  given number of bytes.
+ * @is_supported: check hook, called to check if compression with given name and version is
+ *		  supported by this plugin.
+ *
+ * Returns 0 on success, or -1 in case of an error. If algorithm with given name and version is
+ * already registered, -1 is returned.
+ */
+int tracecmd_compress_proto_register(const char *name, const char *version, int weight,
+				     int (*compress)(char *in, unsigned int in_bytes,
+						     char *out, unsigned int *out_bytes),
+				     int (*uncompress)(char *in, unsigned int in_bytes,
+						       char *out, unsigned int *out_bytes),
+				     unsigned int (*comress_size)(unsigned int bytes),
+				     bool (*is_supported)(const char *name, const char *version))
+{
+	struct compress_proto *new;
+
+	if (!name || !compress || !uncompress)
+		return -1;
+	if (tracecmd_compress_is_supported(name, version))
+		return -1;
+
+	new = calloc(1, sizeof(*new));
+	if (!new)
+		return -1;
+
+	new->proto_name = strdup(name);
+	if (!new->proto_name)
+		goto error;
+	new->proto_version = strdup(version);
+	if (!new->proto_version)
+		goto error;
+	new->comress_block = compress;
+	new->uncompress_block = uncompress;
+	new->comress_size = comress_size;
+	new->is_supported = is_supported;
+	new->weight = weight;
+	new->next = proto_list;
+	proto_list = new;
+	return 0;
+
+error:
+	free(new->proto_name);
+	free(new->proto_version);
+	free(new);
+	return -1;
+}
+
+/**
+ * tracecmd_compress_free - free the library resources, related to available compression algorithms
+ *
+ */
+void tracecmd_compress_free(void)
+{
+	struct compress_proto *proto = proto_list;
+	struct compress_proto *del;
+
+	while (proto) {
+		del = proto;
+		proto = proto->next;
+		free(del->proto_name);
+		free(del->proto_version);
+		free(del);
+	}
+	proto_list = NULL;
+}
+
+/**
+ * tracecmd_compress_protos_get - get a list of all supported compression algorithms and versions
+ * @names: return, array with names of all supported compression algorithms
+ * @versions: return, array with versions of all supported compression algorithms
+ *
+ * On success, the size of @names and @versions arrays is returned. Those arrays are allocated by
+ * the API and must be freed with free() by the caller. Both arrays are with same size, each name
+ * from @names corresponds to a version from @versions.
+ * On error -1 is returned and @names and @versions arrays are not allocated.
+ */
+int tracecmd_compress_protos_get(char ***names, char ***versions)
+{
+	struct compress_proto *proto = proto_list;
+	char **n = NULL;
+	char **v = NULL;
+	int c, i;
+
+	for (c = 0; proto; proto = proto->next)
+		c++;
+
+	if (c < 1)
+		return c;
+
+	n = calloc(c, sizeof(char *));
+	if (!n)
+		goto error;
+	v = calloc(c, sizeof(char *));
+	if (!v)
+		goto error;
+
+	proto = proto_list;
+	for (i = 0; i < c && proto; i++) {
+		n[i] = proto->proto_name;
+		v[i] = proto->proto_version;
+		proto = proto->next;
+	}
+
+	*names = n;
+	*versions = v;
+	return c;
+
+error:
+	free(n);
+	free(v);
+	return -1;
+}
diff --git a/lib/trace-cmd/trace-util.c b/lib/trace-cmd/trace-util.c
index 3ef10eae..a42499fe 100644
--- a/lib/trace-cmd/trace-util.c
+++ b/lib/trace-cmd/trace-util.c
@@ -592,9 +592,12 @@ bool tracecmd_is_version_supported(unsigned int version)
 
 int tracecmd_lib_init(void)
 {
+
+	tracecmd_compress_init();
 	return 0;
 }
 
 void tracecmd_lib_free(void)
 {
+	tracecmd_compress_free();
 }
-- 
2.31.1

[PATCH v3 08/25] trace-cmd list: Show supported compression algorithms

[Tzvetomir Stoyanov (VMware)]

Add new parameter "trace-cmd list -c" to show supported compression
algorithms.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 tracecmd/trace-list.c  | 26 ++++++++++++++++++++++++++
 tracecmd/trace-usage.c |  1 +
 2 files changed, 27 insertions(+)

diff --git a/tracecmd/trace-list.c b/tracecmd/trace-list.c
index d060c810..900da73b 100644
--- a/tracecmd/trace-list.c
+++ b/tracecmd/trace-list.c
@@ -549,6 +549,24 @@ static void show_plugins(void)
 	tep_free(pevent);
 }
 
+static void show_compression(void)
+{
+	char **versions, **names;
+	int c, i;
+
+	c = tracecmd_compress_protos_get(&names, &versions);
+	if (c <= 0) {
+		printf("No compression algorithms are supported\n");
+		return;
+	}
+	printf("Supported compression algorithms:\n");
+	for (i = 0; i < c; i++)
+		printf("\t%s, %s\n", names[i], versions[i]);
+
+	free(names);
+	free(versions);
+}
+
 void trace_list(int argc, char **argv)
 {
 	int events = 0;
@@ -562,6 +580,7 @@ void trace_list(int argc, char **argv)
 	int flags = 0;
 	int systems = 0;
 	int show_all = 1;
+	int compression = 0;
 	int i;
 	const char *arg;
 	const char *funcre = NULL;
@@ -626,6 +645,10 @@ void trace_list(int argc, char **argv)
 				systems = 1;
 				show_all = 0;
 				break;
+			case 'c':
+				compression = 1;
+				show_all = 0;
+				break;
 			case '-':
 				if (strcmp(argv[i], "--debug") == 0) {
 					tracecmd_set_debug(true);
@@ -670,6 +693,8 @@ void trace_list(int argc, char **argv)
 		show_clocks();
 	if (systems)
 		show_systems();
+	if (compression)
+		show_compression();
 	if (show_all) {
 		printf("event systems:\n");
 		show_systems();
@@ -679,6 +704,7 @@ void trace_list(int argc, char **argv)
 		show_tracers();
 		printf("\noptions:\n");
 		show_options();
+		show_compression();
 	}
 
 	return;
diff --git a/tracecmd/trace-usage.c b/tracecmd/trace-usage.c
index 998f5a24..c388eccd 100644
--- a/tracecmd/trace-usage.c
+++ b/tracecmd/trace-usage.c
@@ -330,6 +330,7 @@ static struct usage_help usage_help[] = {
 		"          -O list plugin options\n"
 		"          -B list defined buffer instances\n"
 		"          -C list the defined clocks (and active one)\n"
+		"          -c list the supported trace file compression algorithms\n"
 	},
 	{
 		"restore",
-- 
2.31.1

[PATCH v3 09/25] trace-cmd library: Bump the trace file version to 7

[Tzvetomir Stoyanov (VMware)]

Adding a compression of the trace.dat file will change its structure.
These changes are not backward compatible, the old trace-cmd binaries
will not be able to read compressed trace files. Bumping the version to
7 will prevent old trace-cmd to read such files.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/include/trace-cmd-local.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/trace-cmd/include/trace-cmd-local.h b/lib/trace-cmd/include/trace-cmd-local.h
index 862283fc..c8c51ff0 100644
--- a/lib/trace-cmd/include/trace-cmd-local.h
+++ b/lib/trace-cmd/include/trace-cmd-local.h
@@ -14,7 +14,7 @@ void tracecmd_warning(const char *fmt, ...);
 void tracecmd_fatal(const char *fmt, ...);
 
 /* trace.dat file format version */
-#define FILE_VERSION 6
+#define FILE_VERSION 7
 
 #define _STR(x)	#x
 #define STR(x)	_STR(x)
-- 
2.31.1

[PATCH v3 10/25] trace-cmd library: Compress part of the trace file

[Tzvetomir Stoyanov (VMware)]

Compress part of the trace.dat file metadata. If there is compression
support, chose file version 7 and compress these parts 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

A new compression header is added in the file, right after the page size
information.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/trace-output.c | 145 +++++++++++++++++++++++++++++------
 1 file changed, 123 insertions(+), 22 deletions(-)

diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index 3c30edc1..627cea42 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -58,6 +58,10 @@ struct tracecmd_output {
 	bool			quiet;
 	unsigned long		file_state;
 	unsigned long		file_version;
+
+	bool			do_compress;
+	struct tracecmd_compression *compress;
+
 	struct list_head	options;
 	struct tracecmd_msg_handle *msg_handle;
 	char			*trace_clock;
@@ -78,12 +82,31 @@ struct list_event_system {
 static stsize_t
 do_write_check(struct tracecmd_output *handle, const void *data, tsize_t size)
 {
+	if (handle->do_compress && handle->compress)
+		return tracecmd_compress_write(handle->compress, data, size);
+
 	if (handle->msg_handle)
 		return tracecmd_msg_data_send(handle->msg_handle, data, size);
 
 	return __do_write_check(handle->fd, data, size);
 }
 
+static inline int do_lseek(struct tracecmd_output *handle, off_t offset, int whence)
+{
+	if (handle->do_compress)
+		return tracecmd_compress_lseek(handle->compress, offset, whence);
+	else
+		return lseek64(handle->fd, offset, whence);
+}
+
+static inline int do_preed(struct tracecmd_output *handle, void *dst, int len, off_t offset)
+{
+	if (handle->do_compress)
+		return tracecmd_compress_pread(handle->compress, dst, len, offset);
+	else
+		return pread(handle->fd, dst, len, offset);
+}
+
 static short convert_endian_2(struct tracecmd_output *handle, short val)
 {
 	if (!handle->pevent)
@@ -109,6 +132,31 @@ static unsigned long long convert_endian_8(struct tracecmd_output *handle,
 	return tep_read_number(handle->pevent, &val, 8);
 }
 
+static inline void compression_reset(struct tracecmd_output *handle)
+{
+	if (handle->file_version < 7 || !handle->compress)
+		return;
+	tracecmd_compress_reset(handle->compress);
+	handle->do_compress = false;
+}
+
+static inline int compression_start(struct tracecmd_output *handle)
+{
+	if (handle->file_version < 7 || !handle->compress)
+		return 0;
+	tracecmd_compress_reset(handle->compress);
+	handle->do_compress = true;
+	return 0;
+}
+
+static inline int compression_end(struct tracecmd_output *handle)
+{
+	if (handle->file_version < 7 || !handle->compress)
+		return 0;
+	handle->do_compress = false;
+	return tracecmd_compress_block(handle->compress);
+}
+
 /**
  * tracecmd_set_quiet - Set if to print output to the screen
  * @quiet: If non zero, print no output to the screen
@@ -159,6 +207,7 @@ void tracecmd_output_free(struct tracecmd_output *handle)
 		free(option);
 	}
 	free(handle->trace_clock);
+	tracecmd_compress_destroy(handle->compress);
 	free(handle);
 }
 
@@ -659,13 +708,17 @@ static int read_ftrace_files(struct tracecmd_output *handle)
 	}
 
 	create_event_list_item(handle, &systems, &list);
-
+	compression_start(handle);
 	ret = copy_event_system(handle, systems);
+	if (!ret)
+		ret = compression_end(handle);
+	else
+		compression_reset(handle);
 
 	free_list_events(systems);
 
-	handle->file_state = TRACECMD_FILE_FTRACE_EVENTS;
-
+	if (!ret)
+		handle->file_state = TRACECMD_FILE_FTRACE_EVENTS;
 	return ret;
 }
 
@@ -715,6 +768,7 @@ static int read_event_files(struct tracecmd_output *handle,
 	for (slist = systems; slist; slist = slist->next)
 		count++;
 
+	compression_start(handle);
 	ret = -1;
 	endian4 = convert_endian_4(handle, count);
 	if (do_write_check(handle, &endian4, 4))
@@ -730,8 +784,14 @@ static int read_event_files(struct tracecmd_output *handle,
 		ret = copy_event_system(handle, slist);
 	}
 
-	handle->file_state = TRACECMD_FILE_ALL_EVENTS;
+	if (!ret)
+		ret = compression_end(handle);
  out_free:
+	if (!ret)
+		handle->file_state = TRACECMD_FILE_ALL_EVENTS;
+	else
+		compression_reset(handle);
+
 	free_list_events(systems);
 
 	return ret;
@@ -793,20 +853,20 @@ static int read_proc_kallsyms(struct tracecmd_output *handle,
 
 	if (kallsyms)
 		path = kallsyms;
-
+	compression_start(handle);
 	ret = stat(path, &st);
 	if (ret < 0) {
 		/* not found */
 		size = 0;
 		endian4 = convert_endian_4(handle, size);
-		if (do_write_check(handle, &endian4, 4))
-			return -1;
-		return 0;
+		ret = do_write_check(handle, &endian4, 4);
+		goto out;
 	}
 	size = get_size(path);
 	endian4 = convert_endian_4(handle, size);
-	if (do_write_check(handle, &endian4, 4))
-		return -1;
+	ret = do_write_check(handle, &endian4, 4);
+	if (ret)
+		goto out;
 
 	set_proc_kptr_restrict(0);
 	check_size = copy_file(handle, path);
@@ -814,13 +874,18 @@ static int read_proc_kallsyms(struct tracecmd_output *handle,
 		errno = EINVAL;
 		tracecmd_warning("error in size of file '%s'", path);
 		set_proc_kptr_restrict(1);
-		return -1;
+		ret = -1;
+		goto out;
 	}
 	set_proc_kptr_restrict(1);
 
-	handle->file_state = TRACECMD_FILE_KALLSYMS;
-
-	return 0;
+	ret = compression_end(handle);
+out:
+	if (!ret)
+		handle->file_state = TRACECMD_FILE_KALLSYMS;
+	else
+		compression_reset(handle);
+	return ret;
 }
 
 static int read_ftrace_printk(struct tracecmd_output *handle)
@@ -840,6 +905,7 @@ static int read_ftrace_printk(struct tracecmd_output *handle)
 	if (!path)
 		return -1;
 
+	compression_start(handle);
 	ret = stat(path, &st);
 	if (ret < 0) {
 		/* not found */
@@ -861,11 +927,14 @@ static int read_ftrace_printk(struct tracecmd_output *handle)
 	}
 
  out:
-	handle->file_state = TRACECMD_FILE_PRINTK;
 	put_tracing_file(path);
+	if (compression_end(handle))
+		return -1;
+	handle->file_state = TRACECMD_FILE_PRINTK;
 	return 0;
  fail:
 	put_tracing_file(path);
+	compression_reset(handle);
 	return -1;
 }
 
@@ -911,14 +980,39 @@ out_free:
 static int select_file_version(struct tracecmd_output *handle,
 				struct tracecmd_input *ihandle)
 {
-	if (ihandle)
+	if (ihandle) {
 		handle->file_version = tracecmd_get_file_version(ihandle);
-	else
-		handle->file_version = FILE_VERSION;
+	} else {
+		handle->compress = tracecmd_compress_alloc(NULL, NULL, handle->fd,
+							   handle->pevent, handle->msg_handle);
+		if (handle->compress)
+			handle->file_version = 7;
+		else
+			handle->file_version = 6;
+	}
 
 	return 0;
 }
 
+static int write_compression_header(struct tracecmd_output *handle)
+{
+	const char *name = NULL;
+	const char *ver = NULL;
+	char *buf;
+	int ret;
+
+	ret = tracecmd_compress_proto_get_name(handle->compress, &name, &ver);
+	if (ret < 0 || !name || !ver)
+		return -1;
+	ret = asprintf(&buf, "%s %s", name, ver);
+	if (ret < 0)
+		return -1;
+	ret = do_write_check(handle, buf, strlen(buf) + 1);
+
+	free(buf);
+	return ret;
+}
+
 static struct tracecmd_output *
 create_file_fd(int fd, struct tracecmd_input *ihandle,
 	       const char *tracing_dir,
@@ -993,7 +1087,8 @@ create_file_fd(int fd, struct tracecmd_input *ihandle,
 	if (do_write_check(handle, &endian4, 4))
 		goto out_free;
 	handle->file_state = TRACECMD_FILE_INIT;
-
+	if (handle->file_version >= 7 && write_compression_header(handle))
+		goto out_free;
 	if (ihandle)
 		return handle;
 
@@ -1285,11 +1380,17 @@ int tracecmd_write_cmdlines(struct tracecmd_output *handle)
 				 handle->file_state);
 		return ret;
 	}
+	compression_start(handle);
+
 	ret = save_tracing_file_data(handle, "saved_cmdlines");
-	if (ret < 0)
+	if (ret < 0) {
+		compression_reset(handle);
 		return ret;
-	handle->file_state = TRACECMD_FILE_CMD_LINES;
-	return 0;
+	}
+	ret = compression_end(handle);
+	if (!ret)
+		handle->file_state = TRACECMD_FILE_CMD_LINES;
+	return ret;
 }
 
 struct tracecmd_output *tracecmd_create_file_latency(const char *output_file, int cpus)
-- 
2.31.1

[PATCH v3 11/25] trace-cmd library: Read compressed trace file

[Tzvetomir Stoyanov (VMware)]

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/trace-input.c | 247 +++++++++++++++++++++++++-----------
 1 file changed, 171 insertions(+), 76 deletions(-)

diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 9c9180d6..a23c26bd 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;
 }
 
+static void uncompress_reset(struct tracecmd_input *handle)
+{
+	if (handle->compress && handle->file_version >= 7) {
+		handle->read_compress = false;
+		tracecmd_compress_reset(handle->compress);
+	}
+}
+
+static int 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 (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;
+	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 (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:
+	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 (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);
+	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 (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);
+	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 (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);
+	uncompress_reset(handle);
+	return ret;
 }
 
 static void extract_trace_clock(struct tracecmd_input *handle, char *line)
@@ -3268,7 +3341,8 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 	struct tracecmd_input *handle;
 	char test[] = TRACECMD_MAGIC;
 	unsigned int page_size;
-	char *version;
+	char *str = NULL;
+	char *zver;
 	char buf[BUFSIZ];
 	unsigned long ver;
 
@@ -3291,11 +3365,11 @@ 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;
-	pr_stat("version = %s\n", version);
-	ver = strtol(version, NULL, 10);
+	pr_stat("version = %s\n", str);
+	ver = strtol(str, NULL, 10);
 	if (!ver && errno)
 		goto failed_read;
 	if (!tracecmd_is_version_supported(ver)) {
@@ -3303,7 +3377,8 @@ 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;
@@ -3337,11 +3412,30 @@ struct tracecmd_input *tracecmd_alloc_fd(int fd, int flags)
 	handle->header_files_start =
 		lseek64(handle->fd, handle->header_files_start, SEEK_SET);
 
+	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->file_state = TRACECMD_FILE_INIT;
 
 	return handle;
 
  failed_read:
+	free(str);
 	free(handle);
 
 	return NULL;
@@ -3519,7 +3613,8 @@ 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

[PATCH v3 12/25] trace-cmd library: Add new API to get compression of input handler

[Tzvetomir Stoyanov (VMware)]

The new API returns name and version of the compression algorithm,
used to compress the trace file associated with given input file handler:
 tracecmd_get_file_compress_proto()

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 .../include/private/trace-cmd-private.h          |  2 ++
 lib/trace-cmd/trace-input.c                      | 16 ++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 602817cb..4265e37a 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -236,6 +236,8 @@ unsigned long long
 tracecmd_get_cursor(struct tracecmd_input *handle, int cpu);
 
 unsigned long tracecmd_get_file_version(struct tracecmd_input *handle);
+int tracecmd_get_file_compress_proto(struct tracecmd_input *handle,
+				     const char **name, const char **version);
 
 int tracecmd_ftrace_overrides(struct tracecmd_input *handle, struct tracecmd_ftrace *finfo);
 bool tracecmd_get_use_trace_clock(struct tracecmd_input *handle);
diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index a23c26bd..9dff2188 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -4150,6 +4150,22 @@ unsigned long tracecmd_get_file_version(struct tracecmd_input *handle)
 	return handle->file_version;
 }
 
+/**
+ * tracecmd_get_file_compress_proto - get name and version of compression algorithm,
+ *				      used to compress the trace file
+ * @handle: input handle for the trace.dat file
+ * @name: return, name of the compression algorithm.
+ * @version: return, version of the compression algorithm.
+ *
+ * Returns 0 on success, or -1 in case of an error. If 0 is returned, the name and version of the
+ * algorithm are stored in @name and @version. The returned strings must *not* be freed.
+ */
+int tracecmd_get_file_compress_proto(struct tracecmd_input *handle,
+				     const char **name, const char **version)
+{
+	return tracecmd_compress_proto_get_name(handle->compress, name, version);
+}
+
 /**
  * tracecmd_get_use_trace_clock - return use_trace_clock
  * @handle: input handle for the trace.dat file
-- 
2.31.1

[PATCH v3 13/25] trace-cmd library: Inherit compression algorithm from input file

[Tzvetomir Stoyanov (VMware)]

When a new trace file output handler is allocated, based on given trace
file input handler - use the same compression algorithm.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/trace-output.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index 627cea42..ea90ef75 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -980,17 +980,27 @@ out_free:
 static int select_file_version(struct tracecmd_output *handle,
 				struct tracecmd_input *ihandle)
 {
+	const char *cname = NULL;
+	const char *cver = NULL;
+
 	if (ihandle) {
 		handle->file_version = tracecmd_get_file_version(ihandle);
-	} else {
-		handle->compress = tracecmd_compress_alloc(NULL, NULL, handle->fd,
-							   handle->pevent, handle->msg_handle);
-		if (handle->compress)
-			handle->file_version = 7;
-		else
-			handle->file_version = 6;
+		if (!tracecmd_get_file_compress_proto(ihandle, &cname, &cver)) {
+			handle->compress = tracecmd_compress_alloc(cname, cver, handle->fd,
+								   handle->pevent, handle->msg_handle);
+			if (!handle->compress)
+				return -1;
+		}
+		return 0;
 	}
 
+	handle->compress = tracecmd_compress_alloc(NULL, NULL, handle->fd,
+						   handle->pevent, handle->msg_handle);
+	if (handle->compress)
+		handle->file_version = 7;
+	else
+		handle->file_version = 6;
+
 	return 0;
 }
 
@@ -1645,6 +1655,8 @@ struct tracecmd_output *tracecmd_get_output_handle_fd(int fd)
 {
 	struct tracecmd_output *handle = NULL;
 	struct tracecmd_input *ihandle;
+	const char *cname = NULL;
+	const char *cver = NULL;
 	int fd2;
 
 	/* Move the file descriptor to the beginning */
@@ -1682,6 +1694,12 @@ struct tracecmd_output *tracecmd_get_output_handle_fd(int fd)
 	handle->file_version = tracecmd_get_file_version(ihandle);
 	list_head_init(&handle->options);
 
+	if (!tracecmd_get_file_compress_proto(ihandle, &cname, &cver)) {
+		handle->compress = tracecmd_compress_alloc(cname, cver, handle->fd,
+							   handle->pevent, handle->msg_handle);
+		if (!handle->compress)
+			goto out_free;
+	}
 	tracecmd_close(ihandle);
 
 	return handle;
-- 
2.31.1

[PATCH v3 14/25] trace-cmd library: Extend the create file APIs to support different compression

[Tzvetomir Stoyanov (VMware)]

Added additional parameter for file compression to all trace-cmd library
APIs for creating a new trace file. The caller could specify what
compression algorithm should be used when creating a new trace file:
 tracecmd_create_file_latency
 tracecmd_create_init_file_glob
 tracecmd_create_init_fd_glob
 tracecmd_create_init_fd_msg
 tracecmd_create_init_file
 tracecmd_create_init_file_override

The new parameter is of type string and can be one of:
 "any" - auto select the best available compression algorithm
 "none" - do not compress the trace file
 name - the name of the desired compression algorithms

If a compression is used, trace file version 7 is selected, otherwise
trace file version 6 is used.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 .../include/private/trace-cmd-private.h       | 17 +++--
 lib/trace-cmd/trace-output.c                  | 75 +++++++++++++------
 tracecmd/trace-record.c                       | 12 ++-
 tracecmd/trace-restore.c                      |  4 +-
 4 files changed, 68 insertions(+), 40 deletions(-)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 4265e37a..7c5e3fe1 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -271,20 +271,23 @@ struct tracecmd_event_list {
 struct tracecmd_option;
 struct tracecmd_msg_handle;
 
-struct tracecmd_output *tracecmd_create_file_latency(const char *output_file, int cpus);
+struct tracecmd_output *tracecmd_create_file_latency(const char *output_file, int cpus,
+						     const char *compression);
 struct tracecmd_output *
-tracecmd_create_init_file_glob(const char *output_file,
-			       struct tracecmd_event_list *list);
+tracecmd_create_init_file_glob(const char *output_file, struct tracecmd_event_list *list,
+			       const char *compression);
 struct tracecmd_output *tracecmd_create_init_fd(int fd);
 struct tracecmd_output *
-tracecmd_create_init_fd_glob(int fd, struct tracecmd_event_list *list);
+tracecmd_create_init_fd_glob(int fd, struct tracecmd_event_list *list, const char *compression);
 struct tracecmd_output *
 tracecmd_create_init_fd_msg(struct tracecmd_msg_handle *msg_handle,
-			    struct tracecmd_event_list *list);
-struct tracecmd_output *tracecmd_create_init_file(const char *output_file);
+			    struct tracecmd_event_list *list,
+			    const char *compression);
+struct tracecmd_output *tracecmd_create_init_file(const char *output_file, const char *compression);
 struct tracecmd_output *tracecmd_create_init_file_override(const char *output_file,
 							   const char *tracing_dir,
-							   const char *kallsyms);
+							   const char *kallsyms,
+							   const char *compression);
 struct tracecmd_option *tracecmd_add_option(struct tracecmd_output *handle,
 					    unsigned short id, int size,
 					    const void *data);
diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index ea90ef75..56b68edd 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -978,7 +978,8 @@ out_free:
 }
 
 static int select_file_version(struct tracecmd_output *handle,
-				struct tracecmd_input *ihandle)
+				struct tracecmd_input *ihandle,
+				const char *compression)
 {
 	const char *cname = NULL;
 	const char *cver = NULL;
@@ -994,8 +995,28 @@ static int select_file_version(struct tracecmd_output *handle,
 		return 0;
 	}
 
-	handle->compress = tracecmd_compress_alloc(NULL, NULL, handle->fd,
-						   handle->pevent, handle->msg_handle);
+	if (compression) {
+		if (!strcmp(compression, "any")) {
+			handle->compress = tracecmd_compress_alloc(NULL, NULL, handle->fd,
+								   handle->pevent, handle->msg_handle);
+			if (!handle->compress) {
+				tracecmd_warning("No compression algorithms are not supported");
+				return -1;
+			}
+		} else if (strcmp(compression, "none")) {
+			handle->compress = tracecmd_compress_alloc(compression, NULL, handle->fd,
+								   handle->pevent, handle->msg_handle);
+			if (!handle->compress) {
+				tracecmd_warning("Compression algorithm %s is not supported",
+						  compression);
+				return -1;
+			}
+		}
+	} else {
+		handle->compress = tracecmd_compress_alloc(NULL, NULL, handle->fd,
+							    handle->pevent, handle->msg_handle);
+	}
+
 	if (handle->compress)
 		handle->file_version = 7;
 	else
@@ -1028,7 +1049,8 @@ create_file_fd(int fd, struct tracecmd_input *ihandle,
 	       const char *tracing_dir,
 	       const char *kallsyms,
 	       struct tracecmd_event_list *list,
-	       struct tracecmd_msg_handle *msg_handle)
+	       struct tracecmd_msg_handle *msg_handle,
+	       const char *compression)
 {
 	struct tracecmd_output *handle;
 	struct tep_handle *pevent;
@@ -1049,7 +1071,7 @@ create_file_fd(int fd, struct tracecmd_input *ihandle,
 
 	handle->msg_handle = msg_handle;
 
-	if (select_file_version(handle, ihandle))
+	if (select_file_version(handle, ihandle, compression))
 		goto out_free;
 
 	list_head_init(&handle->options);
@@ -1128,7 +1150,8 @@ static struct tracecmd_output *create_file(const char *output_file,
 					   struct tracecmd_input *ihandle,
 					   const char *tracing_dir,
 					   const char *kallsyms,
-					   struct tracecmd_event_list *list)
+					   struct tracecmd_event_list *list,
+					   const char *compression)
 {
 	struct tracecmd_output *handle;
 	int fd;
@@ -1137,7 +1160,7 @@ static struct tracecmd_output *create_file(const char *output_file,
 	if (fd < 0)
 		return NULL;
 
-	handle = create_file_fd(fd, ihandle, tracing_dir, kallsyms, list, NULL);
+	handle = create_file_fd(fd, ihandle, tracing_dir, kallsyms, list, NULL, compression);
 	if (!handle) {
 		close(fd);
 		unlink(output_file);
@@ -1403,13 +1426,14 @@ int tracecmd_write_cmdlines(struct tracecmd_output *handle)
 	return ret;
 }
 
-struct tracecmd_output *tracecmd_create_file_latency(const char *output_file, int cpus)
+struct tracecmd_output *tracecmd_create_file_latency(const char *output_file, int cpus,
+						     const char *compression)
 {
 	struct tracecmd_output *handle;
 	char *path;
 	int ret;
 
-	handle = create_file(output_file, NULL, NULL, NULL, &all_event_list);
+	handle = create_file(output_file, NULL, NULL, NULL, &all_event_list, compression);
 	if (!handle)
 		return NULL;
 
@@ -1712,39 +1736,41 @@ struct tracecmd_output *tracecmd_get_output_handle_fd(int fd)
 
 struct tracecmd_output *tracecmd_create_init_fd(int fd)
 {
-	return create_file_fd(fd, NULL, NULL, NULL, &all_event_list, NULL);
+	return create_file_fd(fd, NULL, NULL, NULL, &all_event_list, NULL, NULL);
 }
 
 struct tracecmd_output *
 tracecmd_create_init_fd_msg(struct tracecmd_msg_handle *msg_handle,
-			    struct tracecmd_event_list *list)
+			    struct tracecmd_event_list *list, const char *compression)
 {
-	return create_file_fd(msg_handle->fd, NULL, NULL, NULL, list, msg_handle);
+	return create_file_fd(msg_handle->fd, NULL, NULL, NULL,
+			      list, msg_handle, compression);
 }
 
 struct tracecmd_output *
-tracecmd_create_init_fd_glob(int fd, struct tracecmd_event_list *list)
+tracecmd_create_init_fd_glob(int fd, struct tracecmd_event_list *list, const char *compression)
 {
-	return create_file_fd(fd, NULL, NULL, NULL, list, NULL);
+	return create_file_fd(fd, NULL, NULL, NULL, list, NULL, compression);
 }
 
 struct tracecmd_output *
-tracecmd_create_init_file_glob(const char *output_file,
-			       struct tracecmd_event_list *list)
+tracecmd_create_init_file_glob(const char *output_file, struct tracecmd_event_list *list,
+			       const char *compression)
 {
-	return create_file(output_file, NULL, NULL, NULL, list);
+	return create_file(output_file, NULL, NULL, NULL, list, compression);
 }
 
-struct tracecmd_output *tracecmd_create_init_file(const char *output_file)
+struct tracecmd_output *tracecmd_create_init_file(const char *output_file, const char *compression)
 {
-	return create_file(output_file, NULL, NULL, NULL, &all_event_list);
+	return create_file(output_file, NULL, NULL, NULL, &all_event_list, compression);
 }
 
 struct tracecmd_output *tracecmd_create_init_file_override(const char *output_file,
 							   const char *tracing_dir,
-							   const char *kallsyms)
+							   const char *kallsyms,
+							   const char *compression)
 {
-	return create_file(output_file, NULL, tracing_dir, kallsyms, &all_event_list);
+	return create_file(output_file, NULL, tracing_dir, kallsyms, &all_event_list, compression);
 }
 
 /**
@@ -1756,12 +1782,13 @@ struct tracecmd_output *tracecmd_create_init_file_override(const char *output_fi
  * with the same characteristics (events and all) and returns
  * tracecmd_output handle to this new file.
  */
-struct tracecmd_output *tracecmd_copy(struct tracecmd_input *ihandle,
-				      const char *file)
+struct tracecmd_output *tracecmd_copy(struct tracecmd_input *ihandle, const char *file)
 {
 	struct tracecmd_output *handle;
+	const char *compr_name = NULL;
 
-	handle = create_file(file, ihandle, NULL, NULL, &all_event_list);
+	tracecmd_get_file_compress_proto(ihandle, &compr_name, NULL);
+	handle = create_file(file, ihandle, NULL, NULL, &all_event_list, compr_name);
 	if (!handle)
 		return NULL;
 
diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c
index 5dd8be4a..e7a360a4 100644
--- a/tracecmd/trace-record.c
+++ b/tracecmd/trace-record.c
@@ -3642,7 +3642,7 @@ setup_connection(struct buffer_instance *instance, struct common_record_context
 
 	/* Now create the handle through this socket */
 	if (msg_handle->version == V3_PROTOCOL) {
-		network_handle = tracecmd_create_init_fd_msg(msg_handle, listed_events);
+		network_handle = tracecmd_create_init_fd_msg(msg_handle, listed_events, NULL);
 		if (!network_handle)
 			goto error;
 		tracecmd_set_quiet(network_handle, quiet);
@@ -3660,8 +3660,7 @@ setup_connection(struct buffer_instance *instance, struct common_record_context
 		if (ret)
 			goto error;
 	} else {
-		network_handle = tracecmd_create_init_fd_glob(msg_handle->fd,
-							      listed_events);
+		network_handle = tracecmd_create_init_fd_glob(msg_handle->fd, listed_events, NULL);
 		if (!network_handle)
 			goto error;
 		tracecmd_set_quiet(network_handle, quiet);
@@ -3849,8 +3848,7 @@ static void setup_agent(struct buffer_instance *instance,
 {
 	struct tracecmd_output *network_handle;
 
-	network_handle = tracecmd_create_init_fd_msg(instance->msg_handle,
-						     listed_events);
+	network_handle = tracecmd_create_init_fd_msg(instance->msg_handle, listed_events, NULL);
 	add_options(network_handle, ctx);
 	tracecmd_write_cmdlines(network_handle);
 	tracecmd_write_cpus(network_handle, instance->cpu_count);
@@ -4242,7 +4240,7 @@ static void record_data(struct common_record_context *ctx)
 		return;
 
 	if (latency) {
-		handle = tracecmd_create_file_latency(ctx->output, local_cpu_count);
+		handle = tracecmd_create_file_latency(ctx->output, local_cpu_count, NULL);
 		tracecmd_set_quiet(handle, quiet);
 	} else {
 		if (!local_cpu_count)
@@ -4273,7 +4271,7 @@ static void record_data(struct common_record_context *ctx)
 				touch_file(temp_files[i]);
 		}
 
-		handle = tracecmd_create_init_file_glob(ctx->output, listed_events);
+		handle = tracecmd_create_init_file_glob(ctx->output, listed_events, NULL);
 		if (!handle)
 			die("Error creating output file");
 		tracecmd_set_quiet(handle, quiet);
diff --git a/tracecmd/trace-restore.c b/tracecmd/trace-restore.c
index 280a37f0..96b4fb5d 100644
--- a/tracecmd/trace-restore.c
+++ b/tracecmd/trace-restore.c
@@ -91,7 +91,7 @@ void trace_restore (int argc, char **argv)
 		}
 
 		handle = tracecmd_create_init_file_override(output, tracing_dir,
-							    kallsyms);
+							    kallsyms, NULL);
 		if (!handle)
 			die("Unabled to create output file %s", output);
 		if (tracecmd_write_cmdlines(handle) < 0)
@@ -128,7 +128,7 @@ void trace_restore (int argc, char **argv)
 		handle = tracecmd_copy(ihandle, output);
 		tracecmd_close(ihandle);
 	} else
-		handle = tracecmd_create_init_file(output);
+		handle = tracecmd_create_init_file(output, NULL);
 
 	if (!handle)
 		die("error writing to %s", output);
-- 
2.31.1

[PATCH v3 15/25] trace-cmd record: Add new parameter --compression

[Tzvetomir Stoyanov (VMware)]

Added a new parameter "trace-cmd record --compression", can be used to
select the desired compression algorithm for the trace output file.
One of these strings can be passed:
 "any" - auto select the best available compression algorithm
 "none" - do not compress the trace file
 name - the name of the desired compression algorithms, available
        algorithms can be listed with "trace-cmd list -c"

If a compression is used, trace file version 7 is selected, otherwise
trace file version 6 is used.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 tracecmd/trace-record.c | 24 +++++++++++++++++++-----
 tracecmd/trace-usage.c  |  5 +++++
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c
index e7a360a4..5e969dc7 100644
--- a/tracecmd/trace-record.c
+++ b/tracecmd/trace-record.c
@@ -199,6 +199,7 @@ struct common_record_context {
 	char *date2ts;
 	char *user;
 	const char *clock;
+	const char *compression;
 	struct tsc_nsec tsc2nsec;
 	int data_flags;
 	int tsync_loop_interval;
@@ -3642,7 +3643,8 @@ setup_connection(struct buffer_instance *instance, struct common_record_context
 
 	/* Now create the handle through this socket */
 	if (msg_handle->version == V3_PROTOCOL) {
-		network_handle = tracecmd_create_init_fd_msg(msg_handle, listed_events, NULL);
+		network_handle = tracecmd_create_init_fd_msg(msg_handle,
+							     listed_events, ctx->compression);
 		if (!network_handle)
 			goto error;
 		tracecmd_set_quiet(network_handle, quiet);
@@ -3660,7 +3662,8 @@ setup_connection(struct buffer_instance *instance, struct common_record_context
 		if (ret)
 			goto error;
 	} else {
-		network_handle = tracecmd_create_init_fd_glob(msg_handle->fd, listed_events, NULL);
+		network_handle = tracecmd_create_init_fd_glob(msg_handle->fd,
+							      listed_events, ctx->compression);
 		if (!network_handle)
 			goto error;
 		tracecmd_set_quiet(network_handle, quiet);
@@ -3848,7 +3851,8 @@ static void setup_agent(struct buffer_instance *instance,
 {
 	struct tracecmd_output *network_handle;
 
-	network_handle = tracecmd_create_init_fd_msg(instance->msg_handle, listed_events, NULL);
+	network_handle = tracecmd_create_init_fd_msg(instance->msg_handle,
+						     listed_events, ctx->compression);
 	add_options(network_handle, ctx);
 	tracecmd_write_cmdlines(network_handle);
 	tracecmd_write_cpus(network_handle, instance->cpu_count);
@@ -4240,7 +4244,8 @@ static void record_data(struct common_record_context *ctx)
 		return;
 
 	if (latency) {
-		handle = tracecmd_create_file_latency(ctx->output, local_cpu_count, NULL);
+		handle = tracecmd_create_file_latency(ctx->output,
+						      local_cpu_count, ctx->compression);
 		tracecmd_set_quiet(handle, quiet);
 	} else {
 		if (!local_cpu_count)
@@ -4271,7 +4276,8 @@ static void record_data(struct common_record_context *ctx)
 				touch_file(temp_files[i]);
 		}
 
-		handle = tracecmd_create_init_file_glob(ctx->output, listed_events, NULL);
+		handle = tracecmd_create_init_file_glob(ctx->output,
+							listed_events, ctx->compression);
 		if (!handle)
 			die("Error creating output file");
 		tracecmd_set_quiet(handle, quiet);
@@ -5531,6 +5537,7 @@ void init_top_instance(void)
 }
 
 enum {
+	OPT_comporession	= 239,
 	OPT_tsc2nsec		= 240,
 	OPT_fork		= 241,
 	OPT_tsyncinterval	= 242,
@@ -5965,6 +5972,7 @@ static void parse_record_options(int argc,
 			{"tsync-interval", required_argument, NULL, OPT_tsyncinterval},
 			{"fork", no_argument, NULL, OPT_fork},
 			{"tsc2nsec", no_argument, NULL, OPT_tsc2nsec},
+			{"compression", required_argument, NULL, OPT_comporession},
 			{NULL, 0, NULL, 0}
 		};
 
@@ -6386,6 +6394,12 @@ static void parse_record_options(int argc,
 				die("TSC to nanosecond is not supported");
 			ctx->instance->flags |= BUFFER_FL_TSC2NSEC;
 			break;
+		case OPT_comporession:
+			if (strcmp(optarg, "any") && strcmp(optarg, "none") &&
+			    !tracecmd_compress_is_supported(optarg, NULL))
+				die("Compression algorithm  %s is not supported", optarg);
+			ctx->compression = strdup(optarg);
+			break;
 		case OPT_quiet:
 		case 'q':
 			quiet = true;
diff --git a/tracecmd/trace-usage.c b/tracecmd/trace-usage.c
index c388eccd..a1d7799a 100644
--- a/tracecmd/trace-usage.c
+++ b/tracecmd/trace-usage.c
@@ -68,6 +68,11 @@ static struct usage_help usage_help[] = {
 		"               If a negative number is specified, timestamps synchronization is disabled"
 		"               If 0 is specified, no loop is performed - timestamps offset is calculated only twice,"
 		"                                                         at the beginnig and at the end of the trace\n"
+		"          --compression compress the trace output file, one of these strings can be passed:\n"
+		"                            any  - auto select the best available compression algorithm\n"
+		"                            none - do not compress the trace file\n"
+		"                            name - the name of the desired compression algorithms\n"
+		"                        available algorithms can be listed with trace-cmd list -c\n"
 	},
 	{
 		"set",
-- 
2.31.1

[PATCH v3 16/25] trace-cmd dump: Add support for trace files version 7

[Tzvetomir Stoyanov (VMware)]

Added support to read and dump information of trace files version 7.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 tracecmd/trace-dump.c | 125 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 105 insertions(+), 20 deletions(-)

diff --git a/tracecmd/trace-dump.c b/tracecmd/trace-dump.c
index 03cc82b4..ed82104b 100644
--- a/tracecmd/trace-dump.c
+++ b/tracecmd/trace-dump.c
@@ -26,6 +26,9 @@
 static struct tep_handle *tep;
 static unsigned int trace_cpus;
 static int has_clock;
+static unsigned long file_version;
+static bool	read_compress;
+static struct tracecmd_compression *compress;
 
 enum dump_items {
 	SUMMARY		= (1 << 0),
@@ -52,46 +55,62 @@ enum dump_items verbosity;
 			tracecmd_plog(fmt, ##__VA_ARGS__);	\
 	} while (0)
 
-static int read_file_string(int fd, char *dst, int len)
+static int read_fd(int fd, char *dst, int len)
 {
 	size_t size = 0;
 	int r;
 
 	do {
-		r = read(fd, dst+size, 1);
+		r = read(fd, dst+size, len);
 		if (r > 0) {
-			size++;
-			len--;
+			size += r;
+			len -= r;
 		} else
 			break;
-		if (!dst[size - 1])
-			break;
-	} while (r > 0 && len);
+	} while (r > 0);
 
-	if (!size || dst[size - 1])
+	if (len)
 		return -1;
-	return 0;
+	return size;
 }
 
-static int read_file_bytes(int fd, char *dst, int len)
+static int read_compressed(int fd, char *dst, int len)
+{
+
+	if (read_compress)
+		return tracecmd_compress_read(compress, dst, len);
+	return read_fd(fd, dst, len);
+}
+
+static int read_file_string(int fd, char *dst, int len)
 {
 	size_t size = 0;
 	int r;
 
 	do {
-		r = read(fd, dst+size, len);
+		r = read_compressed(fd, dst+size, 1);
 		if (r > 0) {
-			size += r;
-			len -= r;
+			size++;
+			len--;
 		} else
 			break;
-	} while (r > 0);
+		if (!dst[size - 1])
+			break;
+	} while (r > 0 && len);
 
-	if (len)
+	if (!size || dst[size - 1])
 		return -1;
 	return 0;
 }
 
+static int read_file_bytes(int fd, char *dst, int len)
+{
+	int ret;
+
+	ret = read_compressed(fd, dst, len);
+	return ret < 0 ? ret : 0;
+}
+
 static void read_dump_string(int fd, int size, enum dump_items id)
 {
 	char buf[DUMP_SIZE];
@@ -146,7 +165,6 @@ static void dump_initial_format(int fd)
 	char magic[] = TRACECMD_MAGIC;
 	char buf[DUMP_SIZE];
 	int val4;
-	unsigned long ver;
 
 	do_print(SUMMARY, "\t[Initial format]\n");
 
@@ -168,11 +186,11 @@ static void dump_initial_format(int fd)
 		die("no version string");
 
 	do_print(SUMMARY, "\t\t%s\t[Version]\n", buf);
-	ver = strtol(buf, NULL, 10);
-	if (!ver && errno)
+	file_version = strtol(buf, NULL, 10);
+	if (!file_version && errno)
 		die("Invalid file version string %s", buf);
-	if (!tracecmd_is_version_supported(ver))
-		die("Unsupported file version %lu", ver);
+	if (!tracecmd_is_version_supported(file_version))
+		die("Unsupported file version %lu", file_version);
 
 	/* get file endianness*/
 	if (read_file_bytes(fd, buf, 1))
@@ -192,6 +210,29 @@ static void dump_initial_format(int fd)
 	do_print(SUMMARY, "\t\t%d\t[Page size, bytes]\n", val4);
 }
 
+static void dump_compress(int fd)
+{
+	char compr[DUMP_SIZE];
+	char *ver = NULL;
+
+	if (file_version < 7)
+		return;
+
+	/* get compression header */
+	if (read_file_string(fd, compr, DUMP_SIZE))
+		die("no compression header");
+	ver = strchr(compr, ' ');
+	if (!ver)
+		die("no compression version");
+	*ver = '\0';
+	do_print((SUMMARY), "\t\t%s\t[Compression algorithm]\n", compr);
+	do_print((SUMMARY), "\t\t%s\t[Compression version]\n", ver + 1);
+
+	compress = tracecmd_compress_alloc(compr, ver + 1, fd, tep, NULL);
+	if (!compress)
+		die("cannot uncomress the file");
+}
+
 static void dump_header_page(int fd)
 {
 	unsigned long long size;
@@ -234,11 +275,34 @@ static void dump_header_event(int fd)
 	read_dump_string(fd, size, HEAD_EVENT);
 }
 
+static void uncompress_reset(void)
+{
+	if (compress && file_version >= 7) {
+		read_compress = false;
+		tracecmd_compress_reset(compress);
+	}
+}
+
+static int uncompress_block(void)
+{
+	int ret = 0;
+
+	if (compress && file_version >= 7) {
+		ret = tracecmd_uncompress_block(compress);
+		if (!ret)
+			read_compress = true;
+
+	}
+	return ret;
+}
+
 static void dump_ftrace_events_format(int fd)
 {
 	unsigned long long size;
 	unsigned int count;
 
+	if (uncompress_block())
+		die("cannot uncompress file block");
 	do_print((SUMMARY | FTRACE_FORMAT), "\t[Ftrace format, ");
 	if (read_file_number(fd, &count, 4))
 		die("cannot read the count of the ftrace events");
@@ -251,6 +315,7 @@ static void dump_ftrace_events_format(int fd)
 		read_dump_string(fd, size, FTRACE_FORMAT);
 		count--;
 	}
+	uncompress_reset();
 }
 
 static void dump_events_format(int fd)
@@ -262,6 +327,9 @@ static void dump_events_format(int fd)
 
 	do_print((SUMMARY | EVENT_FORMAT | EVENT_SYSTEMS), "\t[Events format, ");
 
+	if (uncompress_block())
+		die("cannot uncompress file block");
+
 	if (read_file_number(fd, &systems, 4))
 		die("cannot read the count of the event systems");
 
@@ -284,6 +352,7 @@ static void dump_events_format(int fd)
 		}
 		systems--;
 	}
+	uncompress_reset();
 }
 
 static void dump_kallsyms(int fd)
@@ -292,12 +361,17 @@ static void dump_kallsyms(int fd)
 
 	do_print((SUMMARY | KALLSYMS), "\t[Kallsyms, ");
 
+	if (uncompress_block())
+		die("cannot uncompress file block");
+
 	if (read_file_number(fd, &size, 4))
 		die("cannot read the size of the kallsyms");
 
 	do_print((SUMMARY | KALLSYMS), "%d bytes]\n", size);
 
 	read_dump_string(fd, size, KALLSYMS);
+
+	uncompress_reset();
 }
 
 static void dump_printk(int fd)
@@ -306,12 +380,17 @@ static void dump_printk(int fd)
 
 	do_print((SUMMARY | TRACE_PRINTK), "\t[Trace printk, ");
 
+	if (uncompress_block())
+		die("cannot uncompress file block");
+
 	if (read_file_number(fd, &size, 4))
 		die("cannot read the size of the trace printk");
 
 	do_print((SUMMARY | TRACE_PRINTK), "%d bytes]\n", size);
 
 	read_dump_string(fd, size, TRACE_PRINTK);
+
+	uncompress_reset();
 }
 
 static void dump_cmdlines(int fd)
@@ -320,12 +399,17 @@ static void dump_cmdlines(int fd)
 
 	do_print((SUMMARY | CMDLINES), "\t[Saved command lines, ");
 
+	if (uncompress_block())
+		die("cannot uncompress file block");
+
 	if (read_file_number(fd, &size, 8))
 		die("cannot read the size of the saved command lines");
 
 	do_print((SUMMARY | CMDLINES), "%d bytes]\n", size);
 
 	read_dump_string(fd, size, CMDLINES);
+
+	uncompress_reset();
 }
 
 static void dump_cpus_count(int fd)
@@ -669,6 +753,7 @@ static void dump_file(const char *file)
 	do_print(SUMMARY, "\n Tracing meta data in file %s:\n", file);
 
 	dump_initial_format(fd);
+	dump_compress(fd);
 	dump_header_page(fd);
 	dump_header_event(fd);
 	dump_ftrace_events_format(fd);
-- 
2.31.1

[PATCH v3 17/25] trace-cmd library: Add support for zlib compression library

[Tzvetomir Stoyanov (VMware)]

If libz is available, use that library to provide trace file compression
support. The library is detected runtime.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/Makefile                  |  10 ++
 lib/trace-cmd/include/trace-cmd-local.h |   5 +
 lib/trace-cmd/trace-compress-zlib.c     | 172 ++++++++++++++++++++++++
 lib/trace-cmd/trace-compress.c          |   8 ++
 4 files changed, 195 insertions(+)
 create mode 100644 lib/trace-cmd/trace-compress-zlib.c

diff --git a/lib/trace-cmd/Makefile b/lib/trace-cmd/Makefile
index bab4322d..83ba7016 100644
--- a/lib/trace-cmd/Makefile
+++ b/lib/trace-cmd/Makefile
@@ -7,6 +7,13 @@ ldir:=$(src)/lib/trace-cmd
 
 DEFAULT_TARGET = $(LIBTRACECMD_STATIC)
 
+pound := \#
+ZLIB_INSTALLED := $(shell if (printf "$(pound)include <zlib.h>\n void main(){deflateInit(NULL, Z_BEST_COMPRESSION);}" | $(CC) -o /dev/null -x c - -lz >/dev/null 2>&1) ; then echo 1; else echo 0 ; fi)
+ifeq ($(ZLIB_INSTALLED), 1)
+CFLAGS += -DHAVE_ZLIB
+$(info    Have zlib compression support)
+endif
+
 OBJS =
 OBJS += trace-hash.o
 OBJS += trace-hooks.o
@@ -26,6 +33,9 @@ OBJS += trace-timesync-ptp.o
 OBJS += trace-timesync-kvm.o
 endif
 OBJS += trace-compress.o
+ifeq ($(ZLIB_INSTALLED), 1)
+OBJS += trace-compress-zlib.o
+endif
 
 # Additional util objects
 OBJS += trace-blk-hack.o
diff --git a/lib/trace-cmd/include/trace-cmd-local.h b/lib/trace-cmd/include/trace-cmd-local.h
index c8c51ff0..86d91caf 100644
--- a/lib/trace-cmd/include/trace-cmd-local.h
+++ b/lib/trace-cmd/include/trace-cmd-local.h
@@ -30,6 +30,11 @@ void tracecmd_fatal(const char *fmt, ...);
 #endif
 #endif
 
+#ifdef HAVE_ZLIB
+int tracecmd_zlib_init(void);
+void tracecmd_zlib_free(void);
+#endif
+
 int tracecmd_compress_init(void);
 void tracecmd_compress_free(void);
 
diff --git a/lib/trace-cmd/trace-compress-zlib.c b/lib/trace-cmd/trace-compress-zlib.c
new file mode 100644
index 00000000..3208d57b
--- /dev/null
+++ b/lib/trace-cmd/trace-compress-zlib.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * Copyright (C) 2021, VMware, Tzvetomir Stoyanov tz.stoyanov@gmail.com>
+ *
+ */
+#include <stdlib.h>
+#include <dlfcn.h>
+#include <zlib.h>
+#include <errno.h>
+
+#include "trace-cmd-private.h"
+
+#define __ZLIB_NAME		"zlib"
+#define __ZLIB_WEIGTH		10
+#define __ZLIB_FILE		"libz.so"
+#define ZLIB_FUNC_COMPRESS	"compress2"
+#define ZLIB_FUNC_DECOMOPRESS	"uncompress"
+#define ZLIB_FUNC_SIZE		"compressBound"
+#define ZLIB_FUNC_VERSION	"zlibVersion"
+
+static void *zlib_handle;
+static int (*_lib_compress)(unsigned char *out, unsigned long *out_bytes,
+			    unsigned char *in, unsigned long in_bytes, int level);
+static int (*_libz_decompress)(unsigned char *out, unsigned long *out_bytes,
+			       unsigned char *in, unsigned long in_bytes);
+static unsigned long (*_libz_compress_bound)(unsigned long in_bytes);
+static const char *(*_libz_version)(void);
+
+static int zlib_compress(char *in, unsigned int in_bytes,
+			 char *out, unsigned int *out_bytes)
+{
+	unsigned long out_size = *out_bytes;
+	int ret;
+
+	if (!_lib_compress)
+		return -1;
+
+	ret = _lib_compress((unsigned char *)out, &out_size,
+			    (unsigned char *)in, (unsigned long)in_bytes, Z_BEST_COMPRESSION);
+	*out_bytes = out_size;
+	errno = 0;
+	switch (ret) {
+	case Z_OK:
+		return 0;
+	case Z_BUF_ERROR:
+		errno = -ENOBUFS;
+		break;
+	case Z_MEM_ERROR:
+		errno = -ENOMEM;
+		break;
+	case Z_STREAM_ERROR:
+		errno = -EINVAL;
+		break;
+	default:
+		errno = -EFAULT;
+		break;
+	}
+
+	return -1;
+}
+
+static int zlib_decompress(char *in, unsigned int in_bytes,
+			   char *out, unsigned int *out_bytes)
+{
+	unsigned long out_size = *out_bytes;
+	int ret;
+
+	if (!_libz_decompress)
+		return -1;
+
+	ret = _libz_decompress((unsigned char *)out, &out_size,
+			       (unsigned char *)in, (unsigned long)in_bytes);
+	*out_bytes = out_size;
+	errno = 0;
+	switch (ret) {
+	case Z_OK:
+		return 0;
+	case Z_BUF_ERROR:
+		errno = -ENOBUFS;
+		break;
+	case Z_MEM_ERROR:
+		errno = -ENOMEM;
+		break;
+	case Z_DATA_ERROR:
+		errno = -EINVAL;
+		break;
+	default:
+		errno = -EFAULT;
+		break;
+	}
+
+	return -1;
+}
+
+static unsigned int zlib_compress_bound(unsigned int in_bytes)
+{
+	if (!_libz_compress_bound)
+		return 0;
+	return _libz_compress_bound(in_bytes);
+}
+
+static bool zlib_is_supported(const char *name, const char *version)
+{
+	const char *zver;
+
+	if (!name)
+		return false;
+	if (strlen(name) != strlen(__ZLIB_NAME) || strcmp(name, __ZLIB_NAME))
+		return false;
+
+	if (!version)
+		return true;
+
+	if (!_libz_version)
+		return false;
+	zver = _libz_version();
+	if (!zver)
+		return false;
+
+	/* Compare the major version number */
+	if (atoi(version) <= atoi(zver))
+		return true;
+
+	return false;
+}
+
+int tracecmd_zlib_init(void)
+{
+	if (zlib_handle)
+		return 0;
+
+	zlib_handle = dlopen(__ZLIB_FILE, RTLD_NOW | RTLD_GLOBAL);
+	if (!zlib_handle)
+		return -1;
+	_lib_compress = dlsym(zlib_handle, ZLIB_FUNC_COMPRESS);
+	if (!_lib_compress)
+		goto error;
+	_libz_decompress = dlsym(zlib_handle, ZLIB_FUNC_DECOMOPRESS);
+	if (!_libz_decompress)
+		goto error;
+	_libz_compress_bound = dlsym(zlib_handle, ZLIB_FUNC_SIZE);
+	if (!_libz_compress_bound)
+		goto error;
+	_libz_version = dlsym(zlib_handle, ZLIB_FUNC_VERSION);
+	if (!_libz_version)
+		goto error;
+
+	return tracecmd_compress_proto_register(__ZLIB_NAME, _libz_version(), __ZLIB_WEIGTH,
+						zlib_compress, zlib_decompress,
+						zlib_compress_bound, zlib_is_supported);
+
+error:
+	_lib_compress = NULL;
+	_libz_decompress = NULL;
+	_libz_version = NULL;
+	dlclose(zlib_handle);
+	zlib_handle = NULL;
+	return -1;
+}
+
+void tracecmd_zlib_free(void)
+{
+	_lib_compress = NULL;
+	_libz_decompress = NULL;
+	_libz_version = NULL;
+
+	if (zlib_handle) {
+		dlclose(zlib_handle);
+		zlib_handle = NULL;
+	}
+
+}
diff --git a/lib/trace-cmd/trace-compress.c b/lib/trace-cmd/trace-compress.c
index ff742226..2b329d00 100644
--- a/lib/trace-cmd/trace-compress.c
+++ b/lib/trace-cmd/trace-compress.c
@@ -353,6 +353,10 @@ int tracecmd_compress_init(void)
 	gettimeofday(&time, NULL);
 	srand((time.tv_sec * 1000) + (time.tv_usec / 1000));
 
+#ifdef HAVE_ZLIB
+	tracecmd_zlib_init();
+#endif
+
 	return 0;
 }
 
@@ -530,6 +534,10 @@ void tracecmd_compress_free(void)
 	struct compress_proto *proto = proto_list;
 	struct compress_proto *del;
 
+#ifdef HAVE_ZLIB
+	tracecmd_zlib_free();
+#endif
+
 	while (proto) {
 		del = proto;
 		proto = proto->next;
-- 
2.31.1

[PATCH v3 18/25] trace-cmd library: Hide the logic for updating buffer offset

[Tzvetomir Stoyanov (VMware)]

When a trace buffer data are written in the trace file, the buffer
option in the file metadata is updated with the file offset of the
tracing data. Hide this logic into the trace-cmd library.
Added new APIs:
 tracecmd_add_buffer_description()
 tracecmd_write_buffers_description()
Changed APIs:
 tracecmd_append_buffer_cpu_data()
Removed APIs:
 tracecmd_add_buffer_option()

This internal refactoring is needed for changes, related to compression
of the options sections of the trace file.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 .../include/private/trace-cmd-private.h       |  8 +-
 lib/trace-cmd/trace-output.c                  | 83 +++++++++++++++++--
 tracecmd/trace-record.c                       | 16 ++--
 3 files changed, 84 insertions(+), 23 deletions(-)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 7c5e3fe1..7d34f27b 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -295,8 +295,8 @@ struct tracecmd_option *
 tracecmd_add_option_v(struct tracecmd_output *handle,
 		      unsigned short id, const struct iovec *vector, int count);
 
-struct tracecmd_option *tracecmd_add_buffer_option(struct tracecmd_output *handle,
-						   const char *name, int cpus);
+int tracecmd_add_buffer_description(struct tracecmd_output *handle, const char *name, int cpus);
+int tracecmd_write_buffers_description(struct tracecmd_output *handle);
 
 int tracecmd_write_cpus(struct tracecmd_output *handle, int cpus);
 int tracecmd_write_cmdlines(struct tracecmd_output *handle);
@@ -312,9 +312,7 @@ int tracecmd_write_cpu_data(struct tracecmd_output *handle,
 int tracecmd_append_cpu_data(struct tracecmd_output *handle,
 			     int cpus, char * const *cpu_data_files);
 int tracecmd_append_buffer_cpu_data(struct tracecmd_output *handle,
-				    struct tracecmd_option *option,
-				    int cpus, char * const *cpu_data_files);
-
+				    const char *name, int cpus, char * const *cpu_data_files);
 struct tracecmd_output *tracecmd_get_output_handle_fd(int fd);
 
 /* --- Reading the Fly Recorder Trace --- */
diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index 56b68edd..aa55a089 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -44,6 +44,14 @@ struct tracecmd_option {
 	struct list_head list;
 };
 
+struct tracecmd_buffer {
+	int		cpus;
+	void		*name;
+	tsize_t		offset;
+	struct tracecmd_option *option;
+	struct list_head list;
+};
+
 enum {
 	OUTPUT_FL_SEND_META	= (1 << 0),
 };
@@ -63,6 +71,7 @@ struct tracecmd_output {
 	struct tracecmd_compression *compress;
 
 	struct list_head	options;
+	struct list_head	buffers;
 	struct tracecmd_msg_handle *msg_handle;
 	char			*trace_clock;
 };
@@ -189,6 +198,7 @@ bool tracecmd_get_quiet(struct tracecmd_output *handle)
 void tracecmd_output_free(struct tracecmd_output *handle)
 {
 	struct tracecmd_option *option;
+	struct tracecmd_buffer *buffer;
 
 	if (!handle)
 		return;
@@ -199,6 +209,13 @@ void tracecmd_output_free(struct tracecmd_output *handle)
 	if (handle->pevent)
 		tep_unref(handle->pevent);
 
+	while (!list_empty(&handle->buffers)) {
+		buffer = container_of(handle->buffers.next,
+				      struct tracecmd_buffer, list);
+		list_del(&buffer->list);
+		free(buffer->name);
+		free(buffer);
+	}
 	while (!list_empty(&handle->options)) {
 		option = container_of(handle->options.next,
 				      struct tracecmd_option, list);
@@ -1075,6 +1092,7 @@ create_file_fd(int fd, struct tracecmd_input *ihandle,
 		goto out_free;
 
 	list_head_init(&handle->options);
+	list_head_init(&handle->buffers);
 
 	buf[0] = 23;
 	buf[1] = 8;
@@ -1373,9 +1391,8 @@ int tracecmd_append_options(struct tracecmd_output *handle)
 	return 0;
 }
 
-struct tracecmd_option *
-tracecmd_add_buffer_option(struct tracecmd_output *handle, const char *name,
-			   int cpus)
+static struct tracecmd_option *
+add_buffer_option(struct tracecmd_output *handle, const char *name, int cpus)
 {
 	struct tracecmd_option *option;
 	char *buf;
@@ -1403,6 +1420,52 @@ tracecmd_add_buffer_option(struct tracecmd_output *handle, const char *name,
 	return option;
 }
 
+int tracecmd_add_buffer_description(struct tracecmd_output *handle, const char *name, int cpus)
+{
+	struct tracecmd_buffer *buf;
+
+	buf = calloc(1, sizeof(struct tracecmd_buffer));
+	if (!buf)
+		return -1;
+	buf->name = strdup(name);
+	if (!buf->name) {
+		free(buf);
+		return -1;
+	}
+	list_add_tail(&buf->list, &handle->buffers);
+	return 0;
+}
+
+int tracecmd_write_buffers_description(struct tracecmd_output *handle)
+{
+	struct tracecmd_option *option;
+	struct tracecmd_buffer *buf;
+
+	list_for_each_entry(buf, &handle->buffers, list) {
+		option = add_buffer_option(handle, buf->name, buf->cpus);
+		if (!option)
+			return -1;
+		buf->option = option;
+	}
+	return 0;
+}
+
+static tsize_t get_buffer_file_offset(struct tracecmd_output *handle, const char *name)
+{
+	struct tracecmd_buffer *buf;
+
+	list_for_each_entry(buf, &handle->buffers, list) {
+		if (strlen(name) == strlen(buf->name) && !strcmp(name, buf->name)) {
+			if (handle->file_version >= 7)
+				return buf->offset;
+			if (!buf->option)
+				break;
+			return buf->option->offset;
+		}
+	}
+	return 0;
+}
+
 int tracecmd_write_cmdlines(struct tracecmd_output *handle)
 {
 	int ret;
@@ -1647,18 +1710,23 @@ int tracecmd_append_cpu_data(struct tracecmd_output *handle,
 }
 
 int tracecmd_append_buffer_cpu_data(struct tracecmd_output *handle,
-				    struct tracecmd_option *option,
-				    int cpus, char * const *cpu_data_files)
+				    const char *name, int cpus, char * const *cpu_data_files)
 {
+	tsize_t b_offset;
 	tsize_t offset;
 	stsize_t ret;
 
+	b_offset = get_buffer_file_offset(handle, name);
+	if (!b_offset) {
+		tracecmd_warning("Cannot find description for buffer %s\n", name);
+		return -1;
+	}
 	offset = lseek64(handle->fd, 0, SEEK_CUR);
 
 	/* Go to the option data, where will write the offest */
-	ret = lseek64(handle->fd, option->offset, SEEK_SET);
+	ret = lseek64(handle->fd, b_offset, SEEK_SET);
 	if (ret == (off64_t)-1) {
-		tracecmd_warning("could not seek to %lld\n", option->offset);
+		tracecmd_warning("could not seek to %lld\n", b_offset);
 		return -1;
 	}
 
@@ -1717,6 +1785,7 @@ struct tracecmd_output *tracecmd_get_output_handle_fd(int fd)
 	handle->page_size = tracecmd_page_size(ihandle);
 	handle->file_version = tracecmd_get_file_version(ihandle);
 	list_head_init(&handle->options);
+	list_head_init(&handle->buffers);
 
 	if (!tracecmd_get_file_compress_proto(ihandle, &cname, &cver)) {
 		handle->compress = tracecmd_compress_alloc(cname, cver, handle->fd,
diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c
index 5e969dc7..e12d77cc 100644
--- a/tracecmd/trace-record.c
+++ b/tracecmd/trace-record.c
@@ -3934,7 +3934,6 @@ static void touch_file(const char *file)
 }
 
 static void append_buffer(struct tracecmd_output *handle,
-			  struct tracecmd_option *buffer_option,
 			  struct buffer_instance *instance,
 			  char **temp_files)
 {
@@ -3962,7 +3961,7 @@ static void append_buffer(struct tracecmd_output *handle,
 			touch_file(temp_files[i]);
 	}
 
-	tracecmd_append_buffer_cpu_data(handle, buffer_option,
+	tracecmd_append_buffer_cpu_data(handle, tracefs_instance_get_name(instance->tracefs),
 					cpu_count, temp_files);
 
 	for (i = 0; i < instance->cpu_count; i++) {
@@ -4223,7 +4222,6 @@ static void write_guest_file(struct buffer_instance *instance)
 
 static void record_data(struct common_record_context *ctx)
 {
-	struct tracecmd_option **buffer_options;
 	struct tracecmd_output *handle;
 	struct buffer_instance *instance;
 	bool local = false;
@@ -4294,9 +4292,6 @@ static void record_data(struct common_record_context *ctx)
 		}
 
 		if (buffers) {
-			buffer_options = malloc(sizeof(*buffer_options) * buffers);
-			if (!buffer_options)
-				die("Failed to allocate buffer options");
 			i = 0;
 			for_each_instance(instance) {
 				int cpus = instance->cpu_count != local_cpu_count ?
@@ -4304,10 +4299,9 @@ static void record_data(struct common_record_context *ctx)
 
 				if (instance->msg_handle)
 					continue;
-
-				buffer_options[i++] = tracecmd_add_buffer_option(handle,
-										 tracefs_instance_get_name(instance->tracefs),
-										 cpus);
+				tracecmd_add_buffer_description(handle,
+								tracefs_instance_get_name(instance->tracefs),
+								cpus);
 				add_buffer_stat(handle, instance);
 			}
 		}
@@ -4342,7 +4336,7 @@ static void record_data(struct common_record_context *ctx)
 				if (instance->msg_handle)
 					continue;
 				print_stat(instance);
-				append_buffer(handle, buffer_options[i++], instance, temp_files);
+				append_buffer(handle, instance, temp_files);
 			}
 		}
 
-- 
2.31.1

[PATCH v3 19/25] trace-cmd: Move buffers description outside of options

[Tzvetomir Stoyanov (VMware)]

When a new buffer data are written in the trace file, the file offset is
stored in the buffer description. As the buffer description is part of
the trace options, which are already written in the file, the offset field
in this option is updated with the new value. This causes a serious
problem when option section of the file is compressed. Updating a value
in already compressed section may change the size of this section, which
can make the calculated offset of the buffer trace data invalid. To
solve that problem and to enable the compression of the option section
of the file, the structure of the trace file is changed:
 - In trace file v7, the description of the buffers is moved to a
   separate section in the trace file medatata. It is stored after the
   CPU count section and before the option section. The format of this
   new buffers description is:
    4 bytes - count of the buffers, stored in the file. The top buffer
      is not counted.
    For each buffer:
     8 bytes, offset of the trace data for this buffer in the file.
     null-terminated string, name of the buffer.
   The new section is mandatory, in case of no buffers - the count 0 is
   stored in the first 4 bytes.
 - In trace file v6, the description of the buffers is not changed.

These changes are needed for compression of the options sections from
the trace file.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 .../include/private/trace-cmd-private.h       |  1 +
 lib/trace-cmd/trace-input.c                   | 40 ++++++++++
 lib/trace-cmd/trace-output.c                  | 78 ++++++++++++++++++-
 tracecmd/trace-dump.c                         | 24 ++++++
 tracecmd/trace-listen.c                       |  3 +
 tracecmd/trace-record.c                       |  4 +
 6 files changed, 146 insertions(+), 4 deletions(-)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index 7d34f27b..d7488346 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -112,6 +112,7 @@ enum tracecmd_file_states {
 	TRACECMD_FILE_PRINTK,
 	TRACECMD_FILE_CMD_LINES,
 	TRACECMD_FILE_CPU_COUNT,
+	TRACECMD_FILE_BUFERS,
 	TRACECMD_FILE_OPTIONS,
 	TRACECMD_FILE_CPU_LATENCY,
 	TRACECMD_FILE_CPU_FLYRECORD,
diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 9dff2188..5088a059 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -881,6 +881,39 @@ static int read_cpus(struct tracecmd_input *handle)
 	return 0;
 }
 
+static int read_buffers(struct tracecmd_input *handle)
+{
+	struct input_buffer_instance *buffer;
+	unsigned long long offset;
+	unsigned int count;
+	int i;
+
+	if (handle->file_version < 7 || handle->file_state >= TRACECMD_FILE_BUFERS)
+		return 0;
+
+	if (read4(handle, &count) < 0)
+		return -1;
+	i = handle->nr_buffers;
+	handle->nr_buffers += count;
+	handle->buffers = realloc(handle->buffers,
+				  sizeof(*handle->buffers) * handle->nr_buffers);
+	if (!handle->buffers)
+		return -1;
+
+	for (; i < handle->nr_buffers; i++) {
+		buffer = &handle->buffers[i];
+		if (read8(handle, &offset) < 0)
+			return -1;
+		buffer->offset = offset;
+		buffer->name = read_string(handle);
+		if (!buffer->name)
+			return -1;
+	}
+
+	handle->file_state = TRACECMD_FILE_BUFERS;
+	return 0;
+}
+
 /**
  * tracecmd_read_headers - read the header information from trace.dat
  * @handle: input handle for the trace.dat file
@@ -955,6 +988,13 @@ int tracecmd_read_headers(struct tracecmd_input *handle,
 	if (state <= handle->file_state)
 		return 0;
 
+	if (read_buffers(handle) < 0)
+		return -1;
+
+	if (state <= handle->file_state)
+		return 0;
+
+
 	if (read_options_type(handle) < 0)
 		return -1;
 
diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index aa55a089..57b11493 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -376,6 +376,17 @@ static int check_out_state(struct tracecmd_output *handle, int new_state)
 	if (!handle)
 		return -1;
 
+	if (handle->file_version < 7) {
+		switch (new_state) {
+		case TRACECMD_FILE_BUFERS:
+			tracecmd_warning("State %d is not supported in trace file version %d",
+					 new_state, handle->file_version);
+			return -1;
+		default:
+			break;
+		}
+	}
+
 	switch (new_state) {
 	case TRACECMD_FILE_HEADERS:
 	case TRACECMD_FILE_FTRACE_EVENTS:
@@ -384,10 +395,16 @@ static int check_out_state(struct tracecmd_output *handle, int new_state)
 	case TRACECMD_FILE_PRINTK:
 	case TRACECMD_FILE_CMD_LINES:
 	case TRACECMD_FILE_CPU_COUNT:
-	case TRACECMD_FILE_OPTIONS:
+	case TRACECMD_FILE_BUFERS:
 		if (handle->file_state == (new_state - 1))
 			return 0;
 		break;
+	case TRACECMD_FILE_OPTIONS:
+		if (handle->file_version < 7 && handle->file_state == TRACECMD_FILE_CPU_COUNT)
+			return 0;
+		if (handle->file_version >= 7 && handle->file_state == TRACECMD_FILE_BUFERS)
+			return 0;
+		break;
 	case TRACECMD_FILE_CPU_LATENCY:
 	case TRACECMD_FILE_CPU_FLYRECORD:
 		if (handle->file_state == TRACECMD_FILE_OPTIONS)
@@ -1436,7 +1453,7 @@ int tracecmd_add_buffer_description(struct tracecmd_output *handle, const char *
 	return 0;
 }
 
-int tracecmd_write_buffers_description(struct tracecmd_output *handle)
+static int write_buffers_description_v6(struct tracecmd_output *handle)
 {
 	struct tracecmd_option *option;
 	struct tracecmd_buffer *buf;
@@ -1450,6 +1467,56 @@ int tracecmd_write_buffers_description(struct tracecmd_output *handle)
 	return 0;
 }
 
+static int write_buffers_description_v7(struct tracecmd_output *handle)
+{
+	struct tracecmd_buffer *buf;
+	char *data = NULL;
+	int count = 0;
+	int size;
+	int ret;
+
+	ret = check_out_state(handle, TRACECMD_FILE_BUFERS);
+	if (ret < 0) {
+		tracecmd_warning("Cannot write buffers descriptions");
+		return ret;
+	}
+
+	list_for_each_entry(buf, &handle->buffers, list) {
+		count++;
+	}
+
+	count = convert_endian_4(handle, count);
+	ret = do_write_check(handle, &count, 4);
+	if (ret < 0)
+		return ret;
+
+	list_for_each_entry(buf, &handle->buffers, list) {
+		size = 8 + strlen(buf->name) + 1;
+		data = malloc(size);
+		if (!data)
+			goto error;
+		*(tsize_t *)data = 0;
+		strcpy(data + 8, buf->name);
+		/* Save the data location in case it needs to be updated */
+		buf->offset = do_lseek(handle, 0, SEEK_CUR);
+		if (do_write_check(handle, data, size))
+			goto error;
+	}
+
+	handle->file_state = TRACECMD_FILE_BUFERS;
+	return 0;
+error:
+	return -1;
+}
+
+int tracecmd_write_buffers_description(struct tracecmd_output *handle)
+{
+	if (handle->file_version >= 7)
+		return write_buffers_description_v7(handle);
+
+	return write_buffers_description_v6(handle);
+}
+
 static tsize_t get_buffer_file_offset(struct tracecmd_output *handle, const char *name)
 {
 	struct tracecmd_buffer *buf;
@@ -1508,7 +1575,8 @@ struct tracecmd_output *tracecmd_create_file_latency(const char *output_file, in
 
 	if (tracecmd_write_cpus(handle, cpus) < 0)
 		goto out_free;
-
+	if (tracecmd_write_buffers_description(handle) < 0)
+		goto out_free;
 	if (tracecmd_write_options(handle) < 0)
 		goto out_free;
 
@@ -1701,7 +1769,9 @@ int tracecmd_append_cpu_data(struct tracecmd_output *handle,
 	ret = tracecmd_write_cpus(handle, cpus);
 	if (ret)
 		return ret;
-
+	ret = tracecmd_write_buffers_description(handle);
+	if (ret)
+		return ret;
 	ret = tracecmd_write_options(handle);
 	if (ret)
 		return ret;
diff --git a/tracecmd/trace-dump.c b/tracecmd/trace-dump.c
index ed82104b..56acb01d 100644
--- a/tracecmd/trace-dump.c
+++ b/tracecmd/trace-dump.c
@@ -420,6 +420,29 @@ static void dump_cpus_count(int fd)
 	do_print(SUMMARY, "\t%d [CPUs with tracing data]\n", trace_cpus);
 }
 
+static void dump_buffers(int fd)
+{
+	unsigned long long offset;
+	char name[DUMP_SIZE];
+	int count;
+
+	if (file_version < 7)
+		return;
+
+	if (read_file_number(fd, &count, 4))
+		die("cannot read the buffers count");
+	do_print(SUMMARY, "\t%d [buffers with tracing data]\n", count);
+
+	while (count) {
+		if (read_file_number(fd, &offset, 8))
+			die("cannot read the buffer offset");
+		if (read_file_string(fd, name, DUMP_SIZE))
+			die("cannot read the buffer name");
+		do_print(SUMMARY, "\t\t 0x%llx %s[data offset, buffer name]\n", offset, name);
+		count--;
+	}
+}
+
 static void dump_option_string(int fd, int size, char *desc)
 {
 	do_print(OPTIONS, "\t\t[Option %s, %d bytes]\n", desc, size);
@@ -762,6 +785,7 @@ static void dump_file(const char *file)
 	dump_printk(fd);
 	dump_cmdlines(fd);
 	dump_cpus_count(fd);
+	dump_buffers(fd);
 	dump_therest(fd);
 
 	tep_free(tep);
diff --git a/tracecmd/trace-listen.c b/tracecmd/trace-listen.c
index 0ae1c948..62debdb6 100644
--- a/tracecmd/trace-listen.c
+++ b/tracecmd/trace-listen.c
@@ -604,6 +604,9 @@ static int put_together_file(int cpus, int ofd, const char *node,
 
 	if (write_options) {
 		ret = tracecmd_write_cpus(handle, cpus);
+		if (ret)
+			goto out;
+		ret = tracecmd_write_buffers_description(handle);
 		if (ret)
 			goto out;
 		ret = tracecmd_write_options(handle);
diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c
index e12d77cc..5516fe3a 100644
--- a/tracecmd/trace-record.c
+++ b/tracecmd/trace-record.c
@@ -3653,6 +3653,9 @@ setup_connection(struct buffer_instance *instance, struct common_record_context
 		if (ret)
 			goto error;
 		ret = tracecmd_write_cpus(network_handle, instance->cpu_count);
+		if (ret)
+			goto error;
+		ret = tracecmd_write_buffers_description(network_handle);
 		if (ret)
 			goto error;
 		ret = tracecmd_write_options(network_handle);
@@ -3856,6 +3859,7 @@ static void setup_agent(struct buffer_instance *instance,
 	add_options(network_handle, ctx);
 	tracecmd_write_cmdlines(network_handle);
 	tracecmd_write_cpus(network_handle, instance->cpu_count);
+	tracecmd_write_buffers_description(network_handle);
 	tracecmd_write_options(network_handle);
 	tracecmd_msg_finish_sending_data(instance->msg_handle);
 	instance->network_handle = network_handle;
-- 
2.31.1

[PATCH v3 20/25] trace-cmd library: Track the offset in the option section in the trace file

[Tzvetomir Stoyanov (VMware)]

When reading / writing trace file, store the offset of the option
section in the file. A new internal API is added, to get the offset of
the option section from an input file handler:
 tracecmd_get_options_offset()

These changes are needed for compression of the option section from
the trace file.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/include/private/trace-cmd-private.h |  1 +
 lib/trace-cmd/trace-input.c                       | 11 +++++++++++
 lib/trace-cmd/trace-output.c                      |  2 ++
 3 files changed, 14 insertions(+)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index d7488346..a9b66736 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -239,6 +239,7 @@ tracecmd_get_cursor(struct tracecmd_input *handle, int cpu);
 unsigned long tracecmd_get_file_version(struct tracecmd_input *handle);
 int tracecmd_get_file_compress_proto(struct tracecmd_input *handle,
 				     const char **name, const char **version);
+size_t tracecmd_get_options_offset(struct tracecmd_input *handle);
 
 int tracecmd_ftrace_overrides(struct tracecmd_input *handle, struct tracecmd_ftrace *finfo);
 bool tracecmd_get_use_trace_clock(struct tracecmd_input *handle);
diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 5088a059..78581789 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -157,6 +157,7 @@ struct tracecmd_input {
 	size_t			header_files_start;
 	size_t			ftrace_files_start;
 	size_t			event_files_start;
+	size_t			options_start;
 	size_t			total_file_size;
 
 	/* For custom profilers. */
@@ -2759,6 +2760,7 @@ static int handle_options(struct tracecmd_input *handle)
 
 	/* By default, use usecs, unless told otherwise */
 	handle->flags |= TRACECMD_FL_IN_USECS;
+	handle->options_start = lseek64(handle->fd, 0, SEEK_CUR);
 
 	for (;;) {
 		if (do_read_check(handle, &option, 2))
@@ -4215,6 +4217,15 @@ bool tracecmd_get_use_trace_clock(struct tracecmd_input *handle)
 	return handle->use_trace_clock;
 }
 
+/**
+ * tracecmd_get_options_offset - get offset of the options sections in the file
+ * @handle: input handle for the trace.dat file
+ */
+size_t tracecmd_get_options_offset(struct tracecmd_input *handle)
+{
+	return handle->options_start;
+}
+
 /**
  * tracecmd_get_show_data_func - return the show data func
  * @handle: input handle for the trace.dat file
diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index 57b11493..1bd2351f 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -66,6 +66,7 @@ struct tracecmd_output {
 	bool			quiet;
 	unsigned long		file_state;
 	unsigned long		file_version;
+	size_t			options_start;
 
 	bool			do_compress;
 	struct tracecmd_compression *compress;
@@ -1854,6 +1855,7 @@ struct tracecmd_output *tracecmd_get_output_handle_fd(int fd)
 	tep_ref(handle->pevent);
 	handle->page_size = tracecmd_page_size(ihandle);
 	handle->file_version = tracecmd_get_file_version(ihandle);
+	handle->options_start = tracecmd_get_options_offset(ihandle);
 	list_head_init(&handle->options);
 	list_head_init(&handle->buffers);
 
-- 
2.31.1

[PATCH v3 21/25] trace-cmd library: Add compression of the option section of the trace file

[Tzvetomir Stoyanov (VMware)]

Comperss the option section of the trace file. This section is not big
currently and compressing it does not reduce significantly the size of
the file. This could be useful in the future as new options can be
added, storing a potentially huge amount of data.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/trace-input.c  | 46 +++++++++++++++---------
 lib/trace-cmd/trace-output.c | 68 ++++++++++++++++++++++++------------
 tracecmd/trace-dump.c        | 16 +++++++--
 3 files changed, 89 insertions(+), 41 deletions(-)

diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 78581789..1cec6917 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -2761,23 +2761,29 @@ static int handle_options(struct tracecmd_input *handle)
 	/* By default, use usecs, unless told otherwise */
 	handle->flags |= TRACECMD_FL_IN_USECS;
 	handle->options_start = lseek64(handle->fd, 0, SEEK_CUR);
-
+	if (uncompress_block(handle))
+		return -1;
 	for (;;) {
-		if (do_read_check(handle, &option, 2))
-			return -1;
+		ret = do_read_check(handle, &option, 2);
+		if (ret)
+			goto out;
 
 		if (option == TRACECMD_OPTION_DONE)
 			break;
 
 		/* next 4 bytes is the size of the option */
-		if (do_read_check(handle, &size, 4))
-			return -1;
+		ret = do_read_check(handle, &size, 4);
+		if (ret)
+			goto out;
 		size = tep_read_number(handle->pevent, &size, 4);
 		buf = malloc(size);
-		if (!buf)
-			return -ENOMEM;
-		if (do_read_check(handle, buf, size))
-			return -1;
+		if (!buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		ret = do_read_check(handle, buf, size);
+		if (ret)
+			goto out;
 
 		switch (option) {
 		case TRACECMD_OPTION_DATE:
@@ -2827,14 +2833,16 @@ static int handle_options(struct tracecmd_input *handle)
 							     buf + 8, 4);
 			ret = tsync_cpu_offsets_load(handle, buf + 12, size - 12);
 			if (ret < 0)
-				return ret;
+				goto out;
 			tracecmd_enable_tsync(handle, true);
 			break;
 		case TRACECMD_OPTION_CPUSTAT:
 			buf[size-1] = '\n';
 			cpustats = realloc(cpustats, cpustats_size + size + 1);
-			if (!cpustats)
-				return -ENOMEM;
+			if (!cpustats) {
+				ret = -ENOMEM;
+				goto out;
+			}
 			memcpy(cpustats + cpustats_size, buf, size);
 			cpustats_size += size;
 			cpustats[cpustats_size] = 0;
@@ -2844,14 +2852,17 @@ static int handle_options(struct tracecmd_input *handle)
 			handle->nr_buffers++;
 			handle->buffers = realloc(handle->buffers,
 						  sizeof(*handle->buffers) * handle->nr_buffers);
-			if (!handle->buffers)
-				return -ENOMEM;
+			if (!handle->buffers) {
+				ret = -ENOMEM;
+				goto out;
+			}
 			buffer = &handle->buffers[handle->nr_buffers - 1];
 			buffer->name = strdup(buf + 8);
 			if (!buffer->name) {
 				free(handle->buffers);
 				handle->buffers = NULL;
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto out;
 			}
 			offset = *(unsigned long long *)buf;
 			buffer->offset = tep_read_number(handle->pevent, &offset, 8);
@@ -2908,8 +2919,11 @@ static int handle_options(struct tracecmd_input *handle)
 	}
 
 	handle->cpustats = cpustats;
+	ret = 0;
 
-	return 0;
+out:
+	uncompress_reset(handle);
+	return ret;
 }
 
 static int read_options_type(struct tracecmd_input *handle)
diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index 1bd2351f..ca115872 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -150,6 +150,18 @@ static inline void compression_reset(struct tracecmd_output *handle)
 	handle->do_compress = false;
 }
 
+static int uncompress_block(struct tracecmd_output *handle)
+{
+	int ret = 0;
+
+	if (handle->file_version < 7 || !handle->compress)
+		return 0;
+	ret = tracecmd_uncompress_block(handle->compress);
+	if (!ret)
+		handle->do_compress = true;
+	return ret;
+}
+
 static inline int compression_start(struct tracecmd_output *handle)
 {
 	if (handle->file_version < 7 || !handle->compress)
@@ -1330,32 +1342,38 @@ int tracecmd_write_options(struct tracecmd_output *handle)
 
 	if (do_write_check(handle, "options  ", 10))
 		return -1;
-
+	handle->options_start = lseek64(handle->fd, 0, SEEK_CUR);
+	compression_start(handle);
 	list_for_each_entry(options, &handle->options, list) {
 		endian2 = convert_endian_2(handle, options->id);
 		if (do_write_check(handle, &endian2, 2))
-			return -1;
+			goto error;
 
 		endian4 = convert_endian_4(handle, options->size);
 		if (do_write_check(handle, &endian4, 4))
-			return -1;
+			goto error;
 
 		/* Save the data location in case it needs to be updated */
-		options->offset = lseek64(handle->fd, 0, SEEK_CUR);
+		options->offset = do_lseek(handle, 0, SEEK_CUR);
 
 		if (do_write_check(handle, options->data,
 				   options->size))
-			return -1;
+			goto error;
 	}
 
 	option = TRACECMD_OPTION_DONE;
 
 	if (do_write_check(handle, &option, 2))
-		return -1;
+		goto error;
+	if (compression_end(handle))
+		goto error;
 
 	handle->file_state = TRACECMD_FILE_OPTIONS;
 
 	return 0;
+error:
+	compression_reset(handle);
+	return -1;
 }
 
 int tracecmd_append_options(struct tracecmd_output *handle)
@@ -1371,42 +1389,48 @@ int tracecmd_append_options(struct tracecmd_output *handle)
 	 * We can append only if options are already written and tracing data
 	 * is not yet written
 	 */
-	if (handle->file_state != TRACECMD_FILE_OPTIONS)
+	if (handle->file_state != TRACECMD_FILE_OPTIONS || !handle->options_start)
 		return -1;
-
-	if (lseek64(handle->fd, 0, SEEK_END) == (off_t)-1)
+	if (lseek64(handle->fd, handle->options_start, SEEK_SET) == (off_t)-1)
 		return -1;
-	offset = lseek64(handle->fd, -2, SEEK_CUR);
-	if (offset == (off_t)-1)
+	if (uncompress_block(handle))
 		return -1;
-
-	r = pread(handle->fd, &option, 2, offset);
+	if (do_lseek(handle, 0, SEEK_END) == -1)
+		goto error;
+	offset = do_lseek(handle, -2, SEEK_CUR);
+	if (offset == (off_t)-1)
+		goto error;
+	r = do_preed(handle, &option, 2, offset);
 	if (r != 2 || option != TRACECMD_OPTION_DONE)
-		return -1;
-
+		goto error;
 	list_for_each_entry(options, &handle->options, list) {
 		endian2 = convert_endian_2(handle, options->id);
 		if (do_write_check(handle, &endian2, 2))
-			return -1;
+			goto error;
 
 		endian4 = convert_endian_4(handle, options->size);
 		if (do_write_check(handle, &endian4, 4))
-			return -1;
+			goto error;
 
 		/* Save the data location in case it needs to be updated */
-		options->offset = lseek64(handle->fd, 0, SEEK_CUR);
+		options->offset = do_lseek(handle, 0, SEEK_CUR);
 
 		if (do_write_check(handle, options->data,
 				   options->size))
-			return -1;
+			goto error;
 	}
-
 	option = TRACECMD_OPTION_DONE;
 
 	if (do_write_check(handle, &option, 2))
-		return -1;
-
+		goto error;
+	if (lseek64(handle->fd, handle->options_start, SEEK_SET) == (off_t)-1)
+		goto error;
+	if (compression_end(handle))
+		goto error;
 	return 0;
+error:
+	compression_reset(handle);
+	return -1;
 }
 
 static struct tracecmd_option *
diff --git a/tracecmd/trace-dump.c b/tracecmd/trace-dump.c
index 56acb01d..8d0f2251 100644
--- a/tracecmd/trace-dump.c
+++ b/tracecmd/trace-dump.c
@@ -82,6 +82,13 @@ static int read_compressed(int fd, char *dst, int len)
 	return read_fd(fd, dst, len);
 }
 
+static int do_lseek(int fd, int offset, int whence)
+{
+	if (read_compress)
+		return tracecmd_compress_lseek(compress, offset, whence);
+	return lseek64(fd, offset, whence);
+}
+
 static int read_file_string(int fd, char *dst, int len)
 {
 	size_t size = 0;
@@ -625,6 +632,9 @@ static void dump_options(int fd)
 	unsigned int size;
 	int count = 0;
 
+	if (uncompress_block())
+		die("cannot uncompress file block");
+
 	for (;;) {
 		if (read_file_number(fd, &option, 2))
 			die("cannot read the option id");
@@ -635,7 +645,7 @@ static void dump_options(int fd)
 
 		count++;
 		if (!DUMP_CHECK(OPTIONS) && !DUMP_CHECK(CLOCK) && !DUMP_CHECK(SUMMARY)) {
-			lseek64(fd, size, SEEK_CUR);
+			do_lseek(fd, size, SEEK_CUR);
 			continue;
 		}
 		switch (option) {
@@ -685,12 +695,12 @@ static void dump_options(int fd)
 		default:
 			do_print(OPTIONS, " %d %d\t[Unknown option, size - skipping]\n",
 				 option, size);
-			lseek64(fd, size, SEEK_CUR);
+			do_lseek(fd, size, SEEK_CUR);
 			break;
 		}
 	}
 	do_print(SUMMARY, "\t[%d options]\n", count);
-
+	uncompress_reset();
 }
 
 static void dump_latency(int fd)
-- 
2.31.1

[PATCH v3 22/25] trace-cmd library: Refactor the logic for writing trace data in the file

[Tzvetomir Stoyanov (VMware)]

Refactored the internal logic of tracecmd_write_cpu_data() API to be
suitable for adding trace data compression.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/trace-output.c | 97 +++++++++++++++++-------------------
 1 file changed, 46 insertions(+), 51 deletions(-)

diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index ca115872..08d05744 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -155,8 +155,7 @@ static int uncompress_block(struct tracecmd_output *handle)
 	int ret = 0;
 
 	if (handle->file_version < 7 || !handle->compress)
-		return 0;
-	ret = tracecmd_uncompress_block(handle->compress);
+		return 0;	ret = tracecmd_uncompress_block(handle->compress);
 	if (!ret)
 		handle->do_compress = true;
 	return ret;
@@ -1672,11 +1671,17 @@ static char *get_clock(struct tracecmd_output *handle)
 	return handle->trace_clock;
 }
 
+struct data_file_write {
+	int file_size;
+	off64_t soffset;
+	off64_t data_offset;
+	off64_t doffset;
+};
+
 int tracecmd_write_cpu_data(struct tracecmd_output *handle,
 			    int cpus, char * const *cpu_data_files)
 {
-	off64_t *offsets = NULL;
-	unsigned long long *sizes = NULL;
+	struct data_file_write *data_files = NULL;
 	off64_t offset;
 	unsigned long long endian8;
 	char *clock = NULL;
@@ -1698,37 +1703,11 @@ int tracecmd_write_cpu_data(struct tracecmd_output *handle,
 	if (do_write_check(handle, "flyrecord", 10))
 		goto out_free;
 
-	offsets = malloc(sizeof(*offsets) * cpus);
-	if (!offsets)
-		goto out_free;
-	sizes = malloc(sizeof(*sizes) * cpus);
-	if (!sizes)
-		goto out_free;
-
-	offset = lseek64(handle->fd, 0, SEEK_CUR);
-
-	/* hold any extra data for data */
-	offset += cpus * (16);
-
-	/*
-	 * Unfortunately, the trace_clock data was placed after the
-	 * cpu data, and wasn't accounted for with the offsets.
-	 * We need to save room for the trace_clock file. This means
-	 * we need to find the size of it before we define the final
-	 * offsets.
-	 */
-	clock = get_clock(handle);
-	if (!clock)
+	data_files = calloc(cpus, sizeof(struct data_file_write));
+	if (!data_files)
 		goto out_free;
-	/* Save room for storing the size */
-	offset += 8;
-	offset += strlen(clock);
-	/* 2 bytes for [] around the clock */
-	offset += 2;
-
-	/* Page align offset */
-	offset = (offset + (handle->page_size - 1)) & ~(handle->page_size - 1);
 
+	/* Write 0 for trace data offset and size and store offsets of these fields */
 	for (i = 0; i < cpus; i++) {
 		file = cpu_data_files[i];
 		ret = stat(file, &st);
@@ -1736,53 +1715,69 @@ int tracecmd_write_cpu_data(struct tracecmd_output *handle,
 			tracecmd_warning("can not stat '%s'", file);
 			goto out_free;
 		}
-		offsets[i] = offset;
-		sizes[i] = st.st_size;
-		offset += st.st_size;
-		offset = (offset + (handle->page_size - 1)) & ~(handle->page_size - 1);
+		data_files[i].file_size = st.st_size;
 
-		endian8 = convert_endian_8(handle, offsets[i]);
+		endian8 = 0;
+		data_files[i].doffset = lseek64(handle->fd, 0, SEEK_CUR);
 		if (do_write_check(handle, &endian8, 8))
 			goto out_free;
-		endian8 = convert_endian_8(handle, sizes[i]);
+		data_files[i].soffset = lseek64(handle->fd, 0, SEEK_CUR);
 		if (do_write_check(handle, &endian8, 8))
 			goto out_free;
 	}
 
+	clock = get_clock(handle);
+	if (!clock)
+		goto out_free;
 	if (save_clock(handle, clock))
 		goto out_free;
 
 	for (i = 0; i < cpus; i++) {
+		data_files[i].data_offset = lseek64(handle->fd, 0, SEEK_CUR);
+		/* Page align offset */
+		data_files[i].data_offset = (data_files[i].data_offset + (handle->page_size - 1)) & ~(handle->page_size - 1);
+		data_files[i].data_offset = lseek64(handle->fd, data_files[i].data_offset, SEEK_SET);
+		if (data_files[i].data_offset == (off64_t)-1)
+			goto out_free;
 		if (!tracecmd_get_quiet(handle))
 			fprintf(stderr, "CPU%d data recorded at offset=0x%llx\n",
-				i, (unsigned long long) offsets[i]);
-		offset = lseek64(handle->fd, offsets[i], SEEK_SET);
-		if (offset == (off64_t)-1) {
-			tracecmd_warning("could not seek to %lld\n", offsets[i]);
-			goto out_free;
-		}
+				i, (unsigned long long) data_files[i].data_offset);
+
 		check_size = copy_file(handle, cpu_data_files[i]);
-		if (check_size != sizes[i]) {
+		if (check_size != data_files[i].file_size) {
 			errno = EINVAL;
 			tracecmd_warning("did not match size of %lld to %lld",
-					 check_size, sizes[i]);
+					 check_size, data_files[i].file_size);
 			goto out_free;
 		}
+		/* Write the real CPU data offset inthe file */
+		offset = lseek64(handle->fd, data_files[i].doffset, SEEK_SET);
+		endian8 = convert_endian_8(handle, data_files[i].data_offset);
+		if (do_write_check(handle, &endian8, 8))
+			goto out_free;
+		/* Write the real CPU data size in the file */
+		offset = lseek64(handle->fd, data_files[i].soffset, SEEK_SET);
+		endian8 = convert_endian_8(handle, check_size);
+		if (do_write_check(handle, &endian8, 8))
+			goto out_free;
+		offset = data_files[i].data_offset + check_size;
+		offset = lseek64(handle->fd, offset, SEEK_SET);
 		if (!tracecmd_get_quiet(handle))
 			fprintf(stderr, "    %llu bytes in size\n",
 				(unsigned long long)check_size);
 	}
 
-	free(offsets);
-	free(sizes);
+	if (lseek64(handle->fd, 0, SEEK_END) == (off64_t)-1)
+		goto out_free;
 
+	free(data_files);
 	handle->file_state = TRACECMD_FILE_CPU_FLYRECORD;
 
 	return 0;
 
  out_free:
-	free(offsets);
-	free(sizes);
+	lseek64(handle->fd, 0, SEEK_END);
+	free(data_files);
 	return -1;
 }
 
-- 
2.31.1

[PATCH v3 23/25] trace-cmd library: Add APIs for read and write compressed data in chunks

[Tzvetomir Stoyanov (VMware)]

New compression APIs are added for writing and reading compressed data
from / to files in chunks:
 tracecmd_compress_copy_from()
 tracecmd_uncompress_copy_to()
Format of the compressed data, used by these APIs, is:
 - 4 bytes, chunks count
   - for each chunk:
     - 4 bytes, size of compressed data in this chunk
     - 4 bytes, uncompressed size of the data in this chunk
     - data, bytes of <size of compressed data in this chunk>

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 .../include/private/trace-cmd-private.h       |   5 +-
 lib/trace-cmd/trace-compress.c                | 191 ++++++++++++++++++
 2 files changed, 195 insertions(+), 1 deletion(-)

diff --git a/lib/trace-cmd/include/private/trace-cmd-private.h b/lib/trace-cmd/include/private/trace-cmd-private.h
index a9b66736..950e6b51 100644
--- a/lib/trace-cmd/include/private/trace-cmd-private.h
+++ b/lib/trace-cmd/include/private/trace-cmd-private.h
@@ -493,7 +493,10 @@ int tracecmd_compress_proto_register(const char *name, const char *version, int
 						       char *out, unsigned int *out_bytes),
 				     unsigned int (*comress_size)(unsigned int bytes),
 				     bool (*is_supported)(const char *name, const char *version));
-
+int tracecmd_compress_copy_from(struct tracecmd_compression *handle, int fd, int chunk_size,
+				unsigned long long *read_size, unsigned long long *write_size);
+int tracecmd_uncompress_copy_to(struct tracecmd_compression *handle, int fd,
+				unsigned long long *read_size, unsigned long long *write_size);
 /* --- Plugin handling --- */
 extern struct tep_plugin_option trace_ftrace_options[];
 
diff --git a/lib/trace-cmd/trace-compress.c b/lib/trace-cmd/trace-compress.c
index 2b329d00..3a7accc2 100644
--- a/lib/trace-cmd/trace-compress.c
+++ b/lib/trace-cmd/trace-compress.c
@@ -594,3 +594,194 @@ error:
 	free(v);
 	return -1;
 }
+
+/**
+ * tracecmd_compress_copy_from - Copy and compress data from a file
+ * @handle: compression handler
+ * @fd: file descriptor to uncompressed data
+ * @chunk_size: size of one compression chunk
+ * @read_size: return, size of the uncompressed data read from @fd
+ * @write_size: return, size of the compressed data written into @handle
+ *
+ * This function reads uncompressed data from given @fd until EOF is reached, compresses
+ * the data using the @handle compression context and writes the compressed data into the fd
+ * associated with the @handle. The data is compressed on chunks with given @chunk_size size.
+ * The compressed data is written in the format:
+ *  - 4 bytes, chunks count
+ *  - for each chunk:
+ *    - 4 bytes, size of compressed data in this chunk
+ *    - 4 bytes, uncompressed size of the data in this chunk
+ *    - data, bytes of <size of compressed data in this chunk>
+ *
+ * On success 0 is returned, @read_size and @write_size are updated with the size of
+ * read and written data.
+ */
+int tracecmd_compress_copy_from(struct tracecmd_compression *handle, int fd, int chunk_size,
+				unsigned long long *read_size, unsigned long long *write_size)
+{
+	unsigned int chunks = 0;
+	unsigned int rsize = 0;
+	unsigned int wsize = 0;
+	unsigned int csize;
+	unsigned int size;
+	unsigned int r;
+	off64_t offset;
+	char *buf_from;
+	char *buf_to;
+	int endian4;
+	int ret;
+
+	if (!handle || !handle->proto ||
+	    !handle->proto->comress_block || !handle->proto->comress_size)
+		return 0;
+
+	csize = handle->proto->comress_size(chunk_size);
+	buf_from = malloc(chunk_size);
+	if (!buf_from)
+		return -1;
+	buf_to = malloc(csize);
+	if (!buf_to)
+		return -1;
+	/* save the initial offset and write 0 chunks */
+	offset = lseek64(handle->fd, 0, SEEK_CUR);
+	write_fd(handle->fd, &chunks, 4);
+
+	do {
+		r = read(fd, buf_from, chunk_size);
+		if (r < 0)
+			break;
+		rsize += r;
+		size = csize;
+		if (r > 0) {
+			ret = handle->proto->comress_block(buf_from, r, buf_to, &size);
+			if (ret < 0) {
+				if (errno == EINTR)
+					continue;
+				break;
+			}
+			/* Write compressed data size */
+			endian4 = tep_read_number(handle->tep, &size, 4);
+			ret = write_fd(handle->fd, &endian4, 4);
+			if (ret != 4)
+				break;
+			/* Write uncompressed data size */
+			endian4 = tep_read_number(handle->tep, &r, 4);
+			ret = write_fd(handle->fd, &endian4, 4);
+			if (ret != 4)
+				break;
+			/* Write the compressed data */
+			ret = write_fd(handle->fd, buf_to, size);
+			if (ret != size)
+				break;
+			/* data + compress header */
+			wsize += (size + 8);
+			chunks++;
+		}
+	} while (r > 0);
+	free(buf_from);
+	free(buf_to);
+	if (r)
+		return -1;
+	if (lseek64(handle->fd, offset, SEEK_SET) == (off_t)-1)
+		return -1;
+	endian4 = tep_read_number(handle->tep, &chunks, 4);
+	/* write chunks count*/
+	write_fd(handle->fd, &chunks, 4);
+	lseek64(handle->fd, offset, SEEK_SET);
+	if (lseek64(handle->fd, 0, SEEK_END) == (off_t)-1)
+		return -1;
+	if (read_size)
+		*read_size = rsize;
+	if (write_size)
+		*write_size = wsize;
+	return 0;
+}
+
+/**
+ * tracecmd_uncompress_copy_to - Uncompress data and copy to a file
+ * @handle: compression handler
+ * @fd: file descriptor to uncompressed data
+ * @read_size: return, size of the compressed data read from @handle
+ * @write_size: return, size of the uncompressed data written into @fd
+ *
+ * This function reads compressed data from the fd, associated with @handle, uncompresses it
+ * using the @handle compression context and writes the uncompressed data into the fd.
+ * The compressed data must be in the format:
+ *  - 4 bytes, chunks count
+ *  - for each chunk:
+ *    - 4 bytes, size of compressed data in this chunk
+ *    - 4 bytes, uncompressed size of the data in this chunk
+ *    - data, bytes of <size of compressed data in this chunk>
+ *
+ * On success 0 is returned, @read_size and @write_size are updated with the size of
+ * read and written data.
+ */
+int tracecmd_uncompress_copy_to(struct tracecmd_compression *handle, int fd,
+				unsigned long long *read_size, unsigned long long *write_size)
+{
+	unsigned int s_uncompressed;
+	unsigned int s_compressed;
+	unsigned int rsize = 0;
+	unsigned int wsize = 0;
+	char *bytes_out = NULL;
+	char *bytes_in = NULL;
+	int size_out;
+	int size_in;
+	int chunks;
+	char buf[4];
+	char *tmp;
+	int ret;
+
+	if (!handle || !handle->proto || !handle->proto->uncompress_block)
+		return -1;
+
+	if (read(handle->fd, buf, 4) != 4)
+		return -1;
+	chunks = tep_read_number(handle->tep, buf, 4);
+	rsize += 4;
+	while (chunks) {
+		if (read(handle->fd, buf, 4) != 4)
+			break;
+		s_compressed = tep_read_number(handle->tep, buf, 4);
+		rsize += 4;
+		if (read(handle->fd, buf, 4) != 4)
+			break;
+		s_uncompressed = tep_read_number(handle->tep, buf, 4);
+		rsize += 4;
+		if (!bytes_in || size_in < s_compressed) {
+			tmp = realloc(bytes_in, s_compressed);
+			if (!tmp)
+				break;
+			bytes_in = tmp;
+			size_in = s_compressed;
+		}
+
+		if (!bytes_out || size_out < s_uncompressed) {
+			tmp = realloc(bytes_out, s_uncompressed);
+			if (!tmp)
+				break;
+			bytes_out = tmp;
+			size_out = s_uncompressed;
+		}
+
+		if (read_fd(handle->fd, bytes_in, s_compressed) < 0)
+			break;
+		rsize += s_compressed;
+		ret = handle->proto->uncompress_block(bytes_in, s_compressed,
+						      bytes_out, &s_uncompressed);
+		if (ret)
+			break;
+		write_fd(fd, bytes_out, s_uncompressed);
+		wsize += s_uncompressed;
+		chunks--;
+	}
+	free(bytes_in);
+	free(bytes_out);
+	if (chunks)
+		return -1;
+	if (read_size)
+		*read_size = rsize;
+	if (write_size)
+		*write_size = wsize;
+	return 0;
+}
-- 
2.31.1

[PATCH v3 24/25] trace-cmd: Compress trace data

[Tzvetomir Stoyanov (VMware)]

When creating a trace.dat file of version 7, compress the trace data.
The data is compressed in chunks. The chunk size is a compile time
parameter, set by default to 1MB.

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/trace-output.c | 50 +++++++++++++++++++++++++++++++-----
 1 file changed, 43 insertions(+), 7 deletions(-)

diff --git a/lib/trace-cmd/trace-output.c b/lib/trace-cmd/trace-output.c
index 08d05744..fab01f56 100644
--- a/lib/trace-cmd/trace-output.c
+++ b/lib/trace-cmd/trace-output.c
@@ -320,6 +320,41 @@ static tsize_t copy_file(struct tracecmd_output *handle,
 	return size;
 }
 
+#define COMPRESS_CHUNK_SIZE (1*1024*1024)
+static tsize_t copy_file_compress(struct tracecmd_output *handle,
+				  const char *file, unsigned long long *write_size)
+{
+	unsigned long long rsize = 0;
+	unsigned long long wsize = 0;
+	tsize_t size;
+	int ret;
+	int fd;
+
+	fd = open(file, O_RDONLY);
+	if (fd < 0) {
+		tracecmd_warning("Can't read '%s'", file);
+		return 0;
+	}
+
+	if (handle->file_version >= 7) {
+		ret = tracecmd_compress_copy_from(handle->compress, fd,
+						  COMPRESS_CHUNK_SIZE, &rsize, &wsize);
+		if (ret < 0) {
+			tracecmd_warning("Can't compress '%s'", file);
+			close(fd);
+			return 0;
+		}
+		size = rsize;
+		*write_size = wsize;
+	} else {
+		size = copy_file_fd(handle, fd);
+		*write_size = size;
+	}
+
+	close(fd);
+	return size;
+}
+
 /*
  * Finds the path to the debugfs/tracing
  * Allocates the string and stores it.
@@ -1684,8 +1719,9 @@ int tracecmd_write_cpu_data(struct tracecmd_output *handle,
 	struct data_file_write *data_files = NULL;
 	off64_t offset;
 	unsigned long long endian8;
+	unsigned long long read_size;
+	unsigned long long write_size;
 	char *clock = NULL;
-	off64_t check_size;
 	char *file;
 	struct stat st;
 	int ret;
@@ -1743,11 +1779,11 @@ int tracecmd_write_cpu_data(struct tracecmd_output *handle,
 			fprintf(stderr, "CPU%d data recorded at offset=0x%llx\n",
 				i, (unsigned long long) data_files[i].data_offset);
 
-		check_size = copy_file(handle, cpu_data_files[i]);
-		if (check_size != data_files[i].file_size) {
+		read_size = copy_file_compress(handle, cpu_data_files[i], &write_size);
+		if (read_size != data_files[i].file_size) {
 			errno = EINVAL;
 			tracecmd_warning("did not match size of %lld to %lld",
-					 check_size, data_files[i].file_size);
+					 read_size, data_files[i].file_size);
 			goto out_free;
 		}
 		/* Write the real CPU data offset inthe file */
@@ -1757,14 +1793,14 @@ int tracecmd_write_cpu_data(struct tracecmd_output *handle,
 			goto out_free;
 		/* Write the real CPU data size in the file */
 		offset = lseek64(handle->fd, data_files[i].soffset, SEEK_SET);
-		endian8 = convert_endian_8(handle, check_size);
+		endian8 = convert_endian_8(handle, write_size);
 		if (do_write_check(handle, &endian8, 8))
 			goto out_free;
-		offset = data_files[i].data_offset + check_size;
+		offset = data_files[i].data_offset + write_size;
 		offset = lseek64(handle->fd, offset, SEEK_SET);
 		if (!tracecmd_get_quiet(handle))
 			fprintf(stderr, "    %llu bytes in size\n",
-				(unsigned long long)check_size);
+				(unsigned long long)write_size);
 	}
 
 	if (lseek64(handle->fd, 0, SEEK_END) == (off64_t)-1)
-- 
2.31.1

[PATCH v3 25/25] trace-cmd: Read compressed trace data

[Tzvetomir Stoyanov (VMware)]

When reading a trace.dat file of version 7, uncompress the trace data.
The trace data for each CPU is uncompressed in a temporary file, located
in /tmp directory with prefix "trace_cpu_data".

Signed-off-by: Tzvetomir Stoyanov (VMware) <tz.stoyanov@gmail.com>
---
 lib/trace-cmd/trace-input.c | 74 +++++++++++++++++++++++++++++--------
 tracecmd/trace-read.c       |  8 ++++
 2 files changed, 67 insertions(+), 15 deletions(-)

diff --git a/lib/trace-cmd/trace-input.c b/lib/trace-cmd/trace-input.c
index 1cec6917..e7fd0d30 100644
--- a/lib/trace-cmd/trace-input.c
+++ b/lib/trace-cmd/trace-input.c
@@ -54,6 +54,7 @@ struct page {
 #endif
 };
 
+#define COMPR_TEMP_FILE "/tmp/trace_cpu_dataXXXXXX"
 struct cpu_data {
 	/* the first two never change */
 	unsigned long long	file_offset;
@@ -72,6 +73,10 @@ struct cpu_data {
 	int			page_cnt;
 	int			cpu;
 	int			pipe_fd;
+
+	/* temporary file for uncompressed cpu data */
+	int			cfd;
+	char			cfile[26]; /* strlen(COMPR_TEMP_FILE) */
 };
 
 struct input_buffer_instance {
@@ -1080,6 +1085,7 @@ static void *allocate_page_map(struct tracecmd_input *handle,
 	off64_t map_offset;
 	void *map;
 	int ret;
+	int fd;
 
 	if (handle->read_page) {
 		map = malloc(handle->page_size);
@@ -1119,12 +1125,15 @@ static void *allocate_page_map(struct tracecmd_input *handle,
 		map_size -= map_offset + map_size -
 			(cpu_data->file_offset + cpu_data->file_size);
 
+	if (cpu_data->cfd >= 0)
+		fd = cpu_data->cfd;
+	else
+		fd = handle->fd;
  again:
 	page_map->size = map_size;
 	page_map->offset = map_offset;
 
-	page_map->map = mmap(NULL, map_size, PROT_READ, MAP_PRIVATE,
-			 handle->fd, map_offset);
+	page_map->map = mmap(NULL, map_size, PROT_READ, MAP_PRIVATE, fd, map_offset);
 
 	if (page_map->map == MAP_FAILED) {
 		/* Try a smaller map */
@@ -2316,13 +2325,41 @@ tracecmd_read_prev(struct tracecmd_input *handle, struct tep_record *record)
 	/* Not reached */
 }
 
+static int cpu_data_uncompress(struct tracecmd_input *handle, int cpu, unsigned long long *size)
+{
+	struct cpu_data *cpu_data;
+
+	cpu_data = &handle->cpu_data[cpu];
+	strcpy(cpu_data->cfile, COMPR_TEMP_FILE);
+	cpu_data->cfd = mkstemp(cpu_data->cfile);
+	if (cpu_data->cfd < 0)
+		return -1;
+	return tracecmd_uncompress_copy_to(handle->compress, cpu_data->cfd, NULL, size);
+}
+
 static int init_cpu(struct tracecmd_input *handle, int cpu)
 {
 	struct cpu_data *cpu_data = &handle->cpu_data[cpu];
+	unsigned long long size;
+	off64_t offset;
 	int i;
 
-	cpu_data->offset = cpu_data->file_offset;
-	cpu_data->size = cpu_data->file_size;
+	if (handle->file_version >= 7) {
+		offset = lseek64(handle->fd, 0, SEEK_CUR);
+		if (lseek64(handle->fd, cpu_data->file_offset, SEEK_SET) == (off_t)-1)
+			return -1;
+		if (cpu_data_uncompress(handle, cpu, &size) < 0)
+			return -1;
+		cpu_data->offset = 0;
+		cpu_data->file_offset = 0;
+		cpu_data->file_size = size;
+		cpu_data->size = size;
+		if (lseek64(handle->fd, offset, SEEK_SET) == (off_t)-1)
+			return -1;
+	} else {
+		cpu_data->offset = cpu_data->file_offset;
+		cpu_data->size = cpu_data->file_size;
+	}
 	cpu_data->timestamp = 0;
 
 	list_head_init(&cpu_data->page_maps);
@@ -3015,6 +3052,7 @@ static int read_cpu_data(struct tracecmd_input *handle)
 
 		handle->cpu_data[cpu].file_offset = offset;
 		handle->cpu_data[cpu].file_size = size;
+		handle->cpu_data[cpu].cfd = -1;
 		if (size > max_size)
 			max_size = size;
 
@@ -3637,17 +3675,23 @@ void tracecmd_close(struct tracecmd_input *handle)
 		/* The tracecmd_peek_data may have cached a record */
 		free_next(handle, cpu);
 		free_page(handle, cpu);
-		if (handle->cpu_data && handle->cpu_data[cpu].kbuf) {
-			kbuffer_free(handle->cpu_data[cpu].kbuf);
-			if (handle->cpu_data[cpu].page_map)
-				free_page_map(handle->cpu_data[cpu].page_map);
-
-			if (handle->cpu_data[cpu].page_cnt)
-				tracecmd_warning("%d pages still allocated on cpu %d%s",
-						 handle->cpu_data[cpu].page_cnt, cpu,
-						 show_records(handle->cpu_data[cpu].pages,
-							      handle->cpu_data[cpu].nr_pages));
-			free(handle->cpu_data[cpu].pages);
+		if (handle->cpu_data) {
+			if (handle->cpu_data[cpu].kbuf) {
+				kbuffer_free(handle->cpu_data[cpu].kbuf);
+				if (handle->cpu_data[cpu].page_map)
+					free_page_map(handle->cpu_data[cpu].page_map);
+
+				if (handle->cpu_data[cpu].page_cnt)
+					tracecmd_warning("%d pages still allocated on cpu %d%s",
+							 handle->cpu_data[cpu].page_cnt, cpu,
+							 show_records(handle->cpu_data[cpu].pages,
+								      handle->cpu_data[cpu].nr_pages));
+				free(handle->cpu_data[cpu].pages);
+			}
+			if (handle->cpu_data[cpu].cfd >= 0) {
+				close(handle->cpu_data[cpu].cfd);
+				unlink(handle->cpu_data[cpu].cfile);
+			}
 		}
 	}
 
diff --git a/tracecmd/trace-read.c b/tracecmd/trace-read.c
index b315283e..e7a4f196 100644
--- a/tracecmd/trace-read.c
+++ b/tracecmd/trace-read.c
@@ -1363,7 +1363,14 @@ struct tracecmd_input *read_trace_header(const char *file, int flags)
 
 static void sig_end(int sig)
 {
+	struct handle_list *handles;
+
 	fprintf(stderr, "trace-cmd: Received SIGINT\n");
+
+	list_for_each_entry(handles, &handle_list, list) {
+		tracecmd_close(handles->handle);
+	}
+
 	exit(0);
 }
 
@@ -1922,6 +1929,7 @@ void trace_report (int argc, char **argv)
 	/* and version overrides uname! */
 	if (show_version)
 		otype = OUTPUT_VERSION_ONLY;
+
 	read_data_info(&handle_list, otype, global, align_ts);
 
 	list_for_each_entry(handles, &handle_list, list) {
-- 
2.31.1