replicant-frameworks_native/libs/utils/BackupData.cpp
Christopher Tate d78797f6e6 Full local backup infrastructure
This is the basic infrastructure for pulling a full(*) backup of the
device's data over an adb(**) connection to the local device.  The
basic process consists of these interacting pieces:

1. The framework's BackupManagerService, which coordinates the
   collection of app data and routing to the destination.

2. A new framework-provided BackupAgent implementation called
   FullBackupAgent, which is instantiated in the target applications'
   processes in turn, and knows how to emit a datastream that contains
   all of the app's saved data files.

3. A new shell-level program called "bu" that is used to bridge from
   adb to the framework's Backup Manager.

4. adb itself, which now knows how to use 'bu' to kick off a backup
   operation and pull the resulting data stream to the desktop host.

5. A system-provided application that verifies with the user that
   an attempted backup/restore operation is in fact expected and to
   be allowed.

The full agent implementation is not used during normal operation of
the delta-based app-customized remote backup process.  Instead it's
used during user-confirmed *full* backup of applications and all their
data to a local destination, e.g. via the adb connection.

The output format is 'tar'.  This makes it very easy for the end
user to examine the resulting dataset, e.g. for purpose of extracting
files for debug purposes; as well as making it easy to contemplate
adding things like a direct gzip stage to the data pipeline during
backup/restore.  It also makes it convenient to construct and maintain
synthetic backup datasets for testing purposes.

Within the tar format, certain artificial conventions are used.
All files are stored within top-level directories according to
their semantic origin:

apps/pkgname/a/  : Application .apk file itself
apps/pkgname/obb/: The application's associated .obb containers
apps/pkgname/f/  : The subtree rooted at the getFilesDir() location
apps/pkgname/db/ : The subtree rooted at the getDatabasePath() parent
apps/pkgname/sp/ : The subtree rooted at the getSharedPrefsFile() parent
apps/pkgname/r/  : Files stored relative to the root of the app's file tree
apps/pkgname/c/  : Reserved for the app's getCacheDir() tree; not stored.

For each package, the first entry in the tar stream is a file called
"_manifest", nominally rooted at apps/pkgname.  This file contains some
metadata about the package whose data is stored in the archive.

The contents of shared storage can optionally be included in the tar
stream. It is placed in the synthetic location:

shared/...

uid/gid are ignored; app uids are assigned at install time, and the
app's data is handled from within its own execution environment, so
will automatically have the app's correct uid.

Forward-locked .apk files are never backed up.  System-partition
.apk files are not backed up unless they have been overridden by a
post-factory upgrade, in which case the current .apk *is* backed up --
i.e. the .apk that matches the on-disk data.  The manifest preceding
each application's portion of the tar stream provides version numbers
and signature blocks for version checking, as well as an indication
of whether the restore logic should expect to install the .apk before
extracting the data.

System packages can designate their own full backup agents.  This is
to manage things like the settings provider which (a) cannot be shut
down on the fly in order to do a clean snapshot of their file trees,
and (b) manage data that is not only irrelevant but actively hostile
to non-identical devices -- CDMA telephony settings would seriously
mess up a GSM device if emplaced there blind, for example.

When a full backup or restore is initiated from adb, the system will
present a confirmation UI that the user must explicitly respond to
within a short [~ 30 seconds] timeout.  This is to avoid the
possibility of malicious desktop-side software secretly grabbing a copy
of all the user's data for nefarious purposes.

(*) The backup is not strictly a full mirror.  In particular, the
    settings database is not cloned; it is handled the same way that
    it is in cloud backup/restore.  This is because some settings
    are actively destructive if cloned onto a different (or
    especially a different-model) device: telephony settings and
    AndroidID are good examples of this.

(**) On the framework side it doesn't care that it's adb; it just
    sends the tar stream to a file descriptor.  This can easily be
    retargeted around whatever transport we might decide to use
    in the future.

KNOWN ISSUES:

* the security UI is desperately ugly; no proper designs have yet
  been done for it
* restore is not yet implemented
* shared storage backup is not yet implemented
* symlinks aren't yet handled, though some infrastructure for
  dealing with them has been put in place.

Change-Id: Ia8347611e23b398af36ea22c36dff0a276b1ce91
2011-05-10 17:52:51 -07:00

381 lines
8.9 KiB
C++

/*
* Copyright (C) 2009 The Android Open Source Project
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#define LOG_TAG "backup_data"
#include <utils/BackupHelpers.h>
#include <utils/ByteOrder.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <cutils/log.h>
namespace android {
static const bool DEBUG = false;
/*
* File Format (v1):
*
* All ints are stored little-endian.
*
* - An app_header_v1 struct.
* - The name of the package, utf-8, null terminated, padded to 4-byte boundary.
* - A sequence of zero or more key/value paires (entities), each with
* - A entity_header_v1 struct
* - The key, utf-8, null terminated, padded to 4-byte boundary.
* - The value, padded to 4 byte boundary
*/
const static int ROUND_UP[4] = { 0, 3, 2, 1 };
static inline size_t
round_up(size_t n)
{
return n + ROUND_UP[n % 4];
}
static inline size_t
padding_extra(size_t n)
{
return ROUND_UP[n % 4];
}
BackupDataWriter::BackupDataWriter(int fd)
:m_fd(fd),
m_status(NO_ERROR),
m_pos(0),
m_entityCount(0)
{
}
BackupDataWriter::~BackupDataWriter()
{
}
// Pad out anything they've previously written to the next 4 byte boundary.
status_t
BackupDataWriter::write_padding_for(int n)
{
ssize_t amt;
ssize_t paddingSize;
paddingSize = padding_extra(n);
if (paddingSize > 0) {
uint32_t padding = 0xbcbcbcbc;
if (DEBUG) LOGI("writing %d padding bytes for %d", paddingSize, n);
amt = write(m_fd, &padding, paddingSize);
if (amt != paddingSize) {
m_status = errno;
return m_status;
}
m_pos += amt;
}
return NO_ERROR;
}
status_t
BackupDataWriter::WriteEntityHeader(const String8& key, size_t dataSize)
{
if (m_status != NO_ERROR) {
return m_status;
}
ssize_t amt;
amt = write_padding_for(m_pos);
if (amt != 0) {
return amt;
}
String8 k;
if (m_keyPrefix.length() > 0) {
k = m_keyPrefix;
k += ":";
k += key;
} else {
k = key;
}
if (DEBUG) {
LOGD("Writing header: prefix='%s' key='%s' dataSize=%d", m_keyPrefix.string(), key.string(),
dataSize);
}
entity_header_v1 header;
ssize_t keyLen;
keyLen = k.length();
header.type = tolel(BACKUP_HEADER_ENTITY_V1);
header.keyLen = tolel(keyLen);
header.dataSize = tolel(dataSize);
if (DEBUG) LOGI("writing entity header, %d bytes", sizeof(entity_header_v1));
amt = write(m_fd, &header, sizeof(entity_header_v1));
if (amt != sizeof(entity_header_v1)) {
m_status = errno;
return m_status;
}
m_pos += amt;
if (DEBUG) LOGI("writing entity header key, %d bytes", keyLen+1);
amt = write(m_fd, k.string(), keyLen+1);
if (amt != keyLen+1) {
m_status = errno;
return m_status;
}
m_pos += amt;
amt = write_padding_for(keyLen+1);
m_entityCount++;
return amt;
}
status_t
BackupDataWriter::WriteEntityData(const void* data, size_t size)
{
if (DEBUG) LOGD("Writing data: size=%lu", (unsigned long) size);
if (m_status != NO_ERROR) {
if (DEBUG) {
LOGD("Not writing data - stream in error state %d (%s)", m_status, strerror(m_status));
}
return m_status;
}
// We don't write padding here, because they're allowed to call this several
// times with smaller buffers. We write it at the end of WriteEntityHeader
// instead.
ssize_t amt = write(m_fd, data, size);
if (amt != (ssize_t)size) {
m_status = errno;
if (DEBUG) LOGD("write returned error %d (%s)", m_status, strerror(m_status));
return m_status;
}
m_pos += amt;
return NO_ERROR;
}
void
BackupDataWriter::SetKeyPrefix(const String8& keyPrefix)
{
m_keyPrefix = keyPrefix;
}
BackupDataReader::BackupDataReader(int fd)
:m_fd(fd),
m_done(false),
m_status(NO_ERROR),
m_pos(0),
m_entityCount(0)
{
memset(&m_header, 0, sizeof(m_header));
}
BackupDataReader::~BackupDataReader()
{
}
status_t
BackupDataReader::Status()
{
return m_status;
}
#define CHECK_SIZE(actual, expected) \
do { \
if ((actual) != (expected)) { \
if ((actual) == 0) { \
m_status = EIO; \
m_done = true; \
} else { \
m_status = errno; \
LOGD("CHECK_SIZE(a=%ld e=%ld) failed at line %d m_status='%s'", \
long(actual), long(expected), __LINE__, strerror(m_status)); \
} \
return m_status; \
} \
} while(0)
#define SKIP_PADDING() \
do { \
status_t err = skip_padding(); \
if (err != NO_ERROR) { \
LOGD("SKIP_PADDING FAILED at line %d", __LINE__); \
m_status = err; \
return err; \
} \
} while(0)
status_t
BackupDataReader::ReadNextHeader(bool* done, int* type)
{
*done = m_done;
if (m_status != NO_ERROR) {
return m_status;
}
int amt;
amt = skip_padding();
if (amt == EIO) {
*done = m_done = true;
return NO_ERROR;
}
else if (amt != NO_ERROR) {
return amt;
}
amt = read(m_fd, &m_header, sizeof(m_header));
*done = m_done = (amt == 0);
if (*done) {
return NO_ERROR;
}
CHECK_SIZE(amt, sizeof(m_header));
m_pos += sizeof(m_header);
if (type) {
*type = m_header.type;
}
// validate and fix up the fields.
m_header.type = fromlel(m_header.type);
switch (m_header.type)
{
case BACKUP_HEADER_ENTITY_V1:
{
m_header.entity.keyLen = fromlel(m_header.entity.keyLen);
if (m_header.entity.keyLen <= 0) {
LOGD("Entity header at %d has keyLen<=0: 0x%08x\n", (int)m_pos,
(int)m_header.entity.keyLen);
m_status = EINVAL;
}
m_header.entity.dataSize = fromlel(m_header.entity.dataSize);
m_entityCount++;
// read the rest of the header (filename)
size_t size = m_header.entity.keyLen;
char* buf = m_key.lockBuffer(size);
if (buf == NULL) {
m_status = ENOMEM;
return m_status;
}
int amt = read(m_fd, buf, size+1);
CHECK_SIZE(amt, (int)size+1);
m_key.unlockBuffer(size);
m_pos += size+1;
SKIP_PADDING();
m_dataEndPos = m_pos + m_header.entity.dataSize;
break;
}
default:
LOGD("Chunk header at %d has invalid type: 0x%08x", (int)m_pos, (int)m_header.type);
m_status = EINVAL;
}
return m_status;
}
bool
BackupDataReader::HasEntities()
{
return m_status == NO_ERROR && m_header.type == BACKUP_HEADER_ENTITY_V1;
}
status_t
BackupDataReader::ReadEntityHeader(String8* key, size_t* dataSize)
{
if (m_status != NO_ERROR) {
return m_status;
}
if (m_header.type != BACKUP_HEADER_ENTITY_V1) {
return EINVAL;
}
*key = m_key;
*dataSize = m_header.entity.dataSize;
return NO_ERROR;
}
status_t
BackupDataReader::SkipEntityData()
{
if (m_status != NO_ERROR) {
return m_status;
}
if (m_header.type != BACKUP_HEADER_ENTITY_V1) {
return EINVAL;
}
if (m_header.entity.dataSize > 0) {
int pos = lseek(m_fd, m_dataEndPos, SEEK_SET);
if (pos == -1) {
return errno;
}
}
SKIP_PADDING();
return NO_ERROR;
}
ssize_t
BackupDataReader::ReadEntityData(void* data, size_t size)
{
if (m_status != NO_ERROR) {
return -1;
}
int remaining = m_dataEndPos - m_pos;
//LOGD("ReadEntityData size=%d m_pos=0x%x m_dataEndPos=0x%x remaining=%d\n",
// size, m_pos, m_dataEndPos, remaining);
if (remaining <= 0) {
return 0;
}
if (((int)size) > remaining) {
size = remaining;
}
//LOGD(" reading %d bytes", size);
int amt = read(m_fd, data, size);
if (amt < 0) {
m_status = errno;
return -1;
}
if (amt == 0) {
m_status = EIO;
m_done = true;
}
m_pos += amt;
return amt;
}
status_t
BackupDataReader::skip_padding()
{
ssize_t amt;
ssize_t paddingSize;
paddingSize = padding_extra(m_pos);
if (paddingSize > 0) {
uint32_t padding;
amt = read(m_fd, &padding, paddingSize);
CHECK_SIZE(amt, paddingSize);
m_pos += amt;
}
return NO_ERROR;
}
} // namespace android