Revert "filemap: remove FilemapSeek class"

FIEMAP API is not supported by tmpfs file system, but
SEEK_HOLE/SEEK_DATA is supported.

Returned back FilemapSeek class that implements support
of SEEK_HOLE/SEEK_DATA API to make sparse_copy API working
on tmpfs again.

This reverts commit 6b80c13f7a82a312a3b981de5a56c66466ba1fac.

Signed-off-by: Ed Bartosh <ed.bartosh@linux.intel.com>
Signed-off-by: Ross Burton <ross.burton@intel.com>

1 files changed, 260 insertions, 49 deletions

diff --git a/scripts/lib/wic/filemap.py b/scripts/lib/wic/filemap.py
index 34523c02b6..080668e7c2 100644
--- a/scripts/lib/wic/filemap.py
+++ b/scripts/lib/wic/filemap.py
@@ -54,46 +54,24 @@ class Error(Exception):
     """A class for all the other exceptions raised by this module."""
     pass
 
-# Below goes the FIEMAP ioctl implementation, which is not very readable
-# because it deals with the rather complex FIEMAP ioctl. To understand the
-# code, you need to know the FIEMAP interface, which is documented in the
-# "Documentation/filesystems/fiemap.txt" file in the Linux kernel sources.
-
-# Format string for 'struct fiemap'
-_FIEMAP_FORMAT = "=QQLLLL"
-# sizeof(struct fiemap)
-_FIEMAP_SIZE = struct.calcsize(_FIEMAP_FORMAT)
-# Format string for 'struct fiemap_extent'
-_FIEMAP_EXTENT_FORMAT = "=QQQQQLLLL"
-# sizeof(struct fiemap_extent)
-_FIEMAP_EXTENT_SIZE = struct.calcsize(_FIEMAP_EXTENT_FORMAT)
-# The FIEMAP ioctl number
-_FIEMAP_IOCTL = 0xC020660B
-# This FIEMAP ioctl flag which instructs the kernel to sync the file before
-# reading the block map
-_FIEMAP_FLAG_SYNC = 0x00000001
-# Size of the buffer for 'struct fiemap_extent' elements which will be used
-# when invoking the FIEMAP ioctl. The larger is the buffer, the less times the
-# FIEMAP ioctl will be invoked.
-_FIEMAP_BUFFER_SIZE = 256 * 1024
 
-class FilemapFiemap:
+class _FilemapBase(object):
     """
-    This class provides API to the FIEMAP ioctl. Namely, it allows to iterate
-    over all mapped blocks and over all holes.
-
-    This class synchronizes the image file every time it invokes the FIEMAP
-    ioctl in order to work-around early FIEMAP implementation kernel bugs.
+    This is a base class for a couple of other classes in this module. This
+    class simply performs the common parts of the initialization process: opens
+    the image file, gets its size, etc. The 'log' parameter is the logger object
+    to use for printing messages.
     """
 
-    def __init__(self, image):
+    def __init__(self, image, log=None):
         """
-        Initialize a class instance. The 'image' argument is full the file
-        object to operate on.
+        Initialize a class instance. The 'image' argument is full path to the
+        file or file object to operate on.
         """
-        self._log = logging.getLogger(__name__)
 
-        self._log.debug("FilemapFiemap: initializing")
+        self._log = log
+        if self._log is None:
+            self._log = logging.getLogger(__name__)
 
         self._f_image_needs_close = False
 
@@ -135,21 +113,6 @@ class FilemapFiemap:
         self._log.debug("block size %d, blocks count %d, image size %d"
                         % (self.block_size, self.blocks_cnt, self.image_size))
 
-        self._buf_size = _FIEMAP_BUFFER_SIZE
-
-        # Calculate how many 'struct fiemap_extent' elements fit the buffer
-        self._buf_size -= _FIEMAP_SIZE
-        self._fiemap_extent_cnt = self._buf_size // _FIEMAP_EXTENT_SIZE
-        assert self._fiemap_extent_cnt > 0
-        self._buf_size = self._fiemap_extent_cnt * _FIEMAP_EXTENT_SIZE
-        self._buf_size += _FIEMAP_SIZE
-
-        # Allocate a mutable buffer for the FIEMAP ioctl
-        self._buf = array.array('B', [0] * self._buf_size)
-
-        # Check if the FIEMAP ioctl is supported
-        self.block_is_mapped(0)
-
     def __del__(self):
         """The class destructor which just closes the image file."""
         if self._f_image_needs_close:
@@ -165,6 +128,240 @@ class FilemapFiemap:
 
         self._f_image_needs_close = True
 
+    def block_is_mapped(self, block): # pylint: disable=W0613,R0201
+        """
+        This method has has to be implemented by child classes. It returns
+        'True' if block number 'block' of the image file is mapped and 'False'
+        otherwise.
+        """
+
+        raise Error("the method is not implemented")
+
+    def block_is_unmapped(self, block): # pylint: disable=W0613,R0201
+        """
+        This method has has to be implemented by child classes. It returns
+        'True' if block number 'block' of the image file is not mapped (hole)
+        and 'False' otherwise.
+        """
+
+        raise Error("the method is not implemented")
+
+    def get_mapped_ranges(self, start, count): # pylint: disable=W0613,R0201
+        """
+        This method has has to be implemented by child classes. This is a
+        generator which yields ranges of mapped blocks in the file. The ranges
+        are tuples of 2 elements: [first, last], where 'first' is the first
+        mapped block and 'last' is the last mapped block.
+
+        The ranges are yielded for the area of the file of size 'count' blocks,
+        starting from block 'start'.
+        """
+
+        raise Error("the method is not implemented")
+
+    def get_unmapped_ranges(self, start, count): # pylint: disable=W0613,R0201
+        """
+        This method has has to be implemented by child classes. Just like
+        'get_mapped_ranges()', but yields unmapped block ranges instead
+        (holes).
+        """
+
+        raise Error("the method is not implemented")
+
+
+# The 'SEEK_HOLE' and 'SEEK_DATA' options of the file seek system call
+_SEEK_DATA = 3
+_SEEK_HOLE = 4
+
+def _lseek(file_obj, offset, whence):
+    """This is a helper function which invokes 'os.lseek' for file object
+    'file_obj' and with specified 'offset' and 'whence'. The 'whence'
+    argument is supposed to be either '_SEEK_DATA' or '_SEEK_HOLE'. When
+    there is no more data or hole starting from 'offset', this function
+    returns '-1'.  Otherwise the data or hole position is returned."""
+
+    try:
+        return os.lseek(file_obj.fileno(), offset, whence)
+    except OSError as err:
+        # The 'lseek' system call returns the ENXIO if there is no data or
+        # hole starting from the specified offset.
+        if err.errno == os.errno.ENXIO:
+            return -1
+        elif err.errno == os.errno.EINVAL:
+            raise ErrorNotSupp("the kernel or file-system does not support "
+                               "\"SEEK_HOLE\" and \"SEEK_DATA\"")
+        else:
+            raise
+
+class FilemapSeek(_FilemapBase):
+    """
+    This class uses the 'SEEK_HOLE' and 'SEEK_DATA' to find file block mapping.
+    Unfortunately, the current implementation requires the caller to have write
+    access to the image file.
+    """
+
+    def __init__(self, image, log=None):
+        """Refer the '_FilemapBase' class for the documentation."""
+
+        # Call the base class constructor first
+        _FilemapBase.__init__(self, image, log)
+        self._log.debug("FilemapSeek: initializing")
+
+        self._probe_seek_hole()
+
+    def _probe_seek_hole(self):
+        """
+        Check whether the system implements 'SEEK_HOLE' and 'SEEK_DATA'.
+        Unfortunately, there seems to be no clean way for detecting this,
+        because often the system just fakes them by just assuming that all
+        files are fully mapped, so 'SEEK_HOLE' always returns EOF and
+        'SEEK_DATA' always returns the requested offset.
+
+        I could not invent a better way of detecting the fake 'SEEK_HOLE'
+        implementation than just to create a temporary file in the same
+        directory where the image file resides. It would be nice to change this
+        to something better.
+        """
+
+        directory = os.path.dirname(self._image_path)
+
+        try:
+            tmp_obj = tempfile.TemporaryFile("w+", dir=directory)
+        except IOError as err:
+            raise ErrorNotSupp("cannot create a temporary in \"%s\": %s"
+                              % (directory, err))
+
+        try:
+            os.ftruncate(tmp_obj.fileno(), self.block_size)
+        except OSError as err:
+            raise ErrorNotSupp("cannot truncate temporary file in \"%s\": %s"
+                               % (directory, err))
+
+        offs = _lseek(tmp_obj, 0, _SEEK_HOLE)
+        if offs != 0:
+            # We are dealing with the stub 'SEEK_HOLE' implementation which
+            # always returns EOF.
+            self._log.debug("lseek(0, SEEK_HOLE) returned %d" % offs)
+            raise ErrorNotSupp("the file-system does not support "
+                               "\"SEEK_HOLE\" and \"SEEK_DATA\" but only "
+                               "provides a stub implementation")
+
+        tmp_obj.close()
+
+    def block_is_mapped(self, block):
+        """Refer the '_FilemapBase' class for the documentation."""
+        offs = _lseek(self._f_image, block * self.block_size, _SEEK_DATA)
+        if offs == -1:
+            result = False
+        else:
+            result = (offs // self.block_size == block)
+
+        self._log.debug("FilemapSeek: block_is_mapped(%d) returns %s"
+                        % (block, result))
+        return result
+
+    def block_is_unmapped(self, block):
+        """Refer the '_FilemapBase' class for the documentation."""
+        return not self.block_is_mapped(block)
+
+    def _get_ranges(self, start, count, whence1, whence2):
+        """
+        This function implements 'get_mapped_ranges()' and
+        'get_unmapped_ranges()' depending on what is passed in the 'whence1'
+        and 'whence2' arguments.
+        """
+
+        assert whence1 != whence2
+        end = start * self.block_size
+        limit = end + count * self.block_size
+
+        while True:
+            start = _lseek(self._f_image, end, whence1)
+            if start == -1 or start >= limit or start == self.image_size:
+                break
+
+            end = _lseek(self._f_image, start, whence2)
+            if end == -1 or end == self.image_size:
+                end = self.blocks_cnt * self.block_size
+            if end > limit:
+                end = limit
+
+            start_blk = start // self.block_size
+            end_blk = end // self.block_size - 1
+            self._log.debug("FilemapSeek: yielding range (%d, %d)"
+                            % (start_blk, end_blk))
+            yield (start_blk, end_blk)
+
+    def get_mapped_ranges(self, start, count):
+        """Refer the '_FilemapBase' class for the documentation."""
+        self._log.debug("FilemapSeek: get_mapped_ranges(%d,  %d(%d))"
+                        % (start, count, start + count - 1))
+        return self._get_ranges(start, count, _SEEK_DATA, _SEEK_HOLE)
+
+    def get_unmapped_ranges(self, start, count):
+        """Refer the '_FilemapBase' class for the documentation."""
+        self._log.debug("FilemapSeek: get_unmapped_ranges(%d,  %d(%d))"
+                        % (start, count, start + count - 1))
+        return self._get_ranges(start, count, _SEEK_HOLE, _SEEK_DATA)
+
+
+# Below goes the FIEMAP ioctl implementation, which is not very readable
+# because it deals with the rather complex FIEMAP ioctl. To understand the
+# code, you need to know the FIEMAP interface, which is documented in the
+# "Documentation/filesystems/fiemap.txt" file in the Linux kernel sources.
+
+# Format string for 'struct fiemap'
+_FIEMAP_FORMAT = "=QQLLLL"
+# sizeof(struct fiemap)
+_FIEMAP_SIZE = struct.calcsize(_FIEMAP_FORMAT)
+# Format string for 'struct fiemap_extent'
+_FIEMAP_EXTENT_FORMAT = "=QQQQQLLLL"
+# sizeof(struct fiemap_extent)
+_FIEMAP_EXTENT_SIZE = struct.calcsize(_FIEMAP_EXTENT_FORMAT)
+# The FIEMAP ioctl number
+_FIEMAP_IOCTL = 0xC020660B
+# This FIEMAP ioctl flag which instructs the kernel to sync the file before
+# reading the block map
+_FIEMAP_FLAG_SYNC = 0x00000001
+# Size of the buffer for 'struct fiemap_extent' elements which will be used
+# when invoking the FIEMAP ioctl. The larger is the buffer, the less times the
+# FIEMAP ioctl will be invoked.
+_FIEMAP_BUFFER_SIZE = 256 * 1024
+
+class FilemapFiemap(_FilemapBase):
+    """
+    This class provides API to the FIEMAP ioctl. Namely, it allows to iterate
+    over all mapped blocks and over all holes.
+
+    This class synchronizes the image file every time it invokes the FIEMAP
+    ioctl in order to work-around early FIEMAP implementation kernel bugs.
+    """
+
+    def __init__(self, image, log=None):
+        """
+        Initialize a class instance. The 'image' argument is full the file
+        object to operate on.
+        """
+
+        # Call the base class constructor first
+        _FilemapBase.__init__(self, image, log)
+        self._log.debug("FilemapFiemap: initializing")
+
+        self._buf_size = _FIEMAP_BUFFER_SIZE
+
+        # Calculate how many 'struct fiemap_extent' elements fit the buffer
+        self._buf_size -= _FIEMAP_SIZE
+        self._fiemap_extent_cnt = self._buf_size // _FIEMAP_EXTENT_SIZE
+        assert self._fiemap_extent_cnt > 0
+        self._buf_size = self._fiemap_extent_cnt * _FIEMAP_EXTENT_SIZE
+        self._buf_size += _FIEMAP_SIZE
+
+        # Allocate a mutable buffer for the FIEMAP ioctl
+        self._buf = array.array('B', [0] * self._buf_size)
+
+        # Check if the FIEMAP ioctl is supported
+        self.block_is_mapped(0)
+
     def _invoke_fiemap(self, block, count):
         """
         Invoke the FIEMAP ioctl for 'count' blocks of the file starting from
@@ -318,10 +515,24 @@ class FilemapFiemap:
                             % (hole_first, start + count - 1))
             yield (hole_first, start + count - 1)
 
+def filemap(image, log=None):
+    """
+    Create and return an instance of a Filemap class - 'FilemapFiemap' or
+    'FilemapSeek', depending on what the system we run on supports. If the
+    FIEMAP ioctl is supported, an instance of the 'FilemapFiemap' class is
+    returned. Otherwise, if 'SEEK_HOLE' is supported an instance of the
+    'FilemapSeek' class is returned. If none of these are supported, the
+    function generates an 'Error' type exception.
+    """
+
+    try:
+        return FilemapFiemap(image, log)
+    except ErrorNotSupp:
+        return FilemapSeek(image, log)
 
 def sparse_copy(src_fname, dst_fname, offset=0, skip=0):
     """Efficiently copy sparse file to or into another file."""
-    fmap = FilemapFiemap(src_fname)
+    fmap = filemap(src_fname)
     try:
         dst_file = open(dst_fname, 'r+b')
     except IOError: