[PATCH][V2] lib/oe/qa: handle binaries with segments outside the first 4kb

[PATCH][V2] lib/oe/qa: handle binaries with segments outside the first 4kb

[Ross Burton]

The ELF parser was assuming that the segment tables are in the first 4kb of the
binary.  Whilst this generally appears to be the case, there have been instances
where the segment table is elsewhere (offset 2MB, in this sample I have).  Solve
this problem by mmap()ing the file instead.

Also clean up the code a little whilst chasing the problem.

Signed-off-by: Ross Burton <ross.burton@intel.com>
---
 meta/lib/oe/qa.py | 82 +++++++++++++++++++++++++++----------------------------
 1 file changed, 41 insertions(+), 41 deletions(-)

diff --git a/meta/lib/oe/qa.py b/meta/lib/oe/qa.py
index fbe719d..22d76dc 100644
--- a/meta/lib/oe/qa.py
+++ b/meta/lib/oe/qa.py
@@ -1,4 +1,4 @@
-import os, struct
+import os, struct, mmap
 
 class NotELFFileError(Exception):
     pass
@@ -23,9 +23,9 @@ class ELFFile:
     EV_CURRENT   = 1
 
     # possible values for EI_DATA
-    ELFDATANONE  = 0
-    ELFDATA2LSB  = 1
-    ELFDATA2MSB  = 2
+    EI_DATA_NONE  = 0
+    EI_DATA_LSB  = 1
+    EI_DATA_MSB  = 2
 
     PT_INTERP = 3
 
@@ -34,51 +34,46 @@ class ELFFile:
             #print "'%x','%x' %s" % (ord(expectation), ord(result), self.name)
             raise NotELFFileError("%s is not an ELF" % self.name)
 
-    def __init__(self, name, bits = 0):
+    def __init__(self, name):
         self.name = name
-        self.bits = bits
         self.objdump_output = {}
 
-    def open(self):
-        if not os.path.isfile(self.name):
-            raise NotELFFileError("%s is not a normal file" % self.name)
+    # Context Manager functions to close the mmap explicitly
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.data.close()
 
+    def open(self):
         with open(self.name, "rb") as f:
-            # Read 4k which should cover most of the headers we're after
-            self.data = f.read(4096)
+            try:
+                self.data = mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ)
+            except ValueError:
+                # This means the file is empty
+                raise NotELFFileError("%s is empty" % self.name)
 
+        # Check the file has the minimum number of ELF table entries
         if len(self.data) < ELFFile.EI_NIDENT + 4:
             raise NotELFFileError("%s is not an ELF" % self.name)
 
+        # ELF header
         self.my_assert(self.data[0], 0x7f)
         self.my_assert(self.data[1], ord('E'))
         self.my_assert(self.data[2], ord('L'))
         self.my_assert(self.data[3], ord('F'))
-        if self.bits == 0:
-            if self.data[ELFFile.EI_CLASS] == ELFFile.ELFCLASS32:
-                self.bits = 32
-            elif self.data[ELFFile.EI_CLASS] == ELFFile.ELFCLASS64:
-                self.bits = 64
-            else:
-                # Not 32-bit or 64.. lets assert
-                raise NotELFFileError("ELF but not 32 or 64 bit.")
-        elif self.bits == 32:
-            self.my_assert(self.data[ELFFile.EI_CLASS], ELFFile.ELFCLASS32)
-        elif self.bits == 64:
-            self.my_assert(self.data[ELFFile.EI_CLASS], ELFFile.ELFCLASS64)
+        if self.data[ELFFile.EI_CLASS] == ELFFile.ELFCLASS32:
+            self.bits = 32
+        elif self.data[ELFFile.EI_CLASS] == ELFFile.ELFCLASS64:
+            self.bits = 64
         else:
-            raise NotELFFileError("Must specify unknown, 32 or 64 bit size.")
+            # Not 32-bit or 64.. lets assert
+            raise NotELFFileError("ELF but not 32 or 64 bit.")
         self.my_assert(self.data[ELFFile.EI_VERSION], ELFFile.EV_CURRENT)
 
-        self.sex = self.data[ELFFile.EI_DATA]
-        if self.sex == ELFFile.ELFDATANONE:
-            raise NotELFFileError("self.sex == ELFDATANONE")
-        elif self.sex == ELFFile.ELFDATA2LSB:
-            self.sex = "<"
-        elif self.sex == ELFFile.ELFDATA2MSB:
-            self.sex = ">"
-        else:
-            raise NotELFFileError("Unknown self.sex")
+        self.endian = self.data[ELFFile.EI_DATA]
+        if self.endian not in (ELFFile.EI_DATA_LSB, ELFFile.EI_DATA_MSB):
+            raise NotELFFileError("Unexpected EI_DATA %x" % self.endian)
 
     def osAbi(self):
         return self.data[ELFFile.EI_OSABI]
@@ -90,16 +85,20 @@ class ELFFile:
         return self.bits
 
     def isLittleEndian(self):
-        return self.sex == "<"
+        return self.endian == ELFFile.EI_DATA_LSB
 
     def isBigEndian(self):
-        return self.sex == ">"
+        return self.endian == ELFFile.EI_DATA_MSB
+
+    def getStructEndian(self):
+        return {ELFFile.EI_DATA_LSB: "<",
+                ELFFile.EI_DATA_MSB: ">"}[self.endian]
 
     def getShort(self, offset):
-        return struct.unpack_from(self.sex+"H", self.data, offset)[0]
+        return struct.unpack_from(self.getStructEndian() + "H", self.data, offset)[0]
 
     def getWord(self, offset):
-        return struct.unpack_from(self.sex+"i", self.data, offset)[0]
+        return struct.unpack_from(self.getStructEndian() + "i", self.data, offset)[0]
 
     def isDynamic(self):
         """
@@ -118,7 +117,7 @@ class ELFFile:
 
     def machine(self):
         """
-        We know the sex stored in self.sex and we
+        We know the endian stored in self.endian and we
         know the position
         """
         return self.getShort(ELFFile.E_MACHINE)
@@ -166,6 +165,7 @@ def elf_machine_to_string(machine):
 
 if __name__ == "__main__":
     import sys
-    elf = ELFFile(sys.argv[1])
-    elf.open()
-    print(elf.isDynamic())
+
+    with ELFFile(sys.argv[1]) as elf:
+        elf.open()
+        print(elf.isDynamic())
-- 
2.8.1