rev: Update rop gadget search functionality

Development on the rop chain builder has produced this upgrade to our
gadget search facility.  The primary advantages in this version are
increased flexibility and runtime performance.

It is now easier to find specific 'stray' instructions (not immediately
followed by a ret) since we search from every position in the data
returned by r2.  If you _do_ want a ret, just specify it in your input
regexes.  For this reason, a dedicated function for locating a simple
'ret' gadget is no longer present - elf.gadget("ret") is the equivalent.

A major change in this version is that we now obtain and operate on r2's
JSON representation of the gadget data.  We now only reach out to r2
once to get all information for a binary (which is cached) and the
actual 'search' is implemented in Python.  This provides a significant
performance speedup in cases where we need many gadgets from one binary,
as r2 doesn't need to inspect the entire file each time.  Additional
caching is done on specific search results, so that 100% redundant
searches are returned immediately.  Access to the raw JSON data is made
available through a new function rop_json(), but is not exposed in the
ELF interface, since it seems like a niche need.

Search results are returned via Gadget objects (or a list thereof),
which contain regular expression Match objects for each assembly
instruction found in the gadget.  This allows the caller to retrieve the
values contained in regular expression capture groups if present.

Also, anecdotally, the search functionality in r2 has seemed to return
false negatives for some queries in the past, whereas I haven't noticed
similar cases with this implementation yet.

Signed-off-by: Malfurious <m@lfurio.us>
Signed-off-by: dusoleil <howcansocksbereal@gmail.com>

2 files changed, 61 insertions, 32 deletions

diff --git a/sploit/rev/elf.py b/sploit/rev/elf.py
index 78f4e47..d173897 100644
--- a/sploit/rev/elf.py
+++ b/sploit/rev/elf.py
@@ -44,11 +44,8 @@ class ELF:
     def retaddr(self, caller, callee):
         return [c.ret_addr for c in r2.get_call_returns(self.path, caller, callee)]
 
-    def retgad(self):
-        return r2.ret_gadget(self.path)
+    def gadgets(self, *regexes, cont=False):
+        return r2.rop_gadgets(self.path, *regexes, cont=cont)
 
-    def gad(self, gad):
-        return [g.addr for g in r2.rop_gadget(self.path, gad)]
-
-    def egad(self, gad):
-        return r2.rop_gadget_exact(self.path, gad).addr
+    def gadget(self, *regexes):
+        return r2.rop_gadget(self.path, *regexes)
diff --git a/sploit/rev/r2.py b/sploit/rev/r2.py
index 7fe57d8..f2650da 100644
--- a/sploit/rev/r2.py
+++ b/sploit/rev/r2.py
@@ -1,10 +1,13 @@
 from sploit.arch import arch
 from sploit.log import ilog
+from sploit.rev.gadget import Gadget
 from sploit.symtbl import Symtbl
 from sploit.util import run_cmd_cached
 
-import re
 from collections import namedtuple as nt
+from functools import cache
+import json
+import re
 
 def run_cmd(binary,cmd):
     return run_cmd_cached(['r2','-q','-c',cmd,'-e','scr.color=false',binary])
@@ -56,30 +59,59 @@ def get_locals(binary,func):
     out = {var[1]:-(int(var[0],0)-arch.wordsize) for var in out}
     return Symtbl(sbp=0, **out)
 
-def ret_gadget(binary):
-    ilog(f'Searching for a ret gadget in {binary} with r2...')
-
-    cmd_ret = '/R/ ret~ret'
-    out = run_cmd(binary,cmd_ret)
-    out = out[0]
-    out = re.split(r'\s+',out)
-    out = out[1]
-    return int(out,0)
-
-def rop_gadget(binary,gad):
-    ilog(f'Searching for "{gad}" gadgets in {binary} with r2...')
-
-    cmd_gad = f'"/R/q {gad}"'
-    out = run_cmd(binary,cmd_gad)
-    Gad = nt("Gad", "addr asm")
-    out = [Gad(int(gad[:gad.find(':')],0),gad[gad.find(':')+2:]) for gad in out]
-    return out
-
-def rop_gadget_exact(binary,gad):
-    gads = rop_gadget(binary,gad)
-    for g in gads:
-        if g.asm[:-1].replace('; ',';') == gad:
-            return g
+def rop_json(binary):
+    # Gadget JSON schema:
+    # [
+    #   {
+    #     retaddr: int
+    #     size: int
+    #     opcodes: [
+    #       {
+    #         offset: int
+    #         size: int
+    #         opcode: string
+    #         type: string
+    #       }
+    #     ]
+    #   }
+    # ]
+    return json.loads("\n".join(run_cmd(binary, "/Rj")))
+
+@cache
+def rop_gadgets(binary, *regexes, cont=False):
+    ilog(f"Searching {binary} for {'; '.join(regexes)} gadgets with r2...")
+    gadgets = rop_json(binary)
+    results = []
+
+    for gadget in gadgets:
+        opcodes = gadget['opcodes']
+        end_idx = len(opcodes) - len(regexes)
+
+        for start_idx in range(end_idx + 1):
+            idx = start_idx
+            size = end_idx - idx
+            regexes_use = (regexes + (".*",) * size) if cont else regexes
+
+            offset = opcodes[idx]['offset']
+            matches = []
+
+            for regex in regexes_use:
+                match = re.fullmatch(regex, opcodes[idx]['opcode'])
+                if not match:
+                    break
+                matches.append(match)
+                idx += 1
+
+            if len(matches) == len(regexes_use):
+                results.append(Gadget(offset, matches))
+
+    return results
+
+def rop_gadget(binary, *regexes):
+    results = rop_gadgets(binary, *regexes)
+    if len(results) == 0:
+        raise LookupError(f"Could not find gadget for: {'; '.join(regexes)}")
+    return results[0]
 
 def get_call_returns(binary,xref_from,xref_to):
     ilog(f'Getting return addresses of calls from {hex(xref_from)} to {hex(xref_to)} in {binary} with r2...')