fuzz: heuristic split write based on past IOs

If previous write commands write the same length of data with the same step,
we view it as a hint.

Signed-off-by: Qiuhao Li <Qiuhao.Li@outlook.com>
Reviewed-by: Alexander Bulekov <alxndr@bu.edu>
Tested-by: Alexander Bulekov <alxndr@bu.edu>
Message-Id: <SYCPR01MB3502480AD07811A6A49B8FEAFCAB0@SYCPR01MB3502.ausprd01.prod.outlook.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>

scripts/oss-fuzz/minimize_qtest_trace.py

@@ -88,6 +88,43 @@ def check_if_trace_crashes(trace, path):
     return False
 
 
+# If previous write commands write the same length of data at the same
+# interval, we view it as a hint.
+def split_write_hint(newtrace, i):
+    HINT_LEN = 3 # > 2
+    if i <=(HINT_LEN-1):
+        return None
+
+    #find previous continuous write traces
+    k = 0
+    l = i-1
+    writes = []
+    while (k != HINT_LEN and l >= 0):
+        if newtrace[l].startswith("write "):
+            writes.append(newtrace[l])
+            k += 1
+            l -= 1
+        elif newtrace[l] == "":
+            l -= 1
+        else:
+            return None
+    if k != HINT_LEN:
+        return None
+
+    length = int(writes[0].split()[2], 16)
+    for j in range(1, HINT_LEN):
+        if length != int(writes[j].split()[2], 16):
+            return None
+
+    step = int(writes[0].split()[1], 16) - int(writes[1].split()[1], 16)
+    for j in range(1, HINT_LEN-1):
+        if step != int(writes[j].split()[1], 16) - \
+            int(writes[j+1].split()[1], 16):
+            return None
+
+    return (int(writes[0].split()[1], 16)+step, length)
+
+
 def remove_lines(newtrace, outpath):
     remove_step = 1
     i = 0
@@ -151,6 +188,25 @@ def remove_lines(newtrace, outpath):
             length = int(newtrace[i].split()[2], 16)
             data = newtrace[i].split()[3][2:]
             if length > 1:
+
+                # Can we get a hint from previous writes?
+                hint = split_write_hint(newtrace, i)
+                if hint is not None:
+                    hint_addr = hint[0]
+                    hint_len = hint[1]
+                    if hint_addr >= addr and hint_addr+hint_len <= addr+length:
+                        newtrace[i] = "write {addr} {size} 0x{data}\n".format(
+                            addr=hex(hint_addr),
+                            size=hex(hint_len),
+                            data=data[(hint_addr-addr)*2:\
+                                (hint_addr-addr)*2+hint_len*2])
+                        if check_if_trace_crashes(newtrace, outpath):
+                            # next round
+                            i += 1
+                            continue
+                        newtrace[i] = prior[0]
+
+                # Try splitting it using a binary approach
                 leftlength = int(length/2)
                 rightlength = length - leftlength
                 newtrace.insert(i+1, "")