Fix taint hybrid-checking on BSD

[exim.git] / src / src / store.c

diff --git a/src/src/store.c b/src/src/store.c
index a06e1c19afd1035a804d005cf0b9ff7142d0b562..1fe97e6c9897f0ef7116561da1d483cb3e39fa2f 100644 (file)
--- a/src/src/store.c
+++ b/src/src/store.c
@@ -41,8 +41,32 @@ The following different types of store are recognized:
   and tainted.  The latter is used for values derived from untrusted input, and
   the string-expansion mechanism refuses to operate on such values (obviously,
   it can expand an untainted value to return a tainted result).  The classes
   and tainted.  The latter is used for values derived from untrusted input, and
   the string-expansion mechanism refuses to operate on such values (obviously,
   it can expand an untainted value to return a tainted result).  The classes

-  are implemented by duplicating the three pool types. Pool resets are requested
+  are implemented by duplicating the three pool types.  Pool resets are requested

   against the nontainted sibling and apply to both siblings.
   against the nontainted sibling and apply to both siblings.

+
+  Only memory blocks requested for tainted use are regarded as tainted; anything
+  else (including stack auto variables) is untainted.  Care is needed when coding
+  to not copy untrusted data into untainted memory, as downstream taint-checks
+  would be avoided.
+
+  Internally we currently use malloc for nontainted pools, and mmap for tainted
+  pools.  The disparity is for speed of testing the taintedness of pointers;
+  because Linux appears to use distinct non-overlapping address allocations for
+  mmap vs. everything else, which means only two pointer-compares suffice for the
+  test.  Other OS' cannot use that optimisation, and a more lengthy test against
+  the limits of tainted-pool allcations has to be done.
+
+  Intermediate layers (eg. the string functions) can test for taint, and use this
+  for ensurinng that results have proper state.  For example the
+  string_vformat_trc() routing supporting the string_sprintf() interface will
+  recopy a string being built into a tainted allocation if it meets a %s for a
+  tainted argument.  Any intermediate-layer function that (can) return a new
+  allocation should behave this way; returning a tainted result if any tainted
+  content is used.  Intermediate-layer functions (eg. Ustrncpy) that modify
+  existing allocations fail if tainted data is written into an untainted area.
+  Users of functions that modify existing allocations should check if a tainted
+  source and an untainted destination is used, and fail instead (sprintf() being
+  the classic case).

 */
 
 
 */
 
 


@@ -162,32 +186,34 @@ static void   internal_tainted_free(storeblock *, const char *, int linenumber);
 
 /******************************************************************************/
 
 
 /******************************************************************************/
 

-/* Slower version check, for use when platform intermixes malloc and mmap area
-addresses. */
+/* Test if a pointer refers to tainted memory.
+
+Slower version check, for use when platform intermixes malloc and mmap area
+addresses. Test against the current-block of all tainted pools first, then all
+blocks of all tainted pools.
+
+Return: TRUE iff tainted
+*/

 
 BOOL
 is_tainted_fn(const void * p)
 {
 storeblock * b;
 
 BOOL
 is_tainted_fn(const void * p)
 {
 storeblock * b;

-int pool;

 
 

-for (pool = 0; pool < nelem(chainbase); pool++)
+for (int pool = POOL_TAINT_BASE; pool < nelem(chainbase); pool++)

   if ((b = current_block[pool]))
     {
   if ((b = current_block[pool]))
     {

-    char * bc = CS b + ALIGNED_SIZEOF_STOREBLOCK;
-    if (CS p >= bc && CS p <= bc + b->length) goto hit;
+    uschar * bc = US b + ALIGNED_SIZEOF_STOREBLOCK;
+    if (US p >= bc && US p <= bc + b->length) return TRUE;

     }
 
     }
 

-for (pool = 0; pool < nelem(chainbase); pool++)
+for (int pool = POOL_TAINT_BASE; pool < nelem(chainbase); pool++)

   for (b = chainbase[pool]; b; b = b->next)
     {
   for (b = chainbase[pool]; b; b = b->next)
     {

-    char * bc = CS b + ALIGNED_SIZEOF_STOREBLOCK;
-    if (CS p >= bc && CS p <= bc + b->length) goto hit;
+    uschar * bc = US b + ALIGNED_SIZEOF_STOREBLOCK;
+    if (US p >= bc && US p <= bc + b->length) return TRUE;

     }
 return FALSE;
     }
 return FALSE;

-
-hit:
-return pool >= POOL_TAINT_BASE;

 }
 
 
 }
 
 


@@ -198,6 +224,31 @@ log_write(0, LOG_MAIN|LOG_PANIC_DIE, "Taint mismatch, %s: %s %d\n",
        msg, func, line);
 }
 
        msg, func, line);
 }
 

+static void
+use_slow_taint_check(void)
+{
+#ifndef COMPILE_UTILITY
+DEBUG(D_any) debug_printf("switching to slow-mode taint checking\n");
+#endif
+f.taint_check_slow = TRUE;
+}
+
+static void
+verify_all_untainted(void)
+{
+for (int pool = 0; pool < POOL_TAINT_BASE; pool++)
+  for (storeblock * b = chainbase[pool]; b; b = b->next)
+    {
+    uschar * bc = US b + ALIGNED_SIZEOF_STOREBLOCK;
+    if (is_tainted(bc))
+      {
+      use_slow_taint_check();
+      return;
+      }
+    }
+}
+
+

 
 /*************************************************
 *       Get a block from the current pool        *
 
 /*************************************************
 *       Get a block from the current pool        *


@@ -209,7 +260,8 @@ block, getting a new one if necessary. The address is saved in
 store_last_was_get.
 
 Arguments:
 store_last_was_get.
 
 Arguments:

-  size        amount wanted
+  size        amount wanted, bytes
+  tainted     class: set to true for untrusted data (eg. from smtp input)

   func        function from which called
   linenumber  line number in source file
 
   func        function from which called
   linenumber  line number in source file
 


@@ -730,7 +782,7 @@ int pool = tainted ? store_pool + POOL_TAINT_BASE : store_pool;
 BOOL release_ok = !tainted && store_last_get[pool] == block;
 uschar * newtext;
 
 BOOL release_ok = !tainted && store_last_get[pool] == block;
 uschar * newtext;
 

-#ifndef MACRO_PREDEF
+#if !defined(MACRO_PREDEF) && !defined(COMPILE_UTILITY)

 if (is_tainted(block) != tainted)
   die_tainted(US"store_newblock", CUS func, linenumber);
 #endif
 if (is_tainted(block) != tainted)
   die_tainted(US"store_newblock", CUS func, linenumber);
 #endif


@@ -789,6 +841,7 @@ if (!(yield = mmap(NULL, (size_t)size,
 
 if (yield < tainted_base) tainted_base = yield;
 if ((top = US yield + size) > tainted_top) tainted_top = top;
 
 if (yield < tainted_base) tainted_base = yield;
 if ((top = US yield + size) > tainted_top) tainted_top = top;

+if (!f.taint_check_slow) use_slow_taint_check();

 
 return store_alloc_tail(yield, size, func, line, US"Mmap");
 }
 
 return store_alloc_tail(yield, size, func, line, US"Mmap");
 }


@@ -820,6 +873,14 @@ if (!(yield = malloc((size_t)size)))
   log_write(0, LOG_MAIN|LOG_PANIC_DIE, "failed to malloc %d bytes of memory: "
     "called from line %d in %s", size, linenumber, func);
 
   log_write(0, LOG_MAIN|LOG_PANIC_DIE, "failed to malloc %d bytes of memory: "
     "called from line %d in %s", size, linenumber, func);
 

+/* If malloc ever returns apparently tainted memory, which glibc
+malloc will as it uses mmap for larger requests, we must switch to
+the slower checking for tainting (checking an address against all
+the tainted pool block spans, rather than just the mmap span) */
+
+if (!f.taint_check_slow && is_tainted(yield))
+  use_slow_taint_check();
+

 return store_alloc_tail(yield, size, func, linenumber, US"Malloc");
 }
 
 return store_alloc_tail(yield, size, func, linenumber, US"Malloc");
 }