Enable sanitization for hash tables.

2019-06-07  Martin Liska  <mliska@suse.cz>

	* cselib.c (cselib_init): Disable hash table
	sanitization.
	* hash-set.h: Pass new default argument to m_table.
	* hash-table.c: Add global variable with hash table
	sanitization limit.
	* hash-table.h (Allocator>::hash_table): Add new argument
	to ctor.
	(hashtab_chk_error): New.
	* params.def (PARAM_HASH_TABLE_VERIFICATION_LIMIT): New.
	* toplev.c (process_options): Set hash_table_sanitize_eq_limit
	from the PARAM_HASH_TABLE_VERIFICATION_LIMIT value.

From-SVN: r272038

7 files changed, 91 insertions, 7 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index dbcf512..a1cffe1 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,17 @@
+2019-06-07  Martin Liska  <mliska@suse.cz>
+
+	* cselib.c (cselib_init): Disable hash table
+	sanitization.
+	* hash-set.h: Pass new default argument to m_table.
+	* hash-table.c: Add global variable with hash table
+	sanitization limit.
+	* hash-table.h (Allocator>::hash_table): Add new argument
+	to ctor.
+	(hashtab_chk_error): New.
+	* params.def (PARAM_HASH_TABLE_VERIFICATION_LIMIT): New.
+	* toplev.c (process_options): Set hash_table_sanitize_eq_limit
+	from the PARAM_HASH_TABLE_VERIFICATION_LIMIT value.
+
 2019-06-07  Jan Hubicka  <hubicka@ucw.cz>
 
 	* common.opt (flto-odr-type-merging): Ignore.
diff --git a/gcc/cselib.c b/gcc/cselib.c
index 84c17c2..a1cbdec 100644
--- a/gcc/cselib.c
+++ b/gcc/cselib.c
@@ -2858,9 +2858,14 @@ cselib_init (int record_what)
     }
   used_regs = XNEWVEC (unsigned int, cselib_nregs);
   n_used_regs = 0;
-  cselib_hash_table = new hash_table<cselib_hasher> (31);
+  /* FIXME: enable sanitization (PR87845) */
+  cselib_hash_table
+    = new hash_table<cselib_hasher> (31, /* ggc */ false,
+				     /* sanitize_eq_and_hash */ false);
   if (cselib_preserve_constants)
-    cselib_preserved_hash_table = new hash_table<cselib_hasher> (31);
+    cselib_preserved_hash_table
+      = new hash_table<cselib_hasher> (31, /* ggc */ false,
+				       /* sanitize_eq_and_hash */ false);
   next_uid = 1;
 }
 
diff --git a/gcc/hash-set.h b/gcc/hash-set.h
index de3532f..d891ed7 100644
--- a/gcc/hash-set.h
+++ b/gcc/hash-set.h
@@ -28,7 +28,7 @@ class hash_set
 public:
   typedef typename Traits::value_type Key;
   explicit hash_set (size_t n = 13, bool ggc = false CXX_MEM_STAT_INFO)
-    : m_table (n, ggc, GATHER_STATISTICS, HASH_SET_ORIGIN PASS_MEM_STAT) {}
+    : m_table (n, ggc, true, GATHER_STATISTICS, HASH_SET_ORIGIN PASS_MEM_STAT) {}
 
   /* Create a hash_set in gc memory with space for at least n elements.  */
 
diff --git a/gcc/hash-table.c b/gcc/hash-table.c
index 646a7a1..8e86fff 100644
--- a/gcc/hash-table.c
+++ b/gcc/hash-table.c
@@ -74,6 +74,9 @@ struct prime_ent const prime_tab[] = {
   { 0xfffffffb, 0x00000006, 0x00000008, 31 }
 };
 
+/* Limit number of comparisons when calling hash_table<>::verify.  */
+unsigned int hash_table_sanitize_eq_limit;
+
 /* The following function returns an index into the above table of the
    nearest prime number which is greater than N, and near a power of two. */
 
diff --git a/gcc/hash-table.h b/gcc/hash-table.h
index 4178616..686a13d 100644
--- a/gcc/hash-table.h
+++ b/gcc/hash-table.h
@@ -295,6 +295,8 @@ struct prime_ent
 
 extern struct prime_ent const prime_tab[];
 
+/* Limit number of comparisons when calling hash_table<>::verify.  */
+extern unsigned int hash_table_sanitize_eq_limit;
 
 /* Functions for computing hash table indexes.  */
 
@@ -371,10 +373,12 @@ class hash_table
 
 public:
   explicit hash_table (size_t, bool ggc = false,
+		       bool sanitize_eq_and_hash = true,
 		       bool gather_mem_stats = GATHER_STATISTICS,
 		       mem_alloc_origin origin = HASH_TABLE_ORIGIN
 		       CXX_MEM_STAT_INFO);
   explicit hash_table (const hash_table &, bool ggc = false,
+		       bool sanitize_eq_and_hash = true,
 		       bool gather_mem_stats = GATHER_STATISTICS,
 		       mem_alloc_origin origin = HASH_TABLE_ORIGIN
 		       CXX_MEM_STAT_INFO);
@@ -516,6 +520,7 @@ private:
 
   value_type *alloc_entries (size_t n CXX_MEM_STAT_INFO) const;
   value_type *find_empty_slot_for_expand (hashval_t);
+  void verify (const compare_type &comparable, hashval_t hash);
   bool too_empty_p (unsigned int);
   void expand ();
   static bool is_deleted (value_type &v)
@@ -564,6 +569,9 @@ private:
   /* if m_entries is stored in ggc memory.  */
   bool m_ggc;
 
+  /* True if the table should be sanitized for equal and hash functions.  */
+  bool m_sanitize_eq_and_hash;
+
   /* If we should gather memory statistics for the table.  */
 #if GATHER_STATISTICS
   bool m_gather_mem_stats;
@@ -586,12 +594,13 @@ extern void dump_hash_table_loc_statistics (void);
 template<typename Descriptor, bool Lazy,
 	 template<typename Type> class Allocator>
 hash_table<Descriptor, Lazy, Allocator>::hash_table (size_t size, bool ggc,
+						     bool sanitize_eq_and_hash,
 						     bool gather_mem_stats
 						     ATTRIBUTE_UNUSED,
 						     mem_alloc_origin origin
 						     MEM_STAT_DECL) :
   m_n_elements (0), m_n_deleted (0), m_searches (0), m_collisions (0),
-  m_ggc (ggc)
+  m_ggc (ggc), m_sanitize_eq_and_hash (sanitize_eq_and_hash)
 #if GATHER_STATISTICS
   , m_gather_mem_stats (gather_mem_stats)
 #endif
@@ -617,12 +626,14 @@ template<typename Descriptor, bool Lazy,
 	 template<typename Type> class Allocator>
 hash_table<Descriptor, Lazy, Allocator>::hash_table (const hash_table &h,
 						     bool ggc,
+						     bool sanitize_eq_and_hash,
 						     bool gather_mem_stats
 						     ATTRIBUTE_UNUSED,
 						     mem_alloc_origin origin
 						     MEM_STAT_DECL) :
   m_n_elements (h.m_n_elements), m_n_deleted (h.m_n_deleted),
-  m_searches (0), m_collisions (0), m_ggc (ggc)
+  m_searches (0), m_collisions (0), m_ggc (ggc),
+  m_sanitize_eq_and_hash (sanitize_eq_and_hash)
 #if GATHER_STATISTICS
   , m_gather_mem_stats (gather_mem_stats)
 #endif
@@ -912,7 +923,13 @@ hash_table<Descriptor, Lazy, Allocator>
       entry = &m_entries[index];
       if (is_empty (*entry)
           || (!is_deleted (*entry) && Descriptor::equal (*entry, comparable)))
-        return *entry;
+	{
+#if CHECKING_P
+	  if (m_sanitize_eq_and_hash)
+	    verify (comparable, hash);
+#endif
+	  return *entry;
+	}
     }
 }
 
@@ -941,8 +958,12 @@ hash_table<Descriptor, Lazy, Allocator>
   if (insert == INSERT && m_size * 3 <= m_n_elements * 4)
     expand ();
 
-  m_searches++;
+#if CHECKING_P
+  if (m_sanitize_eq_and_hash)
+    verify (comparable, hash);
+#endif
 
+  m_searches++;
   value_type *first_deleted_slot = NULL;
   hashval_t index = hash_table_mod1 (hash, m_size_prime_index);
   hashval_t hash2 = hash_table_mod2 (hash, m_size_prime_index);
@@ -989,6 +1010,37 @@ hash_table<Descriptor, Lazy, Allocator>
   return &m_entries[index];
 }
 
+/* Report a hash table checking error.  */
+
+ATTRIBUTE_NORETURN ATTRIBUTE_COLD
+static void
+hashtab_chk_error ()
+{
+  fprintf (stderr, "hash table checking failed: "
+	   "equal operator returns true for a pair "
+	   "of values with a different hash value\n");
+  gcc_unreachable ();
+}
+
+/* Verify that all existing elements in th hash table which are
+   equal to COMPARABLE have an equal HASH value provided as argument.  */
+
+template<typename Descriptor, bool Lazy,
+	 template<typename Type> class Allocator>
+void
+hash_table<Descriptor, Lazy, Allocator>
+::verify (const compare_type &comparable, hashval_t hash)
+{
+  for (size_t i = 0; i < MIN (hash_table_sanitize_eq_limit, m_size); i++)
+    {
+      value_type *entry = &m_entries[i];
+      if (!is_empty (*entry) && !is_deleted (*entry)
+	  && hash != Descriptor::hash (*entry)
+	  && Descriptor::equal (*entry, comparable))
+	hashtab_chk_error ();
+    }
+}
+
 /* This function deletes an element with the given COMPARABLE value
    from hash table starting with the given HASH.  If there is no
    matching element in the hash table, this function does nothing. */
diff --git a/gcc/params.def b/gcc/params.def
index b4a4e4a..0db6095 100644
--- a/gcc/params.def
+++ b/gcc/params.def
@@ -1431,6 +1431,12 @@ DEFPARAM(PARAM_GIMPLE_FE_COMPUTED_HOT_BB_THRESHOLD,
 	 " The parameter is used only in GIMPLE FE.",
 	 0, 0, 0)
 
+DEFPARAM(PARAM_HASH_TABLE_VERIFICATION_LIMIT,
+	 "hash-table-verification-limit",
+	 "The number of elements for which hash table verification is done for "
+	 "each searched element.",
+	 100, 0, 0)
+
 /*
 
 Local variables:
diff --git a/gcc/toplev.c b/gcc/toplev.c
index d300ac2..116be7b 100644
--- a/gcc/toplev.c
+++ b/gcc/toplev.c
@@ -1799,6 +1799,10 @@ process_options (void)
   optimization_default_node = build_optimization_node (&global_options);
   optimization_current_node = optimization_default_node;
 
+  if (flag_checking >= 2)
+    hash_table_sanitize_eq_limit
+      = PARAM_VALUE (PARAM_HASH_TABLE_VERIFICATION_LIMIT);
+
   /* Please don't change global_options after this point, those changes won't
      be reflected in optimization_{default,current}_node.  */
 }