Fix potential integer overflow in hash container create/resize

derekmauro · copybara-github · commit 5a0e2cb5e395 · 2025-01-23T06:34:23.000-08:00
The sized constructors, reserve(), and rehash() methods of
absl::{flat,node}_hash_{set,map} did not impose an upper bound on
their size argument. As a result, it was possible for a caller to pass
a very large size that would cause an integer overflow when computing
the size of the container's backing store. Subsequent accesses to the
container might then access out-of-bounds memory.

The fix is in two parts:

1) Update max_size() to return the maximum number of items that can be
stored in the container

2) Validate the size arguments to the constructors, reserve(), and
rehash() methods, and abort the program when the argument is invalid

We've looked at uses of these containers in Google codebases like
Chrome, and determined this vulnerability is likely to be difficult to
exploit. This is primarily because container sizes are rarely
attacker-controlled.

The bug was discovered by Dmitry Vyukov &lt;dvyukov@google.com&gt;.

PiperOrigin-RevId: 718841870
Change-Id: Ic09dc9de140a35dbb45ab9d90f58383cf2de8286
diff --git a/absl/container/internal/raw_hash_set.cc b/absl/container/internal/raw_hash_set.cc
@@ -24,6 +24,7 @@
 #include "absl/base/config.h"
 #include "absl/base/dynamic_annotations.h"
 #include "absl/base/internal/endian.h"
+#include "absl/base/internal/raw_logging.h"
 #include "absl/base/optimization.h"
 #include "absl/container/internal/container_memory.h"
 #include "absl/container/internal/hashtablez_sampler.h"
@@ -661,6 +662,10 @@ size_t PrepareInsertNonSoo(CommonFields& common, size_t hash, FindInfo target,
   return target.offset;
 }
 
+void HashTableSizeOverflow() {
+  ABSL_RAW_LOG(FATAL, "Hash table size overflow");
+}
+
 }  // namespace container_internal
 ABSL_NAMESPACE_END
 }  // namespace absl
diff --git a/absl/container/internal/raw_hash_set.h b/absl/container/internal/raw_hash_set.h
@@ -1226,6 +1226,9 @@ class RawHashSetLayout {
   // Given the capacity of a table, computes the total size of the backing
   // array.
   size_t alloc_size(size_t slot_size) const {
+    ABSL_SWISSTABLE_ASSERT(
+        slot_size <=
+        ((std::numeric_limits<size_t>::max)() - slot_offset_) / capacity_);
     return slot_offset_ + capacity_ * slot_size;
   }
 
@@ -1544,6 +1547,15 @@ inline size_t NormalizeCapacity(size_t n) {
   return n ? ~size_t{} >> countl_zero(n) : 1;
 }
 
+template <size_t kSlotSize>
+size_t MaxValidCapacity() {
+  return NormalizeCapacity((std::numeric_limits<size_t>::max)() / 4 /
+                           kSlotSize);
+}
+
+// Use a non-inlined function to avoid code bloat.
+[[noreturn]] void HashTableSizeOverflow();
+
 // General notes on capacity/growth methods below:
 // - We use 7/8th as maximum load factor. For 16-wide groups, that gives an
 //   average of two empty slots per group.
@@ -2645,6 +2657,10 @@ class raw_hash_set {
       : settings_(CommonFields::CreateDefault<SooEnabled()>(), hash, eq,
                   alloc) {
     if (bucket_count > DefaultCapacity()) {
+      if (ABSL_PREDICT_FALSE(bucket_count >
+                             MaxValidCapacity<sizeof(slot_type)>())) {
+        HashTableSizeOverflow();
+      }
       resize(NormalizeCapacity(bucket_count));
     }
   }
@@ -2917,7 +2933,9 @@ class raw_hash_set {
     ABSL_ASSUME(cap >= kDefaultCapacity);
     return cap;
   }
-  size_t max_size() const { return (std::numeric_limits<size_t>::max)(); }
+  size_t max_size() const {
+    return CapacityToGrowth(MaxValidCapacity<sizeof(slot_type)>());
+  }
 
   ABSL_ATTRIBUTE_REINITIALIZES void clear() {
     if (SwisstableGenerationsEnabled() &&
@@ -3376,6 +3394,9 @@ class raw_hash_set {
     auto m = NormalizeCapacity(n | GrowthToLowerboundCapacity(size()));
     // n == 0 unconditionally rehashes as per the standard.
     if (n == 0 || m > cap) {
+      if (ABSL_PREDICT_FALSE(m > MaxValidCapacity<sizeof(slot_type)>())) {
+        HashTableSizeOverflow();
+      }
       resize(m);
 
       // This is after resize, to ensure that we have completed the allocation
@@ -3388,6 +3409,9 @@ class raw_hash_set {
     const size_t max_size_before_growth =
         is_soo() ? SooCapacity() : size() + growth_left();
     if (n > max_size_before_growth) {
+      if (ABSL_PREDICT_FALSE(n > max_size())) {
+        HashTableSizeOverflow();
+      }
       size_t m = GrowthToLowerboundCapacity(n);
       resize(NormalizeCapacity(m));
 
diff --git a/absl/container/internal/raw_hash_set_test.cc b/absl/container/internal/raw_hash_set_test.cc
@@ -3737,6 +3737,14 @@ TEST(Table, MovedFromCallsFail) {
   }
 }
 
+TEST(Table, MaxSizeOverflow) {
+  size_t overflow = (std::numeric_limits<size_t>::max)();
+  EXPECT_DEATH_IF_SUPPORTED(IntTable t(overflow), "Hash table size overflow");
+  IntTable t;
+  EXPECT_DEATH_IF_SUPPORTED(t.reserve(overflow), "Hash table size overflow");
+  EXPECT_DEATH_IF_SUPPORTED(t.rehash(overflow), "Hash table size overflow");
+}
+
 }  // namespace
 }  // namespace container_internal
 ABSL_NAMESPACE_END

Original file line number	Diff line number	Diff line change
`@@ -3737,6 +3737,14 @@ TEST(Table, MovedFromCallsFail) {`
`3737`	`3737`	`}`
`3738`	`3738`	`}`
`3739`	`3739`
	`3740`	`+TEST(Table, MaxSizeOverflow) {`
	`3741`	`+ size_t overflow = (std::numeric_limits<size_t>::max)();`
	`3742`	`+ EXPECT_DEATH_IF_SUPPORTED(IntTable t(overflow), "Hash table size overflow");`
	`3743`	`+ IntTable t;`
	`3744`	`+ EXPECT_DEATH_IF_SUPPORTED(t.reserve(overflow), "Hash table size overflow");`
	`3745`	`+ EXPECT_DEATH_IF_SUPPORTED(t.rehash(overflow), "Hash table size overflow");`
	`3746`	`+}`
	`3747`	`+`
`3740`	`3748`	`} // namespace`
`3741`	`3749`	`} // namespace container_internal`
`3742`	`3750`	`ABSL_NAMESPACE_END`