Merge branch 'maint' (bloom single-digest double-hashing)

Forward-merges the bloom SHA-256-once fix from maint. The bloom filter was
relocated to proto/bloom/ by the sans-IO refactor, so the fix applied cleanly
to proto/bloom/core.rs; the behavior-neutral test was re-homed into
proto/bloom/tests/core.rs (maint carried it in the pre-split bloom/tests.rs).

src/proto/bloom/core.rs

@@ -67,16 +67,18 @@ impl BloomFilter {
 
     /// Insert a NodeAddr into the filter.
     pub fn insert(&mut self, node_addr: &NodeAddr) {
+        let (h1, h2) = Self::base_hashes(node_addr.as_bytes());
         for i in 0..self.hash_count {
-            let bit_index = self.hash(node_addr.as_bytes(), i);
+            let bit_index = self.bit_index(h1, h2, i);
             self.set_bit(bit_index);
         }
     }
 
     /// Insert raw bytes into the filter.
     pub fn insert_bytes(&mut self, data: &[u8]) {
+        let (h1, h2) = Self::base_hashes(data);
         for i in 0..self.hash_count {
-            let bit_index = self.hash(data, i);
+            let bit_index = self.bit_index(h1, h2, i);
             self.set_bit(bit_index);
         }
     }
@@ -91,8 +93,9 @@ impl BloomFilter {
 
     /// Check if the filter might contain raw bytes.
     pub fn contains_bytes(&self, data: &[u8]) -> bool {
+        let (h1, h2) = Self::base_hashes(data);
         for i in 0..self.hash_count {
-            let bit_index = self.hash(data, i);
+            let bit_index = self.bit_index(h1, h2, i);
             if !self.get_bit(bit_index) {
                 return false;
             }
@@ -198,21 +201,28 @@ impl BloomFilter {
         self.hash_count
     }
 
-    /// Compute a hash index for the given data and hash function number.
+    /// Compute the two base hashes for `data` with a single SHA-256 digest.
     ///
-    /// Uses double hashing: h(x,i) = (h1(x) + i*h2(x)) mod m
-    fn hash(&self, data: &[u8], k: u8) -> usize {
-        // Use first 16 bytes of SHA-256 for h1 and h2
+    /// Double hashing derives the k hash functions from two base hashes:
+    /// h(x,i) = (h1(x) + i*h2(x)) mod m. Computing the digest once here and
+    /// reusing `(h1, h2)` across all k functions avoids re-hashing per k.
+    fn base_hashes(data: &[u8]) -> (u64, u64) {
+        // Use first 16 bytes of SHA-256 for h1 and h2.
         use sha2::{Digest, Sha256};
         let mut hasher = Sha256::new();
         hasher.update(data);
         let hash = hasher.finalize();
 
-        // h1 from first 8 bytes
+        // h1 from first 8 bytes, h2 from next 8 bytes (little-endian).
         let h1 = u64::from_le_bytes(hash[0..8].try_into().unwrap());
-        // h2 from next 8 bytes
         let h2 = u64::from_le_bytes(hash[8..16].try_into().unwrap());
+        (h1, h2)
+    }
 
+    /// Derive the bit index for hash function `k` from the base hashes.
+    ///
+    /// Uses double hashing: h(x,k) = (h1(x) + k*h2(x)) mod m.
+    fn bit_index(&self, h1: u64, h2: u64, k: u8) -> usize {
         let combined = h1.wrapping_add((k as u64).wrapping_mul(h2));
         (combined as usize) % self.num_bits
     }

src/proto/bloom/tests/core.rs

@@ -288,3 +288,80 @@ fn test_bloom_filter_debug_format() {
     assert!(debug.contains("fill_ratio"));
     assert!(debug.contains("est_count"));
 }
+
+#[test]
+fn test_bloom_filter_bit_indices_match_double_hashing_formula() {
+    use sha2::{Digest, Sha256};
+
+    // Independently recompute the documented double-hashing bit indices:
+    // one SHA-256 digest of the input, h1 = bytes[0..8] LE, h2 = bytes[8..16]
+    // LE, then for k in 0..hash_count: (h1 + k*h2) mod num_bits. This pins
+    // bit-identical behavior regardless of the internal implementation.
+    fn expected_indices(data: &[u8], num_bits: usize, hash_count: u8) -> Vec<usize> {
+        let digest = Sha256::digest(data);
+        let h1 = u64::from_le_bytes(digest[0..8].try_into().unwrap());
+        let h2 = u64::from_le_bytes(digest[8..16].try_into().unwrap());
+        (0..hash_count)
+            .map(|k| {
+                let combined = h1.wrapping_add((k as u64).wrapping_mul(h2));
+                (combined as usize) % num_bits
+            })
+            .collect()
+    }
+
+    fn bit_is_set(filter: &BloomFilter, index: usize) -> bool {
+        let byte = filter.as_bytes()[index / 8];
+        (byte >> (index % 8)) & 1 == 1
+    }
+
+    let configs = [(1024usize, 5u8), (8192usize, 7u8)];
+    let inputs: [&[u8]; 4] = [b"", b"alpha", b"the quick brown fox", &[0u8, 1, 2, 3, 255]];
+
+    for (num_bits, hash_count) in configs {
+        for data in inputs {
+            let mut filter = BloomFilter::with_params(num_bits, hash_count).unwrap();
+            let expected = expected_indices(data, num_bits, hash_count);
+
+            filter.insert_bytes(data);
+
+            // Every expected bit is set.
+            for &idx in &expected {
+                assert!(
+                    bit_is_set(&filter, idx),
+                    "expected bit {} set for input {:?} (num_bits={}, k={})",
+                    idx,
+                    data,
+                    num_bits,
+                    hash_count
+                );
+            }
+
+            // No unexpected bits are set: the set-bit count never exceeds the
+            // number of distinct expected indices.
+            let distinct: alloc::collections::BTreeSet<usize> = expected.iter().copied().collect();
+            assert_eq!(
+                filter.count_ones(),
+                distinct.len(),
+                "unexpected bits set for input {:?}",
+                data
+            );
+
+            // contains reports the inserted item as present.
+            assert!(filter.contains_bytes(data));
+        }
+    }
+
+    // NodeAddr path uses the same formula over its byte view.
+    let node = make_node_addr(7);
+    let mut filter = BloomFilter::with_params(1024, 5).unwrap();
+    let expected = expected_indices(node.as_bytes(), 1024, 5);
+    filter.insert(&node);
+    for &idx in &expected {
+        assert!(bit_is_set(&filter, idx));
+    }
+    assert!(filter.contains(&node));
+
+    // Spot-check a definitely-absent item is reported absent.
+    let absent = make_node_addr(200);
+    assert!(!filter.contains(&absent));
+}