From 32d17997af14947e8814e8009ca1f9ebdaeb1e80 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 9 Mar 2026 17:15:24 -0400
Subject: [PATCH] memory-search: fix returned-set deduplication and pre-seeded
 count

mark_returned() was append-only without checking if the key already
existed, causing duplicates to accumulate across hook invocations.
load_returned() then returned all entries including duplicates, which
made the returned count exceed the seen count, causing a u64 underflow
in the pre-seeded calculation.

Fix: check load_returned() before appending in mark_returned(), dedup
on read in load_returned(), and use saturating_sub for the pre-seeded
count as a safety net.

Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
---
 poc-memory/src/bin/memory-search.rs | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/poc-memory/src/bin/memory-search.rs b/poc-memory/src/bin/memory-search.rs
index 34669fa..8fe2da4 100644
--- a/poc-memory/src/bin/memory-search.rs
+++ b/poc-memory/src/bin/memory-search.rs
@@ -408,6 +408,8 @@ fn mark_seen(dir: &Path, session_id: &str, key: &str) {
 }
 
 fn mark_returned(dir: &Path, session_id: &str, key: &str) {
+    let returned = load_returned(dir, session_id);
+    if returned.contains(&key.to_string()) { return; }
     let path = dir.join(format!("returned-{}", session_id));
     if let Ok(mut f) = fs::OpenOptions::new().create(true).append(true).open(path) {
         writeln!(f, "{}", key).ok();
@@ -417,10 +419,12 @@ fn mark_returned(dir: &Path, session_id: &str, key: &str) {
 fn load_returned(dir: &Path, session_id: &str) -> Vec<String> {
     let path = dir.join(format!("returned-{}", session_id));
     if path.exists() {
+        let mut seen = HashSet::new();
         fs::read_to_string(path)
             .unwrap_or_default()
             .lines()
             .filter(|s| !s.is_empty())
+            .filter(|s| seen.insert(s.to_string()))
             .map(|s| s.to_string())
             .collect()
     } else {
@@ -476,7 +480,8 @@ fn show_seen() {
         .map(|s| s.to_string())
         .collect();
     let returned_set: HashSet<_> = returned.iter().cloned().collect();
-    println!("\nSeen set ({} total, {} pre-seeded):", seen_lines.len(), seen_lines.len() - returned.len());
+    let pre_seeded = seen_lines.len().saturating_sub(returned.len());
+    println!("\nSeen set ({} total, {} pre-seeded):", seen_lines.len(), pre_seeded);
 
     if Args::parse().seen_full {
         for line in &seen_lines {