From 7571ad42f42939d172ec9a68dfe56aac724ee2ef Mon Sep 17 00:00:00 2001
From: Peter Zhu <peter@peterzhu.ca>
Date: Thu, 25 Jul 2024 12:14:26 -0400
Subject: [Bug #20650] Fix memory leak in Regexp capture group when timeout
 (#11244)

Fix memory leak in Regexp capture group when timeout

[Bug #20650]

The capture group allocates memory that is leaked when it times out.

For example:

    re = Regexp.new("^#{"(a*)" * 10_000}x$", timeout: 0.000001)
    str = "a" * 1000000 + "x"

    10.times do
      100.times do
        re =~ str
      rescue Regexp::TimeoutError
      end

      puts `ps -o rss= -p #{$$}`
    end

Before:

    34688
    56416
    78288
    100368
    120784
    140704
    161904
    183568
    204320
    224800

After:

    16288
    16288
    16880
    16896
    16912
    16928
    16944
    17184
    17184
    17200
---
 test/ruby/test_regexp.rb | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'test/ruby')

diff --git a/test/ruby/test_regexp.rb b/test/ruby/test_regexp.rb
index c8caca2891..6b9efcb555 100644
--- a/test/ruby/test_regexp.rb
+++ b/test/ruby/test_regexp.rb
@@ -1895,6 +1895,22 @@ class TestRegexp < Test::Unit::TestCase
     end;
   end
 
+  def test_timeout_memory_leak
+    assert_no_memory_leak([], "#{<<~"begin;"}", "#{<<~'end;'}", "[Bug #20650]", timeout: 100, rss: true)
+      regex = Regexp.new("^#{"(a*)" * 10_000}x$", timeout: 0.000001)
+      str = "a" * 1_000_000 + "x"
+
+      code = proc do
+        regex =~ str
+      rescue
+      end
+
+      10.times(&code)
+    begin;
+      1_000.times(&code)
+    end;
+  end
+
   def test_match_cache_exponential
     assert_separately([], "#{<<-"begin;"}\n#{<<-'end;'}")
       timeout = #{ EnvUtil.apply_timeout_scale(10).inspect }
-- 
cgit v1.2.3