[libc++] Optimize fstream::read

[philnik777]

Benchmark         old       new    Difference    % Difference
-----------  --------  --------  ------------  --------------
bm_read       2468.45    736.27      -1732.18         -70.17%

[llvmbot]

@llvm/pr-subscribers-libcxx

Author: Nikolas Klauser (philnik777)

Changes

Benchmark         old       new    Difference    % Difference
-----------  --------  --------  ------------  --------------
bm_read       2468.45    736.27      -1732.18         -70.17%

---

Full diff: https://github.com/llvm/llvm-project/pull/165223.diff

5 Files Affected:

• (modified) libcxx/docs/ReleaseNotes/22.rst (+2-2)
• (modified) libcxx/include/fstream (+13)
• (renamed) libcxx/test/benchmarks/streams/fstream.bench.cpp (+18)
• (modified) libcxx/test/libcxx/input.output/file.streams/fstreams/filebuf/traits_mismatch.verify.cpp (+1-1)
• (modified) libcxx/test/libcxx/input.output/file.streams/fstreams/traits_mismatch.verify.cpp (+1-1)

diff --git a/libcxx/docs/ReleaseNotes/22.rst b/libcxx/docs/ReleaseNotes/22.rst
index 25d33a9c2eb50..b5376c31ae31c 100644
--- a/libcxx/docs/ReleaseNotes/22.rst
+++ b/libcxx/docs/ReleaseNotes/22.rst
@@ -64,8 +64,8 @@ Improvements and New Features
   by up to 2.5x
 - The performance of ``erase(iterator, iterator)`` in the unordered containers has been improved by up to 1.9x
 - The performance of ``map::insert_or_assign`` has been improved by up to 2x
-- ``ofstream::write`` has been optimized to pass through large strings to system calls directly instead of copying them
-  in chunks into a buffer.
+- ``ofstream::write`` and ``ifstream::read`` have been optimized to pass through large reads and writes to system calls
+  directly instead of copying them in chunks.
 - Multiple internal types have been refactored to use ``[[no_unique_address]]``, resulting in faster compile times and
   reduced debug information.
 
diff --git a/libcxx/include/fstream b/libcxx/include/fstream
index 1f88d134fe061..b07ca636094af 100644
--- a/libcxx/include/fstream
+++ b/libcxx/include/fstream
@@ -308,6 +308,19 @@ protected:
     return basic_streambuf<_CharT, _Traits>::xsputn(__str, __len);
   }
 
+  _LIBCPP_HIDE_FROM_ABI_VIRTUAL streamsize xsgetn(char_type* __str, streamsize __len) override {
+    if (__always_noconv_) {
+      const streamsize __n = std::min(this->egptr() - this->gptr(), __len);
+      if (__n != 0) {
+        traits_type::copy(__str, this->gptr(), __n);
+        this->__gbump_ptrdiff(__n);
+      }
+      if (__len - __n >= this->egptr() - this->eback())
+        return std::fread(__str + __n, sizeof(char_type), __len - __n, __file_);
+    }
+    return basic_streambuf<_CharT, _Traits>::xsgetn(__str, __len);
+  }
+
 private:
   char* __extbuf_;
   const char* __extbufnext_;
diff --git a/libcxx/test/benchmarks/streams/ofstream.bench.cpp b/libcxx/test/benchmarks/streams/fstream.bench.cpp
similarity index 62%
rename from libcxx/test/benchmarks/streams/ofstream.bench.cpp
rename to libcxx/test/benchmarks/streams/fstream.bench.cpp
index 60606a9d67e2f..3fef23506e67e 100644
--- a/libcxx/test/benchmarks/streams/ofstream.bench.cpp
+++ b/libcxx/test/benchmarks/streams/fstream.bench.cpp
@@ -22,4 +22,22 @@ static void bm_write(benchmark::State& state) {
 }
 BENCHMARK(bm_write);
 
+static void bm_read(benchmark::State& state) {
+  std::vector<char> buffer;
+  buffer.resize(16384);
+
+  std::ofstream gen_testfile("testfile");
+  gen_testfile.write(buffer.data(), buffer.size());
+
+  std::ifstream stream("testfile");
+  assert(stream);
+
+  for (auto _ : state) {
+    stream.read(buffer.data(), buffer.size());
+    benchmark::DoNotOptimize(buffer);
+    stream.seekg(0);
+  }
+}
+BENCHMARK(bm_read);
+
 BENCHMARK_MAIN();
diff --git a/libcxx/test/libcxx/input.output/file.streams/fstreams/filebuf/traits_mismatch.verify.cpp b/libcxx/test/libcxx/input.output/file.streams/fstreams/filebuf/traits_mismatch.verify.cpp
index 283adbc057d1e..30e7b66d42325 100644
--- a/libcxx/test/libcxx/input.output/file.streams/fstreams/filebuf/traits_mismatch.verify.cpp
+++ b/libcxx/test/libcxx/input.output/file.streams/fstreams/filebuf/traits_mismatch.verify.cpp
@@ -19,4 +19,4 @@
 
 std::basic_filebuf<char, std::char_traits<wchar_t> > f;
 // expected-error-re@*:* {{static assertion failed{{.*}}traits_type::char_type must be the same type as CharT}}
-// expected-error@*:* 10 {{only virtual member functions can be marked 'override'}}
+// expected-error@*:* 11 {{only virtual member functions can be marked 'override'}}
diff --git a/libcxx/test/libcxx/input.output/file.streams/fstreams/traits_mismatch.verify.cpp b/libcxx/test/libcxx/input.output/file.streams/fstreams/traits_mismatch.verify.cpp
index ba6f3c31d3e34..daafb36f9151a 100644
--- a/libcxx/test/libcxx/input.output/file.streams/fstreams/traits_mismatch.verify.cpp
+++ b/libcxx/test/libcxx/input.output/file.streams/fstreams/traits_mismatch.verify.cpp
@@ -21,7 +21,7 @@ std::basic_fstream<char, std::char_traits<wchar_t> > f;
 // expected-error-re@*:* {{static assertion failed{{.*}}traits_type::char_type must be the same type as CharT}}
 // expected-error-re@*:* {{static assertion failed{{.*}}traits_type::char_type must be the same type as CharT}}
 
-// expected-error@*:* 12 {{only virtual member functions can be marked 'override'}}
+// expected-error@*:* 13 {{only virtual member functions can be marked 'override'}}
 
 // FIXME: As of commit r324062 Clang incorrectly generates a diagnostic about mismatching
 // exception specifications for types which are already invalid for one reason or another.