Single threaded stdio optimization

Locking overhead can be significant in some stdio operations
that are common in single threaded applications.

This patch adds the _IO_FLAGS2_NEED_LOCK flag to indicate if
an _IO_FILE object needs to be locked and some of the stdio
functions just jump to their _unlocked variant when not.  The
flag is set on all _IO_FILE objects when the first thread is
created.  A new GLIBC_PRIVATE libc symbol, _IO_enable_locks,
was added to do this from libpthread.

The optimization can be applied to more stdio functions,
currently it is only applied to single flag check or single
non-wide-char standard operations.  The flag should probably
be never set for files with _IO_USER_LOCK, but that's just a
further optimization, not a correctness requirement.

The optimization is valid in a single thread because stdio
operations are non-as-safe (so lock state is not observable
from a signal handler) and stdio locks are recursive (so lock
state is not observable via deadlock).  The optimization is not
valid if a thread may be created while an stdio lock is taken
and thus it should be disabled if any user code may run during
an stdio operation (interposed malloc, printf hooks, etc).
This makes the optimization more complicated for some stdio
operations (e.g. printf), but those are bigger and thus less
important to optimize so this patch does not try to do that.

	* libio/libio.h (_IO_FLAGS2_NEED_LOCK, _IO_need_lock): Define.
	* libio/libioP.h (_IO_enable_locks): Declare.
	* libio/Versions (_IO_enable_locks): New symbol.
	* libio/genops.c (_IO_enable_locks): Define.
	(_IO_old_init): Initialize flags2.
	* libio/feof.c.c (_IO_feof): Avoid locking when not needed.
	* libio/ferror.c (_IO_ferror): Likewise.
	* libio/fputc.c (fputc): Likewise.
	* libio/putc.c (_IO_putc): Likewise.
	* libio/getc.c (_IO_getc): Likewise.
	* libio/getchar.c (getchar): Likewise.
	* libio/ioungetc.c (_IO_ungetc): Likewise.
	* nptl/pthread_create.c (__pthread_create_2_1): Enable stdio locks.
	* libio/iofopncook.c (_IO_fopencookie): Enable locking for the file.
	* sysdeps/pthread/flockfile.c (__flockfile): Likewise.

12 files changed, 53 insertions, 0 deletions

diff --git a/libio/Versions b/libio/Versions
index 2a1d6e6..7712334 100644
--- a/libio/Versions
+++ b/libio/Versions
@@ -155,5 +155,8 @@ libc {
   GLIBC_PRIVATE {
     # Used by NPTL and librt
     __libc_fatal;
+
+    # Used by NPTL
+    _IO_enable_locks;
   }
 }
diff --git a/libio/feof.c b/libio/feof.c
index 9712a81..8890a5f 100644
--- a/libio/feof.c
+++ b/libio/feof.c
@@ -32,6 +32,8 @@ _IO_feof (_IO_FILE *fp)
 {
   int result;
   CHECK_FILE (fp, EOF);
+  if (!_IO_need_lock (fp))
+    return _IO_feof_unlocked (fp);
   _IO_flockfile (fp);
   result = _IO_feof_unlocked (fp);
   _IO_funlockfile (fp);
diff --git a/libio/ferror.c b/libio/ferror.c
index 01e3bd8..d10fcd9 100644
--- a/libio/ferror.c
+++ b/libio/ferror.c
@@ -32,6 +32,8 @@ _IO_ferror (_IO_FILE *fp)
 {
   int result;
   CHECK_FILE (fp, EOF);
+  if (!_IO_need_lock (fp))
+    return _IO_ferror_unlocked (fp);
   _IO_flockfile (fp);
   result = _IO_ferror_unlocked (fp);
   _IO_funlockfile (fp);
diff --git a/libio/fputc.c b/libio/fputc.c
index a7cd682..b72305c 100644
--- a/libio/fputc.c
+++ b/libio/fputc.c
@@ -32,6 +32,8 @@ fputc (int c, _IO_FILE *fp)
 {
   int result;
   CHECK_FILE (fp, EOF);
+  if (!_IO_need_lock (fp))
+    return _IO_putc_unlocked (c, fp);
   _IO_acquire_lock (fp);
   result = _IO_putc_unlocked (c, fp);
   _IO_release_lock (fp);
diff --git a/libio/genops.c b/libio/genops.c
index a466cfa..6ad7346 100644
--- a/libio/genops.c
+++ b/libio/genops.c
@@ -570,11 +570,39 @@ _IO_init (_IO_FILE *fp, int flags)
   _IO_init_internal (fp, flags);
 }
 
+static int stdio_needs_locking;
+
+/* In a single-threaded process most stdio locks can be omitted.  After
+   _IO_enable_locks is called, locks are not optimized away any more.
+   It must be first called while the process is still single-threaded.
+
+   This lock optimization can be disabled on a per-file basis by setting
+   _IO_FLAGS2_NEED_LOCK, because a file can have user-defined callbacks
+   or can be locked with flockfile and then a thread may be created
+   between a lock and unlock, so omitting the lock is not valid.
+
+   Here we have to make sure that the flag is set on all existing files
+   and files created later.  */
+void
+_IO_enable_locks (void)
+{
+  _IO_ITER i;
+
+  if (stdio_needs_locking)
+    return;
+  stdio_needs_locking = 1;
+  for (i = _IO_iter_begin (); i != _IO_iter_end (); i = _IO_iter_next (i))
+    _IO_iter_file (i)->_flags2 |= _IO_FLAGS2_NEED_LOCK;
+}
+libc_hidden_def (_IO_enable_locks)
+
 void
 _IO_old_init (_IO_FILE *fp, int flags)
 {
   fp->_flags = _IO_MAGIC|flags;
   fp->_flags2 = 0;
+  if (stdio_needs_locking)
+    fp->_flags2 |= _IO_FLAGS2_NEED_LOCK;
   fp->_IO_buf_base = NULL;
   fp->_IO_buf_end = NULL;
   fp->_IO_read_base = NULL;
diff --git a/libio/getc.c b/libio/getc.c
index b58fd62..fd66ef9 100644
--- a/libio/getc.c
+++ b/libio/getc.c
@@ -34,6 +34,8 @@ _IO_getc (FILE *fp)
 {
   int result;
   CHECK_FILE (fp, EOF);
+  if (!_IO_need_lock (fp))
+    return _IO_getc_unlocked (fp);
   _IO_acquire_lock (fp);
   result = _IO_getc_unlocked (fp);
   _IO_release_lock (fp);
diff --git a/libio/getchar.c b/libio/getchar.c
index 5b41595..d799321 100644
--- a/libio/getchar.c
+++ b/libio/getchar.c
@@ -33,6 +33,8 @@ int
 getchar (void)
 {
   int result;
+  if (!_IO_need_lock (_IO_stdin))
+    return _IO_getc_unlocked (_IO_stdin);
   _IO_acquire_lock (_IO_stdin);
   result = _IO_getc_unlocked (_IO_stdin);
   _IO_release_lock (_IO_stdin);
diff --git a/libio/iofopncook.c b/libio/iofopncook.c
index a08dfda..982f464 100644
--- a/libio/iofopncook.c
+++ b/libio/iofopncook.c
@@ -172,6 +172,8 @@ _IO_cookie_init (struct _IO_cookie_file *cfile, int read_write,
   _IO_mask_flags (&cfile->__fp.file, read_write,
 		  _IO_NO_READS+_IO_NO_WRITES+_IO_IS_APPENDING);
 
+  cfile->__fp.file._flags2 |= _IO_FLAGS2_NEED_LOCK;
+
   /* We use a negative number different from -1 for _fileno to mark that
      this special stream is not associated with a real file, but still has
      to be treated as such.  */
diff --git a/libio/ioungetc.c b/libio/ioungetc.c
index 951064f..917cad8 100644
--- a/libio/ioungetc.c
+++ b/libio/ioungetc.c
@@ -33,6 +33,8 @@ _IO_ungetc (int c, _IO_FILE *fp)
   CHECK_FILE (fp, EOF);
   if (c == EOF)
     return EOF;
+  if (!_IO_need_lock (fp))
+    return _IO_sputbackc (fp, (unsigned char) c);
   _IO_acquire_lock (fp);
   result = _IO_sputbackc (fp, (unsigned char) c);
   _IO_release_lock (fp);
diff --git a/libio/libio.h b/libio/libio.h
index 518ffd8..14bcb92 100644
--- a/libio/libio.h
+++ b/libio/libio.h
@@ -119,6 +119,7 @@
 # define _IO_FLAGS2_SCANF_STD 16
 # define _IO_FLAGS2_NOCLOSE 32
 # define _IO_FLAGS2_CLOEXEC 64
+# define _IO_FLAGS2_NEED_LOCK 128
 #endif
 
 /* These are "formatting flags" matching the iostream fmtflags enum values. */
@@ -451,6 +452,9 @@ extern int _IO_ftrylockfile (_IO_FILE *) __THROW;
 #define _IO_cleanup_region_end(_Doit) /**/
 #endif
 
+#define _IO_need_lock(_fp) \
+  (((_fp)->_flags2 & _IO_FLAGS2_NEED_LOCK) != 0)
+
 extern int _IO_vfscanf (_IO_FILE * __restrict, const char * __restrict,
 			_IO_va_list, int *__restrict);
 extern int _IO_vfprintf (_IO_FILE *__restrict, const char *__restrict,
diff --git a/libio/libioP.h b/libio/libioP.h
index eb93418..1832b44 100644
--- a/libio/libioP.h
+++ b/libio/libioP.h
@@ -444,6 +444,8 @@ extern void _IO_list_unlock (void) __THROW;
 libc_hidden_proto (_IO_list_unlock)
 extern void _IO_list_resetlock (void) __THROW;
 libc_hidden_proto (_IO_list_resetlock)
+extern void _IO_enable_locks (void) __THROW;
+libc_hidden_proto (_IO_enable_locks)
 
 /* Default jumptable functions. */
 
diff --git a/libio/putc.c b/libio/putc.c
index b591c55..6e1fdee 100644
--- a/libio/putc.c
+++ b/libio/putc.c
@@ -25,6 +25,8 @@ _IO_putc (int c, _IO_FILE *fp)
 {
   int result;
   CHECK_FILE (fp, EOF);
+  if (!_IO_need_lock (fp))
+    return _IO_putc_unlocked (c, fp);
   _IO_acquire_lock (fp);
   result = _IO_putc_unlocked (c, fp);
   _IO_release_lock (fp);