[SHELL] Optimize dash -c "command" to avoid a fork

On Sun, Apr 10, 2011 at 07:36:49AM +0000, Jonathan Nieder wrote:
> From: Jilles Tjoelker <jilles@stack.nl>
> Date: Sat, 13 Jun 2009 16:17:45 -0500
> 
> This change only affects strings passed to -c, when the -s option is
> not used.
> 
> Use the EV_EXIT flag to inform the eval machinery that the string
> being passed is the entirety of input.  This way, a fork may be
> omitted in many special cases.
> 
> If there are empty lines after the last command, the evalcmd will not
> see the end early enough and forks will not be omitted. The same thing
> seems to happen in bash.
> 
> Example:
>   sh -c 'ps lT'
> No longer shows a shell process waiting for ps to finish.
> 
> [jn: ported from FreeBSD SVN r194128.  Bugs are mine.]
> 
> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>

Instead of detecting EOF using the input layer, I'm going to
use the parser instead.  In either case, we always have to read
ahead in order to complete the parsing of the previous node.
Therefore we always know whether there is more to come, except
in the case where we see a newline/semicolon or similar.

For the purposes of sh -c, this should be sufficient.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

7 files changed, 29 insertions, 14 deletions

diff --git a/src/Makefile.am b/src/Makefile.am
index ba68d55..2a37381 100644
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -12,7 +12,8 @@ AM_CFLAGS_FOR_BUILD = -g -O2 $(COMMON_CFLAGS)
 AM_CPPFLAGS_FOR_BUILD = $(COMMON_CPPFLAGS)
 
 COMPILE_FOR_BUILD = \
-	$(CC_FOR_BUILD) $(AM_CPPFLAGS_FOR_BUILD) $(CPPFLAGS_FOR_BUILD) \
+	$(CC_FOR_BUILD) $(DEFAULT_INCLUDES) $(AM_CPPFLAGS_FOR_BUILD) \
+	$(CPPFLAGS_FOR_BUILD) \
 	$(AM_CFLAGS_FOR_BUILD) $(CFLAGS_FOR_BUILD) 
 
 bin_PROGRAMS = dash
@@ -33,7 +34,7 @@ dash_LDADD = builtins.o init.o nodes.o signames.o syntax.o
 
 HELPERS = mkinit mksyntax mknodes mksignames
 
-BUILT_SOURCES = builtins.h nodes.h syntax.h token.h
+BUILT_SOURCES = builtins.h nodes.h syntax.h token.h token_vars.h
 CLEANFILES = \
 	$(BUILT_SOURCES) $(patsubst %.o,%.c,$(dash_LDADD)) \
 	$(HELPERS) builtins.def
@@ -44,7 +45,7 @@ EXTRA_DIST = \
 	mktokens mkbuiltins builtins.def.in mkinit.c \
 	mknodes.c nodetypes nodes.c.pat mksyntax.c mksignames.c
 
-token.h: mktokens
+token.h token_vars.h: mktokens
 	sh $^
 
 builtins.def: builtins.def.in $(top_builddir)/config.h
@@ -65,5 +66,7 @@ syntax.c syntax.h: mksyntax
 signames.c: mksignames
 	./$^
 
+mksyntax: token.h
+
 $(HELPERS): %: %.c
 	$(COMPILE_FOR_BUILD) -o $@ $<
diff --git a/src/eval.c b/src/eval.c
index 86423b4..6e7b932 100644
--- a/src/eval.c
+++ b/src/eval.c
@@ -65,10 +65,6 @@
 #endif
 
 
-/* flags in argument to evaltree */
-#define EV_EXIT 01		/* exit after evaluating tree */
-#define EV_TESTED 02		/* exit status is checked; ignore -e flag */
-
 int evalskip;			/* set if we are skipping commands */
 STATIC int skipcount;		/* number of levels to skip */
 MKINIT int loopnest;		/* current loop nesting level */
@@ -169,7 +165,7 @@ evalstring(char *s, int flags)
 
 	status = 0;
 	while ((n = parsecmd(0)) != NEOF) {
-		evaltree(n, flags);
+		evaltree(n, flags & ~(parser_eof() ? 0 : EV_EXIT));
 		status = exitstatus;
 		popstackmark(&smark);
 		if (evalskip)
diff --git a/src/eval.h b/src/eval.h
index ac394e8..4e4de30 100644
--- a/src/eval.h
+++ b/src/eval.h
@@ -46,6 +46,10 @@ struct backcmd {		/* result of evalbackcmd */
 	struct job *jp;		/* job structure for command */
 };
 
+/* flags in argument to evaltree */
+#define EV_EXIT 01		/* exit after evaluating tree */
+#define EV_TESTED 02		/* exit status is checked; ignore -e flag */
+
 int evalstring(char *, int);
 union node;	/* BLETCH for ansi C */
 void evaltree(union node *, int);
diff --git a/src/main.c b/src/main.c
index b38dc27..af987c6 100644
--- a/src/main.c
+++ b/src/main.c
@@ -171,7 +171,7 @@ state2:
 state3:
 	state = 4;
 	if (minusc)
-		evalstring(minusc, 0);
+		evalstring(minusc, sflag ? 0 : EV_EXIT);
 
 	if (sflag || minusc == NULL) {
 state4:	/* XXX ??? - why isn't this before the "if" statement */
diff --git a/src/mktokens b/src/mktokens
index 7c873af..cd52241 100644
--- a/src/mktokens
+++ b/src/mktokens
@@ -71,13 +71,16 @@ TEND	1	"}"
 nl=`wc -l /tmp/ka$$`
 exec > token.h
 awk '{print "#define " $1 " " NR-1}' /tmp/ka$$
+
+exec > token_vars.h
+
 echo '
 /* Array indicating which tokens mark the end of a list */
-const char tokendlist[] = {'
+static const char tokendlist[] = {'
 awk '{print "\t" $2 ","}' /tmp/ka$$
 echo '};
 
-const char *const tokname[] = {'
+static const char *const tokname[] = {'
 sed -e 's/"/\\"/g' \
     -e 's/[^	 ]*[	 ][	 ]*[^	 ]*[	 ][	 ]*\(.*\)/	"\1",/' \
     /tmp/ka$$
@@ -85,7 +88,7 @@ echo '};
 '
 sed 's/"//g' /tmp/ka$$ | awk '
 /TNOT/{print "#define KWDOFFSET " NR-1; print ""; 
-      print "STATIC const char *const parsekwd[] = {"}
+      print "static const char *const parsekwd[] = {"}
 /TNOT/,/neverfound/{if (last) print "	\"" last "\","; last = $3}
 END{print "	\"" last "\"\n};"}'
 
diff --git a/src/parser.c b/src/parser.c
index 528d005..6de2762 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -64,7 +64,7 @@
  */
 
 /* values returned by readtoken */
-#include "token.h"
+#include "token_vars.h"
 
 
 
@@ -86,7 +86,7 @@ struct heredoc *heredoclist;	/* list of here documents to read */
 int doprompt;			/* if set, prompt the user */
 int needprompt;			/* true if interactive and at start of line */
 int lasttoken;			/* last token read */
-MKINIT int tokpushback;		/* last token pushed back */
+int tokpushback;		/* last token pushed back */
 char *wordtext;			/* text of last word returned by readtoken */
 int checkkwd;
 struct nodelist *backquotelist;
@@ -210,6 +210,7 @@ list(int nlflag)
 				parseheredoc();
 			else
 				pungetc();		/* push back EOF on input */
+			tokpushback++;
 			return n1;
 		default:
 			if (nlflag == 1)
diff --git a/src/parser.h b/src/parser.h
index e6caed6..2875cce 100644
--- a/src/parser.h
+++ b/src/parser.h
@@ -34,6 +34,8 @@
  *	@(#)parser.h	8.3 (Berkeley) 5/4/95
  */
 
+#include "token.h"
+
 /* control characters in argument strings */
 #define CTL_FIRST -127		/* first 'special' character */
 #define CTLESC -127		/* escape next character */
@@ -73,6 +75,7 @@
  * must be distinct from NULL, so we use the address of a variable that
  * happens to be handy.
  */
+extern int lasttoken;
 extern int tokpushback;
 #define NEOF ((union node *)&tokpushback)
 extern int whichprompt;		/* 1 == PS1, 2 == PS2 */
@@ -91,3 +94,8 @@ goodname(const char *p)
 {
 	return !*endofname(p);
 }
+
+static inline int parser_eof(void)
+{
+	return tokpushback && lasttoken == TEOF;
+}