public inbox for libc-alpha@sourceware.org
 help / color / mirror / Atom feed
From: Adhemerval Zanella <adhemerval.zanella@linaro.org>
To: libc-alpha@sourceware.org, Paul Eggert <eggert@cs.ucla.edu>,
	bug-gnulib@gnu.org
Subject: [PATCH 1/3] posix: Remove alloca usage on regex set_regs
Date: Wed,  6 Jan 2021 15:17:05 -0300	[thread overview]
Message-ID: <20210106181707.1738066-1-adhemerval.zanella@linaro.org> (raw)

It replaces the regmatch_t with a dynarray list.

Checked on x86_64-linux-gnu.
---
 posix/regexec.c | 62 ++++++++++++++++++++++++-------------------------
 1 file changed, 31 insertions(+), 31 deletions(-)

diff --git a/posix/regexec.c b/posix/regexec.c
index b083342f77..5e22f90842 100644
--- a/posix/regexec.c
+++ b/posix/regexec.c
@@ -54,9 +54,6 @@ static Idx check_matching (re_match_context_t *mctx, bool fl_longest_match,
 			   Idx *p_match_first);
 static Idx check_halt_state_context (const re_match_context_t *mctx,
 				     const re_dfastate_t *state, Idx idx);
-static void update_regs (const re_dfa_t *dfa, regmatch_t *pmatch,
-			 regmatch_t *prev_idx_match, Idx cur_node,
-			 Idx cur_idx, Idx nmatch);
 static reg_errcode_t push_fail_stack (struct re_fail_stack_t *fs,
 				      Idx str_idx, Idx dest_node, Idx nregs,
 				      regmatch_t *regs,
@@ -1355,6 +1352,16 @@ pop_fail_stack (struct re_fail_stack_t *fs, Idx *pidx, Idx nregs,
   return fs->stack[num].node;
 }
 
+
+#define DYNARRAY_STRUCT  regmatch_list
+#define DYNARRAY_ELEMENT regmatch_t
+#define DYNARRAY_PREFIX  regmatch_list_
+#include <malloc/dynarray-skeleton.c>
+
+static void update_regs (const re_dfa_t *dfa, regmatch_t *pmatch,
+			 struct regmatch_list *prev_idx_match, Idx cur_node,
+			 Idx cur_idx, Idx nmatch);
+
 /* Set the positions where the subexpressions are starts/ends to registers
    PMATCH.
    Note: We assume that pmatch[0] is already set, and
@@ -1370,8 +1377,8 @@ set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch,
   re_node_set eps_via_nodes;
   struct re_fail_stack_t *fs;
   struct re_fail_stack_t fs_body = { 0, 2, NULL };
-  regmatch_t *prev_idx_match;
-  bool prev_idx_match_malloced = false;
+  struct regmatch_list prev_idx_match;
+  regmatch_list_init (&prev_idx_match);
 
   DEBUG_ASSERT (nmatch > 1);
   DEBUG_ASSERT (mctx->state_log != NULL);
@@ -1388,23 +1395,18 @@ set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch,
   cur_node = dfa->init_node;
   re_node_set_init_empty (&eps_via_nodes);
 
-  if (__libc_use_alloca (nmatch * sizeof (regmatch_t)))
-    prev_idx_match = (regmatch_t *) alloca (nmatch * sizeof (regmatch_t));
-  else
+  if (!regmatch_list_resize (&prev_idx_match, nmatch))
     {
-      prev_idx_match = re_malloc (regmatch_t, nmatch);
-      if (prev_idx_match == NULL)
-	{
-	  free_fail_stack_return (fs);
-	  return REG_ESPACE;
-	}
-      prev_idx_match_malloced = true;
+      regmatch_list_free (&prev_idx_match);
+      free_fail_stack_return (fs);
+      return REG_ESPACE;
     }
-  memcpy (prev_idx_match, pmatch, sizeof (regmatch_t) * nmatch);
+  for (size_t i = 0; i < nmatch; i++)
+    *regmatch_list_at (&prev_idx_match, i) = pmatch[i];
 
   for (idx = pmatch[0].rm_so; idx <= pmatch[0].rm_eo ;)
     {
-      update_regs (dfa, pmatch, prev_idx_match, cur_node, idx, nmatch);
+      update_regs (dfa, pmatch, &prev_idx_match, cur_node, idx, nmatch);
 
       if (idx == pmatch[0].rm_eo && cur_node == mctx->last_node)
 	{
@@ -1417,8 +1419,7 @@ set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch,
 	      if (reg_idx == nmatch)
 		{
 		  re_node_set_free (&eps_via_nodes);
-		  if (prev_idx_match_malloced)
-		    re_free (prev_idx_match);
+		  regmatch_list_free (&prev_idx_match);
 		  return free_fail_stack_return (fs);
 		}
 	      cur_node = pop_fail_stack (fs, &idx, nmatch, pmatch,
@@ -1427,8 +1428,7 @@ set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch,
 	  else
 	    {
 	      re_node_set_free (&eps_via_nodes);
-	      if (prev_idx_match_malloced)
-		re_free (prev_idx_match);
+	      regmatch_list_free (&prev_idx_match);
 	      return REG_NOERROR;
 	    }
 	}
@@ -1442,8 +1442,7 @@ set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch,
 	  if (__glibc_unlikely (cur_node == -2))
 	    {
 	      re_node_set_free (&eps_via_nodes);
-	      if (prev_idx_match_malloced)
-		re_free (prev_idx_match);
+	      regmatch_list_free (&prev_idx_match);
 	      free_fail_stack_return (fs);
 	      return REG_ESPACE;
 	    }
@@ -1453,15 +1452,13 @@ set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch,
 	  else
 	    {
 	      re_node_set_free (&eps_via_nodes);
-	      if (prev_idx_match_malloced)
-		re_free (prev_idx_match);
+	      regmatch_list_free (&prev_idx_match);
 	      return REG_NOMATCH;
 	    }
 	}
     }
   re_node_set_free (&eps_via_nodes);
-  if (prev_idx_match_malloced)
-    re_free (prev_idx_match);
+  regmatch_list_free (&prev_idx_match);
   return free_fail_stack_return (fs);
 }
 
@@ -1483,7 +1480,8 @@ free_fail_stack_return (struct re_fail_stack_t *fs)
 
 static void
 update_regs (const re_dfa_t *dfa, regmatch_t *pmatch,
-	     regmatch_t *prev_idx_match, Idx cur_node, Idx cur_idx, Idx nmatch)
+	     struct regmatch_list *prev_idx_match, Idx cur_node, Idx cur_idx,
+	     Idx nmatch)
 {
   int type = dfa->nodes[cur_node].type;
   if (type == OP_OPEN_SUBEXP)
@@ -1508,18 +1506,20 @@ update_regs (const re_dfa_t *dfa, regmatch_t *pmatch,
 	      pmatch[reg_num].rm_eo = cur_idx;
 	      /* This is a non-empty match or we are not inside an optional
 		 subexpression.  Accept this right away.  */
-	      memcpy (prev_idx_match, pmatch, sizeof (regmatch_t) * nmatch);
+	      for (size_t i = 0; i < nmatch; i++)
+		*regmatch_list_at (prev_idx_match, i) = pmatch[i];
 	    }
 	  else
 	    {
 	      if (dfa->nodes[cur_node].opt_subexp
-		  && prev_idx_match[reg_num].rm_so != -1)
+		  && regmatch_list_at (prev_idx_match, reg_num)->rm_so != -1)
 		/* We transited through an empty match for an optional
 		   subexpression, like (a?)*, and this is not the subexp's
 		   first match.  Copy back the old content of the registers
 		   so that matches of an inner subexpression are undone as
 		   well, like in ((a?))*.  */
-		memcpy (pmatch, prev_idx_match, sizeof (regmatch_t) * nmatch);
+		memcpy (pmatch, regmatch_list_begin (prev_idx_match),
+			sizeof (regmatch_t) * nmatch);
 	      else
 		/* We completed a subexpression, but it may be part of
 		   an optional one, so do not update PREV_IDX_MATCH.  */
-- 
2.25.1


             reply	other threads:[~2021-01-06 18:17 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-06 18:17 Adhemerval Zanella [this message]
2021-01-06 18:17 ` [PATCH 2/3] posix: Remove alloca usage on regex build_trtable Adhemerval Zanella
2021-01-08 22:30   ` Paul Eggert
2021-01-11 12:31     ` Adhemerval Zanella
2021-01-06 18:17 ` [PATCH 3/3] posix: Remove alloca definition from regex Adhemerval Zanella
2021-01-09  1:20   ` Paul Eggert
2021-01-11 12:33     ` Adhemerval Zanella
2021-01-08 20:14 ` [PATCH 1/3] posix: Remove alloca usage on regex set_regs Paul Eggert
2021-01-11 12:35   ` Adhemerval Zanella
2021-01-09  1:24 ` Darshit Shah
2021-01-09  3:54   ` Paul Eggert

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210106181707.1738066-1-adhemerval.zanella@linaro.org \
    --to=adhemerval.zanella@linaro.org \
    --cc=bug-gnulib@gnu.org \
    --cc=eggert@cs.ucla.edu \
    --cc=libc-alpha@sourceware.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).