[Qemu-devel] [PATCH] Fix path mangling in linux-user/path.c

[Qemu-devel] [PATCH] Fix path mangling in linux-user/path.c

[Lauri Leukkunen]

[-- Attachment #1: Type: text/plain, Size: 250 bytes --]

This patch improves performance at user-mode emulation startup and fixes a nasty
looping bug caused by a symlink such as /usr/bin/X11 -> ../bin

I've tested this using current CVS version on debian/testing on amd64
with arm user-mode target.

/lauri

[-- Attachment #2: qemu-linux-user-path.diff --]
[-- Type: text/x-patch, Size: 8344 bytes --]

Index: path.c
===================================================================
RCS file: /sources/qemu/qemu/linux-user/path.c,v
retrieving revision 1.2
diff -u -r1.2 path.c
--- path.c	13 Sep 2004 21:39:32 -0000	1.2
+++ path.c	22 Apr 2007 19:18:42 -0000
@@ -10,138 +10,191 @@
 #include <string.h>
 #include <errno.h>
 #include <stdio.h>
+#include <libgen.h>
 #include "qemu.h"
 
-struct pathelem
-{
-    /* Name of this, eg. lib */
-    char *name;
-    /* Full path name, eg. /usr/gnemul/x86-linux/lib. */
-    char *pathname;
-    struct pathelem *parent;
-    /* Children */
-    unsigned int num_entries;
-    struct pathelem *entries[0];
-};
-
-static struct pathelem *base;
-
-/* First N chars of S1 match S2, and S2 is N chars long. */
-static int strneq(const char *s1, unsigned int n, const char *s2)
-{
-    unsigned int i;
-
-    for (i = 0; i < n; i++)
-	if (s1[i] != s2[i])
-	    return 0;
-    return s2[i] == 0;
-}
+char *base = NULL;
 
-static struct pathelem *add_entry(struct pathelem *root, const char *name);
+struct path_entry {
+    struct path_entry *prev;
+    struct path_entry *next;
+    char name[PATH_MAX];
+};
 
-static struct pathelem *new_entry(const char *root,
-				  struct pathelem *parent,
-				  const char *name)
+char *decolonize_path(const char *path)
 {
-    struct pathelem *new = malloc(sizeof(*new));
-    new->name = strdup(name);
-    asprintf(&new->pathname, "%s/%s", root, name);
-    new->num_entries = 0;
-    return new;
-}
-
-#define streq(a,b) (strcmp((a), (b)) == 0)
+    char *cpath, *index, *start;
+    char cwd[PATH_MAX];
+    struct path_entry list;
+    struct path_entry *work;
+    struct path_entry *new;
+    char *buf = NULL;
 
-static struct pathelem *add_dir_maybe(struct pathelem *path)
-{
-    DIR *dir;
+    if (!path) {
+        return NULL;
+    }
 
-    if ((dir = opendir(path->pathname)) != NULL) {
-	struct dirent *dirent;
+    buf = malloc((PATH_MAX + 1) * sizeof(char));
+    memset(buf, '\0', PATH_MAX + 1);
 
-	while ((dirent = readdir(dir)) != NULL) {
-	    if (!streq(dirent->d_name,".") && !streq(dirent->d_name,"..")){
-		path = add_entry(path, dirent->d_name);
-	    }
-	}
-        closedir(dir);
+    list.next = NULL;
+    list.prev = NULL;
+    work = &list;
+
+    if (path[0] != '/') {
+        /* not an absolute path */
+        memset(cwd, '\0', PATH_MAX);
+        if (getcwd(cwd, PATH_MAX) < 0) {
+            perror("error getting current work dir\n");
+            return NULL;
+        }
+        unsigned int l = (strlen(cwd) + 1 + strlen(path) + 1);
+        cpath = malloc((strlen(cwd) + 1
+                        + strlen(path) + 1) * sizeof(char));
+        memset(cpath, '\0', l);
+        strcpy(cpath, cwd);
+        strcat(cpath, "/");
+        strcat(cpath, path);
+    } else {
+        cpath = strdup(path);
     }
-    return path;
-}
-
-static struct pathelem *add_entry(struct pathelem *root, const char *name)
-{
-    root->num_entries++;
 
-    root = realloc(root, sizeof(*root)
-		   + sizeof(root->entries[0])*root->num_entries);
+    start = cpath + 1;          /* ignore leading '/' */
+    while (1) {
+        index = strstr(start, "/");
+        if (!index) {
+            /* add the last item */
+            new = malloc(sizeof(struct path_entry));
+            memset(new->name, '\0', PATH_MAX);
+            new->prev = work;
+            work->next = new;
+            new->next = NULL;
+            strcpy(new->name, start);
+            work = new;
+            break;
+        }
+        *index = '\0';
+        if (index == (start)) {
+            goto proceed;       /* skip over empty strings 
+                                   resulting from // */
+        }
+
+        if (strcmp(start, "..") == 0) {
+            /* travel up one */
+            if (!work->prev)
+                goto proceed;
+            work = work->prev;
+            free(work->next);
+            work->next = NULL;
+        } else if (strcmp(start, ".") == 0) {
+            /* ignore */
+            goto proceed;
+        } else {
+            /* add an entry to our path_entry list */
+            new = malloc(sizeof(struct path_entry));
+            memset(new->name, '\0', PATH_MAX);
+            new->prev = work;
+            work->next = new;
+            new->next = NULL;
+            strcpy(new->name, start);
+            work = new;
+        }
+
+      proceed:
+        *index = '/';
+        start = index + 1;
+    }
 
-    root->entries[root->num_entries-1] = new_entry(root->pathname, root, name);
-    root->entries[root->num_entries-1]
-	= add_dir_maybe(root->entries[root->num_entries-1]);
-    return root;
+    work = list.next;
+    while (work) {
+        struct path_entry *tmp;
+        strcat(buf, "/");
+        strcat(buf, work->name);
+        tmp = work;
+        work = work->next;
+        free(tmp);
+    }
+    return buf;
 }
 
-/* This needs to be done after tree is stabalized (ie. no more reallocs!). */
-static void set_parents(struct pathelem *child, struct pathelem *parent)
-{
-    unsigned int i;
-
-    child->parent = parent;
-    for (i = 0; i < child->num_entries; i++)
-	set_parents(child->entries[i], child);
-}
 
 void init_paths(const char *prefix)
 {
-    if (prefix[0] != '/' ||
-        prefix[0] == '\0' ||
-        !strcmp(prefix, "/"))
-        return;
-
-    base = new_entry("", NULL, prefix+1);
-    base = add_dir_maybe(base);
-    if (base->num_entries == 0) {
-        free (base);
-        base = NULL;
-    } else {
-        set_parents(base, base);
-    }
+    base = strdup(prefix);
 }
 
-/* FIXME: Doesn't handle DIR/.. where DIR is not in emulated dir. */
-static const char *
-follow_path(const struct pathelem *cursor, const char *name)
+
+
+char *adjust_for_leakage(char *path)
 {
-    unsigned int i, namelen;
+    char tmp[PATH_MAX + 1];
+    char tmp2[PATH_MAX + 1];
+    char *buf;
+    char *bname = NULL, *dname = NULL;
+    int i;
 
-    name += strspn(name, "/");
-    namelen = strcspn(name, "/");
+    if (!path)
+        return NULL;
 
-    if (namelen == 0)
-	return cursor->pathname;
+    memset(tmp, '\0', PATH_MAX + 1);
+    memset(tmp2, '\0', PATH_MAX + 1);
+    if ((i = readlink(path, tmp, PATH_MAX) < 0)) {
+        /* not a symlink */
+        return strdup(path);
+    }
 
-    if (strneq(name, namelen, ".."))
-	return follow_path(cursor->parent, name + namelen);
+    bname = basename(strdup(path));
+    dname = dirname(strdup(path));
 
-    if (strneq(name, namelen, "."))
-	return follow_path(cursor, name + namelen);
+    /* check if the symlink refers to itself */
+    if (strcmp(tmp, bname) == 0) {
+        /* symlink refers to itself */
+        return strdup(path);
+    }
 
-    for (i = 0; i < cursor->num_entries; i++)
-	if (strneq(name, namelen, cursor->entries[i]->name))
-	    return follow_path(cursor->entries[i], name + namelen);
+    /* make tmp absolute if it's not */
+    if (tmp[0] != '/') {
+        strcpy(tmp2, dname);
+        strcat(tmp2, "/");
+        strcat(tmp2, tmp);
+    }
 
-    /* Not found */
-    return NULL;
+    /* remove "." and ".." entries from tmp, done in-place */
+    buf = decolonize_path(tmp2);
+    strcpy(tmp2, buf);
+
+    free(buf);
+    free(bname);
+    free(dname);
+
+    if (strncmp(tmp2, base, strlen(base)) != 0) {
+        /* tried to leak out, fix it */
+        strcpy(tmp, base);
+        strcpy(tmp, "/");
+        strcpy(tmp, tmp2);
+        return adjust_for_leakage(tmp);
+    } else {
+        return adjust_for_leakage(tmp2);
+    }
 }
 
 /* Look for path in emulation dir, otherwise return name. */
 const char *path(const char *name)
 {
-    /* Only do absolute paths: quick and dirty, but should mostly be OK.
-       Could do relative by tracking cwd. */
-    if (!base || name[0] != '/')
-	return name;
+    char *tmp, *ret;
 
-    return follow_path(base, name) ?: name;
+    if (strncmp(name, base, strlen(base)) == 0) {
+        /* name is within emulation dir */
+        ret = adjust_for_leakage(name);
+    } else {
+        /* name is elsewhere, use base + "/" + name */
+        tmp = malloc(sizeof(char) * strlen(base) + strlen(name) + 2);
+        strcpy(tmp, base);
+        if (name[0] != '/')
+            strcat(tmp, "/");
+        strcat(tmp, name);
+        ret = adjust_for_leakage(tmp);
+        free(tmp);
+    }
+    return ret;
 }