Merge branch 'getname2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull getname/putname updates from Al Viro:
 "Rework of getname/getname_kernel/etc., mostly from Paul Moore.  Gets
  rid of quite a pile of kludges between namei and audit..."

* 'getname2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  audit: replace getname()/putname() hacks with reference counters
  audit: fix filename matching in __audit_inode() and __audit_inode_child()
  audit: enable filename recording via getname_kernel()
  simpler calling conventions for filename_mountpoint()
  fs: create proper filename objects using getname_kernel()
  fs: rework getname_kernel to handle up to PATH_MAX sized filenames
  cut down the number of do_path_lookup() callers

2 files changed, 37 insertions, 151 deletions

diff --git a/kernel/audit.h b/kernel/audit.h
index 3cdffad5a1d9..1caa0d345d90 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -24,12 +24,6 @@
 #include <linux/skbuff.h>
 #include <uapi/linux/mqueue.h>
 
-/* 0 = no checking
-   1 = put_count checking
-   2 = verbose put_count checking
-*/
-#define AUDIT_DEBUG 0
-
 /* AUDIT_NAMES is the number of slots we reserve in the audit_context
  * for saving names from getname().  If we get more names we will allocate
  * a name dynamically and also add those to the list anchored by names_list. */
@@ -74,9 +68,8 @@ struct audit_cap_data {
         };
 };
 
-/* When fs/namei.c:getname() is called, we store the pointer in name and
- * we don't let putname() free it (instead we free all of the saved
- * pointers at syscall exit time).
+/* When fs/namei.c:getname() is called, we store the pointer in name and bump
+ * the refcnt in the associated filename struct.
  *
  * Further, in fs/namei.c:path_lookup() we store the inode and device.
  */
@@ -86,7 +79,6 @@ struct audit_names {
         struct filename         *name;
         int                     name_len;       /* number of chars to log */
         bool                    hidden;         /* don't log this record */
-        bool                    name_put;       /* call __putname()? */
 
         unsigned long           ino;
         dev_t                   dev;
@@ -208,11 +200,6 @@ struct audit_context {
         };
         int fds[2];
         struct audit_proctitle proctitle;
-
-#if AUDIT_DEBUG
-        int                 put_count;
-        int                 ino_count;
-#endif
 };
 
 extern u32 audit_ever_enabled;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 55f82fce2526..dc4ae70a7413 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -866,33 +866,10 @@ static inline void audit_free_names(struct audit_context *context)
 {
         struct audit_names *n, *next;
 
-#if AUDIT_DEBUG == 2
-        if (context->put_count + context->ino_count != context->name_count) {
-                int i = 0;
-
-                pr_err("%s:%d(:%d): major=%d in_syscall=%d"
-                       " name_count=%d put_count=%d ino_count=%d"
-                       " [NOT freeing]\n", __FILE__, __LINE__,
-                       context->serial, context->major, context->in_syscall,
-                       context->name_count, context->put_count,
-                       context->ino_count);
-                list_for_each_entry(n, &context->names_list, list) {
-                        pr_err("names[%d] = %p = %s\n", i++, n->name,
-                               n->name->name ?: "(null)");
-                }
-                dump_stack();
-                return;
-        }
-#endif
-#if AUDIT_DEBUG
-        context->put_count  = 0;
-        context->ino_count  = 0;
-#endif
-
         list_for_each_entry_safe(n, next, &context->names_list, list) {
                 list_del(&n->list);
-                if (n->name && n->name_put)
-                        final_putname(n->name);
+                if (n->name)
+                        putname(n->name);
                 if (n->should_free)
                         kfree(n);
         }
@@ -1711,9 +1688,6 @@ static struct audit_names *audit_alloc_name(struct audit_context *context,
         list_add_tail(&aname->list, &context->names_list);
 
         context->name_count++;
-#if AUDIT_DEBUG
-        context->ino_count++;
-#endif
         return aname;
 }
 
@@ -1734,8 +1708,10 @@ __audit_reusename(const __user char *uptr)
         list_for_each_entry(n, &context->names_list, list) {
                 if (!n->name)
                         continue;
-                if (n->name->uptr == uptr)
+                if (n->name->uptr == uptr) {
+                        n->name->refcnt++;
                         return n->name;
+                }
         }
         return NULL;
 }
@@ -1752,19 +1728,8 @@ void __audit_getname(struct filename *name)
         struct audit_context *context = current->audit_context;
         struct audit_names *n;
 
-        if (!context->in_syscall) {
-#if AUDIT_DEBUG == 2
-                pr_err("%s:%d(:%d): ignoring getname(%p)\n",
-                       __FILE__, __LINE__, context->serial, name);
-                dump_stack();
-#endif
+        if (!context->in_syscall)
                 return;
-        }
-
-#if AUDIT_DEBUG
-        /* The filename _must_ have a populated ->name */
-        BUG_ON(!name->name);
-#endif
 
         n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN);
         if (!n)
@@ -1772,56 +1737,13 @@ void __audit_getname(struct filename *name)
 
         n->name = name;
         n->name_len = AUDIT_NAME_FULL;
-        n->name_put = true;
         name->aname = n;
+        name->refcnt++;
 
         if (!context->pwd.dentry)
                 get_fs_pwd(current->fs, &context->pwd);
 }
 
-/* audit_putname - intercept a putname request
- * @name: name to intercept and delay for putname
- *
- * If we have stored the name from getname in the audit context,
- * then we delay the putname until syscall exit.
- * Called from include/linux/fs.h:putname().
- */
-void audit_putname(struct filename *name)
-{
-        struct audit_context *context = current->audit_context;
-
-        BUG_ON(!context);
-        if (!name->aname || !context->in_syscall) {
-#if AUDIT_DEBUG == 2
-                pr_err("%s:%d(:%d): final_putname(%p)\n",
-                       __FILE__, __LINE__, context->serial, name);
-                if (context->name_count) {
-                        struct audit_names *n;
-                        int i = 0;
-
-                        list_for_each_entry(n, &context->names_list, list)
-                                pr_err("name[%d] = %p = %s\n", i++, n->name,
-                                       n->name->name ?: "(null)");
-                        }
-#endif
-                final_putname(name);
-        }
-#if AUDIT_DEBUG
-        else {
-                ++context->put_count;
-                if (context->put_count > context->name_count) {
-                        pr_err("%s:%d(:%d): major=%d in_syscall=%d putname(%p)"
-                               " name_count=%d put_count=%d\n",
-                               __FILE__, __LINE__,
-                               context->serial, context->major,
-                               context->in_syscall, name->name,
-                               context->name_count, context->put_count);
-                        dump_stack();
-                }
-        }
-#endif
-}
-
 /**
  * __audit_inode - store the inode and device from a lookup
  * @name: name being audited
@@ -1842,10 +1764,6 @@ void __audit_inode(struct filename *name, const struct dentry *dentry,
         if (!name)
                 goto out_alloc;
 
-#if AUDIT_DEBUG
-        /* The struct filename _must_ have a populated ->name */
-        BUG_ON(!name->name);
-#endif
         /*
          * If we have a pointer to an audit_names entry already, then we can
          * just use it directly if the type is correct.
@@ -1863,7 +1781,17 @@ void __audit_inode(struct filename *name, const struct dentry *dentry,
         }
 
         list_for_each_entry_reverse(n, &context->names_list, list) {
-                if (!n->name || strcmp(n->name->name, name->name))
+                if (n->ino) {
+                        /* valid inode number, use that for the comparison */
+                        if (n->ino != inode->i_ino ||
+                            n->dev != inode->i_sb->s_dev)
+                                continue;
+                } else if (n->name) {
+                        /* inode number has not been set, check the name */
+                        if (strcmp(n->name->name, name->name))
+                                continue;
+                } else
+                        /* no inode and no name (?!) ... this is odd ... */
                         continue;
 
                 /* match the correct record type */
@@ -1882,44 +1810,11 @@ out_alloc:
         n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN);
         if (!n)
                 return;
-        /* unfortunately, while we may have a path name to record with the
-         * inode, we can't always rely on the string lasting until the end of
-         * the syscall so we need to create our own copy, it may fail due to
-         * memory allocation issues, but we do our best */
         if (name) {
-                /* we can't use getname_kernel() due to size limits */
-                size_t len = strlen(name->name) + 1;
-                struct filename *new = __getname();
-
-                if (unlikely(!new))
-                        goto out;
-
-                if (len <= (PATH_MAX - sizeof(*new))) {
-                        new->name = (char *)(new) + sizeof(*new);
-                        new->separate = false;
-                } else if (len <= PATH_MAX) {
-                        /* this looks odd, but is due to final_putname() */
-                        struct filename *new2;
-
-                        new2 = kmalloc(sizeof(*new2), GFP_KERNEL);
-                        if (unlikely(!new2)) {
-                                __putname(new);
-                                goto out;
-                        }
-                        new2->name = (char *)new;
-                        new2->separate = true;
-                        new = new2;
-                } else {
-                        /* we should never get here, but let's be safe */
-                        __putname(new);
-                        goto out;
-                }
-                strlcpy((char *)new->name, name->name, len);
-                new->uptr = NULL;
-                new->aname = n;
-                n->name = new;
-                n->name_put = true;
+                n->name = name;
+                name->refcnt++;
         }
+
 out:
         if (parent) {
                 n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
@@ -1970,11 +1865,16 @@ void __audit_inode_child(const struct inode *parent,
 
         /* look for a parent entry first */
         list_for_each_entry(n, &context->names_list, list) {
-                if (!n->name || n->type != AUDIT_TYPE_PARENT)
+                if (!n->name ||
+                    (n->type != AUDIT_TYPE_PARENT &&
+                     n->type != AUDIT_TYPE_UNKNOWN))
                         continue;
 
-                if (n->ino == parent->i_ino &&
-                    !audit_compare_dname_path(dname, n->name->name, n->name_len)) {
+                if (n->ino == parent->i_ino && n->dev == parent->i_sb->s_dev &&
+                    !audit_compare_dname_path(dname,
+                                              n->name->name, n->name_len)) {
+                        if (n->type == AUDIT_TYPE_UNKNOWN)
+                                n->type = AUDIT_TYPE_PARENT;
                         found_parent = n;
                         break;
                 }
@@ -1983,11 +1883,8 @@ void __audit_inode_child(const struct inode *parent,
         /* is there a matching child entry? */
         list_for_each_entry(n, &context->names_list, list) {
                 /* can only match entries that have a name */
-                if (!n->name || n->type != type)
-                        continue;
-
-                /* if we found a parent, make sure this one is a child of it */
-                if (found_parent && (n->name != found_parent->name))
+                if (!n->name ||
+                    (n->type != type && n->type != AUDIT_TYPE_UNKNOWN))
                         continue;
 
                 if (!strcmp(dname, n->name->name) ||
@@ -1995,6 +1892,8 @@ void __audit_inode_child(const struct inode *parent,
                                                 found_parent ?
                                                 found_parent->name_len :
                                                 AUDIT_NAME_FULL)) {
+                        if (n->type == AUDIT_TYPE_UNKNOWN)
+                                n->type = type;
                         found_child = n;
                         break;
                 }
@@ -2019,10 +1918,10 @@ void __audit_inode_child(const struct inode *parent,
                 if (found_parent) {
                         found_child->name = found_parent->name;
                         found_child->name_len = AUDIT_NAME_FULL;
-                        /* don't call __putname() */
-                        found_child->name_put = false;
+                        found_child->name->refcnt++;
                 }
         }
+
         if (inode)
                 audit_copy_inode(found_child, dentry, inode);
         else