Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull third pile of VFS updates from Al Viro:
 "Stuff from Jeff Layton, mostly.  Sanitizing interplay between audit
  and namei, removing a lot of insanity from audit_inode() mess and
  getting things ready for his ESTALE patchset."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  procfs: don't need a PATH_MAX allocation to hold a string representation of an int
  vfs: embed struct filename inside of names_cache allocation if possible
  audit: make audit_inode take struct filename
  vfs: make path_openat take a struct filename pointer
  vfs: turn do_path_lookup into wrapper around struct filename variant
  audit: allow audit code to satisfy getname requests from its names_list
  vfs: define struct filename and have getname() return it
  vfs: unexport getname and putname symbols
  acct: constify the name arg to acct_on
  vfs: allocate page instead of names_cache buffer in mount_block_root
  audit: overhaul __audit_inode_child to accomodate retrying
  audit: optimize audit_compare_dname_path
  audit: make audit_compare_dname_path use parent_len helper
  audit: remove dirlen argument to audit_compare_dname_path
  audit: set the name_len in audit_inode for parent lookups
  audit: add a new "type" field to audit_names struct
  audit: reverse arguments to audit_inode_child
  audit: no need to walk list in audit_inode if name is NULL
  audit: pass in dentry to audit_copy_inode wherever possible
  audit: remove unnecessary NULL ptr checks from do_path_lookup

5 files changed, 199 insertions, 99 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index 6cd7529..051e071 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -193,7 +193,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file,
 	}
 }
 
-static int acct_on(char *name)
+static int acct_on(struct filename *pathname)
 {
 	struct file *file;
 	struct vfsmount *mnt;
@@ -201,7 +201,7 @@ static int acct_on(char *name)
 	struct bsd_acct_struct *acct = NULL;
 
 	/* Difference from BSD - they don't do O_APPEND */
-	file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
+	file = file_open_name(pathname, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
@@ -260,7 +260,7 @@ SYSCALL_DEFINE1(acct, const char __user *, name)
 		return -EPERM;
 
 	if (name) {
-		char *tmp = getname(name);
+		struct filename *tmp = getname(name);
 		if (IS_ERR(tmp))
 			return (PTR_ERR(tmp));
 		error = acct_on(tmp);
diff --git a/kernel/audit.h b/kernel/audit.h
index 9eb3d79..d51cba8 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -74,12 +74,15 @@ static inline int audit_hash_ino(u32 ino)
 	return (ino & (AUDIT_INODE_BUCKETS-1));
 }
 
+/* Indicates that audit should log the full pathname. */
+#define AUDIT_NAME_FULL -1
+
 extern int audit_match_class(int class, unsigned syscall);
 extern int audit_comparator(const u32 left, const u32 op, const u32 right);
 extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right);
 extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right);
-extern int audit_compare_dname_path(const char *dname, const char *path,
-				    int *dirlen);
+extern int parent_len(const char *path);
+extern int audit_compare_dname_path(const char *dname, const char *path, int plen);
 extern struct sk_buff *	    audit_make_reply(int pid, int seq, int type,
 					     int done, int multi,
 					     const void *payload, int size);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 1c22ec3..9a9ae6e 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -265,7 +265,8 @@ static void audit_update_watch(struct audit_parent *parent,
 	/* Run all of the watches on this parent looking for the one that
 	 * matches the given dname */
 	list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) {
-		if (audit_compare_dname_path(dname, owatch->path, NULL))
+		if (audit_compare_dname_path(dname, owatch->path,
+					     AUDIT_NAME_FULL))
 			continue;
 
 		/* If the update involves invalidating rules, do the inode-based
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index c4bcdba..7f19f23 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1298,41 +1298,60 @@ int audit_gid_comparator(kgid_t left, u32 op, kgid_t right)
 	}
 }
 
-/* Compare given dentry name with last component in given path,
- * return of 0 indicates a match. */
-int audit_compare_dname_path(const char *dname, const char *path,
-			     int *dirlen)
+/**
+ * parent_len - find the length of the parent portion of a pathname
+ * @path: pathname of which to determine length
+ */
+int parent_len(const char *path)
 {
-	int dlen, plen;
+	int plen;
 	const char *p;
 
-	if (!dname || !path)
-		return 1;
-
-	dlen = strlen(dname);
 	plen = strlen(path);
-	if (plen < dlen)
-		return 1;
+
+	if (plen == 0)
+		return plen;
 
 	/* disregard trailing slashes */
 	p = path + plen - 1;
 	while ((*p == '/') && (p > path))
 		p--;
 
-	/* find last path component */
-	p = p - dlen + 1;
-	if (p < path)
+	/* walk backward until we find the next slash or hit beginning */
+	while ((*p != '/') && (p > path))
+		p--;
+
+	/* did we find a slash? Then increment to include it in path */
+	if (*p == '/')
+		p++;
+
+	return p - path;
+}
+
+/**
+ * audit_compare_dname_path - compare given dentry name with last component in
+ * 			      given path. Return of 0 indicates a match.
+ * @dname:	dentry name that we're comparing
+ * @path:	full pathname that we're comparing
+ * @parentlen:	length of the parent if known. Passing in AUDIT_NAME_FULL
+ * 		here indicates that we must compute this value.
+ */
+int audit_compare_dname_path(const char *dname, const char *path, int parentlen)
+{
+	int dlen, pathlen;
+	const char *p;
+
+	dlen = strlen(dname);
+	pathlen = strlen(path);
+	if (pathlen < dlen)
 		return 1;
-	else if (p > path) {
-		if (*--p != '/')
-			return 1;
-		else
-			p++;
-	}
 
-	/* return length of path's directory component */
-	if (dirlen)
-		*dirlen = p - path;
+	parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen;
+	if (pathlen - parentlen != dlen)
+		return 1;
+
+	p = path + parentlen;
+
 	return strncmp(p, dname, dlen);
 }
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index f4a7756..2f186ed 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -81,9 +81,6 @@
  * a name dynamically and also add those to the list anchored by names_list. */
 #define AUDIT_NAMES	5
 
-/* Indicates that audit should log the full pathname. */
-#define AUDIT_NAME_FULL -1
-
 /* no execve audit message should be longer than this (userspace limits) */
 #define MAX_EXECVE_AUDIT_LEN 7500
 
@@ -106,27 +103,29 @@ struct audit_cap_data {
  * we don't let putname() free it (instead we free all of the saved
  * pointers at syscall exit time).
  *
- * Further, in fs/namei.c:path_lookup() we store the inode and device. */
+ * Further, in fs/namei.c:path_lookup() we store the inode and device.
+ */
 struct audit_names {
-	struct list_head list;		/* audit_context->names_list */
-	const char	*name;
-	unsigned long	ino;
-	dev_t		dev;
-	umode_t		mode;
-	kuid_t		uid;
-	kgid_t		gid;
-	dev_t		rdev;
-	u32		osid;
-	struct audit_cap_data fcap;
-	unsigned int	fcap_ver;
-	int		name_len;	/* number of name's characters to log */
-	bool		name_put;	/* call __putname() for this name */
+	struct list_head	list;		/* audit_context->names_list */
+	struct filename	*name;
+	unsigned long		ino;
+	dev_t			dev;
+	umode_t			mode;
+	kuid_t			uid;
+	kgid_t			gid;
+	dev_t			rdev;
+	u32			osid;
+	struct audit_cap_data	 fcap;
+	unsigned int		fcap_ver;
+	int			name_len;	/* number of name's characters to log */
+	unsigned char		type;		/* record type */
+	bool			name_put;	/* call __putname() for this name */
 	/*
 	 * This was an allocated audit_names and not from the array of
 	 * names allocated in the task audit context.  Thus this name
 	 * should be freed on syscall exit
 	 */
-	bool		should_free;
+	bool			should_free;
 };
 
 struct audit_aux_data {
@@ -998,7 +997,7 @@ static inline void audit_free_names(struct audit_context *context)
 		       context->ino_count);
 		list_for_each_entry(n, &context->names_list, list) {
 			printk(KERN_ERR "names[%d] = %p = %s\n", i,
-			       n->name, n->name ?: "(null)");
+			       n->name, n->name->name ?: "(null)");
 		}
 		dump_stack();
 		return;
@@ -1555,7 +1554,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n,
 		case AUDIT_NAME_FULL:
 			/* log the full path */
 			audit_log_format(ab, " name=");
-			audit_log_untrustedstring(ab, n->name);
+			audit_log_untrustedstring(ab, n->name->name);
 			break;
 		case 0:
 			/* name was specified as a relative path and the
@@ -1565,7 +1564,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n,
 		default:
 			/* log the name's directory component */
 			audit_log_format(ab, " name=");
-			audit_log_n_untrustedstring(ab, n->name,
+			audit_log_n_untrustedstring(ab, n->name->name,
 						    n->name_len);
 		}
 	} else
@@ -1995,7 +1994,8 @@ retry:
 #endif
 }
 
-static struct audit_names *audit_alloc_name(struct audit_context *context)
+static struct audit_names *audit_alloc_name(struct audit_context *context,
+						unsigned char type)
 {
 	struct audit_names *aname;
 
@@ -2010,6 +2010,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context)
 	}
 
 	aname->ino = (unsigned long)-1;
+	aname->type = type;
 	list_add_tail(&aname->list, &context->names_list);
 
 	context->name_count++;
@@ -2020,13 +2021,36 @@ static struct audit_names *audit_alloc_name(struct audit_context *context)
 }
 
 /**
+ * audit_reusename - fill out filename with info from existing entry
+ * @uptr: userland ptr to pathname
+ *
+ * Search the audit_names list for the current audit context. If there is an
+ * existing entry with a matching "uptr" then return the filename
+ * associated with that audit_name. If not, return NULL.
+ */
+struct filename *
+__audit_reusename(const __user char *uptr)
+{
+	struct audit_context *context = current->audit_context;
+	struct audit_names *n;
+
+	list_for_each_entry(n, &context->names_list, list) {
+		if (!n->name)
+			continue;
+		if (n->name->uptr == uptr)
+			return n->name;
+	}
+	return NULL;
+}
+
+/**
  * audit_getname - add a name to the list
  * @name: name to add
  *
  * Add a name to the list of audit names for this context.
  * Called from fs/namei.c:getname().
  */
-void __audit_getname(const char *name)
+void __audit_getname(struct filename *name)
 {
 	struct audit_context *context = current->audit_context;
 	struct audit_names *n;
@@ -2040,13 +2064,19 @@ void __audit_getname(const char *name)
 		return;
 	}
 
-	n = audit_alloc_name(context);
+#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)
 		return;
 
 	n->name = name;
 	n->name_len = AUDIT_NAME_FULL;
 	n->name_put = true;
+	name->aname = n;
 
 	if (!context->pwd.dentry)
 		get_fs_pwd(current->fs, &context->pwd);
@@ -2059,7 +2089,7 @@ void __audit_getname(const char *name)
  * then we delay the putname until syscall exit.
  * Called from include/linux/fs.h:putname().
  */
-void audit_putname(const char *name)
+void audit_putname(struct filename *name)
 {
 	struct audit_context *context = current->audit_context;
 
@@ -2074,7 +2104,7 @@ void audit_putname(const char *name)
 
 			list_for_each_entry(n, &context->names_list, list)
 				printk(KERN_ERR "name[%d] = %p = %s\n", i,
-				       n->name, n->name ?: "(null)");
+				       n->name, n->name->name ?: "(null)");
 			}
 #endif
 		__putname(name);
@@ -2088,8 +2118,8 @@ void audit_putname(const char *name)
 			       " put_count=%d\n",
 			       __FILE__, __LINE__,
 			       context->serial, context->major,
-			       context->in_syscall, name, context->name_count,
-			       context->put_count);
+			       context->in_syscall, name->name,
+			       context->name_count, context->put_count);
 			dump_stack();
 		}
 	}
@@ -2132,13 +2162,13 @@ static void audit_copy_inode(struct audit_names *name, const struct dentry *dent
 }
 
 /**
- * audit_inode - store the inode and device from a lookup
+ * __audit_inode - store the inode and device from a lookup
  * @name: name being audited
  * @dentry: dentry being audited
- *
- * Called from fs/namei.c:path_lookup().
+ * @parent: does this dentry represent the parent?
  */
-void __audit_inode(const char *name, const struct dentry *dentry)
+void __audit_inode(struct filename *name, const struct dentry *dentry,
+		   unsigned int parent)
 {
 	struct audit_context *context = current->audit_context;
 	const struct inode *inode = dentry->d_inode;
@@ -2147,24 +2177,69 @@ void __audit_inode(const char *name, const struct dentry *dentry)
 	if (!context->in_syscall)
 		return;
 
+	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.
+	 */
+	n = name->aname;
+	if (n) {
+		if (parent) {
+			if (n->type == AUDIT_TYPE_PARENT ||
+			    n->type == AUDIT_TYPE_UNKNOWN)
+				goto out;
+		} else {
+			if (n->type != AUDIT_TYPE_PARENT)
+				goto out;
+		}
+	}
+
 	list_for_each_entry_reverse(n, &context->names_list, list) {
-		if (n->name && (n->name == name))
-			goto out;
+		/* does the name pointer match? */
+		if (!n->name || n->name->name != name->name)
+			continue;
+
+		/* match the correct record type */
+		if (parent) {
+			if (n->type == AUDIT_TYPE_PARENT ||
+			    n->type == AUDIT_TYPE_UNKNOWN)
+				goto out;
+		} else {
+			if (n->type != AUDIT_TYPE_PARENT)
+				goto out;
+		}
 	}
 
-	/* unable to find the name from a previous getname() */
-	n = audit_alloc_name(context);
+out_alloc:
+	/* unable to find the name from a previous getname(). Allocate a new
+	 * anonymous entry.
+	 */
+	n = audit_alloc_name(context, AUDIT_TYPE_NORMAL);
 	if (!n)
 		return;
 out:
+	if (parent) {
+		n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
+		n->type = AUDIT_TYPE_PARENT;
+	} else {
+		n->name_len = AUDIT_NAME_FULL;
+		n->type = AUDIT_TYPE_NORMAL;
+	}
 	handle_path(dentry);
 	audit_copy_inode(n, dentry, inode);
 }
 
 /**
- * audit_inode_child - collect inode info for created/removed objects
- * @dentry: dentry being audited
+ * __audit_inode_child - collect inode info for created/removed objects
  * @parent: inode of dentry parent
+ * @dentry: dentry being audited
+ * @type:   AUDIT_TYPE_* value that we're looking for
  *
  * For syscalls that create or remove filesystem objects, audit_inode
  * can only collect information for the filesystem object's parent.
@@ -2174,15 +2249,14 @@ out:
  * must be hooked prior, in order to capture the target inode during
  * unsuccessful attempts.
  */
-void __audit_inode_child(const struct dentry *dentry,
-			 const struct inode *parent)
+void __audit_inode_child(const struct inode *parent,
+			 const struct dentry *dentry,
+			 const unsigned char type)
 {
 	struct audit_context *context = current->audit_context;
-	const char *found_parent = NULL, *found_child = NULL;
 	const struct inode *inode = dentry->d_inode;
 	const char *dname = dentry->d_name.name;
-	struct audit_names *n;
-	int dirlen = 0;
+	struct audit_names *n, *found_parent = NULL, *found_child = NULL;
 
 	if (!context->in_syscall)
 		return;
@@ -2190,62 +2264,65 @@ void __audit_inode_child(const struct dentry *dentry,
 	if (inode)
 		handle_one(inode);
 
-	/* parent is more likely, look for it first */
+	/* look for a parent entry first */
 	list_for_each_entry(n, &context->names_list, list) {
-		if (!n->name)
+		if (!n->name || n->type != AUDIT_TYPE_PARENT)
 			continue;
 
 		if (n->ino == parent->i_ino &&
-		    !audit_compare_dname_path(dname, n->name, &dirlen)) {
-			n->name_len = dirlen; /* update parent data in place */
-			found_parent = n->name;
-			goto add_names;
+		    !audit_compare_dname_path(dname, n->name->name, n->name_len)) {
+			found_parent = n;
+			break;
 		}
 	}
 
-	/* no matching parent, look for matching child */
+	/* is there a matching child entry? */
 	list_for_each_entry(n, &context->names_list, list) {
-		if (!n->name)
+		/* can only match entries that have a name */
+		if (!n->name || n->type != type)
 			continue;
 
-		/* strcmp() is the more likely scenario */
-		if (!strcmp(dname, n->name) ||
-		     !audit_compare_dname_path(dname, n->name, &dirlen)) {
-			if (inode)
-				audit_copy_inode(n, NULL, inode);
-			else
-				n->ino = (unsigned long)-1;
-			found_child = n->name;
-			goto add_names;
+		/* if we found a parent, make sure this one is a child of it */
+		if (found_parent && (n->name != found_parent->name))
+			continue;
+
+		if (!strcmp(dname, n->name->name) ||
+		    !audit_compare_dname_path(dname, n->name->name,
+						found_parent ?
+						found_parent->name_len :
+						AUDIT_NAME_FULL)) {
+			found_child = n;
+			break;
 		}
 	}
 
-add_names:
 	if (!found_parent) {
-		n = audit_alloc_name(context);
+		/* create a new, "anonymous" parent record */
+		n = audit_alloc_name(context, AUDIT_TYPE_PARENT);
 		if (!n)
 			return;
 		audit_copy_inode(n, NULL, parent);
 	}
 
 	if (!found_child) {
-		n = audit_alloc_name(context);
-		if (!n)
+		found_child = audit_alloc_name(context, type);
+		if (!found_child)
 			return;
 
 		/* Re-use the name belonging to the slot for a matching parent
 		 * directory. All names for this context are relinquished in
 		 * audit_free_names() */
 		if (found_parent) {
-			n->name = found_parent;
-			n->name_len = AUDIT_NAME_FULL;
+			found_child->name = found_parent->name;
+			found_child->name_len = AUDIT_NAME_FULL;
 			/* don't call __putname() */
-			n->name_put = false;
+			found_child->name_put = false;
 		}
-
-		if (inode)
-			audit_copy_inode(n, NULL, inode);
 	}
+	if (inode)
+		audit_copy_inode(found_child, dentry, inode);
+	else
+		found_child->ino = (unsigned long)-1;
 }
 EXPORT_SYMBOL_GPL(__audit_inode_child);