1 files changed, 21 insertions, 79 deletions

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index dcd2040d330c..e46ca685b9be 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -29,14 +29,12 @@
 #include <linux/init.h> /* module_init */
 #include <linux/inotify.h>
 #include <linux/kernel.h> /* roundup() */
-#include <linux/magic.h> /* superblock magic number */
-#include <linux/mount.h> /* mntget */
 #include <linux/namei.h> /* LOOKUP_FOLLOW */
-#include <linux/path.h> /* struct path */
 #include <linux/sched.h> /* struct user */
 #include <linux/slab.h> /* struct kmem_cache */
 #include <linux/syscalls.h>
 #include <linux/types.h>
+#include <linux/anon_inodes.h>
 #include <linux/uaccess.h>
 #include <linux/poll.h>
 #include <linux/wait.h>
@@ -45,8 +43,6 @@
 
 #include <asm/ioctls.h>
 
-static struct vfsmount *inotify_mnt __read_mostly;
-
 /* these are configurable via /proc/sys/fs/inotify/ */
 static int inotify_max_user_instances __read_mostly;
 static int inotify_max_queued_events __read_mostly;
@@ -69,36 +65,30 @@ static int zero;
 
 ctl_table inotify_table[] = {
         {
-                .ctl_name       = INOTIFY_MAX_USER_INSTANCES,
                 .procname       = "max_user_instances",
                 .data           = &inotify_max_user_instances,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
         },
         {
-                .ctl_name       = INOTIFY_MAX_USER_WATCHES,
                 .procname       = "max_user_watches",
                 .data           = &inotify_max_user_watches,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero,
         },
         {
-                .ctl_name       = INOTIFY_MAX_QUEUED_EVENTS,
                 .procname       = "max_queued_events",
                 .data           = &inotify_max_queued_events,
                 .maxlen         = sizeof(int),
                 .mode           = 0644,
-                .proc_handler   = &proc_dointvec_minmax,
-                .strategy       = &sysctl_intvec,
+                .proc_handler   = proc_dointvec_minmax,
                 .extra1         = &zero
         },
-        { .ctl_name = 0 }
+        { }
 };
 #endif /* CONFIG_SYSCTL */
 
@@ -556,21 +546,24 @@ retry:
         if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
                 goto out_err;
 
+        /* we are putting the mark on the idr, take a reference */
+        fsnotify_get_mark(&tmp_ientry->fsn_entry);
+
         spin_lock(&group->inotify_data.idr_lock);
         ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
-                                group->inotify_data.last_wd,
+                                group->inotify_data.last_wd+1,
                                 &tmp_ientry->wd);
         spin_unlock(&group->inotify_data.idr_lock);
         if (ret) {
+                /* we didn't get on the idr, drop the idr reference */
+                fsnotify_put_mark(&tmp_ientry->fsn_entry);
+
                 /* idr was out of memory allocate and try again */
                 if (ret == -EAGAIN)
                         goto retry;
                 goto out_err;
         }
 
-        /* we put the mark on the idr, take a reference */
-        fsnotify_get_mark(&tmp_ientry->fsn_entry);
-
         /* we are on the idr, now get on the inode */
         ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
         if (ret) {
@@ -588,16 +581,13 @@ retry:
         /* return the watch descriptor for this new entry */
         ret = tmp_ientry->wd;
 
-        /* match the ref from fsnotify_init_markentry() */
-        fsnotify_put_mark(&tmp_ientry->fsn_entry);
-
         /* if this mark added a new event update the group mask */
         if (mask & ~group->mask)
                 fsnotify_recalc_group_mask(group);
 
 out_err:
-        if (ret < 0)
-                kmem_cache_free(inotify_inode_mark_cachep, tmp_ientry);
+        /* match the ref from fsnotify_init_markentry() */
+        fsnotify_put_mark(&tmp_ientry->fsn_entry);
 
         return ret;
 }
@@ -638,7 +628,7 @@ static struct fsnotify_group *inotify_new_group(struct user_struct *user, unsign
 
         spin_lock_init(&group->inotify_data.idr_lock);
         idr_init(&group->inotify_data.idr);
-        group->inotify_data.last_wd = 1;
+        group->inotify_data.last_wd = 0;
         group->inotify_data.user = user;
         group->inotify_data.fa = NULL;
 
@@ -651,8 +641,7 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
 {
         struct fsnotify_group *group;
         struct user_struct *user;
-        struct file *filp;
-        int fd, ret;
+        int ret;
 
         /* Check the IN_* constants for consistency.  */
         BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
@@ -661,16 +650,6 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
         if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
                 return -EINVAL;
 
-        fd = get_unused_fd_flags(flags & O_CLOEXEC);
-        if (fd < 0)
-                return fd;
-
-        filp = get_empty_filp();
-        if (!filp) {
-                ret = -ENFILE;
-                goto out_put_fd;
-        }
-
         user = get_current_user();
         if (unlikely(atomic_read(&user->inotify_devs) >=
                         inotify_max_user_instances)) {
@@ -685,25 +664,16 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
                 goto out_free_uid;
         }
 
-        filp->f_op = &inotify_fops;
-        filp->f_path.mnt = mntget(inotify_mnt);
-        filp->f_path.dentry = dget(inotify_mnt->mnt_root);
-        filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping;
-        filp->f_mode = FMODE_READ;
-        filp->f_flags = O_RDONLY | (flags & O_NONBLOCK);
-        filp->private_data = group;
-
         atomic_inc(&user->inotify_devs);
 
-        fd_install(fd, filp);
-
-        return fd;
+        ret = anon_inode_getfd("inotify", &inotify_fops, group,
+                                  O_RDONLY | flags);
+        if (ret >= 0)
+                return ret;
 
+        atomic_dec(&user->inotify_devs);
 out_free_uid:
         free_uid(user);
-        put_filp(filp);
-out_put_fd:
-        put_unused_fd(fd);
         return ret;
 }
 
@@ -747,10 +717,6 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
 
         /* create/update an inode mark */
         ret = inotify_update_watch(group, inode, mask);
-        if (unlikely(ret))
-                goto path_put_and_out;
-
-path_put_and_out:
         path_put(&path);
 fput_and_out:
         fput_light(filp, fput_needed);
@@ -794,20 +760,6 @@ out:
         return ret;
 }
 
-static int
-inotify_get_sb(struct file_system_type *fs_type, int flags,
-               const char *dev_name, void *data, struct vfsmount *mnt)
-{
-        return get_sb_pseudo(fs_type, "inotify", NULL,
-                        INOTIFYFS_SUPER_MAGIC, mnt);
-}
-
-static struct file_system_type inotify_fs_type = {
-    .name       = "inotifyfs",
-    .get_sb     = inotify_get_sb,
-    .kill_sb    = kill_anon_super,
-};
-
 /*
  * inotify_user_setup - Our initialization function.  Note that we cannnot return
  * error because we have compiled-in VFS hooks.  So an (unlikely) failure here
@@ -815,16 +767,6 @@ static struct file_system_type inotify_fs_type = {
  */
 static int __init inotify_user_setup(void)
 {
-        int ret;
-
-        ret = register_filesystem(&inotify_fs_type);
-        if (unlikely(ret))
-                panic("inotify: register_filesystem returned %d!\n", ret);
-
-        inotify_mnt = kern_mount(&inotify_fs_type);
-        if (IS_ERR(inotify_mnt))
-                panic("inotify: kern_mount ret %ld!\n", PTR_ERR(inotify_mnt));
-
         inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark_entry, SLAB_PANIC);
         event_priv_cachep = KMEM_CACHE(inotify_event_private_data, SLAB_PANIC);