Merge branch 'for-linus' of git://git.infradead.org/users/eparis/notify

* 'for-linus' of git://git.infradead.org/users/eparis/notify: (22 commits)
  Ensure FMODE_NONOTIFY is not set by userspace
  make fanotify_read() restartable across signals
  fsnotify: remove alignment padding from fsnotify_mark on 64 bit builds
  fs/notify/fanotify/fanotify_user.c: fix warnings
  fanotify: Fix FAN_CLOSE comments
  fanotify: do not recalculate the mask if the ignored mask changed
  fanotify: ignore events on directories unless specifically requested
  fsnotify: rename FS_IN_ISDIR to FS_ISDIR
  fanotify: do not send events for irregular files
  fanotify: limit number of listeners per user
  fanotify: allow userspace to override max marks
  fanotify: limit the number of marks in a single fanotify group
  fanotify: allow userspace to override max queue depth
  fsnotify: implement a default maximum queue depth
  fanotify: ignore fanotify ignore marks if open writers
  fanotify: allow userspace to flush all marks
  fsnotify: call fsnotify_parent in perm events
  fsnotify: correctly handle return codes from listeners
  fanotify: use __aligned_u64 in fanotify userspace metadata
  fanotify: implement fanotify listener ordering
  ...

12 files changed, 219 insertions, 64 deletions

diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig
index b388443c3a09..22c629eedd82 100644
--- a/fs/notify/Kconfig
+++ b/fs/notify/Kconfig
@@ -3,4 +3,4 @@ config FSNOTIFY
 
 source "fs/notify/dnotify/Kconfig"
 source "fs/notify/inotify/Kconfig"
-#source "fs/notify/fanotify/Kconfig"
+source "fs/notify/fanotify/Kconfig"
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 85366c78cc37..b04f88eed09e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -131,6 +131,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
         BUILD_BUG_ON(FAN_Q_OVERFLOW != FS_Q_OVERFLOW);
         BUILD_BUG_ON(FAN_OPEN_PERM != FS_OPEN_PERM);
         BUILD_BUG_ON(FAN_ACCESS_PERM != FS_ACCESS_PERM);
+        BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR);
 
         pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
@@ -160,20 +161,21 @@ static bool fanotify_should_send_event(struct fsnotify_group *group,
                                        __u32 event_mask, void *data, int data_type)
 {
         __u32 marks_mask, marks_ignored_mask;
+        struct path *path = data;
 
         pr_debug("%s: group=%p to_tell=%p inode_mark=%p vfsmnt_mark=%p "
                  "mask=%x data=%p data_type=%d\n", __func__, group, to_tell,
                  inode_mark, vfsmnt_mark, event_mask, data, data_type);
 
-        /* sorry, fanotify only gives a damn about files and dirs */
-        if (!S_ISREG(to_tell->i_mode) &&
-            !S_ISDIR(to_tell->i_mode))
-                return false;
-
         /* if we don't have enough info to send an event to userspace say no */
         if (data_type != FSNOTIFY_EVENT_PATH)
                 return false;
 
+        /* sorry, fanotify only gives a damn about files and dirs */
+        if (!S_ISREG(path->dentry->d_inode->i_mode) &&
+            !S_ISDIR(path->dentry->d_inode->i_mode))
+                return false;
+
         if (inode_mark && vfsmnt_mark) {
                 marks_mask = (vfsmnt_mark->mask | inode_mark->mask);
                 marks_ignored_mask = (vfsmnt_mark->ignored_mask | inode_mark->ignored_mask);
@@ -194,16 +196,29 @@ static bool fanotify_should_send_event(struct fsnotify_group *group,
                 BUG();
         }
 
+        if (S_ISDIR(path->dentry->d_inode->i_mode) &&
+            (marks_ignored_mask & FS_ISDIR))
+                return false;
+
         if (event_mask & marks_mask & ~marks_ignored_mask)
                 return true;
 
         return false;
 }
 
+static void fanotify_free_group_priv(struct fsnotify_group *group)
+{
+        struct user_struct *user;
+
+        user = group->fanotify_data.user;
+        atomic_dec(&user->fanotify_listeners);
+        free_uid(user);
+}
+
 const struct fsnotify_ops fanotify_fsnotify_ops = {
         .handle_event = fanotify_handle_event,
         .should_send_event = fanotify_should_send_event,
-        .free_group_priv = NULL,
+        .free_group_priv = fanotify_free_group_priv,
         .free_event_priv = NULL,
         .freeing_mark = NULL,
 };
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index bbcb98e7fcc6..063224812b7e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -16,6 +16,10 @@
 
 #include <asm/ioctls.h>
 
+#define FANOTIFY_DEFAULT_MAX_EVENTS     16384
+#define FANOTIFY_DEFAULT_MAX_MARKS      8192
+#define FANOTIFY_DEFAULT_MAX_LISTENERS  128
+
 extern const struct fsnotify_ops fanotify_fsnotify_ops;
 
 static struct kmem_cache *fanotify_mark_cache __read_mostly;
@@ -326,7 +330,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
                 ret = -EAGAIN;
                 if (file->f_flags & O_NONBLOCK)
                         break;
-                ret = -EINTR;
+                ret = -ERESTARTSYS;
                 if (signal_pending(current))
                         break;
 
@@ -372,11 +376,10 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t
 static int fanotify_release(struct inode *ignored, struct file *file)
 {
         struct fsnotify_group *group = file->private_data;
-        struct fanotify_response_event *re, *lre;
-
-        pr_debug("%s: file=%p group=%p\n", __func__, file, group);
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+        struct fanotify_response_event *re, *lre;
+
         mutex_lock(&group->fanotify_data.access_mutex);
 
         group->fanotify_data.bypass_perm = true;
@@ -554,18 +557,24 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
                                        __u32 mask,
                                        unsigned int flags)
 {
-        __u32 oldmask;
+        __u32 oldmask = -1;
 
         spin_lock(&fsn_mark->lock);
         if (!(flags & FAN_MARK_IGNORED_MASK)) {
                 oldmask = fsn_mark->mask;
                 fsnotify_set_mark_mask_locked(fsn_mark, (oldmask | mask));
         } else {
-                oldmask = fsn_mark->ignored_mask;
-                fsnotify_set_mark_ignored_mask_locked(fsn_mark, (oldmask | mask));
+                __u32 tmask = fsn_mark->ignored_mask | mask;
+                fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
                 if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
                         fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
         }
+
+        if (!(flags & FAN_MARK_ONDIR)) {
+                __u32 tmask = fsn_mark->ignored_mask | FAN_ONDIR;
+                fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
+        }
+
         spin_unlock(&fsn_mark->lock);
 
         return mask & ~oldmask;
@@ -582,6 +591,9 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
         if (!fsn_mark) {
                 int ret;
 
+                if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
+                        return -ENOSPC;
+
                 fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
                 if (!fsn_mark)
                         return -ENOMEM;
@@ -610,10 +622,23 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 
         pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
 
+        /*
+         * If some other task has this inode open for write we should not add
+         * an ignored mark, unless that ignored mark is supposed to survive
+         * modification changes anyway.
+         */
+        if ((flags & FAN_MARK_IGNORED_MASK) &&
+            !(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+            (atomic_read(&inode->i_writecount) > 0))
+                return 0;
+
         fsn_mark = fsnotify_find_inode_mark(group, inode);
         if (!fsn_mark) {
                 int ret;
 
+                if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
+                        return -ENOSPC;
+
                 fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
                 if (!fsn_mark)
                         return -ENOMEM;
@@ -637,6 +662,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 {
         struct fsnotify_group *group;
         int f_flags, fd;
+        struct user_struct *user;
 
         pr_debug("%s: flags=%d event_f_flags=%d\n",
                 __func__, flags, event_f_flags);
@@ -647,6 +673,12 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
         if (flags & ~FAN_ALL_INIT_FLAGS)
                 return -EINVAL;
 
+        user = get_current_user();
+        if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
+                free_uid(user);
+                return -EMFILE;
+        }
+
         f_flags = O_RDWR | FMODE_NONOTIFY;
         if (flags & FAN_CLOEXEC)
                 f_flags |= O_CLOEXEC;
@@ -658,12 +690,47 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
         if (IS_ERR(group))
                 return PTR_ERR(group);
 
+        group->fanotify_data.user = user;
+        atomic_inc(&user->fanotify_listeners);
+
         group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
         mutex_init(&group->fanotify_data.access_mutex);
         init_waitqueue_head(&group->fanotify_data.access_waitq);
         INIT_LIST_HEAD(&group->fanotify_data.access_list);
 #endif
+        switch (flags & FAN_ALL_CLASS_BITS) {
+        case FAN_CLASS_NOTIF:
+                group->priority = FS_PRIO_0;
+                break;
+        case FAN_CLASS_CONTENT:
+                group->priority = FS_PRIO_1;
+                break;
+        case FAN_CLASS_PRE_CONTENT:
+                group->priority = FS_PRIO_2;
+                break;
+        default:
+                fd = -EINVAL;
+                goto out_put_group;
+        }
+
+        if (flags & FAN_UNLIMITED_QUEUE) {
+                fd = -EPERM;
+                if (!capable(CAP_SYS_ADMIN))
+                        goto out_put_group;
+                group->max_events = UINT_MAX;
+        } else {
+                group->max_events = FANOTIFY_DEFAULT_MAX_EVENTS;
+        }
+
+        if (flags & FAN_UNLIMITED_MARKS) {
+                fd = -EPERM;
+                if (!capable(CAP_SYS_ADMIN))
+                        goto out_put_group;
+                group->fanotify_data.max_marks = UINT_MAX;
+        } else {
+                group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
+        }
 
         fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
         if (fd < 0)
@@ -704,6 +771,12 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
         default:
                 return -EINVAL;
         }
+
+        if (mask & FAN_ONDIR) {
+                flags |= FAN_MARK_ONDIR;
+                mask &= ~FAN_ONDIR;
+        }
+
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
         if (mask & ~(FAN_ALL_EVENTS | FAN_ALL_PERM_EVENTS | FAN_EVENT_ON_CHILD))
 #else
@@ -719,6 +792,16 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
         ret = -EINVAL;
         if (unlikely(filp->f_op != &fanotify_fops))
                 goto fput_and_out;
+        group = filp->private_data;
+
+        /*
+         * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF.  These are not
+         * allowed to set permissions events.
+         */
+        ret = -EINVAL;
+        if (mask & FAN_ALL_PERM_EVENTS &&
+            group->priority == FS_PRIO_0)
+                goto fput_and_out;
 
         ret = fanotify_find_path(dfd, pathname, &path, flags);
         if (ret)
@@ -729,7 +812,6 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
                 inode = path.dentry->d_inode;
         else
                 mnt = path.mnt;
-        group = filp->private_data;
 
         /* create/update an inode mark */
         switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 4498a208df94..20dc218707ca 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -84,16 +84,17 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 }
 
 /* Notify this dentry's parent about a child's events. */
-void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
+int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 {
         struct dentry *parent;
         struct inode *p_inode;
+        int ret = 0;
 
         if (!dentry)
                 dentry = path->dentry;
 
         if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
-                return;
+                return 0;
 
         parent = dget_parent(dentry);
         p_inode = parent->d_inode;
@@ -106,14 +107,16 @@ void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
                 mask |= FS_EVENT_ON_CHILD;
 
                 if (path)
-                        fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
-                                 dentry->d_name.name, 0);
+                        ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
+                                       dentry->d_name.name, 0);
                 else
-                        fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
-                                 dentry->d_name.name, 0);
+                        ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
+                                       dentry->d_name.name, 0);
         }
 
         dput(parent);
+
+        return ret;
 }
 EXPORT_SYMBOL_GPL(__fsnotify_parent);
 
@@ -252,20 +255,23 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 
                 if (inode_group > vfsmount_group) {
                         /* handle inode */
-                        send_to_group(to_tell, NULL, inode_mark, NULL, mask, data,
-                                      data_is, cookie, file_name, &event);
+                        ret = send_to_group(to_tell, NULL, inode_mark, NULL, mask, data,
+                                            data_is, cookie, file_name, &event);
                         /* we didn't use the vfsmount_mark */
                         vfsmount_group = NULL;
                 } else if (vfsmount_group > inode_group) {
-                        send_to_group(to_tell, mnt, NULL, vfsmount_mark, mask, data,
-                                      data_is, cookie, file_name, &event);
+                        ret = send_to_group(to_tell, mnt, NULL, vfsmount_mark, mask, data,
+                                            data_is, cookie, file_name, &event);
                         inode_group = NULL;
                 } else {
-                        send_to_group(to_tell, mnt, inode_mark, vfsmount_mark,
-                                      mask, data, data_is, cookie, file_name,
-                                      &event);
+                        ret = send_to_group(to_tell, mnt, inode_mark, vfsmount_mark,
+                                            mask, data, data_is, cookie, file_name,
+                                            &event);
                 }
 
+                if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
+                        goto out;
+
                 if (inode_group)
                         inode_node = srcu_dereference(inode_node->next,
                                                       &fsnotify_mark_srcu);
@@ -273,7 +279,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
                         vfsmount_node = srcu_dereference(vfsmount_node->next,
                                                          &fsnotify_mark_srcu);
         }
-
+        ret = 0;
+out:
         srcu_read_unlock(&fsnotify_mark_srcu, idx);
         /*
          * fsnotify_create_event() took a reference so the event can't be cleaned
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 21ed10660b80..4c29fcf557d1 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -177,7 +177,8 @@ void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *mark,
  * Attach an initialized mark to a given inode.
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group and for which inodes.  These
- * marks are ordered according to the group's location in memory.
+ * marks are ordered according to priority, highest number first, and then by
+ * the group's location in memory.
  */
 int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
                             struct fsnotify_group *group, struct inode *inode,
@@ -211,7 +212,11 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
                         goto out;
                 }
 
-                if (mark->group < lmark->group)
+                if (mark->group->priority < lmark->group->priority)
+                        continue;
+
+                if ((mark->group->priority == lmark->group->priority) &&
+                    (mark->group < lmark->group))
                         continue;
 
                 hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 24edc1185d53..444c305a468c 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -862,7 +862,7 @@ static int __init inotify_user_setup(void)
         BUILD_BUG_ON(IN_Q_OVERFLOW != FS_Q_OVERFLOW);
         BUILD_BUG_ON(IN_IGNORED != FS_IN_IGNORED);
         BUILD_BUG_ON(IN_EXCL_UNLINK != FS_EXCL_UNLINK);
-        BUILD_BUG_ON(IN_ISDIR != FS_IN_ISDIR);
+        BUILD_BUG_ON(IN_ISDIR != FS_ISDIR);
         BUILD_BUG_ON(IN_ONESHOT != FS_IN_ONESHOT);
 
         BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21);
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index 56772b578fbd..85eebff6d0d7 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -169,7 +169,11 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
                         goto out;
                 }
 
-                if (mark->group < lmark->group)
+                if (mark->group->priority < lmark->group->priority)
+                        continue;
+
+                if ((mark->group->priority == lmark->group->priority) &&
+                    (mark->group < lmark->group))
                         continue;
 
                 hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 90e3ed3a3144..97319a8fc1e0 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -118,6 +118,7 @@ header-y += eventpoll.h
 header-y += ext2_fs.h
 header-y += fadvise.h
 header-y += falloc.h
+header-y += fanotify.h
 header-y += fb.h
 header-y += fcntl.h
 header-y += fd.h
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 63531a6b4d2a..0f0121467fc4 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -6,18 +6,19 @@
 /* the following events that user-space can register for */
 #define FAN_ACCESS              0x00000001      /* File was accessed */
 #define FAN_MODIFY              0x00000002      /* File was modified */
-#define FAN_CLOSE_WRITE         0x00000008      /* Unwrittable file closed */
-#define FAN_CLOSE_NOWRITE       0x00000010      /* Writtable file closed */
+#define FAN_CLOSE_WRITE         0x00000008      /* Writtable file closed */
+#define FAN_CLOSE_NOWRITE       0x00000010      /* Unwrittable file closed */
 #define FAN_OPEN                0x00000020      /* File was opened */
 
-#define FAN_EVENT_ON_CHILD      0x08000000      /* interested in child events */
-
-/* FIXME currently Q's have no limit.... */
 #define FAN_Q_OVERFLOW          0x00004000      /* Event queued overflowed */
 
 #define FAN_OPEN_PERM           0x00010000      /* File open in perm check */
 #define FAN_ACCESS_PERM         0x00020000      /* File accessed in perm check */
 
+#define FAN_ONDIR               0x40000000      /* event occurred against dir */
+
+#define FAN_EVENT_ON_CHILD      0x08000000      /* interested in child events */
+
 /* helper events */
 #define FAN_CLOSE               (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */
 
@@ -25,7 +26,19 @@
 #define FAN_CLOEXEC             0x00000001
 #define FAN_NONBLOCK            0x00000002
 
-#define FAN_ALL_INIT_FLAGS      (FAN_CLOEXEC | FAN_NONBLOCK)
+/* These are NOT bitwise flags.  Both bits are used togther.  */
+#define FAN_CLASS_NOTIF         0x00000000
+#define FAN_CLASS_CONTENT       0x00000004
+#define FAN_CLASS_PRE_CONTENT   0x00000008
+#define FAN_ALL_CLASS_BITS      (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \
+                                 FAN_CLASS_PRE_CONTENT)
+
+#define FAN_UNLIMITED_QUEUE     0x00000010
+#define FAN_UNLIMITED_MARKS     0x00000020
+
+#define FAN_ALL_INIT_FLAGS      (FAN_CLOEXEC | FAN_NONBLOCK | \
+                                 FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\
+                                 FAN_UNLIMITED_MARKS)
 
 /* flags used for fanotify_modify_mark() */
 #define FAN_MARK_ADD            0x00000001
@@ -36,6 +49,10 @@
 #define FAN_MARK_IGNORED_MASK   0x00000020
 #define FAN_MARK_IGNORED_SURV_MODIFY    0x00000040
 #define FAN_MARK_FLUSH          0x00000080
+#ifdef __KERNEL__
+/* not valid from userspace, only kernel internal */
+#define FAN_MARK_ONDIR          0x00000100
+#endif
 
 #define FAN_ALL_MARK_FLAGS      (FAN_MARK_ADD |\
                                  FAN_MARK_REMOVE |\
@@ -43,7 +60,8 @@
                                  FAN_MARK_ONLYDIR |\
                                  FAN_MARK_MOUNT |\
                                  FAN_MARK_IGNORED_MASK |\
-                                 FAN_MARK_IGNORED_SURV_MODIFY)
+                                 FAN_MARK_IGNORED_SURV_MODIFY |\
+                                 FAN_MARK_FLUSH)
 
 /*
  * All of the events - we build the list by hand so that we can add flags in
@@ -70,10 +88,10 @@
 struct fanotify_event_metadata {
         __u32 event_len;
         __u32 vers;
-        __u64 mask;
+        __aligned_u64 mask;
         __s32 fd;
         __s32 pid;
-} __attribute__ ((packed));
+};
 
 struct fanotify_response {
         __s32 fd;
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 59d0df43ff9d..5c185fa27089 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -26,12 +26,12 @@ static inline void fsnotify_d_instantiate(struct dentry *dentry,
 }
 
 /* Notify this dentry's parent about a child's events. */
-static inline void fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
+static inline int fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 {
         if (!dentry)
                 dentry = path->dentry;
 
-        __fsnotify_parent(path, dentry, mask);
+        return __fsnotify_parent(path, dentry, mask);
 }
 
 /* simple call site for access decisions */
@@ -40,6 +40,7 @@ static inline int fsnotify_perm(struct file *file, int mask)
         struct path *path = &file->f_path;
         struct inode *inode = path->dentry->d_inode;
         __u32 fsnotify_mask = 0;
+        int ret;
 
         if (file->f_mode & FMODE_NONOTIFY)
                 return 0;
@@ -52,6 +53,10 @@ static inline int fsnotify_perm(struct file *file, int mask)
         else
                 BUG();
 
+        ret = fsnotify_parent(path, NULL, fsnotify_mask);
+        if (ret)
+                return ret;
+
         return fsnotify(inode, fsnotify_mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
 }
 
@@ -93,8 +98,8 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
                 old_dir_mask |= FS_DN_RENAME;
 
         if (isdir) {
-                old_dir_mask |= FS_IN_ISDIR;
-                new_dir_mask |= FS_IN_ISDIR;
+                old_dir_mask |= FS_ISDIR;
+                new_dir_mask |= FS_ISDIR;
         }
 
         fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
@@ -132,7 +137,7 @@ static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
         __u32 mask = FS_DELETE;
 
         if (isdir)
-                mask |= FS_IN_ISDIR;
+                mask |= FS_ISDIR;
 
         fsnotify_parent(NULL, dentry, mask);
 }
@@ -174,7 +179,7 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct
  */
 static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 {
-        __u32 mask = (FS_CREATE | FS_IN_ISDIR);
+        __u32 mask = (FS_CREATE | FS_ISDIR);
         struct inode *d_inode = dentry->d_inode;
 
         audit_inode_child(dentry, inode);
@@ -192,7 +197,7 @@ static inline void fsnotify_access(struct file *file)
         __u32 mask = FS_ACCESS;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= FS_IN_ISDIR;
+                mask |= FS_ISDIR;
 
         if (!(file->f_mode & FMODE_NONOTIFY)) {
                 fsnotify_parent(path, NULL, mask);
@@ -210,7 +215,7 @@ static inline void fsnotify_modify(struct file *file)
         __u32 mask = FS_MODIFY;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= FS_IN_ISDIR;
+                mask |= FS_ISDIR;
 
         if (!(file->f_mode & FMODE_NONOTIFY)) {
                 fsnotify_parent(path, NULL, mask);
@@ -228,12 +233,13 @@ static inline void fsnotify_open(struct file *file)
         __u32 mask = FS_OPEN;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= FS_IN_ISDIR;
+                mask |= FS_ISDIR;
 
-        if (!(file->f_mode & FMODE_NONOTIFY)) {
-                fsnotify_parent(path, NULL, mask);
-                fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
-        }
+        /* FMODE_NONOTIFY must never be set from user */
+        file->f_mode &= ~FMODE_NONOTIFY;
+
+        fsnotify_parent(path, NULL, mask);
+        fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
 }
 
 /*
@@ -247,7 +253,7 @@ static inline void fsnotify_close(struct file *file)
         __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= FS_IN_ISDIR;
+                mask |= FS_ISDIR;
 
         if (!(file->f_mode & FMODE_NONOTIFY)) {
                 fsnotify_parent(path, NULL, mask);
@@ -264,7 +270,7 @@ static inline void fsnotify_xattr(struct dentry *dentry)
         __u32 mask = FS_ATTRIB;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= FS_IN_ISDIR;
+                mask |= FS_ISDIR;
 
         fsnotify_parent(NULL, dentry, mask);
         fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
@@ -299,7 +305,7 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 
         if (mask) {
                 if (S_ISDIR(inode->i_mode))
-                        mask |= FS_IN_ISDIR;
+                        mask |= FS_ISDIR;
 
                 fsnotify_parent(NULL, dentry, mask);
                 fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index e40190d16878..0a68f924f06f 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -45,7 +45,7 @@
 #define FS_ACCESS_PERM          0x00020000      /* access event in a permissions hook */
 
 #define FS_EXCL_UNLINK          0x04000000      /* do not send events if object is unlinked */
-#define FS_IN_ISDIR             0x40000000      /* event occurred against dir */
+#define FS_ISDIR                0x40000000      /* event occurred against dir */
 #define FS_IN_ONESHOT           0x80000000      /* only send event once */
 
 #define FS_DN_RENAME            0x10000000      /* file renamed */
@@ -64,13 +64,15 @@
 
 #define FS_MOVE                 (FS_MOVED_FROM | FS_MOVED_TO)
 
+#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM)
+
 #define ALL_FSNOTIFY_EVENTS (FS_ACCESS | FS_MODIFY | FS_ATTRIB | \
                              FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN | \
                              FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE | \
                              FS_DELETE | FS_DELETE_SELF | FS_MOVE_SELF | \
                              FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \
                              FS_OPEN_PERM | FS_ACCESS_PERM | FS_EXCL_UNLINK | \
-                             FS_IN_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \
+                             FS_ISDIR | FS_IN_ONESHOT | FS_DN_RENAME | \
                              FS_DN_MULTISHOT | FS_EVENT_ON_CHILD)
 
 struct fsnotify_group;
@@ -129,6 +131,14 @@ struct fsnotify_group {
         wait_queue_head_t notification_waitq;   /* read() on the notification file blocks on this waitq */
         unsigned int q_len;                     /* events on the queue */
         unsigned int max_events;                /* maximum events allowed on the list */
+        /*
+         * Valid fsnotify group priorities.  Events are send in order from highest
+         * priority to lowest priority.  We default to the lowest priority.
+         */
+        #define FS_PRIO_0       0 /* normal notifiers, no permissions */
+        #define FS_PRIO_1       1 /* fanotify content based access control */
+        #define FS_PRIO_2       2 /* fanotify pre-content access */
+        unsigned int priority;
 
         /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
         spinlock_t mark_lock;           /* protect marks_list */
@@ -159,6 +169,8 @@ struct fsnotify_group {
                         bool bypass_perm; /* protected by access_mutex */
 #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
                         int f_flags;
+                        unsigned int max_marks;
+                        struct user_struct *user;
                 } fanotify_data;
 #endif /* CONFIG_FANOTIFY */
         };
@@ -275,8 +287,8 @@ struct fsnotify_mark {
                 struct fsnotify_inode_mark i;
                 struct fsnotify_vfsmount_mark m;
         };
-        __u32 ignored_mask;             /* events types to ignore */
         struct list_head free_g_list;   /* tmp list used when freeing this mark */
+        __u32 ignored_mask;             /* events types to ignore */
 #define FSNOTIFY_MARK_FLAG_INODE                0x01
 #define FSNOTIFY_MARK_FLAG_VFSMOUNT             0x02
 #define FSNOTIFY_MARK_FLAG_OBJECT_PINNED        0x04
@@ -294,7 +306,7 @@ struct fsnotify_mark {
 /* main fsnotify call to send events */
 extern int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
                     const unsigned char *name, u32 cookie);
-extern void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask);
+extern int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask);
 extern void __fsnotify_inode_delete(struct inode *inode);
 extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt);
 extern u32 fsnotify_get_cookie(void);
@@ -423,8 +435,10 @@ static inline int fsnotify(struct inode *to_tell, __u32 mask, void *data, int da
         return 0;
 }
 
-static inline void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
-{}
+static inline int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
+{
+        return 0;
+}
 
 static inline void __fsnotify_inode_delete(struct inode *inode)
 {}
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f53cdf216cef..d0036e52a24a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -672,6 +672,9 @@ struct user_struct {
         atomic_t inotify_watches; /* How many inotify watches does this user have? */
         atomic_t inotify_devs;  /* How many inotify devs does this user have opened? */
 #endif
+#ifdef CONFIG_FANOTIFY
+        atomic_t fanotify_listeners;
+#endif
 #ifdef CONFIG_EPOLL
         atomic_t epoll_watches; /* The number of file descriptors currently watched */
 #endif