summaryrefslogtreecommitdiffstats
path: root/fs/notify/fanotify
diff options
context:
space:
mode:
Diffstat (limited to 'fs/notify/fanotify')
-rw-r--r--fs/notify/fanotify/Kconfig27
-rw-r--r--fs/notify/fanotify/Makefile2
-rw-r--r--fs/notify/fanotify/fanotify.c1076
-rw-r--r--fs/notify/fanotify/fanotify.h500
-rw-r--r--fs/notify/fanotify/fanotify_user.c1900
5 files changed, 3505 insertions, 0 deletions
diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
new file mode 100644
index 000000000..a511f9d86
--- /dev/null
+++ b/fs/notify/fanotify/Kconfig
@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config FANOTIFY
+ bool "Filesystem wide access notification"
+ select FSNOTIFY
+ select EXPORTFS
+ default n
+ help
+ Say Y here to enable fanotify support. fanotify is a file access
+ notification system which differs from inotify in that it sends
+ an open file descriptor to the userspace listener along with
+ the event.
+
+ If unsure, say Y.
+
+config FANOTIFY_ACCESS_PERMISSIONS
+ bool "fanotify permissions checking"
+ depends on FANOTIFY
+ depends on SECURITY
+ default n
+ help
+ Say Y here is you want fanotify listeners to be able to make permissions
+ decisions concerning filesystem events. This is used by some fanotify
+ listeners which need to scan files before allowing the system access to
+ use those files. This is used by some anti-malware vendors and by some
+ hierarchical storage management systems.
+
+ If unsure, say N.
diff --git a/fs/notify/fanotify/Makefile b/fs/notify/fanotify/Makefile
new file mode 100644
index 000000000..25ef22291
--- /dev/null
+++ b/fs/notify/fanotify/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_FANOTIFY) += fanotify.o fanotify_user.o
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
new file mode 100644
index 000000000..a2a15bc4d
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.c
@@ -0,0 +1,1076 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fanotify.h>
+#include <linux/fdtable.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/init.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h> /* UINT_MAX */
+#include <linux/mount.h>
+#include <linux/sched.h>
+#include <linux/sched/user.h>
+#include <linux/sched/signal.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+#include <linux/audit.h>
+#include <linux/sched/mm.h>
+#include <linux/statfs.h>
+#include <linux/stringhash.h>
+
+#include "fanotify.h"
+
+static bool fanotify_path_equal(const struct path *p1, const struct path *p2)
+{
+ return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
+}
+
+static unsigned int fanotify_hash_path(const struct path *path)
+{
+ return hash_ptr(path->dentry, FANOTIFY_EVENT_HASH_BITS) ^
+ hash_ptr(path->mnt, FANOTIFY_EVENT_HASH_BITS);
+}
+
+static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
+ __kernel_fsid_t *fsid2)
+{
+ return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
+}
+
+static unsigned int fanotify_hash_fsid(__kernel_fsid_t *fsid)
+{
+ return hash_32(fsid->val[0], FANOTIFY_EVENT_HASH_BITS) ^
+ hash_32(fsid->val[1], FANOTIFY_EVENT_HASH_BITS);
+}
+
+static bool fanotify_fh_equal(struct fanotify_fh *fh1,
+ struct fanotify_fh *fh2)
+{
+ if (fh1->type != fh2->type || fh1->len != fh2->len)
+ return false;
+
+ return !fh1->len ||
+ !memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
+}
+
+static unsigned int fanotify_hash_fh(struct fanotify_fh *fh)
+{
+ long salt = (long)fh->type | (long)fh->len << 8;
+
+ /*
+ * full_name_hash() works long by long, so it handles fh buf optimally.
+ */
+ return full_name_hash((void *)salt, fanotify_fh_buf(fh), fh->len);
+}
+
+static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
+ struct fanotify_fid_event *ffe2)
+{
+ /* Do not merge fid events without object fh */
+ if (!ffe1->object_fh.len)
+ return false;
+
+ return fanotify_fsid_equal(&ffe1->fsid, &ffe2->fsid) &&
+ fanotify_fh_equal(&ffe1->object_fh, &ffe2->object_fh);
+}
+
+static bool fanotify_info_equal(struct fanotify_info *info1,
+ struct fanotify_info *info2)
+{
+ if (info1->dir_fh_totlen != info2->dir_fh_totlen ||
+ info1->dir2_fh_totlen != info2->dir2_fh_totlen ||
+ info1->file_fh_totlen != info2->file_fh_totlen ||
+ info1->name_len != info2->name_len ||
+ info1->name2_len != info2->name2_len)
+ return false;
+
+ if (info1->dir_fh_totlen &&
+ !fanotify_fh_equal(fanotify_info_dir_fh(info1),
+ fanotify_info_dir_fh(info2)))
+ return false;
+
+ if (info1->dir2_fh_totlen &&
+ !fanotify_fh_equal(fanotify_info_dir2_fh(info1),
+ fanotify_info_dir2_fh(info2)))
+ return false;
+
+ if (info1->file_fh_totlen &&
+ !fanotify_fh_equal(fanotify_info_file_fh(info1),
+ fanotify_info_file_fh(info2)))
+ return false;
+
+ if (info1->name_len &&
+ memcmp(fanotify_info_name(info1), fanotify_info_name(info2),
+ info1->name_len))
+ return false;
+
+ return !info1->name2_len ||
+ !memcmp(fanotify_info_name2(info1), fanotify_info_name2(info2),
+ info1->name2_len);
+}
+
+static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
+ struct fanotify_name_event *fne2)
+{
+ struct fanotify_info *info1 = &fne1->info;
+ struct fanotify_info *info2 = &fne2->info;
+
+ /* Do not merge name events without dir fh */
+ if (!info1->dir_fh_totlen)
+ return false;
+
+ if (!fanotify_fsid_equal(&fne1->fsid, &fne2->fsid))
+ return false;
+
+ return fanotify_info_equal(info1, info2);
+}
+
+static bool fanotify_error_event_equal(struct fanotify_error_event *fee1,
+ struct fanotify_error_event *fee2)
+{
+ /* Error events against the same file system are always merged. */
+ if (!fanotify_fsid_equal(&fee1->fsid, &fee2->fsid))
+ return false;
+
+ return true;
+}
+
+static bool fanotify_should_merge(struct fanotify_event *old,
+ struct fanotify_event *new)
+{
+ pr_debug("%s: old=%p new=%p\n", __func__, old, new);
+
+ if (old->hash != new->hash ||
+ old->type != new->type || old->pid != new->pid)
+ return false;
+
+ /*
+ * We want to merge many dirent events in the same dir (i.e.
+ * creates/unlinks/renames), but we do not want to merge dirent
+ * events referring to subdirs with dirent events referring to
+ * non subdirs, otherwise, user won't be able to tell from a
+ * mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+
+ * unlink pair or rmdir+create pair of events.
+ */
+ if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR))
+ return false;
+
+ /*
+ * FAN_RENAME event is reported with special info record types,
+ * so we cannot merge it with other events.
+ */
+ if ((old->mask & FAN_RENAME) != (new->mask & FAN_RENAME))
+ return false;
+
+ switch (old->type) {
+ case FANOTIFY_EVENT_TYPE_PATH:
+ return fanotify_path_equal(fanotify_event_path(old),
+ fanotify_event_path(new));
+ case FANOTIFY_EVENT_TYPE_FID:
+ return fanotify_fid_event_equal(FANOTIFY_FE(old),
+ FANOTIFY_FE(new));
+ case FANOTIFY_EVENT_TYPE_FID_NAME:
+ return fanotify_name_event_equal(FANOTIFY_NE(old),
+ FANOTIFY_NE(new));
+ case FANOTIFY_EVENT_TYPE_FS_ERROR:
+ return fanotify_error_event_equal(FANOTIFY_EE(old),
+ FANOTIFY_EE(new));
+ default:
+ WARN_ON_ONCE(1);
+ }
+
+ return false;
+}
+
+/* Limit event merges to limit CPU overhead per event */
+#define FANOTIFY_MAX_MERGE_EVENTS 128
+
+/* and the list better be locked by something too! */
+static int fanotify_merge(struct fsnotify_group *group,
+ struct fsnotify_event *event)
+{
+ struct fanotify_event *old, *new = FANOTIFY_E(event);
+ unsigned int bucket = fanotify_event_hash_bucket(group, new);
+ struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+ int i = 0;
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, bucket);
+
+ /*
+ * Don't merge a permission event with any other event so that we know
+ * the event structure we have created in fanotify_handle_event() is the
+ * one we should check for permission response.
+ */
+ if (fanotify_is_perm_event(new->mask))
+ return 0;
+
+ hlist_for_each_entry(old, hlist, merge_list) {
+ if (++i > FANOTIFY_MAX_MERGE_EVENTS)
+ break;
+ if (fanotify_should_merge(old, new)) {
+ old->mask |= new->mask;
+
+ if (fanotify_is_error_event(old->mask))
+ FANOTIFY_EE(old)->err_count++;
+
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Wait for response to permission event. The function also takes care of
+ * freeing the permission event (or offloads that in case the wait is canceled
+ * by a signal). The function returns 0 in case access got allowed by userspace,
+ * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case
+ * the wait got interrupted by a signal.
+ */
+static int fanotify_get_response(struct fsnotify_group *group,
+ struct fanotify_perm_event *event,
+ struct fsnotify_iter_info *iter_info)
+{
+ int ret;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ ret = wait_event_killable(group->fanotify_data.access_waitq,
+ event->state == FAN_EVENT_ANSWERED);
+ /* Signal pending? */
+ if (ret < 0) {
+ spin_lock(&group->notification_lock);
+ /* Event reported to userspace and no answer yet? */
+ if (event->state == FAN_EVENT_REPORTED) {
+ /* Event will get freed once userspace answers to it */
+ event->state = FAN_EVENT_CANCELED;
+ spin_unlock(&group->notification_lock);
+ return ret;
+ }
+ /* Event not yet reported? Just remove it. */
+ if (event->state == FAN_EVENT_INIT) {
+ fsnotify_remove_queued_event(group, &event->fae.fse);
+ /* Permission events are not supposed to be hashed */
+ WARN_ON_ONCE(!hlist_unhashed(&event->fae.merge_list));
+ }
+ /*
+ * Event may be also answered in case signal delivery raced
+ * with wakeup. In that case we have nothing to do besides
+ * freeing the event and reporting error.
+ */
+ spin_unlock(&group->notification_lock);
+ goto out;
+ }
+
+ /* userspace responded, convert to something usable */
+ switch (event->response & ~FAN_AUDIT) {
+ case FAN_ALLOW:
+ ret = 0;
+ break;
+ case FAN_DENY:
+ default:
+ ret = -EPERM;
+ }
+
+ /* Check if the response should be audited */
+ if (event->response & FAN_AUDIT)
+ audit_fanotify(event->response & ~FAN_AUDIT);
+
+ pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
+ group, event, ret);
+out:
+ fsnotify_destroy_event(group, &event->fae.fse);
+
+ return ret;
+}
+
+/*
+ * This function returns a mask for an event that only contains the flags
+ * that have been specifically requested by the user. Flags that may have
+ * been included within the event mask, but have not been explicitly
+ * requested by the user, will not be present in the returned mask.
+ */
+static u32 fanotify_group_event_mask(struct fsnotify_group *group,
+ struct fsnotify_iter_info *iter_info,
+ u32 *match_mask, u32 event_mask,
+ const void *data, int data_type,
+ struct inode *dir)
+{
+ __u32 marks_mask = 0, marks_ignore_mask = 0;
+ __u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS |
+ FANOTIFY_EVENT_FLAGS;
+ const struct path *path = fsnotify_data_path(data, data_type);
+ unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+ struct fsnotify_mark *mark;
+ bool ondir = event_mask & FAN_ONDIR;
+ int type;
+
+ pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
+ __func__, iter_info->report_mask, event_mask, data, data_type);
+
+ if (!fid_mode) {
+ /* Do we have path to open a file descriptor? */
+ if (!path)
+ return 0;
+ /* Path type events are only relevant for files and dirs */
+ if (!d_is_reg(path->dentry) && !d_can_lookup(path->dentry))
+ return 0;
+ } else if (!(fid_mode & FAN_REPORT_FID)) {
+ /* Do we have a directory inode to report? */
+ if (!dir && !ondir)
+ return 0;
+ }
+
+ fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+ /*
+ * Apply ignore mask depending on event flags in ignore mask.
+ */
+ marks_ignore_mask |=
+ fsnotify_effective_ignore_mask(mark, ondir, type);
+
+ /*
+ * Send the event depending on event flags in mark mask.
+ */
+ if (!fsnotify_mask_applicable(mark->mask, ondir, type))
+ continue;
+
+ marks_mask |= mark->mask;
+
+ /* Record the mark types of this group that matched the event */
+ *match_mask |= 1U << type;
+ }
+
+ test_mask = event_mask & marks_mask & ~marks_ignore_mask;
+
+ /*
+ * For dirent modification events (create/delete/move) that do not carry
+ * the child entry name information, we report FAN_ONDIR for mkdir/rmdir
+ * so user can differentiate them from creat/unlink.
+ *
+ * For backward compatibility and consistency, do not report FAN_ONDIR
+ * to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR
+ * to user in fid mode for all event types.
+ *
+ * We never report FAN_EVENT_ON_CHILD to user, but we do pass it in to
+ * fanotify_alloc_event() when group is reporting fid as indication
+ * that event happened on child.
+ */
+ if (fid_mode) {
+ /* Do not report event flags without any event */
+ if (!(test_mask & ~FANOTIFY_EVENT_FLAGS))
+ return 0;
+ } else {
+ user_mask &= ~FANOTIFY_EVENT_FLAGS;
+ }
+
+ return test_mask & user_mask;
+}
+
+/*
+ * Check size needed to encode fanotify_fh.
+ *
+ * Return size of encoded fh without fanotify_fh header.
+ * Return 0 on failure to encode.
+ */
+static int fanotify_encode_fh_len(struct inode *inode)
+{
+ int dwords = 0;
+ int fh_len;
+
+ if (!inode)
+ return 0;
+
+ exportfs_encode_inode_fh(inode, NULL, &dwords, NULL);
+ fh_len = dwords << 2;
+
+ /*
+ * struct fanotify_error_event might be preallocated and is
+ * limited to MAX_HANDLE_SZ. This should never happen, but
+ * safeguard by forcing an invalid file handle.
+ */
+ if (WARN_ON_ONCE(fh_len > MAX_HANDLE_SZ))
+ return 0;
+
+ return fh_len;
+}
+
+/*
+ * Encode fanotify_fh.
+ *
+ * Return total size of encoded fh including fanotify_fh header.
+ * Return 0 on failure to encode.
+ */
+static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
+ unsigned int fh_len, unsigned int *hash,
+ gfp_t gfp)
+{
+ int dwords, type = 0;
+ char *ext_buf = NULL;
+ void *buf = fh->buf;
+ int err;
+
+ fh->type = FILEID_ROOT;
+ fh->len = 0;
+ fh->flags = 0;
+
+ /*
+ * Invalid FHs are used by FAN_FS_ERROR for errors not
+ * linked to any inode. The f_handle won't be reported
+ * back to userspace.
+ */
+ if (!inode)
+ goto out;
+
+ /*
+ * !gpf means preallocated variable size fh, but fh_len could
+ * be zero in that case if encoding fh len failed.
+ */
+ err = -ENOENT;
+ if (fh_len < 4 || WARN_ON_ONCE(fh_len % 4) || fh_len > MAX_HANDLE_SZ)
+ goto out_err;
+
+ /* No external buffer in a variable size allocated fh */
+ if (gfp && fh_len > FANOTIFY_INLINE_FH_LEN) {
+ /* Treat failure to allocate fh as failure to encode fh */
+ err = -ENOMEM;
+ ext_buf = kmalloc(fh_len, gfp);
+ if (!ext_buf)
+ goto out_err;
+
+ *fanotify_fh_ext_buf_ptr(fh) = ext_buf;
+ buf = ext_buf;
+ fh->flags |= FANOTIFY_FH_FLAG_EXT_BUF;
+ }
+
+ dwords = fh_len >> 2;
+ type = exportfs_encode_inode_fh(inode, buf, &dwords, NULL);
+ err = -EINVAL;
+ if (!type || type == FILEID_INVALID || fh_len != dwords << 2)
+ goto out_err;
+
+ fh->type = type;
+ fh->len = fh_len;
+
+out:
+ /*
+ * Mix fh into event merge key. Hash might be NULL in case of
+ * unhashed FID events (i.e. FAN_FS_ERROR).
+ */
+ if (hash)
+ *hash ^= fanotify_hash_fh(fh);
+
+ return FANOTIFY_FH_HDR_LEN + fh_len;
+
+out_err:
+ pr_warn_ratelimited("fanotify: failed to encode fid (type=%d, len=%d, err=%i)\n",
+ type, fh_len, err);
+ kfree(ext_buf);
+ *fanotify_fh_ext_buf_ptr(fh) = NULL;
+ /* Report the event without a file identifier on encode error */
+ fh->type = FILEID_INVALID;
+ fh->len = 0;
+ return 0;
+}
+
+/*
+ * FAN_REPORT_FID is ambiguous in that it reports the fid of the child for
+ * some events and the fid of the parent for create/delete/move events.
+ *
+ * With the FAN_REPORT_TARGET_FID flag, the fid of the child is reported
+ * also in create/delete/move events in addition to the fid of the parent
+ * and the name of the child.
+ */
+static inline bool fanotify_report_child_fid(unsigned int fid_mode, u32 mask)
+{
+ if (mask & ALL_FSNOTIFY_DIRENT_EVENTS)
+ return (fid_mode & FAN_REPORT_TARGET_FID);
+
+ return (fid_mode & FAN_REPORT_FID) && !(mask & FAN_ONDIR);
+}
+
+/*
+ * The inode to use as identifier when reporting fid depends on the event
+ * and the group flags.
+ *
+ * With the group flag FAN_REPORT_TARGET_FID, always report the child fid.
+ *
+ * Without the group flag FAN_REPORT_TARGET_FID, report the modified directory
+ * fid on dirent events and the child fid otherwise.
+ *
+ * For example:
+ * FS_ATTRIB reports the child fid even if reported on a watched parent.
+ * FS_CREATE reports the modified dir fid without FAN_REPORT_TARGET_FID.
+ * and reports the created child fid with FAN_REPORT_TARGET_FID.
+ */
+static struct inode *fanotify_fid_inode(u32 event_mask, const void *data,
+ int data_type, struct inode *dir,
+ unsigned int fid_mode)
+{
+ if ((event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) &&
+ !(fid_mode & FAN_REPORT_TARGET_FID))
+ return dir;
+
+ return fsnotify_data_inode(data, data_type);
+}
+
+/*
+ * The inode to use as identifier when reporting dir fid depends on the event.
+ * Report the modified directory inode on dirent modification events.
+ * Report the "victim" inode if "victim" is a directory.
+ * Report the parent inode if "victim" is not a directory and event is
+ * reported to parent.
+ * Otherwise, do not report dir fid.
+ */
+static struct inode *fanotify_dfid_inode(u32 event_mask, const void *data,
+ int data_type, struct inode *dir)
+{
+ struct inode *inode = fsnotify_data_inode(data, data_type);
+
+ if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
+ return dir;
+
+ if (inode && S_ISDIR(inode->i_mode))
+ return inode;
+
+ return dir;
+}
+
+static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
+ unsigned int *hash,
+ gfp_t gfp)
+{
+ struct fanotify_path_event *pevent;
+
+ pevent = kmem_cache_alloc(fanotify_path_event_cachep, gfp);
+ if (!pevent)
+ return NULL;
+
+ pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH;
+ pevent->path = *path;
+ *hash ^= fanotify_hash_path(path);
+ path_get(path);
+
+ return &pevent->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
+ gfp_t gfp)
+{
+ struct fanotify_perm_event *pevent;
+
+ pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
+ if (!pevent)
+ return NULL;
+
+ pevent->fae.type = FANOTIFY_EVENT_TYPE_PATH_PERM;
+ pevent->response = 0;
+ pevent->state = FAN_EVENT_INIT;
+ pevent->path = *path;
+ path_get(path);
+
+ return &pevent->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_fid_event(struct inode *id,
+ __kernel_fsid_t *fsid,
+ unsigned int *hash,
+ gfp_t gfp)
+{
+ struct fanotify_fid_event *ffe;
+
+ ffe = kmem_cache_alloc(fanotify_fid_event_cachep, gfp);
+ if (!ffe)
+ return NULL;
+
+ ffe->fae.type = FANOTIFY_EVENT_TYPE_FID;
+ ffe->fsid = *fsid;
+ *hash ^= fanotify_hash_fsid(fsid);
+ fanotify_encode_fh(&ffe->object_fh, id, fanotify_encode_fh_len(id),
+ hash, gfp);
+
+ return &ffe->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_name_event(struct inode *dir,
+ __kernel_fsid_t *fsid,
+ const struct qstr *name,
+ struct inode *child,
+ struct dentry *moved,
+ unsigned int *hash,
+ gfp_t gfp)
+{
+ struct fanotify_name_event *fne;
+ struct fanotify_info *info;
+ struct fanotify_fh *dfh, *ffh;
+ struct inode *dir2 = moved ? d_inode(moved->d_parent) : NULL;
+ const struct qstr *name2 = moved ? &moved->d_name : NULL;
+ unsigned int dir_fh_len = fanotify_encode_fh_len(dir);
+ unsigned int dir2_fh_len = fanotify_encode_fh_len(dir2);
+ unsigned int child_fh_len = fanotify_encode_fh_len(child);
+ unsigned long name_len = name ? name->len : 0;
+ unsigned long name2_len = name2 ? name2->len : 0;
+ unsigned int len, size;
+
+ /* Reserve terminating null byte even for empty name */
+ size = sizeof(*fne) + name_len + name2_len + 2;
+ if (dir_fh_len)
+ size += FANOTIFY_FH_HDR_LEN + dir_fh_len;
+ if (dir2_fh_len)
+ size += FANOTIFY_FH_HDR_LEN + dir2_fh_len;
+ if (child_fh_len)
+ size += FANOTIFY_FH_HDR_LEN + child_fh_len;
+ fne = kmalloc(size, gfp);
+ if (!fne)
+ return NULL;
+
+ fne->fae.type = FANOTIFY_EVENT_TYPE_FID_NAME;
+ fne->fsid = *fsid;
+ *hash ^= fanotify_hash_fsid(fsid);
+ info = &fne->info;
+ fanotify_info_init(info);
+ if (dir_fh_len) {
+ dfh = fanotify_info_dir_fh(info);
+ len = fanotify_encode_fh(dfh, dir, dir_fh_len, hash, 0);
+ fanotify_info_set_dir_fh(info, len);
+ }
+ if (dir2_fh_len) {
+ dfh = fanotify_info_dir2_fh(info);
+ len = fanotify_encode_fh(dfh, dir2, dir2_fh_len, hash, 0);
+ fanotify_info_set_dir2_fh(info, len);
+ }
+ if (child_fh_len) {
+ ffh = fanotify_info_file_fh(info);
+ len = fanotify_encode_fh(ffh, child, child_fh_len, hash, 0);
+ fanotify_info_set_file_fh(info, len);
+ }
+ if (name_len) {
+ fanotify_info_copy_name(info, name);
+ *hash ^= full_name_hash((void *)name_len, name->name, name_len);
+ }
+ if (name2_len) {
+ fanotify_info_copy_name2(info, name2);
+ *hash ^= full_name_hash((void *)name2_len, name2->name,
+ name2_len);
+ }
+
+ pr_debug("%s: size=%u dir_fh_len=%u child_fh_len=%u name_len=%u name='%.*s'\n",
+ __func__, size, dir_fh_len, child_fh_len,
+ info->name_len, info->name_len, fanotify_info_name(info));
+
+ if (dir2_fh_len) {
+ pr_debug("%s: dir2_fh_len=%u name2_len=%u name2='%.*s'\n",
+ __func__, dir2_fh_len, info->name2_len,
+ info->name2_len, fanotify_info_name2(info));
+ }
+
+ return &fne->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_error_event(
+ struct fsnotify_group *group,
+ __kernel_fsid_t *fsid,
+ const void *data, int data_type,
+ unsigned int *hash)
+{
+ struct fs_error_report *report =
+ fsnotify_data_error_report(data, data_type);
+ struct inode *inode;
+ struct fanotify_error_event *fee;
+ int fh_len;
+
+ if (WARN_ON_ONCE(!report))
+ return NULL;
+
+ fee = mempool_alloc(&group->fanotify_data.error_events_pool, GFP_NOFS);
+ if (!fee)
+ return NULL;
+
+ fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR;
+ fee->error = report->error;
+ fee->err_count = 1;
+ fee->fsid = *fsid;
+
+ inode = report->inode;
+ fh_len = fanotify_encode_fh_len(inode);
+
+ /* Bad fh_len. Fallback to using an invalid fh. Should never happen. */
+ if (!fh_len && inode)
+ inode = NULL;
+
+ fanotify_encode_fh(&fee->object_fh, inode, fh_len, NULL, 0);
+
+ *hash ^= fanotify_hash_fsid(fsid);
+
+ return &fee->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_event(
+ struct fsnotify_group *group,
+ u32 mask, const void *data, int data_type,
+ struct inode *dir, const struct qstr *file_name,
+ __kernel_fsid_t *fsid, u32 match_mask)
+{
+ struct fanotify_event *event = NULL;
+ gfp_t gfp = GFP_KERNEL_ACCOUNT;
+ unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+ struct inode *id = fanotify_fid_inode(mask, data, data_type, dir,
+ fid_mode);
+ struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
+ const struct path *path = fsnotify_data_path(data, data_type);
+ struct mem_cgroup *old_memcg;
+ struct dentry *moved = NULL;
+ struct inode *child = NULL;
+ bool name_event = false;
+ unsigned int hash = 0;
+ bool ondir = mask & FAN_ONDIR;
+ struct pid *pid;
+
+ if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
+ /*
+ * For certain events and group flags, report the child fid
+ * in addition to reporting the parent fid and maybe child name.
+ */
+ if (fanotify_report_child_fid(fid_mode, mask) && id != dirid)
+ child = id;
+
+ id = dirid;
+
+ /*
+ * We record file name only in a group with FAN_REPORT_NAME
+ * and when we have a directory inode to report.
+ *
+ * For directory entry modification event, we record the fid of
+ * the directory and the name of the modified entry.
+ *
+ * For event on non-directory that is reported to parent, we
+ * record the fid of the parent and the name of the child.
+ *
+ * Even if not reporting name, we need a variable length
+ * fanotify_name_event if reporting both parent and child fids.
+ */
+ if (!(fid_mode & FAN_REPORT_NAME)) {
+ name_event = !!child;
+ file_name = NULL;
+ } else if ((mask & ALL_FSNOTIFY_DIRENT_EVENTS) || !ondir) {
+ name_event = true;
+ }
+
+ /*
+ * In the special case of FAN_RENAME event, use the match_mask
+ * to determine if we need to report only the old parent+name,
+ * only the new parent+name or both.
+ * 'dirid' and 'file_name' are the old parent+name and
+ * 'moved' has the new parent+name.
+ */
+ if (mask & FAN_RENAME) {
+ bool report_old, report_new;
+
+ if (WARN_ON_ONCE(!match_mask))
+ return NULL;
+
+ /* Report both old and new parent+name if sb watching */
+ report_old = report_new =
+ match_mask & (1U << FSNOTIFY_ITER_TYPE_SB);
+ report_old |=
+ match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE);
+ report_new |=
+ match_mask & (1U << FSNOTIFY_ITER_TYPE_INODE2);
+
+ if (!report_old) {
+ /* Do not report old parent+name */
+ dirid = NULL;
+ file_name = NULL;
+ }
+ if (report_new) {
+ /* Report new parent+name */
+ moved = fsnotify_data_dentry(data, data_type);
+ }
+ }
+ }
+
+ /*
+ * For queues with unlimited length lost events are not expected and
+ * can possibly have security implications. Avoid losing events when
+ * memory is short. For the limited size queues, avoid OOM killer in the
+ * target monitoring memcg as it may have security repercussion.
+ */
+ if (group->max_events == UINT_MAX)
+ gfp |= __GFP_NOFAIL;
+ else
+ gfp |= __GFP_RETRY_MAYFAIL;
+
+ /* Whoever is interested in the event, pays for the allocation. */
+ old_memcg = set_active_memcg(group->memcg);
+
+ if (fanotify_is_perm_event(mask)) {
+ event = fanotify_alloc_perm_event(path, gfp);
+ } else if (fanotify_is_error_event(mask)) {
+ event = fanotify_alloc_error_event(group, fsid, data,
+ data_type, &hash);
+ } else if (name_event && (file_name || moved || child)) {
+ event = fanotify_alloc_name_event(dirid, fsid, file_name, child,
+ moved, &hash, gfp);
+ } else if (fid_mode) {
+ event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
+ } else {
+ event = fanotify_alloc_path_event(path, &hash, gfp);
+ }
+
+ if (!event)
+ goto out;
+
+ if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
+ pid = get_pid(task_pid(current));
+ else
+ pid = get_pid(task_tgid(current));
+
+ /* Mix event info, FAN_ONDIR flag and pid into event merge key */
+ hash ^= hash_long((unsigned long)pid | ondir, FANOTIFY_EVENT_HASH_BITS);
+ fanotify_init_event(event, hash, mask);
+ event->pid = pid;
+
+out:
+ set_active_memcg(old_memcg);
+ return event;
+}
+
+/*
+ * Get cached fsid of the filesystem containing the object from any connector.
+ * All connectors are supposed to have the same fsid, but we do not verify that
+ * here.
+ */
+static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
+{
+ struct fsnotify_mark *mark;
+ int type;
+ __kernel_fsid_t fsid = {};
+
+ fsnotify_foreach_iter_mark_type(iter_info, mark, type) {
+ struct fsnotify_mark_connector *conn;
+
+ conn = READ_ONCE(mark->connector);
+ /* Mark is just getting destroyed or created? */
+ if (!conn)
+ continue;
+ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID))
+ continue;
+ /* Pairs with smp_wmb() in fsnotify_add_mark_list() */
+ smp_rmb();
+ fsid = conn->fsid;
+ if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
+ continue;
+ return fsid;
+ }
+
+ return fsid;
+}
+
+/*
+ * Add an event to hash table for faster merge.
+ */
+static void fanotify_insert_event(struct fsnotify_group *group,
+ struct fsnotify_event *fsn_event)
+{
+ struct fanotify_event *event = FANOTIFY_E(fsn_event);
+ unsigned int bucket = fanotify_event_hash_bucket(group, event);
+ struct hlist_head *hlist = &group->fanotify_data.merge_hash[bucket];
+
+ assert_spin_locked(&group->notification_lock);
+
+ if (!fanotify_is_hashed_event(event->mask))
+ return;
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, bucket);
+
+ hlist_add_head(&event->merge_list, hlist);
+}
+
+static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
+ const void *data, int data_type,
+ struct inode *dir,
+ const struct qstr *file_name, u32 cookie,
+ struct fsnotify_iter_info *iter_info)
+{
+ int ret = 0;
+ struct fanotify_event *event;
+ struct fsnotify_event *fsn_event;
+ __kernel_fsid_t fsid = {};
+ u32 match_mask = 0;
+
+ BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
+ BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
+ BUILD_BUG_ON(FAN_ATTRIB != FS_ATTRIB);
+ BUILD_BUG_ON(FAN_CLOSE_NOWRITE != FS_CLOSE_NOWRITE);
+ BUILD_BUG_ON(FAN_CLOSE_WRITE != FS_CLOSE_WRITE);
+ BUILD_BUG_ON(FAN_OPEN != FS_OPEN);
+ BUILD_BUG_ON(FAN_MOVED_TO != FS_MOVED_TO);
+ BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM);
+ BUILD_BUG_ON(FAN_CREATE != FS_CREATE);
+ BUILD_BUG_ON(FAN_DELETE != FS_DELETE);
+ BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF);
+ BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF);
+ BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
+ 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);
+ BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
+ BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
+ BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
+ BUILD_BUG_ON(FAN_RENAME != FS_RENAME);
+
+ BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21);
+
+ mask = fanotify_group_event_mask(group, iter_info, &match_mask,
+ mask, data, data_type, dir);
+ if (!mask)
+ return 0;
+
+ pr_debug("%s: group=%p mask=%x report_mask=%x\n", __func__,
+ group, mask, match_mask);
+
+ if (fanotify_is_perm_event(mask)) {
+ /*
+ * fsnotify_prepare_user_wait() fails if we race with mark
+ * deletion. Just let the operation pass in that case.
+ */
+ if (!fsnotify_prepare_user_wait(iter_info))
+ return 0;
+ }
+
+ if (FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS)) {
+ fsid = fanotify_get_fsid(iter_info);
+ /* Racing with mark destruction or creation? */
+ if (!fsid.val[0] && !fsid.val[1])
+ return 0;
+ }
+
+ event = fanotify_alloc_event(group, mask, data, data_type, dir,
+ file_name, &fsid, match_mask);
+ ret = -ENOMEM;
+ if (unlikely(!event)) {
+ /*
+ * We don't queue overflow events for permission events as
+ * there the access is denied and so no event is in fact lost.
+ */
+ if (!fanotify_is_perm_event(mask))
+ fsnotify_queue_overflow(group);
+ goto finish;
+ }
+
+ fsn_event = &event->fse;
+ ret = fsnotify_insert_event(group, fsn_event, fanotify_merge,
+ fanotify_insert_event);
+ if (ret) {
+ /* Permission events shouldn't be merged */
+ BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS);
+ /* Our event wasn't used in the end. Free it. */
+ fsnotify_destroy_event(group, fsn_event);
+
+ ret = 0;
+ } else if (fanotify_is_perm_event(mask)) {
+ ret = fanotify_get_response(group, FANOTIFY_PERM(event),
+ iter_info);
+ }
+finish:
+ if (fanotify_is_perm_event(mask))
+ fsnotify_finish_user_wait(iter_info);
+
+ return ret;
+}
+
+static void fanotify_free_group_priv(struct fsnotify_group *group)
+{
+ kfree(group->fanotify_data.merge_hash);
+ if (group->fanotify_data.ucounts)
+ dec_ucount(group->fanotify_data.ucounts,
+ UCOUNT_FANOTIFY_GROUPS);
+
+ if (mempool_initialized(&group->fanotify_data.error_events_pool))
+ mempool_exit(&group->fanotify_data.error_events_pool);
+}
+
+static void fanotify_free_path_event(struct fanotify_event *event)
+{
+ path_put(fanotify_event_path(event));
+ kmem_cache_free(fanotify_path_event_cachep, FANOTIFY_PE(event));
+}
+
+static void fanotify_free_perm_event(struct fanotify_event *event)
+{
+ path_put(fanotify_event_path(event));
+ kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PERM(event));
+}
+
+static void fanotify_free_fid_event(struct fanotify_event *event)
+{
+ struct fanotify_fid_event *ffe = FANOTIFY_FE(event);
+
+ if (fanotify_fh_has_ext_buf(&ffe->object_fh))
+ kfree(fanotify_fh_ext_buf(&ffe->object_fh));
+ kmem_cache_free(fanotify_fid_event_cachep, ffe);
+}
+
+static void fanotify_free_name_event(struct fanotify_event *event)
+{
+ kfree(FANOTIFY_NE(event));
+}
+
+static void fanotify_free_error_event(struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ struct fanotify_error_event *fee = FANOTIFY_EE(event);
+
+ mempool_free(fee, &group->fanotify_data.error_events_pool);
+}
+
+static void fanotify_free_event(struct fsnotify_group *group,
+ struct fsnotify_event *fsn_event)
+{
+ struct fanotify_event *event;
+
+ event = FANOTIFY_E(fsn_event);
+ put_pid(event->pid);
+ switch (event->type) {
+ case FANOTIFY_EVENT_TYPE_PATH:
+ fanotify_free_path_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_PATH_PERM:
+ fanotify_free_perm_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_FID:
+ fanotify_free_fid_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_FID_NAME:
+ fanotify_free_name_event(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_OVERFLOW:
+ kfree(event);
+ break;
+ case FANOTIFY_EVENT_TYPE_FS_ERROR:
+ fanotify_free_error_event(group, event);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ }
+}
+
+static void fanotify_freeing_mark(struct fsnotify_mark *mark,
+ struct fsnotify_group *group)
+{
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
+ dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_MARKS);
+}
+
+static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+ kmem_cache_free(fanotify_mark_cache, fsn_mark);
+}
+
+const struct fsnotify_ops fanotify_fsnotify_ops = {
+ .handle_event = fanotify_handle_event,
+ .free_group_priv = fanotify_free_group_priv,
+ .free_event = fanotify_free_event,
+ .freeing_mark = fanotify_freeing_mark,
+ .free_mark = fanotify_free_mark,
+};
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
new file mode 100644
index 000000000..57f51a9a3
--- /dev/null
+++ b/fs/notify/fanotify/fanotify.h
@@ -0,0 +1,500 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/fsnotify_backend.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/exportfs.h>
+#include <linux/hashtable.h>
+
+extern struct kmem_cache *fanotify_mark_cache;
+extern struct kmem_cache *fanotify_fid_event_cachep;
+extern struct kmem_cache *fanotify_path_event_cachep;
+extern struct kmem_cache *fanotify_perm_event_cachep;
+
+/* Possible states of the permission event */
+enum {
+ FAN_EVENT_INIT,
+ FAN_EVENT_REPORTED,
+ FAN_EVENT_ANSWERED,
+ FAN_EVENT_CANCELED,
+};
+
+/*
+ * 3 dwords are sufficient for most local fs (64bit ino, 32bit generation).
+ * fh buf should be dword aligned. On 64bit arch, the ext_buf pointer is
+ * stored in either the first or last 2 dwords.
+ */
+#define FANOTIFY_INLINE_FH_LEN (3 << 2)
+#define FANOTIFY_FH_HDR_LEN offsetof(struct fanotify_fh, buf)
+
+/* Fixed size struct for file handle */
+struct fanotify_fh {
+ u8 type;
+ u8 len;
+#define FANOTIFY_FH_FLAG_EXT_BUF 1
+ u8 flags;
+ u8 pad;
+ unsigned char buf[];
+} __aligned(4);
+
+/* Variable size struct for dir file handle + child file handle + name */
+struct fanotify_info {
+ /* size of dir_fh/file_fh including fanotify_fh hdr size */
+ u8 dir_fh_totlen;
+ u8 dir2_fh_totlen;
+ u8 file_fh_totlen;
+ u8 name_len;
+ u8 name2_len;
+ u8 pad[3];
+ unsigned char buf[];
+ /*
+ * (struct fanotify_fh) dir_fh starts at buf[0]
+ * (optional) dir2_fh starts at buf[dir_fh_totlen]
+ * (optional) file_fh starts at buf[dir_fh_totlen + dir2_fh_totlen]
+ * name starts at buf[dir_fh_totlen + dir2_fh_totlen + file_fh_totlen]
+ * ...
+ */
+#define FANOTIFY_DIR_FH_SIZE(info) ((info)->dir_fh_totlen)
+#define FANOTIFY_DIR2_FH_SIZE(info) ((info)->dir2_fh_totlen)
+#define FANOTIFY_FILE_FH_SIZE(info) ((info)->file_fh_totlen)
+#define FANOTIFY_NAME_SIZE(info) ((info)->name_len + 1)
+#define FANOTIFY_NAME2_SIZE(info) ((info)->name2_len + 1)
+
+#define FANOTIFY_DIR_FH_OFFSET(info) 0
+#define FANOTIFY_DIR2_FH_OFFSET(info) \
+ (FANOTIFY_DIR_FH_OFFSET(info) + FANOTIFY_DIR_FH_SIZE(info))
+#define FANOTIFY_FILE_FH_OFFSET(info) \
+ (FANOTIFY_DIR2_FH_OFFSET(info) + FANOTIFY_DIR2_FH_SIZE(info))
+#define FANOTIFY_NAME_OFFSET(info) \
+ (FANOTIFY_FILE_FH_OFFSET(info) + FANOTIFY_FILE_FH_SIZE(info))
+#define FANOTIFY_NAME2_OFFSET(info) \
+ (FANOTIFY_NAME_OFFSET(info) + FANOTIFY_NAME_SIZE(info))
+
+#define FANOTIFY_DIR_FH_BUF(info) \
+ ((info)->buf + FANOTIFY_DIR_FH_OFFSET(info))
+#define FANOTIFY_DIR2_FH_BUF(info) \
+ ((info)->buf + FANOTIFY_DIR2_FH_OFFSET(info))
+#define FANOTIFY_FILE_FH_BUF(info) \
+ ((info)->buf + FANOTIFY_FILE_FH_OFFSET(info))
+#define FANOTIFY_NAME_BUF(info) \
+ ((info)->buf + FANOTIFY_NAME_OFFSET(info))
+#define FANOTIFY_NAME2_BUF(info) \
+ ((info)->buf + FANOTIFY_NAME2_OFFSET(info))
+} __aligned(4);
+
+static inline bool fanotify_fh_has_ext_buf(struct fanotify_fh *fh)
+{
+ return (fh->flags & FANOTIFY_FH_FLAG_EXT_BUF);
+}
+
+static inline char **fanotify_fh_ext_buf_ptr(struct fanotify_fh *fh)
+{
+ BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN % 4);
+ BUILD_BUG_ON(__alignof__(char *) - 4 + sizeof(char *) >
+ FANOTIFY_INLINE_FH_LEN);
+ return (char **)ALIGN((unsigned long)(fh->buf), __alignof__(char *));
+}
+
+static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh)
+{
+ return *fanotify_fh_ext_buf_ptr(fh);
+}
+
+static inline void *fanotify_fh_buf(struct fanotify_fh *fh)
+{
+ return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh->buf;
+}
+
+static inline int fanotify_info_dir_fh_len(struct fanotify_info *info)
+{
+ if (!info->dir_fh_totlen ||
+ WARN_ON_ONCE(info->dir_fh_totlen < FANOTIFY_FH_HDR_LEN))
+ return 0;
+
+ return info->dir_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_dir_fh(struct fanotify_info *info)
+{
+ BUILD_BUG_ON(offsetof(struct fanotify_info, buf) % 4);
+
+ return (struct fanotify_fh *)FANOTIFY_DIR_FH_BUF(info);
+}
+
+static inline int fanotify_info_dir2_fh_len(struct fanotify_info *info)
+{
+ if (!info->dir2_fh_totlen ||
+ WARN_ON_ONCE(info->dir2_fh_totlen < FANOTIFY_FH_HDR_LEN))
+ return 0;
+
+ return info->dir2_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_dir2_fh(struct fanotify_info *info)
+{
+ return (struct fanotify_fh *)FANOTIFY_DIR2_FH_BUF(info);
+}
+
+static inline int fanotify_info_file_fh_len(struct fanotify_info *info)
+{
+ if (!info->file_fh_totlen ||
+ WARN_ON_ONCE(info->file_fh_totlen < FANOTIFY_FH_HDR_LEN))
+ return 0;
+
+ return info->file_fh_totlen - FANOTIFY_FH_HDR_LEN;
+}
+
+static inline struct fanotify_fh *fanotify_info_file_fh(struct fanotify_info *info)
+{
+ return (struct fanotify_fh *)FANOTIFY_FILE_FH_BUF(info);
+}
+
+static inline char *fanotify_info_name(struct fanotify_info *info)
+{
+ if (!info->name_len)
+ return NULL;
+
+ return FANOTIFY_NAME_BUF(info);
+}
+
+static inline char *fanotify_info_name2(struct fanotify_info *info)
+{
+ if (!info->name2_len)
+ return NULL;
+
+ return FANOTIFY_NAME2_BUF(info);
+}
+
+static inline void fanotify_info_init(struct fanotify_info *info)
+{
+ BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN + MAX_HANDLE_SZ > U8_MAX);
+ BUILD_BUG_ON(NAME_MAX > U8_MAX);
+
+ info->dir_fh_totlen = 0;
+ info->dir2_fh_totlen = 0;
+ info->file_fh_totlen = 0;
+ info->name_len = 0;
+ info->name2_len = 0;
+}
+
+/* These set/copy helpers MUST be called by order */
+static inline void fanotify_info_set_dir_fh(struct fanotify_info *info,
+ unsigned int totlen)
+{
+ if (WARN_ON_ONCE(info->dir2_fh_totlen > 0) ||
+ WARN_ON_ONCE(info->file_fh_totlen > 0) ||
+ WARN_ON_ONCE(info->name_len > 0) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->dir_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_set_dir2_fh(struct fanotify_info *info,
+ unsigned int totlen)
+{
+ if (WARN_ON_ONCE(info->file_fh_totlen > 0) ||
+ WARN_ON_ONCE(info->name_len > 0) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->dir2_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_set_file_fh(struct fanotify_info *info,
+ unsigned int totlen)
+{
+ if (WARN_ON_ONCE(info->name_len > 0) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->file_fh_totlen = totlen;
+}
+
+static inline void fanotify_info_copy_name(struct fanotify_info *info,
+ const struct qstr *name)
+{
+ if (WARN_ON_ONCE(name->len > NAME_MAX) ||
+ WARN_ON_ONCE(info->name2_len > 0))
+ return;
+
+ info->name_len = name->len;
+ strcpy(fanotify_info_name(info), name->name);
+}
+
+static inline void fanotify_info_copy_name2(struct fanotify_info *info,
+ const struct qstr *name)
+{
+ if (WARN_ON_ONCE(name->len > NAME_MAX))
+ return;
+
+ info->name2_len = name->len;
+ strcpy(fanotify_info_name2(info), name->name);
+}
+
+/*
+ * Common structure for fanotify events. Concrete structs are allocated in
+ * fanotify_handle_event() and freed when the information is retrieved by
+ * userspace. The type of event determines how it was allocated, how it will
+ * be freed and which concrete struct it may be cast to.
+ */
+enum fanotify_event_type {
+ FANOTIFY_EVENT_TYPE_FID, /* fixed length */
+ FANOTIFY_EVENT_TYPE_FID_NAME, /* variable length */
+ FANOTIFY_EVENT_TYPE_PATH,
+ FANOTIFY_EVENT_TYPE_PATH_PERM,
+ FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
+ FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
+ __FANOTIFY_EVENT_TYPE_NUM
+};
+
+#define FANOTIFY_EVENT_TYPE_BITS \
+ (ilog2(__FANOTIFY_EVENT_TYPE_NUM - 1) + 1)
+#define FANOTIFY_EVENT_HASH_BITS \
+ (32 - FANOTIFY_EVENT_TYPE_BITS)
+
+struct fanotify_event {
+ struct fsnotify_event fse;
+ struct hlist_node merge_list; /* List for hashed merge */
+ u32 mask;
+ struct {
+ unsigned int type : FANOTIFY_EVENT_TYPE_BITS;
+ unsigned int hash : FANOTIFY_EVENT_HASH_BITS;
+ };
+ struct pid *pid;
+};
+
+static inline void fanotify_init_event(struct fanotify_event *event,
+ unsigned int hash, u32 mask)
+{
+ fsnotify_init_event(&event->fse);
+ INIT_HLIST_NODE(&event->merge_list);
+ event->hash = hash;
+ event->mask = mask;
+ event->pid = NULL;
+}
+
+#define FANOTIFY_INLINE_FH(name, size) \
+struct { \
+ struct fanotify_fh (name); \
+ /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \
+ unsigned char _inline_fh_buf[(size)]; \
+}
+
+struct fanotify_fid_event {
+ struct fanotify_event fae;
+ __kernel_fsid_t fsid;
+
+ FANOTIFY_INLINE_FH(object_fh, FANOTIFY_INLINE_FH_LEN);
+};
+
+static inline struct fanotify_fid_event *
+FANOTIFY_FE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_fid_event, fae);
+}
+
+struct fanotify_name_event {
+ struct fanotify_event fae;
+ __kernel_fsid_t fsid;
+ struct fanotify_info info;
+};
+
+static inline struct fanotify_name_event *
+FANOTIFY_NE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_name_event, fae);
+}
+
+struct fanotify_error_event {
+ struct fanotify_event fae;
+ s32 error; /* Error reported by the Filesystem. */
+ u32 err_count; /* Suppressed errors count */
+
+ __kernel_fsid_t fsid; /* FSID this error refers to. */
+
+ FANOTIFY_INLINE_FH(object_fh, MAX_HANDLE_SZ);
+};
+
+static inline struct fanotify_error_event *
+FANOTIFY_EE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_error_event, fae);
+}
+
+static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_FID)
+ return &FANOTIFY_FE(event)->fsid;
+ else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+ return &FANOTIFY_NE(event)->fsid;
+ else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return &FANOTIFY_EE(event)->fsid;
+ else
+ return NULL;
+}
+
+static inline struct fanotify_fh *fanotify_event_object_fh(
+ struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_FID)
+ return &FANOTIFY_FE(event)->object_fh;
+ else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+ return fanotify_info_file_fh(&FANOTIFY_NE(event)->info);
+ else if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return &FANOTIFY_EE(event)->object_fh;
+ else
+ return NULL;
+}
+
+static inline struct fanotify_info *fanotify_event_info(
+ struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+ return &FANOTIFY_NE(event)->info;
+ else
+ return NULL;
+}
+
+static inline int fanotify_event_object_fh_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+ struct fanotify_fh *fh = fanotify_event_object_fh(event);
+
+ if (info)
+ return info->file_fh_totlen ? fh->len : 0;
+ else
+ return fh ? fh->len : 0;
+}
+
+static inline int fanotify_event_dir_fh_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+
+ return info ? fanotify_info_dir_fh_len(info) : 0;
+}
+
+static inline int fanotify_event_dir2_fh_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+
+ return info ? fanotify_info_dir2_fh_len(info) : 0;
+}
+
+static inline bool fanotify_event_has_object_fh(struct fanotify_event *event)
+{
+ /* For error events, even zeroed fh are reported. */
+ if (event->type == FANOTIFY_EVENT_TYPE_FS_ERROR)
+ return true;
+ return fanotify_event_object_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir_fh(struct fanotify_event *event)
+{
+ return fanotify_event_dir_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_dir2_fh(struct fanotify_event *event)
+{
+ return fanotify_event_dir2_fh_len(event) > 0;
+}
+
+static inline bool fanotify_event_has_any_dir_fh(struct fanotify_event *event)
+{
+ return fanotify_event_has_dir_fh(event) ||
+ fanotify_event_has_dir2_fh(event);
+}
+
+struct fanotify_path_event {
+ struct fanotify_event fae;
+ struct path path;
+};
+
+static inline struct fanotify_path_event *
+FANOTIFY_PE(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_path_event, fae);
+}
+
+/*
+ * Structure for permission fanotify events. It gets allocated and freed in
+ * fanotify_handle_event() since we wait there for user response. When the
+ * information is retrieved by userspace the structure is moved from
+ * group->notification_list to group->fanotify_data.access_list to wait for
+ * user response.
+ */
+struct fanotify_perm_event {
+ struct fanotify_event fae;
+ struct path path;
+ unsigned short response; /* userspace answer to the event */
+ unsigned short state; /* state of the event */
+ int fd; /* fd we passed to userspace for this event */
+};
+
+static inline struct fanotify_perm_event *
+FANOTIFY_PERM(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_perm_event, fae);
+}
+
+static inline bool fanotify_is_perm_event(u32 mask)
+{
+ return IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS) &&
+ mask & FANOTIFY_PERM_EVENTS;
+}
+
+static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
+{
+ return container_of(fse, struct fanotify_event, fse);
+}
+
+static inline bool fanotify_is_error_event(u32 mask)
+{
+ return mask & FAN_FS_ERROR;
+}
+
+static inline const struct path *fanotify_event_path(struct fanotify_event *event)
+{
+ if (event->type == FANOTIFY_EVENT_TYPE_PATH)
+ return &FANOTIFY_PE(event)->path;
+ else if (event->type == FANOTIFY_EVENT_TYPE_PATH_PERM)
+ return &FANOTIFY_PERM(event)->path;
+ else
+ return NULL;
+}
+
+/*
+ * Use 128 size hash table to speed up events merge.
+ */
+#define FANOTIFY_HTABLE_BITS (7)
+#define FANOTIFY_HTABLE_SIZE (1 << FANOTIFY_HTABLE_BITS)
+#define FANOTIFY_HTABLE_MASK (FANOTIFY_HTABLE_SIZE - 1)
+
+/*
+ * Permission events and overflow event do not get merged - don't hash them.
+ */
+static inline bool fanotify_is_hashed_event(u32 mask)
+{
+ return !(fanotify_is_perm_event(mask) ||
+ fsnotify_is_overflow_event(mask));
+}
+
+static inline unsigned int fanotify_event_hash_bucket(
+ struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ return event->hash & FANOTIFY_HTABLE_MASK;
+}
+
+static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
+{
+ unsigned int mflags = 0;
+
+ if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+ mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
+ if (mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)
+ mflags |= FAN_MARK_EVICTABLE;
+ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
+ mflags |= FAN_MARK_IGNORE;
+
+ return mflags;
+}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
new file mode 100644
index 000000000..9df5db0f1
--- /dev/null
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -0,0 +1,1900 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fanotify.h>
+#include <linux/fcntl.h>
+#include <linux/fdtable.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/init.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/poll.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/compat.h>
+#include <linux/sched/signal.h>
+#include <linux/memcontrol.h>
+#include <linux/statfs.h>
+#include <linux/exportfs.h>
+
+#include <asm/ioctls.h>
+
+#include "../../mount.h"
+#include "../fdinfo.h"
+#include "fanotify.h"
+
+#define FANOTIFY_DEFAULT_MAX_EVENTS 16384
+#define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192
+#define FANOTIFY_DEFAULT_MAX_GROUPS 128
+#define FANOTIFY_DEFAULT_FEE_POOL_SIZE 32
+
+/*
+ * Legacy fanotify marks limits (8192) is per group and we introduced a tunable
+ * limit of marks per user, similar to inotify. Effectively, the legacy limit
+ * of fanotify marks per user is <max marks per group> * <max groups per user>.
+ * This default limit (1M) also happens to match the increased limit of inotify
+ * max_user_watches since v5.10.
+ */
+#define FANOTIFY_DEFAULT_MAX_USER_MARKS \
+ (FANOTIFY_OLD_DEFAULT_MAX_MARKS * FANOTIFY_DEFAULT_MAX_GROUPS)
+
+/*
+ * Most of the memory cost of adding an inode mark is pinning the marked inode.
+ * The size of the filesystem inode struct is not uniform across filesystems,
+ * so double the size of a VFS inode is used as a conservative approximation.
+ */
+#define INODE_MARK_COST (2 * sizeof(struct inode))
+
+/* configurable via /proc/sys/fs/fanotify/ */
+static int fanotify_max_queued_events __read_mostly;
+
+#ifdef CONFIG_SYSCTL
+
+#include <linux/sysctl.h>
+
+static long ft_zero = 0;
+static long ft_int_max = INT_MAX;
+
+static struct ctl_table fanotify_table[] = {
+ {
+ .procname = "max_user_groups",
+ .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
+ .maxlen = sizeof(long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = &ft_zero,
+ .extra2 = &ft_int_max,
+ },
+ {
+ .procname = "max_user_marks",
+ .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS],
+ .maxlen = sizeof(long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ .extra1 = &ft_zero,
+ .extra2 = &ft_int_max,
+ },
+ {
+ .procname = "max_queued_events",
+ .data = &fanotify_max_queued_events,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO
+ },
+ { }
+};
+
+static void __init fanotify_sysctls_init(void)
+{
+ register_sysctl("fs/fanotify", fanotify_table);
+}
+#else
+#define fanotify_sysctls_init() do { } while (0)
+#endif /* CONFIG_SYSCTL */
+
+/*
+ * All flags that may be specified in parameter event_f_flags of fanotify_init.
+ *
+ * Internal and external open flags are stored together in field f_flags of
+ * struct file. Only external open flags shall be allowed in event_f_flags.
+ * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
+ * excluded.
+ */
+#define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \
+ O_ACCMODE | O_APPEND | O_NONBLOCK | \
+ __O_SYNC | O_DSYNC | O_CLOEXEC | \
+ O_LARGEFILE | O_NOATIME )
+
+extern const struct fsnotify_ops fanotify_fsnotify_ops;
+
+struct kmem_cache *fanotify_mark_cache __read_mostly;
+struct kmem_cache *fanotify_fid_event_cachep __read_mostly;
+struct kmem_cache *fanotify_path_event_cachep __read_mostly;
+struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
+
+#define FANOTIFY_EVENT_ALIGN 4
+#define FANOTIFY_FID_INFO_HDR_LEN \
+ (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
+#define FANOTIFY_PIDFD_INFO_HDR_LEN \
+ sizeof(struct fanotify_event_info_pidfd)
+#define FANOTIFY_ERROR_INFO_LEN \
+ (sizeof(struct fanotify_event_info_error))
+
+static int fanotify_fid_info_len(int fh_len, int name_len)
+{
+ int info_len = fh_len;
+
+ if (name_len)
+ info_len += name_len + 1;
+
+ return roundup(FANOTIFY_FID_INFO_HDR_LEN + info_len,
+ FANOTIFY_EVENT_ALIGN);
+}
+
+/* FAN_RENAME may have one or two dir+name info records */
+static int fanotify_dir_name_info_len(struct fanotify_event *event)
+{
+ struct fanotify_info *info = fanotify_event_info(event);
+ int dir_fh_len = fanotify_event_dir_fh_len(event);
+ int dir2_fh_len = fanotify_event_dir2_fh_len(event);
+ int info_len = 0;
+
+ if (dir_fh_len)
+ info_len += fanotify_fid_info_len(dir_fh_len,
+ info->name_len);
+ if (dir2_fh_len)
+ info_len += fanotify_fid_info_len(dir2_fh_len,
+ info->name2_len);
+
+ return info_len;
+}
+
+static size_t fanotify_event_len(unsigned int info_mode,
+ struct fanotify_event *event)
+{
+ size_t event_len = FAN_EVENT_METADATA_LEN;
+ int fh_len;
+ int dot_len = 0;
+
+ if (!info_mode)
+ return event_len;
+
+ if (fanotify_is_error_event(event->mask))
+ event_len += FANOTIFY_ERROR_INFO_LEN;
+
+ if (fanotify_event_has_any_dir_fh(event)) {
+ event_len += fanotify_dir_name_info_len(event);
+ } else if ((info_mode & FAN_REPORT_NAME) &&
+ (event->mask & FAN_ONDIR)) {
+ /*
+ * With group flag FAN_REPORT_NAME, if name was not recorded in
+ * event on a directory, we will report the name ".".
+ */
+ dot_len = 1;
+ }
+
+ if (info_mode & FAN_REPORT_PIDFD)
+ event_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
+
+ if (fanotify_event_has_object_fh(event)) {
+ fh_len = fanotify_event_object_fh_len(event);
+ event_len += fanotify_fid_info_len(fh_len, dot_len);
+ }
+
+ return event_len;
+}
+
+/*
+ * Remove an hashed event from merge hash table.
+ */
+static void fanotify_unhash_event(struct fsnotify_group *group,
+ struct fanotify_event *event)
+{
+ assert_spin_locked(&group->notification_lock);
+
+ pr_debug("%s: group=%p event=%p bucket=%u\n", __func__,
+ group, event, fanotify_event_hash_bucket(group, event));
+
+ if (WARN_ON_ONCE(hlist_unhashed(&event->merge_list)))
+ return;
+
+ hlist_del_init(&event->merge_list);
+}
+
+/*
+ * Get an fanotify notification event if one exists and is small
+ * enough to fit in "count". Return an error pointer if the count
+ * is not large enough. When permission event is dequeued, its state is
+ * updated accordingly.
+ */
+static struct fanotify_event *get_one_event(struct fsnotify_group *group,
+ size_t count)
+{
+ size_t event_size;
+ struct fanotify_event *event = NULL;
+ struct fsnotify_event *fsn_event;
+ unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
+
+ pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
+
+ spin_lock(&group->notification_lock);
+ fsn_event = fsnotify_peek_first_event(group);
+ if (!fsn_event)
+ goto out;
+
+ event = FANOTIFY_E(fsn_event);
+ event_size = fanotify_event_len(info_mode, event);
+
+ if (event_size > count) {
+ event = ERR_PTR(-EINVAL);
+ goto out;
+ }
+
+ /*
+ * Held the notification_lock the whole time, so this is the
+ * same event we peeked above.
+ */
+ fsnotify_remove_first_event(group);
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
+ if (fanotify_is_hashed_event(event->mask))
+ fanotify_unhash_event(group, event);
+out:
+ spin_unlock(&group->notification_lock);
+ return event;
+}
+
+static int create_fd(struct fsnotify_group *group, const struct path *path,
+ struct file **file)
+{
+ int client_fd;
+ struct file *new_file;
+
+ client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
+ if (client_fd < 0)
+ return client_fd;
+
+ /*
+ * we need a new file handle for the userspace program so it can read even if it was
+ * originally opened O_WRONLY.
+ */
+ new_file = dentry_open(path,
+ group->fanotify_data.f_flags | __FMODE_NONOTIFY,
+ current_cred());
+ if (IS_ERR(new_file)) {
+ /*
+ * we still send an event even if we can't open the file. this
+ * can happen when say tasks are gone and we try to open their
+ * /proc files or we try to open a WRONLY file like in sysfs
+ * we just send the errno to userspace since there isn't much
+ * else we can do.
+ */
+ put_unused_fd(client_fd);
+ client_fd = PTR_ERR(new_file);
+ } else {
+ *file = new_file;
+ }
+
+ return client_fd;
+}
+
+/*
+ * Finish processing of permission event by setting it to ANSWERED state and
+ * drop group->notification_lock.
+ */
+static void finish_permission_event(struct fsnotify_group *group,
+ struct fanotify_perm_event *event,
+ unsigned int response)
+ __releases(&group->notification_lock)
+{
+ bool destroy = false;
+
+ assert_spin_locked(&group->notification_lock);
+ event->response = response;
+ if (event->state == FAN_EVENT_CANCELED)
+ destroy = true;
+ else
+ event->state = FAN_EVENT_ANSWERED;
+ spin_unlock(&group->notification_lock);
+ if (destroy)
+ fsnotify_destroy_event(group, &event->fae.fse);
+}
+
+static int process_access_response(struct fsnotify_group *group,
+ struct fanotify_response *response_struct)
+{
+ struct fanotify_perm_event *event;
+ int fd = response_struct->fd;
+ int response = response_struct->response;
+
+ pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
+ fd, response);
+ /*
+ * make sure the response is valid, if invalid we do nothing and either
+ * userspace can send a valid response or we will clean it up after the
+ * timeout
+ */
+ switch (response & ~FAN_AUDIT) {
+ case FAN_ALLOW:
+ case FAN_DENY:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (fd < 0)
+ return -EINVAL;
+
+ if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT))
+ return -EINVAL;
+
+ spin_lock(&group->notification_lock);
+ list_for_each_entry(event, &group->fanotify_data.access_list,
+ fae.fse.list) {
+ if (event->fd != fd)
+ continue;
+
+ list_del_init(&event->fae.fse.list);
+ finish_permission_event(group, event, response);
+ wake_up(&group->fanotify_data.access_waitq);
+ return 0;
+ }
+ spin_unlock(&group->notification_lock);
+
+ return -ENOENT;
+}
+
+static size_t copy_error_info_to_user(struct fanotify_event *event,
+ char __user *buf, int count)
+{
+ struct fanotify_event_info_error info = { };
+ struct fanotify_error_event *fee = FANOTIFY_EE(event);
+
+ info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR;
+ info.hdr.len = FANOTIFY_ERROR_INFO_LEN;
+
+ if (WARN_ON(count < info.hdr.len))
+ return -EFAULT;
+
+ info.error = fee->error;
+ info.error_count = fee->err_count;
+
+ if (copy_to_user(buf, &info, sizeof(info)))
+ return -EFAULT;
+
+ return info.hdr.len;
+}
+
+static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
+ int info_type, const char *name,
+ size_t name_len,
+ char __user *buf, size_t count)
+{
+ struct fanotify_event_info_fid info = { };
+ struct file_handle handle = { };
+ unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf;
+ size_t fh_len = fh ? fh->len : 0;
+ size_t info_len = fanotify_fid_info_len(fh_len, name_len);
+ size_t len = info_len;
+
+ pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
+ __func__, fh_len, name_len, info_len, count);
+
+ if (WARN_ON_ONCE(len < sizeof(info) || len > count))
+ return -EFAULT;
+
+ /*
+ * Copy event info fid header followed by variable sized file handle
+ * and optionally followed by variable sized filename.
+ */
+ switch (info_type) {
+ case FAN_EVENT_INFO_TYPE_FID:
+ case FAN_EVENT_INFO_TYPE_DFID:
+ if (WARN_ON_ONCE(name_len))
+ return -EFAULT;
+ break;
+ case FAN_EVENT_INFO_TYPE_DFID_NAME:
+ case FAN_EVENT_INFO_TYPE_OLD_DFID_NAME:
+ case FAN_EVENT_INFO_TYPE_NEW_DFID_NAME:
+ if (WARN_ON_ONCE(!name || !name_len))
+ return -EFAULT;
+ break;
+ default:
+ return -EFAULT;
+ }
+
+ info.hdr.info_type = info_type;
+ info.hdr.len = len;
+ info.fsid = *fsid;
+ if (copy_to_user(buf, &info, sizeof(info)))
+ return -EFAULT;
+
+ buf += sizeof(info);
+ len -= sizeof(info);
+ if (WARN_ON_ONCE(len < sizeof(handle)))
+ return -EFAULT;
+
+ handle.handle_type = fh->type;
+ handle.handle_bytes = fh_len;
+
+ /* Mangle handle_type for bad file_handle */
+ if (!fh_len)
+ handle.handle_type = FILEID_INVALID;
+
+ if (copy_to_user(buf, &handle, sizeof(handle)))
+ return -EFAULT;
+
+ buf += sizeof(handle);
+ len -= sizeof(handle);
+ if (WARN_ON_ONCE(len < fh_len))
+ return -EFAULT;
+
+ /*
+ * For an inline fh and inline file name, copy through stack to exclude
+ * the copy from usercopy hardening protections.
+ */
+ fh_buf = fanotify_fh_buf(fh);
+ if (fh_len <= FANOTIFY_INLINE_FH_LEN) {
+ memcpy(bounce, fh_buf, fh_len);
+ fh_buf = bounce;
+ }
+ if (copy_to_user(buf, fh_buf, fh_len))
+ return -EFAULT;
+
+ buf += fh_len;
+ len -= fh_len;
+
+ if (name_len) {
+ /* Copy the filename with terminating null */
+ name_len++;
+ if (WARN_ON_ONCE(len < name_len))
+ return -EFAULT;
+
+ if (copy_to_user(buf, name, name_len))
+ return -EFAULT;
+
+ buf += name_len;
+ len -= name_len;
+ }
+
+ /* Pad with 0's */
+ WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN);
+ if (len > 0 && clear_user(buf, len))
+ return -EFAULT;
+
+ return info_len;
+}
+
+static int copy_pidfd_info_to_user(int pidfd,
+ char __user *buf,
+ size_t count)
+{
+ struct fanotify_event_info_pidfd info = { };
+ size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN;
+
+ if (WARN_ON_ONCE(info_len > count))
+ return -EFAULT;
+
+ info.hdr.info_type = FAN_EVENT_INFO_TYPE_PIDFD;
+ info.hdr.len = info_len;
+ info.pidfd = pidfd;
+
+ if (copy_to_user(buf, &info, info_len))
+ return -EFAULT;
+
+ return info_len;
+}
+
+static int copy_info_records_to_user(struct fanotify_event *event,
+ struct fanotify_info *info,
+ unsigned int info_mode, int pidfd,
+ char __user *buf, size_t count)
+{
+ int ret, total_bytes = 0, info_type = 0;
+ unsigned int fid_mode = info_mode & FANOTIFY_FID_BITS;
+ unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
+
+ /*
+ * Event info records order is as follows:
+ * 1. dir fid + name
+ * 2. (optional) new dir fid + new name
+ * 3. (optional) child fid
+ */
+ if (fanotify_event_has_dir_fh(event)) {
+ info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
+ FAN_EVENT_INFO_TYPE_DFID;
+
+ /* FAN_RENAME uses special info types */
+ if (event->mask & FAN_RENAME)
+ info_type = FAN_EVENT_INFO_TYPE_OLD_DFID_NAME;
+
+ ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+ fanotify_info_dir_fh(info),
+ info_type,
+ fanotify_info_name(info),
+ info->name_len, buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ /* New dir fid+name may be reported in addition to old dir fid+name */
+ if (fanotify_event_has_dir2_fh(event)) {
+ info_type = FAN_EVENT_INFO_TYPE_NEW_DFID_NAME;
+ ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+ fanotify_info_dir2_fh(info),
+ info_type,
+ fanotify_info_name2(info),
+ info->name2_len, buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ if (fanotify_event_has_object_fh(event)) {
+ const char *dot = NULL;
+ int dot_len = 0;
+
+ if (fid_mode == FAN_REPORT_FID || info_type) {
+ /*
+ * With only group flag FAN_REPORT_FID only type FID is
+ * reported. Second info record type is always FID.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_FID;
+ } else if ((fid_mode & FAN_REPORT_NAME) &&
+ (event->mask & FAN_ONDIR)) {
+ /*
+ * With group flag FAN_REPORT_NAME, if name was not
+ * recorded in an event on a directory, report the name
+ * "." with info type DFID_NAME.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
+ dot = ".";
+ dot_len = 1;
+ } else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
+ (event->mask & FAN_ONDIR)) {
+ /*
+ * With group flag FAN_REPORT_DIR_FID, a single info
+ * record has type DFID for directory entry modification
+ * event and for event on a directory.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_DFID;
+ } else {
+ /*
+ * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID,
+ * a single info record has type FID for event on a
+ * non-directory, when there is no directory to report.
+ * For example, on FAN_DELETE_SELF event.
+ */
+ info_type = FAN_EVENT_INFO_TYPE_FID;
+ }
+
+ ret = copy_fid_info_to_user(fanotify_event_fsid(event),
+ fanotify_event_object_fh(event),
+ info_type, dot, dot_len,
+ buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ if (pidfd_mode) {
+ ret = copy_pidfd_info_to_user(pidfd, buf, count);
+ if (ret < 0)
+ return ret;
+
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ if (fanotify_is_error_event(event->mask)) {
+ ret = copy_error_info_to_user(event, buf, count);
+ if (ret < 0)
+ return ret;
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ return total_bytes;
+}
+
+static ssize_t copy_event_to_user(struct fsnotify_group *group,
+ struct fanotify_event *event,
+ char __user *buf, size_t count)
+{
+ struct fanotify_event_metadata metadata;
+ const struct path *path = fanotify_event_path(event);
+ struct fanotify_info *info = fanotify_event_info(event);
+ unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
+ unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
+ struct file *f = NULL;
+ int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD;
+
+ pr_debug("%s: group=%p event=%p\n", __func__, group, event);
+
+ metadata.event_len = fanotify_event_len(info_mode, event);
+ metadata.metadata_len = FAN_EVENT_METADATA_LEN;
+ metadata.vers = FANOTIFY_METADATA_VERSION;
+ metadata.reserved = 0;
+ metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
+ metadata.pid = pid_vnr(event->pid);
+ /*
+ * For an unprivileged listener, event->pid can be used to identify the
+ * events generated by the listener process itself, without disclosing
+ * the pids of other processes.
+ */
+ if (FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
+ task_tgid(current) != event->pid)
+ metadata.pid = 0;
+
+ /*
+ * For now, fid mode is required for an unprivileged listener and
+ * fid mode does not report fd in events. Keep this check anyway
+ * for safety in case fid mode requirement is relaxed in the future
+ * to allow unprivileged listener to get events with no fd and no fid.
+ */
+ if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
+ path && path->mnt && path->dentry) {
+ fd = create_fd(group, path, &f);
+ if (fd < 0)
+ return fd;
+ }
+ metadata.fd = fd;
+
+ if (pidfd_mode) {
+ /*
+ * Complain if the FAN_REPORT_PIDFD and FAN_REPORT_TID mutual
+ * exclusion is ever lifted. At the time of incoporating pidfd
+ * support within fanotify, the pidfd API only supported the
+ * creation of pidfds for thread-group leaders.
+ */
+ WARN_ON_ONCE(FAN_GROUP_FLAG(group, FAN_REPORT_TID));
+
+ /*
+ * The PIDTYPE_TGID check for an event->pid is performed
+ * preemptively in an attempt to catch out cases where the event
+ * listener reads events after the event generating process has
+ * already terminated. Report FAN_NOPIDFD to the event listener
+ * in those cases, with all other pidfd creation errors being
+ * reported as FAN_EPIDFD.
+ */
+ if (metadata.pid == 0 ||
+ !pid_has_task(event->pid, PIDTYPE_TGID)) {
+ pidfd = FAN_NOPIDFD;
+ } else {
+ pidfd = pidfd_create(event->pid, 0);
+ if (pidfd < 0)
+ pidfd = FAN_EPIDFD;
+ }
+ }
+
+ ret = -EFAULT;
+ /*
+ * Sanity check copy size in case get_one_event() and
+ * event_len sizes ever get out of sync.
+ */
+ if (WARN_ON_ONCE(metadata.event_len > count))
+ goto out_close_fd;
+
+ if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN))
+ goto out_close_fd;
+
+ buf += FAN_EVENT_METADATA_LEN;
+ count -= FAN_EVENT_METADATA_LEN;
+
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PERM(event)->fd = fd;
+
+ if (info_mode) {
+ ret = copy_info_records_to_user(event, info, info_mode, pidfd,
+ buf, count);
+ if (ret < 0)
+ goto out_close_fd;
+ }
+
+ if (f)
+ fd_install(fd, f);
+
+ return metadata.event_len;
+
+out_close_fd:
+ if (fd != FAN_NOFD) {
+ put_unused_fd(fd);
+ fput(f);
+ }
+
+ if (pidfd >= 0)
+ close_fd(pidfd);
+
+ return ret;
+}
+
+/* intofiy userspace file descriptor functions */
+static __poll_t fanotify_poll(struct file *file, poll_table *wait)
+{
+ struct fsnotify_group *group = file->private_data;
+ __poll_t ret = 0;
+
+ poll_wait(file, &group->notification_waitq, wait);
+ spin_lock(&group->notification_lock);
+ if (!fsnotify_notify_queue_is_empty(group))
+ ret = EPOLLIN | EPOLLRDNORM;
+ spin_unlock(&group->notification_lock);
+
+ return ret;
+}
+
+static ssize_t fanotify_read(struct file *file, char __user *buf,
+ size_t count, loff_t *pos)
+{
+ struct fsnotify_group *group;
+ struct fanotify_event *event;
+ char __user *start;
+ int ret;
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+ start = buf;
+ group = file->private_data;
+
+ pr_debug("%s: group=%p\n", __func__, group);
+
+ add_wait_queue(&group->notification_waitq, &wait);
+ while (1) {
+ /*
+ * User can supply arbitrarily large buffer. Avoid softlockups
+ * in case there are lots of available events.
+ */
+ cond_resched();
+ event = get_one_event(group, count);
+ if (IS_ERR(event)) {
+ ret = PTR_ERR(event);
+ break;
+ }
+
+ if (!event) {
+ ret = -EAGAIN;
+ if (file->f_flags & O_NONBLOCK)
+ break;
+
+ ret = -ERESTARTSYS;
+ if (signal_pending(current))
+ break;
+
+ if (start != buf)
+ break;
+
+ wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+ continue;
+ }
+
+ ret = copy_event_to_user(group, event, buf, count);
+ if (unlikely(ret == -EOPENSTALE)) {
+ /*
+ * We cannot report events with stale fd so drop it.
+ * Setting ret to 0 will continue the event loop and
+ * do the right thing if there are no more events to
+ * read (i.e. return bytes read, -EAGAIN or wait).
+ */
+ ret = 0;
+ }
+
+ /*
+ * Permission events get queued to wait for response. Other
+ * events can be destroyed now.
+ */
+ if (!fanotify_is_perm_event(event->mask)) {
+ fsnotify_destroy_event(group, &event->fse);
+ } else {
+ if (ret <= 0) {
+ spin_lock(&group->notification_lock);
+ finish_permission_event(group,
+ FANOTIFY_PERM(event), FAN_DENY);
+ wake_up(&group->fanotify_data.access_waitq);
+ } else {
+ spin_lock(&group->notification_lock);
+ list_add_tail(&event->fse.list,
+ &group->fanotify_data.access_list);
+ spin_unlock(&group->notification_lock);
+ }
+ }
+ if (ret < 0)
+ break;
+ buf += ret;
+ count -= ret;
+ }
+ remove_wait_queue(&group->notification_waitq, &wait);
+
+ if (start != buf && ret != -EFAULT)
+ ret = buf - start;
+ return ret;
+}
+
+static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
+{
+ struct fanotify_response response = { .fd = -1, .response = -1 };
+ struct fsnotify_group *group;
+ int ret;
+
+ if (!IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
+ return -EINVAL;
+
+ group = file->private_data;
+
+ if (count < sizeof(response))
+ return -EINVAL;
+
+ count = sizeof(response);
+
+ pr_debug("%s: group=%p count=%zu\n", __func__, group, count);
+
+ if (copy_from_user(&response, buf, count))
+ return -EFAULT;
+
+ ret = process_access_response(group, &response);
+ if (ret < 0)
+ count = ret;
+
+ return count;
+}
+
+static int fanotify_release(struct inode *ignored, struct file *file)
+{
+ struct fsnotify_group *group = file->private_data;
+ struct fsnotify_event *fsn_event;
+
+ /*
+ * Stop new events from arriving in the notification queue. since
+ * userspace cannot use fanotify fd anymore, no event can enter or
+ * leave access_list by now either.
+ */
+ fsnotify_group_stop_queueing(group);
+
+ /*
+ * Process all permission events on access_list and notification queue
+ * and simulate reply from userspace.
+ */
+ spin_lock(&group->notification_lock);
+ while (!list_empty(&group->fanotify_data.access_list)) {
+ struct fanotify_perm_event *event;
+
+ event = list_first_entry(&group->fanotify_data.access_list,
+ struct fanotify_perm_event, fae.fse.list);
+ list_del_init(&event->fae.fse.list);
+ finish_permission_event(group, event, FAN_ALLOW);
+ spin_lock(&group->notification_lock);
+ }
+
+ /*
+ * Destroy all non-permission events. For permission events just
+ * dequeue them and set the response. They will be freed once the
+ * response is consumed and fanotify_get_response() returns.
+ */
+ while ((fsn_event = fsnotify_remove_first_event(group))) {
+ struct fanotify_event *event = FANOTIFY_E(fsn_event);
+
+ if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
+ spin_unlock(&group->notification_lock);
+ fsnotify_destroy_event(group, fsn_event);
+ } else {
+ finish_permission_event(group, FANOTIFY_PERM(event),
+ FAN_ALLOW);
+ }
+ spin_lock(&group->notification_lock);
+ }
+ spin_unlock(&group->notification_lock);
+
+ /* Response for all permission events it set, wakeup waiters */
+ wake_up(&group->fanotify_data.access_waitq);
+
+ /* matches the fanotify_init->fsnotify_alloc_group */
+ fsnotify_destroy_group(group);
+
+ return 0;
+}
+
+static long fanotify_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct fsnotify_group *group;
+ struct fsnotify_event *fsn_event;
+ void __user *p;
+ int ret = -ENOTTY;
+ size_t send_len = 0;
+
+ group = file->private_data;
+
+ p = (void __user *) arg;
+
+ switch (cmd) {
+ case FIONREAD:
+ spin_lock(&group->notification_lock);
+ list_for_each_entry(fsn_event, &group->notification_list, list)
+ send_len += FAN_EVENT_METADATA_LEN;
+ spin_unlock(&group->notification_lock);
+ ret = put_user(send_len, (int __user *) p);
+ break;
+ }
+
+ return ret;
+}
+
+static const struct file_operations fanotify_fops = {
+ .show_fdinfo = fanotify_show_fdinfo,
+ .poll = fanotify_poll,
+ .read = fanotify_read,
+ .write = fanotify_write,
+ .fasync = NULL,
+ .release = fanotify_release,
+ .unlocked_ioctl = fanotify_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
+ .llseek = noop_llseek,
+};
+
+static int fanotify_find_path(int dfd, const char __user *filename,
+ struct path *path, unsigned int flags, __u64 mask,
+ unsigned int obj_type)
+{
+ int ret;
+
+ pr_debug("%s: dfd=%d filename=%p flags=%x\n", __func__,
+ dfd, filename, flags);
+
+ if (filename == NULL) {
+ struct fd f = fdget(dfd);
+
+ ret = -EBADF;
+ if (!f.file)
+ goto out;
+
+ ret = -ENOTDIR;
+ if ((flags & FAN_MARK_ONLYDIR) &&
+ !(S_ISDIR(file_inode(f.file)->i_mode))) {
+ fdput(f);
+ goto out;
+ }
+
+ *path = f.file->f_path;
+ path_get(path);
+ fdput(f);
+ } else {
+ unsigned int lookup_flags = 0;
+
+ if (!(flags & FAN_MARK_DONT_FOLLOW))
+ lookup_flags |= LOOKUP_FOLLOW;
+ if (flags & FAN_MARK_ONLYDIR)
+ lookup_flags |= LOOKUP_DIRECTORY;
+
+ ret = user_path_at(dfd, filename, lookup_flags, path);
+ if (ret)
+ goto out;
+ }
+
+ /* you can only watch an inode if you have read permissions on it */
+ ret = path_permission(path, MAY_READ);
+ if (ret) {
+ path_put(path);
+ goto out;
+ }
+
+ ret = security_path_notify(path, mask, obj_type);
+ if (ret)
+ path_put(path);
+
+out:
+ return ret;
+}
+
+static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
+ __u32 mask, unsigned int flags,
+ __u32 umask, int *destroy)
+{
+ __u32 oldmask, newmask;
+
+ /* umask bits cannot be removed by user */
+ mask &= ~umask;
+ spin_lock(&fsn_mark->lock);
+ oldmask = fsnotify_calc_mask(fsn_mark);
+ if (!(flags & FANOTIFY_MARK_IGNORE_BITS)) {
+ fsn_mark->mask &= ~mask;
+ } else {
+ fsn_mark->ignore_mask &= ~mask;
+ }
+ newmask = fsnotify_calc_mask(fsn_mark);
+ /*
+ * We need to keep the mark around even if remaining mask cannot
+ * result in any events (e.g. mask == FAN_ONDIR) to support incremenal
+ * changes to the mask.
+ * Destroy mark when only umask bits remain.
+ */
+ *destroy = !((fsn_mark->mask | fsn_mark->ignore_mask) & ~umask);
+ spin_unlock(&fsn_mark->lock);
+
+ return oldmask & ~newmask;
+}
+
+static int fanotify_remove_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp, __u32 mask,
+ unsigned int flags, __u32 umask)
+{
+ struct fsnotify_mark *fsn_mark = NULL;
+ __u32 removed;
+ int destroy_mark;
+
+ fsnotify_group_lock(group);
+ fsn_mark = fsnotify_find_mark(connp, group);
+ if (!fsn_mark) {
+ fsnotify_group_unlock(group);
+ return -ENOENT;
+ }
+
+ removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
+ umask, &destroy_mark);
+ if (removed & fsnotify_conn_mask(fsn_mark->connector))
+ fsnotify_recalc_mask(fsn_mark->connector);
+ if (destroy_mark)
+ fsnotify_detach_mark(fsn_mark);
+ fsnotify_group_unlock(group);
+ if (destroy_mark)
+ fsnotify_free_mark(fsn_mark);
+
+ /* matches the fsnotify_find_mark() */
+ fsnotify_put_mark(fsn_mark);
+ return 0;
+}
+
+static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
+ struct vfsmount *mnt, __u32 mask,
+ unsigned int flags, __u32 umask)
+{
+ return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
+ mask, flags, umask);
+}
+
+static int fanotify_remove_sb_mark(struct fsnotify_group *group,
+ struct super_block *sb, __u32 mask,
+ unsigned int flags, __u32 umask)
+{
+ return fanotify_remove_mark(group, &sb->s_fsnotify_marks, mask,
+ flags, umask);
+}
+
+static int fanotify_remove_inode_mark(struct fsnotify_group *group,
+ struct inode *inode, __u32 mask,
+ unsigned int flags, __u32 umask)
+{
+ return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask,
+ flags, umask);
+}
+
+static bool fanotify_mark_update_flags(struct fsnotify_mark *fsn_mark,
+ unsigned int fan_flags)
+{
+ bool want_iref = !(fan_flags & FAN_MARK_EVICTABLE);
+ unsigned int ignore = fan_flags & FANOTIFY_MARK_IGNORE_BITS;
+ bool recalc = false;
+
+ /*
+ * When using FAN_MARK_IGNORE for the first time, mark starts using
+ * independent event flags in ignore mask. After that, trying to
+ * update the ignore mask with the old FAN_MARK_IGNORED_MASK API
+ * will result in EEXIST error.
+ */
+ if (ignore == FAN_MARK_IGNORE)
+ fsn_mark->flags |= FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS;
+
+ /*
+ * Setting FAN_MARK_IGNORED_SURV_MODIFY for the first time may lead to
+ * the removal of the FS_MODIFY bit in calculated mask if it was set
+ * because of an ignore mask that is now going to survive FS_MODIFY.
+ */
+ if (ignore && (fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) {
+ fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
+ if (!(fsn_mark->mask & FS_MODIFY))
+ recalc = true;
+ }
+
+ if (fsn_mark->connector->type != FSNOTIFY_OBJ_TYPE_INODE ||
+ want_iref == !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
+ return recalc;
+
+ /*
+ * NO_IREF may be removed from a mark, but not added.
+ * When removed, fsnotify_recalc_mask() will take the inode ref.
+ */
+ WARN_ON_ONCE(!want_iref);
+ fsn_mark->flags &= ~FSNOTIFY_MARK_FLAG_NO_IREF;
+
+ return true;
+}
+
+static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
+ __u32 mask, unsigned int fan_flags)
+{
+ bool recalc;
+
+ spin_lock(&fsn_mark->lock);
+ if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS))
+ fsn_mark->mask |= mask;
+ else
+ fsn_mark->ignore_mask |= mask;
+
+ recalc = fsnotify_calc_mask(fsn_mark) &
+ ~fsnotify_conn_mask(fsn_mark->connector);
+
+ recalc |= fanotify_mark_update_flags(fsn_mark, fan_flags);
+ spin_unlock(&fsn_mark->lock);
+
+ return recalc;
+}
+
+static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp,
+ unsigned int obj_type,
+ unsigned int fan_flags,
+ __kernel_fsid_t *fsid)
+{
+ struct ucounts *ucounts = group->fanotify_data.ucounts;
+ struct fsnotify_mark *mark;
+ int ret;
+
+ /*
+ * Enforce per user marks limits per user in all containing user ns.
+ * A group with FAN_UNLIMITED_MARKS does not contribute to mark count
+ * in the limited groups account.
+ */
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS) &&
+ !inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
+ return ERR_PTR(-ENOSPC);
+
+ mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+ if (!mark) {
+ ret = -ENOMEM;
+ goto out_dec_ucounts;
+ }
+
+ fsnotify_init_mark(mark, group);
+ if (fan_flags & FAN_MARK_EVICTABLE)
+ mark->flags |= FSNOTIFY_MARK_FLAG_NO_IREF;
+
+ ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid);
+ if (ret) {
+ fsnotify_put_mark(mark);
+ goto out_dec_ucounts;
+ }
+
+ return mark;
+
+out_dec_ucounts:
+ if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS))
+ dec_ucount(ucounts, UCOUNT_FANOTIFY_MARKS);
+ return ERR_PTR(ret);
+}
+
+static int fanotify_group_init_error_pool(struct fsnotify_group *group)
+{
+ if (mempool_initialized(&group->fanotify_data.error_events_pool))
+ return 0;
+
+ return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool,
+ FANOTIFY_DEFAULT_FEE_POOL_SIZE,
+ sizeof(struct fanotify_error_event));
+}
+
+static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
+ unsigned int fan_flags)
+{
+ /*
+ * Non evictable mark cannot be downgraded to evictable mark.
+ */
+ if (fan_flags & FAN_MARK_EVICTABLE &&
+ !(fsn_mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
+ return -EEXIST;
+
+ /*
+ * New ignore mask semantics cannot be downgraded to old semantics.
+ */
+ if (fan_flags & FAN_MARK_IGNORED_MASK &&
+ fsn_mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS)
+ return -EEXIST;
+
+ /*
+ * An ignore mask that survives modify could never be downgraded to not
+ * survive modify. With new FAN_MARK_IGNORE semantics we make that rule
+ * explicit and return an error when trying to update the ignore mask
+ * without the original FAN_MARK_IGNORED_SURV_MODIFY value.
+ */
+ if (fan_flags & FAN_MARK_IGNORE &&
+ !(fan_flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
+ return -EEXIST;
+
+ return 0;
+}
+
+static int fanotify_add_mark(struct fsnotify_group *group,
+ fsnotify_connp_t *connp, unsigned int obj_type,
+ __u32 mask, unsigned int fan_flags,
+ __kernel_fsid_t *fsid)
+{
+ struct fsnotify_mark *fsn_mark;
+ bool recalc;
+ int ret = 0;
+
+ fsnotify_group_lock(group);
+ fsn_mark = fsnotify_find_mark(connp, group);
+ if (!fsn_mark) {
+ fsn_mark = fanotify_add_new_mark(group, connp, obj_type,
+ fan_flags, fsid);
+ if (IS_ERR(fsn_mark)) {
+ fsnotify_group_unlock(group);
+ return PTR_ERR(fsn_mark);
+ }
+ }
+
+ /*
+ * Check if requested mark flags conflict with an existing mark flags.
+ */
+ ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags);
+ if (ret)
+ goto out;
+
+ /*
+ * Error events are pre-allocated per group, only if strictly
+ * needed (i.e. FAN_FS_ERROR was requested).
+ */
+ if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS) &&
+ (mask & FAN_FS_ERROR)) {
+ ret = fanotify_group_init_error_pool(group);
+ if (ret)
+ goto out;
+ }
+
+ recalc = fanotify_mark_add_to_mask(fsn_mark, mask, fan_flags);
+ if (recalc)
+ fsnotify_recalc_mask(fsn_mark->connector);
+
+out:
+ fsnotify_group_unlock(group);
+
+ fsnotify_put_mark(fsn_mark);
+ return ret;
+}
+
+static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
+ struct vfsmount *mnt, __u32 mask,
+ unsigned int flags, __kernel_fsid_t *fsid)
+{
+ return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags, fsid);
+}
+
+static int fanotify_add_sb_mark(struct fsnotify_group *group,
+ struct super_block *sb, __u32 mask,
+ unsigned int flags, __kernel_fsid_t *fsid)
+{
+ return fanotify_add_mark(group, &sb->s_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_SB, mask, flags, fsid);
+}
+
+static int fanotify_add_inode_mark(struct fsnotify_group *group,
+ struct inode *inode, __u32 mask,
+ unsigned int flags, __kernel_fsid_t *fsid)
+{
+ 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 ignore mask, unless that ignore mask is supposed to survive
+ * modification changes anyway.
+ */
+ if ((flags & FANOTIFY_MARK_IGNORE_BITS) &&
+ !(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
+ inode_is_open_for_write(inode))
+ return 0;
+
+ return fanotify_add_mark(group, &inode->i_fsnotify_marks,
+ FSNOTIFY_OBJ_TYPE_INODE, mask, flags, fsid);
+}
+
+static struct fsnotify_event *fanotify_alloc_overflow_event(void)
+{
+ struct fanotify_event *oevent;
+
+ oevent = kmalloc(sizeof(*oevent), GFP_KERNEL_ACCOUNT);
+ if (!oevent)
+ return NULL;
+
+ fanotify_init_event(oevent, 0, FS_Q_OVERFLOW);
+ oevent->type = FANOTIFY_EVENT_TYPE_OVERFLOW;
+
+ return &oevent->fse;
+}
+
+static struct hlist_head *fanotify_alloc_merge_hash(void)
+{
+ struct hlist_head *hash;
+
+ hash = kmalloc(sizeof(struct hlist_head) << FANOTIFY_HTABLE_BITS,
+ GFP_KERNEL_ACCOUNT);
+ if (!hash)
+ return NULL;
+
+ __hash_init(hash, FANOTIFY_HTABLE_SIZE);
+
+ return hash;
+}
+
+/* fanotify syscalls */
+SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
+{
+ struct fsnotify_group *group;
+ int f_flags, fd;
+ unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
+ unsigned int class = flags & FANOTIFY_CLASS_BITS;
+ unsigned int internal_flags = 0;
+
+ pr_debug("%s: flags=%x event_f_flags=%x\n",
+ __func__, flags, event_f_flags);
+
+ if (!capable(CAP_SYS_ADMIN)) {
+ /*
+ * An unprivileged user can setup an fanotify group with
+ * limited functionality - an unprivileged group is limited to
+ * notification events with file handles and it cannot use
+ * unlimited queue/marks.
+ */
+ if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
+ return -EPERM;
+
+ /*
+ * Setting the internal flag FANOTIFY_UNPRIV on the group
+ * prevents setting mount/filesystem marks on this group and
+ * prevents reporting pid and open fd in events.
+ */
+ internal_flags |= FANOTIFY_UNPRIV;
+ }
+
+#ifdef CONFIG_AUDITSYSCALL
+ if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT))
+#else
+ if (flags & ~FANOTIFY_INIT_FLAGS)
+#endif
+ return -EINVAL;
+
+ /*
+ * A pidfd can only be returned for a thread-group leader; thus
+ * FAN_REPORT_PIDFD and FAN_REPORT_TID need to remain mutually
+ * exclusive.
+ */
+ if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID))
+ return -EINVAL;
+
+ if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
+ return -EINVAL;
+
+ switch (event_f_flags & O_ACCMODE) {
+ case O_RDONLY:
+ case O_RDWR:
+ case O_WRONLY:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (fid_mode && class != FAN_CLASS_NOTIF)
+ return -EINVAL;
+
+ /*
+ * Child name is reported with parent fid so requires dir fid.
+ * We can report both child fid and dir fid with or without name.
+ */
+ if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID))
+ return -EINVAL;
+
+ /*
+ * FAN_REPORT_TARGET_FID requires FAN_REPORT_NAME and FAN_REPORT_FID
+ * and is used as an indication to report both dir and child fid on all
+ * dirent events.
+ */
+ if ((fid_mode & FAN_REPORT_TARGET_FID) &&
+ (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID)))
+ return -EINVAL;
+
+ f_flags = O_RDWR | __FMODE_NONOTIFY;
+ if (flags & FAN_CLOEXEC)
+ f_flags |= O_CLOEXEC;
+ if (flags & FAN_NONBLOCK)
+ f_flags |= O_NONBLOCK;
+
+ /* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */
+ group = fsnotify_alloc_group(&fanotify_fsnotify_ops,
+ FSNOTIFY_GROUP_USER | FSNOTIFY_GROUP_NOFS);
+ if (IS_ERR(group)) {
+ return PTR_ERR(group);
+ }
+
+ /* Enforce groups limits per user in all containing user ns */
+ group->fanotify_data.ucounts = inc_ucount(current_user_ns(),
+ current_euid(),
+ UCOUNT_FANOTIFY_GROUPS);
+ if (!group->fanotify_data.ucounts) {
+ fd = -EMFILE;
+ goto out_destroy_group;
+ }
+
+ group->fanotify_data.flags = flags | internal_flags;
+ group->memcg = get_mem_cgroup_from_mm(current->mm);
+
+ group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
+ if (!group->fanotify_data.merge_hash) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+
+ group->overflow_event = fanotify_alloc_overflow_event();
+ if (unlikely(!group->overflow_event)) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+
+ if (force_o_largefile())
+ event_f_flags |= O_LARGEFILE;
+ group->fanotify_data.f_flags = event_f_flags;
+ init_waitqueue_head(&group->fanotify_data.access_waitq);
+ INIT_LIST_HEAD(&group->fanotify_data.access_list);
+ switch (class) {
+ 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_destroy_group;
+ }
+
+ if (flags & FAN_UNLIMITED_QUEUE) {
+ fd = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto out_destroy_group;
+ group->max_events = UINT_MAX;
+ } else {
+ group->max_events = fanotify_max_queued_events;
+ }
+
+ if (flags & FAN_UNLIMITED_MARKS) {
+ fd = -EPERM;
+ if (!capable(CAP_SYS_ADMIN))
+ goto out_destroy_group;
+ }
+
+ if (flags & FAN_ENABLE_AUDIT) {
+ fd = -EPERM;
+ if (!capable(CAP_AUDIT_WRITE))
+ goto out_destroy_group;
+ }
+
+ fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
+ if (fd < 0)
+ goto out_destroy_group;
+
+ return fd;
+
+out_destroy_group:
+ fsnotify_destroy_group(group);
+ return fd;
+}
+
+static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
+{
+ __kernel_fsid_t root_fsid;
+ int err;
+
+ /*
+ * Make sure dentry is not of a filesystem with zero fsid (e.g. fuse).
+ */
+ err = vfs_get_fsid(dentry, fsid);
+ if (err)
+ return err;
+
+ if (!fsid->val[0] && !fsid->val[1])
+ return -ENODEV;
+
+ /*
+ * Make sure dentry is not of a filesystem subvolume (e.g. btrfs)
+ * which uses a different fsid than sb root.
+ */
+ err = vfs_get_fsid(dentry->d_sb->s_root, &root_fsid);
+ if (err)
+ return err;
+
+ if (root_fsid.val[0] != fsid->val[0] ||
+ root_fsid.val[1] != fsid->val[1])
+ return -EXDEV;
+
+ return 0;
+}
+
+/* Check if filesystem can encode a unique fid */
+static int fanotify_test_fid(struct dentry *dentry)
+{
+ /*
+ * We need to make sure that the file system supports at least
+ * encoding a file handle so user can use name_to_handle_at() to
+ * compare fid returned with event to the file handle of watched
+ * objects. However, name_to_handle_at() requires that the
+ * filesystem also supports decoding file handles.
+ */
+ if (!dentry->d_sb->s_export_op ||
+ !dentry->d_sb->s_export_op->fh_to_dentry)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static int fanotify_events_supported(struct fsnotify_group *group,
+ const struct path *path, __u64 mask,
+ unsigned int flags)
+{
+ unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+ /* Strict validation of events in non-dir inode mask with v5.17+ APIs */
+ bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) ||
+ (mask & FAN_RENAME) ||
+ (flags & FAN_MARK_IGNORE);
+
+ /*
+ * Some filesystems such as 'proc' acquire unusual locks when opening
+ * files. For them fanotify permission events have high chances of
+ * deadlocking the system - open done when reporting fanotify event
+ * blocks on this "unusual" lock while another process holding the lock
+ * waits for fanotify permission event to be answered. Just disallow
+ * permission events for such filesystems.
+ */
+ if (mask & FANOTIFY_PERM_EVENTS &&
+ path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM)
+ return -EINVAL;
+
+ /*
+ * mount and sb marks are not allowed on kernel internal pseudo fs,
+ * like pipe_mnt, because that would subscribe to events on all the
+ * anonynous pipes in the system.
+ *
+ * SB_NOUSER covers all of the internal pseudo fs whose objects are not
+ * exposed to user's mount namespace, but there are other SB_KERNMOUNT
+ * fs, like nsfs, debugfs, for which the value of allowing sb and mount
+ * mark is questionable. For now we leave them alone.
+ */
+ if (mark_type != FAN_MARK_INODE &&
+ path->mnt->mnt_sb->s_flags & SB_NOUSER)
+ return -EINVAL;
+
+ /*
+ * We shouldn't have allowed setting dirent events and the directory
+ * flags FAN_ONDIR and FAN_EVENT_ON_CHILD in mask of non-dir inode,
+ * but because we always allowed it, error only when using new APIs.
+ */
+ if (strict_dir_events && mark_type == FAN_MARK_INODE &&
+ !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
+ return -ENOTDIR;
+
+ return 0;
+}
+
+static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
+ int dfd, const char __user *pathname)
+{
+ struct inode *inode = NULL;
+ struct vfsmount *mnt = NULL;
+ struct fsnotify_group *group;
+ struct fd f;
+ struct path path;
+ __kernel_fsid_t __fsid, *fsid = NULL;
+ u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
+ unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+ unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
+ unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS;
+ unsigned int obj_type, fid_mode;
+ u32 umask = 0;
+ int ret;
+
+ pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n",
+ __func__, fanotify_fd, flags, dfd, pathname, mask);
+
+ /* we only use the lower 32 bits as of right now. */
+ if (upper_32_bits(mask))
+ return -EINVAL;
+
+ if (flags & ~FANOTIFY_MARK_FLAGS)
+ return -EINVAL;
+
+ switch (mark_type) {
+ case FAN_MARK_INODE:
+ obj_type = FSNOTIFY_OBJ_TYPE_INODE;
+ break;
+ case FAN_MARK_MOUNT:
+ obj_type = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+ break;
+ case FAN_MARK_FILESYSTEM:
+ obj_type = FSNOTIFY_OBJ_TYPE_SB;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (mark_cmd) {
+ case FAN_MARK_ADD:
+ case FAN_MARK_REMOVE:
+ if (!mask)
+ return -EINVAL;
+ break;
+ case FAN_MARK_FLUSH:
+ if (flags & ~(FANOTIFY_MARK_TYPE_BITS | FAN_MARK_FLUSH))
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
+ valid_mask |= FANOTIFY_PERM_EVENTS;
+
+ if (mask & ~valid_mask)
+ return -EINVAL;
+
+
+ /* We don't allow FAN_MARK_IGNORE & FAN_MARK_IGNORED_MASK together */
+ if (ignore == (FAN_MARK_IGNORE | FAN_MARK_IGNORED_MASK))
+ return -EINVAL;
+
+ /*
+ * Event flags (FAN_ONDIR, FAN_EVENT_ON_CHILD) have no effect with
+ * FAN_MARK_IGNORED_MASK.
+ */
+ if (ignore == FAN_MARK_IGNORED_MASK) {
+ mask &= ~FANOTIFY_EVENT_FLAGS;
+ umask = FANOTIFY_EVENT_FLAGS;
+ }
+
+ f = fdget(fanotify_fd);
+ if (unlikely(!f.file))
+ return -EBADF;
+
+ /* verify that this is indeed an fanotify instance */
+ ret = -EINVAL;
+ if (unlikely(f.file->f_op != &fanotify_fops))
+ goto fput_and_out;
+ group = f.file->private_data;
+
+ /*
+ * An unprivileged user is not allowed to setup mount nor filesystem
+ * marks. This also includes setting up such marks by a group that
+ * was initialized by an unprivileged user.
+ */
+ ret = -EPERM;
+ if ((!capable(CAP_SYS_ADMIN) ||
+ FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) &&
+ mark_type != FAN_MARK_INODE)
+ goto fput_and_out;
+
+ /*
+ * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not
+ * allowed to set permissions events.
+ */
+ ret = -EINVAL;
+ if (mask & FANOTIFY_PERM_EVENTS &&
+ group->priority == FS_PRIO_0)
+ goto fput_and_out;
+
+ if (mask & FAN_FS_ERROR &&
+ mark_type != FAN_MARK_FILESYSTEM)
+ goto fput_and_out;
+
+ /*
+ * Evictable is only relevant for inode marks, because only inode object
+ * can be evicted on memory pressure.
+ */
+ if (flags & FAN_MARK_EVICTABLE &&
+ mark_type != FAN_MARK_INODE)
+ goto fput_and_out;
+
+ /*
+ * Events that do not carry enough information to report
+ * event->fd require a group that supports reporting fid. Those
+ * events are not supported on a mount mark, because they do not
+ * carry enough information (i.e. path) to be filtered by mount
+ * point.
+ */
+ fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
+ if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
+ (!fid_mode || mark_type == FAN_MARK_MOUNT))
+ goto fput_and_out;
+
+ /*
+ * FAN_RENAME uses special info type records to report the old and
+ * new parent+name. Reporting only old and new parent id is less
+ * useful and was not implemented.
+ */
+ if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
+ goto fput_and_out;
+
+ if (mark_cmd == FAN_MARK_FLUSH) {
+ ret = 0;
+ if (mark_type == FAN_MARK_MOUNT)
+ fsnotify_clear_vfsmount_marks_by_group(group);
+ else if (mark_type == FAN_MARK_FILESYSTEM)
+ fsnotify_clear_sb_marks_by_group(group);
+ else
+ fsnotify_clear_inode_marks_by_group(group);
+ goto fput_and_out;
+ }
+
+ ret = fanotify_find_path(dfd, pathname, &path, flags,
+ (mask & ALL_FSNOTIFY_EVENTS), obj_type);
+ if (ret)
+ goto fput_and_out;
+
+ if (mark_cmd == FAN_MARK_ADD) {
+ ret = fanotify_events_supported(group, &path, mask, flags);
+ if (ret)
+ goto path_put_and_out;
+ }
+
+ if (fid_mode) {
+ ret = fanotify_test_fsid(path.dentry, &__fsid);
+ if (ret)
+ goto path_put_and_out;
+
+ ret = fanotify_test_fid(path.dentry);
+ if (ret)
+ goto path_put_and_out;
+
+ fsid = &__fsid;
+ }
+
+ /* inode held in place by reference to path; group by fget on fd */
+ if (mark_type == FAN_MARK_INODE)
+ inode = path.dentry->d_inode;
+ else
+ mnt = path.mnt;
+
+ ret = mnt ? -EINVAL : -EISDIR;
+ /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */
+ if (mark_cmd == FAN_MARK_ADD && ignore == FAN_MARK_IGNORE &&
+ (mnt || S_ISDIR(inode->i_mode)) &&
+ !(flags & FAN_MARK_IGNORED_SURV_MODIFY))
+ goto path_put_and_out;
+
+ /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
+ if (mnt || !S_ISDIR(inode->i_mode)) {
+ mask &= ~FAN_EVENT_ON_CHILD;
+ umask = FAN_EVENT_ON_CHILD;
+ /*
+ * If group needs to report parent fid, register for getting
+ * events with parent/name info for non-directory.
+ */
+ if ((fid_mode & FAN_REPORT_DIR_FID) &&
+ (flags & FAN_MARK_ADD) && !ignore)
+ mask |= FAN_EVENT_ON_CHILD;
+ }
+
+ /* create/update an inode mark */
+ switch (mark_cmd) {
+ case FAN_MARK_ADD:
+ if (mark_type == FAN_MARK_MOUNT)
+ ret = fanotify_add_vfsmount_mark(group, mnt, mask,
+ flags, fsid);
+ else if (mark_type == FAN_MARK_FILESYSTEM)
+ ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask,
+ flags, fsid);
+ else
+ ret = fanotify_add_inode_mark(group, inode, mask,
+ flags, fsid);
+ break;
+ case FAN_MARK_REMOVE:
+ if (mark_type == FAN_MARK_MOUNT)
+ ret = fanotify_remove_vfsmount_mark(group, mnt, mask,
+ flags, umask);
+ else if (mark_type == FAN_MARK_FILESYSTEM)
+ ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask,
+ flags, umask);
+ else
+ ret = fanotify_remove_inode_mark(group, inode, mask,
+ flags, umask);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+path_put_and_out:
+ path_put(&path);
+fput_and_out:
+ fdput(f);
+ return ret;
+}
+
+#ifndef CONFIG_ARCH_SPLIT_ARG64
+SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
+ __u64, mask, int, dfd,
+ const char __user *, pathname)
+{
+ return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname);
+}
+#endif
+
+#if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
+SYSCALL32_DEFINE6(fanotify_mark,
+ int, fanotify_fd, unsigned int, flags,
+ SC_ARG64(mask), int, dfd,
+ const char __user *, pathname)
+{
+ return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
+ dfd, pathname);
+}
+#endif
+
+/*
+ * fanotify_user_setup - Our initialization function. Note that we cannot return
+ * error because we have compiled-in VFS hooks. So an (unlikely) failure here
+ * must result in panic().
+ */
+static int __init fanotify_user_setup(void)
+{
+ struct sysinfo si;
+ int max_marks;
+
+ si_meminfo(&si);
+ /*
+ * Allow up to 1% of addressable memory to be accounted for per user
+ * marks limited to the range [8192, 1048576]. mount and sb marks are
+ * a lot cheaper than inode marks, but there is no reason for a user
+ * to have many of those, so calculate by the cost of inode marks.
+ */
+ max_marks = (((si.totalram - si.totalhigh) / 100) << PAGE_SHIFT) /
+ INODE_MARK_COST;
+ max_marks = clamp(max_marks, FANOTIFY_OLD_DEFAULT_MAX_MARKS,
+ FANOTIFY_DEFAULT_MAX_USER_MARKS);
+
+ BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
+
+ fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+ SLAB_PANIC|SLAB_ACCOUNT);
+ fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
+ SLAB_PANIC);
+ fanotify_path_event_cachep = KMEM_CACHE(fanotify_path_event,
+ SLAB_PANIC);
+ if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
+ fanotify_perm_event_cachep =
+ KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
+ }
+
+ fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS;
+ init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =
+ FANOTIFY_DEFAULT_MAX_GROUPS;
+ init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks;
+ fanotify_sysctls_init();
+
+ return 0;
+}
+device_initcall(fanotify_user_setup);