Introduce a new flag FAN_REPORT_PIDFD for fanotify_init(2) which
allows userspace applications to control whether a pidfd info record
containing a pidfd is to be returned with each event.
If FAN_REPORT_PIDFD is enabled for a notification group, an additional
struct fanotify_event_info_pidfd object will be supplied alongside the
generic struct fanotify_event_metadata within a single event. This
functionality is analogous to that of FAN_REPORT_FID in terms of how
the event structure is supplied to the userspace application. Usage of
FAN_REPORT_PIDFD with FAN_REPORT_FID/FAN_REPORT_DFID_NAME is
permitted, and in this case a struct fanotify_event_info_pidfd object
will follow any struct fanotify_event_info_fid object.
Currently, the usage of FAN_REPORT_TID is not permitted along with
FAN_REPORT_PIDFD as the pidfd API only supports the creation of pidfds
for thread-group leaders. Additionally, the FAN_REPORT_PIDFD is
limited to privileged processes only i.e. listeners that are running
with the CAP_SYS_ADMIN capability. Attempting to supply either of
these initialization flags with FAN_REPORT_PIDFD will result with
EINVAL being returned to the caller.
In the event of a pidfd creation error, there are two types of error
values that can be reported back to the listener. There is
FAN_NOPIDFD, which will be reported in cases where the process
responsible for generating the event has terminated prior to fanotify
being able to create pidfd for event->pid via pidfd_create(). The
there is FAN_EPIDFD, which will be reported if a more generic pidfd
creation error occurred when calling pidfd_create().
Signed-off-by: Matthew Bobrowski <repnop@xxxxxxxxxx>
---
Changes since v2:
* The FAN_REPORT_PIDFD flag value has been changed from 0x00001000 to
0x00000080. This was so that future FID related initialization flags
could be grouped nicely.
* Fixed pidfd clean up at out_close_fd label in
copy_event_to_user(). Reversed the conditional and it now uses the
close_fd() helper instead of put_unused_fd() as we also need to close the
backing file, not just just mark the pidfd free in the fdtable.
* Shuffled around the WARN_ON_ONCE(FAN_REPORT_TID) within
copy_event_to_user() so that it's inside the if (pidfd_mode) branch. It
makes more sense to be as close to pidfd creation as possible.
* Fixed up the comment block within the if (pidfd_mode) branch.
fs/notify/fanotify/fanotify_user.c | 88 ++++++++++++++++++++++++++++--
include/linux/fanotify.h | 3 +-
include/uapi/linux/fanotify.h | 13 +++++
3 files changed, 98 insertions(+), 6 deletions(-)
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index d19f70b2c24c..bcc375c258ce 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1,6 +1,7 @@
// 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>
@@ -106,6 +107,8 @@ 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)
static int fanotify_fid_info_len(int fh_len, int name_len)
{
@@ -138,6 +141,9 @@ static int fanotify_event_info_len(unsigned int info_mode,
dot_len = 1;
}
+ if (info_mode & FAN_REPORT_PIDFD)
+ info_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
+
if (fh_len)
info_len += fanotify_fid_info_len(fh_len, dot_len);
@@ -401,13 +407,34 @@ static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
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,
+ 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: dir fid + name, child fid.
@@ -478,6 +505,16 @@ static int copy_info_records_to_user(struct fanotify_event *event,
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;
+ }
+
return total_bytes;
}
@@ -489,8 +526,9 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
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, fd = FAN_NOFD;
+ int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
@@ -524,6 +562,34 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
}
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 attempt to catch those rare instances where
+ * the process responsible for generating the event has
+ * terminated prior to calling into pidfd_create() and acquiring
+ * a valid pidfd. Report FAN_NOPIDFD to the listener in those
+ * cases. All other pidfd creation errors are represented 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
@@ -545,8 +611,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
fd_install(fd, f);
if (info_mode) {
- ret = copy_info_records_to_user(event, info, info_mode,
- buf, count);
+ ret = copy_info_records_to_user(event, info, info_mode, pidfd,
+ buf, count);
if (ret < 0)
goto out_close_fd;
}
@@ -558,6 +624,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
put_unused_fd(fd);
fput(f);
}
+
+ if (pidfd >= 0)
+ close_fd(pidfd);
+
return ret;
}
@@ -1103,6 +1173,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_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;
@@ -1504,7 +1582,7 @@ static int __init fanotify_user_setup(void)
FANOTIFY_DEFAULT_MAX_USER_MARKS);
BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
- BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 11);
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 10a7e26ddba6..eec3b7c40811 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -27,7 +27,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME)
-#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS)
+#define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD)
/*
* fanotify_init() flags that require CAP_SYS_ADMIN.
@@ -37,6 +37,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
*/
#define FANOTIFY_ADMIN_INIT_FLAGS (FANOTIFY_PERM_CLASSES | \
FAN_REPORT_TID | \
+ FAN_REPORT_PIDFD | \
FAN_UNLIMITED_QUEUE | \
FAN_UNLIMITED_MARKS)
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index fbf9c5c7dd59..64553df9d735 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -51,6 +51,7 @@
#define FAN_ENABLE_AUDIT 0x00000040
/* Flags to determine fanotify event format */
+#define FAN_REPORT_PIDFD 0x00000080 /* Report pidfd for event->pid */
#define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */
#define FAN_REPORT_FID 0x00000200 /* Report unique file id */
#define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */
@@ -123,6 +124,7 @@ struct fanotify_event_metadata {
#define FAN_EVENT_INFO_TYPE_FID 1
#define FAN_EVENT_INFO_TYPE_DFID_NAME 2
#define FAN_EVENT_INFO_TYPE_DFID 3
+#define FAN_EVENT_INFO_TYPE_PIDFD 4
/* Variable length info record following event metadata */
struct fanotify_event_info_header {
@@ -148,6 +150,15 @@ struct fanotify_event_info_fid {
unsigned char handle[0];
};
+/*
+ * This structure is used for info records of type FAN_EVENT_INFO_TYPE_PIDFD.
+ * It holds a pidfd for the pid that was responsible for generating an event.
+ */
+struct fanotify_event_info_pidfd {
+ struct fanotify_event_info_header hdr;
+ __s32 pidfd;
+};
+
struct fanotify_response {
__s32 fd;
__u32 response;
@@ -160,6 +171,8 @@ struct fanotify_response {
/* No fd set in event */
#define FAN_NOFD -1
+#define FAN_NOPIDFD FAN_NOFD
+#define FAN_EPIDFD -2
/* Helper functions to deal with fanotify_event_metadata buffers */
#define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata))
--
2.32.0.432.gabb21c7263-goog
/M
