2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-29 07:34:06 +08:00
linux-next/fs/notify/fanotify/fanotify_user.c

954 lines
23 KiB
C
Raw Normal View History

#include <linux/fanotify.h>
#include <linux/fcntl.h>
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/anon_inodes.h>
#include <linux/fsnotify_backend.h>
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
#include <linux/init.h>
#include <linux/mount.h>
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
#include <linux/sched/signal.h>
#include <asm/ioctls.h>
#include "../../mount.h"
fs, notify: add procfs fdinfo helper This allow us to print out fsnotify details such as watchee inode, device, mask and optionally a file handle. For inotify objects if kernel compiled with exportfs support the output will be | pos: 0 | flags: 02000000 | inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d | inotify wd:2 ino:a111 sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:11a1000020542153 | inotify wd:1 ino:6b149 sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:49b1060023552153 If kernel compiled without exportfs support, the file handle won't be provided but inode and device only. | pos: 0 | flags: 02000000 | inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 | inotify wd:2 ino:a111 sdev:800013 mask:800afce ignored_mask:0 | inotify wd:1 ino:6b149 sdev:800013 mask:800afce ignored_mask:0 For fanotify the output is like | pos: 0 | flags: 04002 | fanotify flags:10 event-flags:0 | fanotify mnt_id:12 mask:3b ignored_mask:0 | fanotify ino:50205 sdev:800013 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:05020500fb1d47e7 To minimize impact on general fsnotify code the new functionality is gathered in fs/notify/fdinfo.c file. Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: James Bottomley <jbottomley@parallels.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matthew Helsley <matt.helsley@gmail.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@onelan.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 08:05:12 +08:00
#include "../fdinfo.h"
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
#include "fanotify.h"
#define FANOTIFY_DEFAULT_MAX_EVENTS 16384
#define FANOTIFY_DEFAULT_MAX_MARKS 8192
#define FANOTIFY_DEFAULT_MAX_LISTENERS 128
fanotify: check file flags passed in fanotify_init Without this patch fanotify_init does not validate the value passed in event_f_flags. When a fanotify event is read from the fanotify file descriptor a new file descriptor is created where file.f_flags = event_f_flags. Internal and external open flags are stored together in field f_flags of struct file. Hence, an application might create file descriptors with internal flags like FMODE_EXEC, FMODE_NOCMTIME set. Jan Kara and Eric Paris both aggreed that this is a bug and the value of event_f_flags should be checked: https://lkml.org/lkml/2014/4/29/522 https://lkml.org/lkml/2014/4/29/539 This updated patch version considers the comments by Michael Kerrisk in https://lkml.org/lkml/2014/5/4/10 With the patch the value of event_f_flags is checked. When specifying an invalid value error EINVAL is returned. Internal flags are disallowed. File creation flags are disallowed: O_CREAT, O_DIRECTORY, O_EXCL, O_NOCTTY, O_NOFOLLOW, O_TRUNC, and O_TTY_INIT. Flags which do not make sense with fanotify are disallowed: __O_TMPFILE, O_PATH, FASYNC, and O_DIRECT. This leaves us with the following allowed values: O_RDONLY, O_WRONLY, O_RDWR are basic functionality. The are stored in the bits given by O_ACCMODE. O_APPEND is working as expected. The value might be useful in a logging application which appends the current status each time the log is opened. O_LARGEFILE is needed for files exceeding 4GB on 32bit systems. O_NONBLOCK may be useful when monitoring slow devices like tapes. O_NDELAY is equal to O_NONBLOCK except for platform parisc. To avoid code breaking on parisc either both flags should be allowed or none. The patch allows both. __O_SYNC and O_DSYNC may be used to avoid data loss on power disruption. O_NOATIME may be useful to reduce disk activity. O_CLOEXEC may be useful, if separate processes shall be used to scan files. Once this patch is accepted, the fanotify_init.2 manpage has to be updated. Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:44 +08:00
/*
* 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;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
static struct kmem_cache *fanotify_mark_cache __read_mostly;
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
struct kmem_cache *fanotify_event_cachep __read_mostly;
struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
/*
* Get an fsnotify notification event if one exists and is small
* enough to fit in "count". Return an error pointer if the count
* is not large enough.
*
* Called with the group->notification_lock held.
*/
static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
size_t count)
{
assert_spin_locked(&group->notification_lock);
pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
if (fsnotify_notify_queue_is_empty(group))
return NULL;
if (FAN_EVENT_METADATA_LEN > count)
return ERR_PTR(-EINVAL);
/* held the notification_lock the whole time, so this is the
* same event we peeked above */
return fsnotify_remove_first_event(group);
}
static int create_fd(struct fsnotify_group *group,
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
struct fanotify_event_info *event,
struct file **file)
{
int client_fd;
struct file *new_file;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
fanotify: enable close-on-exec on events' fd when requested in fanotify_init() According to commit 80af258867648 ("fanotify: groups can specify their f_flags for new fd"), file descriptors created as part of file access notification events inherit flags from the event_f_flags argument passed to syscall fanotify_init(2)[1]. Unfortunately O_CLOEXEC is currently silently ignored. Indeed, event_f_flags are only given to dentry_open(), which only seems to care about O_ACCMODE and O_PATH in do_dentry_open(), O_DIRECT in open_check_o_direct() and O_LARGEFILE in generic_file_open(). It's a pity, since, according to some lookup on various search engines and http://codesearch.debian.net/, there's already some userspace code which use O_CLOEXEC: - in systemd's readahead[2]: fanotify_fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK, O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME); - in clsync[3]: #define FANOTIFY_EVFLAGS (O_LARGEFILE|O_RDONLY|O_CLOEXEC) int fanotify_d = fanotify_init(FANOTIFY_FLAGS, FANOTIFY_EVFLAGS); - in examples [4] from "Filesystem monitoring in the Linux kernel" article[5] by Aleksander Morgado: if ((fanotify_fd = fanotify_init (FAN_CLOEXEC, O_RDONLY | O_CLOEXEC | O_LARGEFILE)) < 0) Additionally, since commit 48149e9d3a7e ("fanotify: check file flags passed in fanotify_init"). having O_CLOEXEC as part of fanotify_init() second argument is expressly allowed. So it seems expected to set close-on-exec flag on the file descriptors if userspace is allowed to request it with O_CLOEXEC. But Andrew Morton raised[6] the concern that enabling now close-on-exec might break existing applications which ask for O_CLOEXEC but expect the file descriptor to be inherited across exec(). In the other hand, as reported by Mihai Dontu[7] close-on-exec on the file descriptor returned as part of file access notify can break applications due to deadlock. So close-on-exec is needed for most applications. More, applications asking for close-on-exec are likely expecting it to be enabled, relying on O_CLOEXEC being effective. If not, it might weaken their security, as noted by Jan Kara[8]. So this patch replaces call to macro get_unused_fd() by a call to function get_unused_fd_flags() with event_f_flags value as argument. This way O_CLOEXEC flag in the second argument of fanotify_init(2) syscall is interpreted and close-on-exec get enabled when requested. [1] http://man7.org/linux/man-pages/man2/fanotify_init.2.html [2] http://cgit.freedesktop.org/systemd/systemd/tree/src/readahead/readahead-collect.c?id=v208#n294 [3] https://github.com/xaionaro/clsync/blob/v0.2.1/sync.c#L1631 https://github.com/xaionaro/clsync/blob/v0.2.1/configuration.h#L38 [4] http://www.lanedo.com/~aleksander/fanotify/fanotify-example.c [5] http://www.lanedo.com/2013/filesystem-monitoring-linux-kernel/ [6] http://lkml.kernel.org/r/20141001153621.65e9258e65a6167bf2e4cb50@linux-foundation.org [7] http://lkml.kernel.org/r/20141002095046.3715eb69@mdontu-l [8] http://lkml.kernel.org/r/20141002104410.GB19748@quack.suse.cz Link: http://lkml.kernel.org/r/cover.1411562410.git.ydroneaud@opteya.com Signed-off-by: Yann Droneaud <ydroneaud@opteya.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed by: Heinrich Schuchardt <xypron.glpk@gmx.de> Tested-by: Heinrich Schuchardt <xypron.glpk@gmx.de> Cc: Mihai Don\u021bu <mihai.dontu@gmail.com> Cc: Pádraig Brady <P@draigBrady.com> Cc: Heinrich Schuchardt <xypron.glpk@gmx.de> Cc: Jan Kara <jack@suse.cz> Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Michael Kerrisk-manpages <mtk.manpages@gmail.com> Cc: Lino Sanfilippo <LinoSanfilippo@gmx.de> Cc: Richard Guy Briggs <rgb@redhat.com> Cc: Eric Paris <eparis@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-10 06:24:40 +08:00
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.
*/
/* it's possible this event was an overflow event. in that case dentry and mnt
* are NULL; That's fine, just don't call dentry open */
if (event->path.dentry && event->path.mnt)
new_file = dentry_open(&event->path,
group->fanotify_data.f_flags | FMODE_NONOTIFY,
current_cred());
else
new_file = ERR_PTR(-EOVERFLOW);
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;
}
static int fill_event_metadata(struct fsnotify_group *group,
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
struct fanotify_event_metadata *metadata,
struct fsnotify_event *fsn_event,
struct file **file)
{
int ret = 0;
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
struct fanotify_event_info *event;
pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
group, metadata, fsn_event);
*file = NULL;
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
event = container_of(fsn_event, struct fanotify_event_info, fse);
metadata->event_len = FAN_EVENT_METADATA_LEN;
metadata->metadata_len = FAN_EVENT_METADATA_LEN;
metadata->vers = FANOTIFY_METADATA_VERSION;
metadata->reserved = 0;
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
metadata->mask = fsn_event->mask & FAN_ALL_OUTGOING_EVENTS;
metadata->pid = pid_vnr(event->tgid);
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
if (unlikely(fsn_event->mask & FAN_Q_OVERFLOW))
metadata->fd = FAN_NOFD;
else {
metadata->fd = create_fd(group, event, file);
if (metadata->fd < 0)
ret = metadata->fd;
}
return ret;
}
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
static struct fanotify_perm_event_info *dequeue_event(
struct fsnotify_group *group, int fd)
{
struct fanotify_perm_event_info *event, *return_e = NULL;
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);
return_e = event;
break;
}
spin_unlock(&group->notification_lock);
pr_debug("%s: found return_re=%p\n", __func__, return_e);
return return_e;
}
static int process_access_response(struct fsnotify_group *group,
struct fanotify_response *response_struct)
{
struct fanotify_perm_event_info *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) {
case FAN_ALLOW:
case FAN_DENY:
break;
default:
return -EINVAL;
}
if (fd < 0)
return -EINVAL;
event = dequeue_event(group, fd);
if (!event)
return -ENOENT;
event->response = response;
wake_up(&group->fanotify_data.access_waitq);
return 0;
}
#endif
static ssize_t copy_event_to_user(struct fsnotify_group *group,
struct fsnotify_event *event,
char __user *buf)
{
struct fanotify_event_metadata fanotify_event_metadata;
struct file *f;
int fd, ret;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
ret = fill_event_metadata(group, &fanotify_event_metadata, event, &f);
if (ret < 0)
return ret;
fd = fanotify_event_metadata.fd;
ret = -EFAULT;
if (copy_to_user(buf, &fanotify_event_metadata,
fanotify_event_metadata.event_len))
goto out_close_fd;
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
if (event->mask & FAN_ALL_PERM_EVENTS)
FANOTIFY_PE(event)->fd = fd;
#endif
if (fd != FAN_NOFD)
fd_install(fd, f);
return fanotify_event_metadata.event_len;
out_close_fd:
if (fd != FAN_NOFD) {
put_unused_fd(fd);
fput(f);
}
return ret;
}
/* intofiy userspace file descriptor functions */
static unsigned int fanotify_poll(struct file *file, poll_table *wait)
{
struct fsnotify_group *group = file->private_data;
int ret = 0;
poll_wait(file, &group->notification_waitq, wait);
spin_lock(&group->notification_lock);
if (!fsnotify_notify_queue_is_empty(group))
ret = POLLIN | POLLRDNORM;
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 fsnotify_event *kevent;
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) {
spin_lock(&group->notification_lock);
kevent = get_one_event(group, count);
spin_unlock(&group->notification_lock);
if (IS_ERR(kevent)) {
ret = PTR_ERR(kevent);
break;
}
if (!kevent) {
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, kevent, buf);
/*
* Permission events get queued to wait for response. Other
* events can be destroyed now.
*/
if (!(kevent->mask & FAN_ALL_PERM_EVENTS)) {
fsnotify_destroy_event(group, kevent);
if (ret < 0)
break;
} else {
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
if (ret < 0) {
FANOTIFY_PE(kevent)->response = FAN_DENY;
wake_up(&group->fanotify_data.access_waitq);
break;
}
spin_lock(&group->notification_lock);
list_add_tail(&kevent->list,
&group->fanotify_data.access_list);
spin_unlock(&group->notification_lock);
#endif
}
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)
{
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
struct fanotify_response response = { .fd = -1, .response = -1 };
struct fsnotify_group *group;
int ret;
group = file->private_data;
if (count > sizeof(response))
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;
#else
return -EINVAL;
#endif
}
static int fanotify_release(struct inode *ignored, struct file *file)
{
struct fsnotify_group *group = file->private_data;
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
struct fanotify_perm_event_info *event, *next;
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);
list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
fae.fse.list) {
pr_debug("%s: found group=%p event=%p\n", __func__, group,
event);
list_del_init(&event->fae.fse.list);
event->response = FAN_ALLOW;
}
/*
* 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 (!fsnotify_notify_queue_is_empty(group)) {
fsn_event = fsnotify_remove_first_event(group);
if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS)) {
spin_unlock(&group->notification_lock);
fsnotify_destroy_event(group, fsn_event);
spin_lock(&group->notification_lock);
} else
FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
}
spin_unlock(&group->notification_lock);
/* Response for all permission events it set, wakeup waiters */
wake_up(&group->fanotify_data.access_waitq);
#endif
/* 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;
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
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);
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
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 = {
fs, notify: add procfs fdinfo helper This allow us to print out fsnotify details such as watchee inode, device, mask and optionally a file handle. For inotify objects if kernel compiled with exportfs support the output will be | pos: 0 | flags: 02000000 | inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d | inotify wd:2 ino:a111 sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:11a1000020542153 | inotify wd:1 ino:6b149 sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:49b1060023552153 If kernel compiled without exportfs support, the file handle won't be provided but inode and device only. | pos: 0 | flags: 02000000 | inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 | inotify wd:2 ino:a111 sdev:800013 mask:800afce ignored_mask:0 | inotify wd:1 ino:6b149 sdev:800013 mask:800afce ignored_mask:0 For fanotify the output is like | pos: 0 | flags: 04002 | fanotify flags:10 event-flags:0 | fanotify mnt_id:12 mask:3b ignored_mask:0 | fanotify ino:50205 sdev:800013 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:05020500fb1d47e7 To minimize impact on general fsnotify code the new functionality is gathered in fs/notify/fdinfo.c file. Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Acked-by: Pavel Emelyanov <xemul@parallels.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Andrey Vagin <avagin@openvz.org> Cc: Al Viro <viro@ZenIV.linux.org.uk> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: James Bottomley <jbottomley@parallels.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matthew Helsley <matt.helsley@gmail.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@onelan.co.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-18 08:05:12 +08:00
.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 = fanotify_ioctl,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.llseek = noop_llseek,
};
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
{
kmem_cache_free(fanotify_mark_cache, fsn_mark);
}
static int fanotify_find_path(int dfd, const char __user *filename,
struct path *path, unsigned int flags)
{
int ret;
pr_debug("%s: dfd=%d filename=%p flags=%x\n", __func__,
dfd, filename, flags);
if (filename == NULL) {
struct fd f = fdget(dfd);
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
ret = -EBADF;
if (!f.file)
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
goto out;
ret = -ENOTDIR;
if ((flags & FAN_MARK_ONLYDIR) &&
!(S_ISDIR(file_inode(f.file)->i_mode))) {
fdput(f);
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
goto out;
}
*path = f.file->f_path;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
path_get(path);
fdput(f);
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
} 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 = inode_permission(path->dentry->d_inode, MAY_READ);
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,
int *destroy)
{
__u32 oldmask = 0;
spin_lock(&fsn_mark->lock);
if (!(flags & FAN_MARK_IGNORED_MASK)) {
__u32 tmask = fsn_mark->mask & ~mask;
if (flags & FAN_MARK_ONDIR)
tmask &= ~FAN_ONDIR;
oldmask = fsn_mark->mask;
fsnotify_set_mark_mask_locked(fsn_mark, tmask);
} else {
__u32 tmask = fsn_mark->ignored_mask & ~mask;
if (flags & FAN_MARK_ONDIR)
tmask &= ~FAN_ONDIR;
fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
}
*destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
spin_unlock(&fsn_mark->lock);
return mask & oldmask;
}
static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
struct vfsmount *mnt, __u32 mask,
unsigned int flags)
{
struct fsnotify_mark *fsn_mark = NULL;
__u32 removed;
int destroy_mark;
mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
if (!fsn_mark) {
mutex_unlock(&group->mark_mutex);
return -ENOENT;
}
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (removed & real_mount(mnt)->mnt_fsnotify_mask)
fsnotify_recalc_vfsmount_mask(mnt);
if (destroy_mark)
fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
if (destroy_mark)
fsnotify_free_mark(fsn_mark);
fsnotify_put_mark(fsn_mark);
return 0;
}
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
static int fanotify_remove_inode_mark(struct fsnotify_group *group,
struct inode *inode, __u32 mask,
unsigned int flags)
{
struct fsnotify_mark *fsn_mark = NULL;
__u32 removed;
int destroy_mark;
mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_inode_mark(group, inode);
if (!fsn_mark) {
mutex_unlock(&group->mark_mutex);
return -ENOENT;
}
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (removed & inode->i_fsnotify_mask)
fsnotify_recalc_inode_mask(inode);
if (destroy_mark)
fsnotify_detach_mark(fsn_mark);
mutex_unlock(&group->mark_mutex);
if (destroy_mark)
fsnotify_free_mark(fsn_mark);
/* matches the fsnotify_find_inode_mark() */
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
fsnotify_put_mark(fsn_mark);
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
return 0;
}
static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
__u32 mask,
unsigned int flags)
{
__u32 oldmask = -1;
spin_lock(&fsn_mark->lock);
if (!(flags & FAN_MARK_IGNORED_MASK)) {
__u32 tmask = fsn_mark->mask | mask;
if (flags & FAN_MARK_ONDIR)
tmask |= FAN_ONDIR;
oldmask = fsn_mark->mask;
fsnotify_set_mark_mask_locked(fsn_mark, tmask);
} else {
__u32 tmask = fsn_mark->ignored_mask | mask;
if (flags & FAN_MARK_ONDIR)
tmask |= FAN_ONDIR;
fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
}
spin_unlock(&fsn_mark->lock);
return mask & ~oldmask;
}
static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
struct inode *inode,
struct vfsmount *mnt)
{
struct fsnotify_mark *mark;
int ret;
if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
return ERR_PTR(-ENOSPC);
mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
if (!mark)
return ERR_PTR(-ENOMEM);
fsnotify_init_mark(mark, fanotify_free_mark);
ret = fsnotify_add_mark_locked(mark, group, inode, mnt, 0);
if (ret) {
fsnotify_put_mark(mark);
return ERR_PTR(ret);
}
return mark;
}
static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
struct vfsmount *mnt, __u32 mask,
unsigned int flags)
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
{
struct fsnotify_mark *fsn_mark;
__u32 added;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
if (!fsn_mark) {
fsn_mark = fanotify_add_new_mark(group, NULL, mnt);
if (IS_ERR(fsn_mark)) {
mutex_unlock(&group->mark_mutex);
return PTR_ERR(fsn_mark);
}
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
fsnotify_recalc_vfsmount_mask(mnt);
mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
return 0;
}
static int fanotify_add_inode_mark(struct fsnotify_group *group,
struct inode *inode, __u32 mask,
unsigned int flags)
{
struct fsnotify_mark *fsn_mark;
__u32 added;
pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
fanotify: ignore fanotify ignore marks if open writers fanotify will clear ignore marks if a task changes the contents of an inode. The problem is with the races around when userspace finishes checking a file and when that result is actually attached to the inode. This race was described as such: Consider the following scenario with hostile processes A and B, and victim process C: 1. Process A opens new file for writing. File check request is generated. 2. File check is performed in userspace. Check result is "file has no malware". 3. The "permit" response is delivered to kernel space. 4. File ignored mark set. 5. Process A writes dummy bytes to the file. File ignored flags are cleared. 6. Process B opens the same file for reading. File check request is generated. 7. File check is performed in userspace. Check result is "file has no malware". 8. Process A writes malware bytes to the file. There is no cached response yet. 9. The "permit" response is delivered to kernel space and is cached in fanotify. 10. File ignored mark set. 11. Now any process C will be permitted to open the malware file. There is a race between steps 8 and 10 While fanotify makes no strong guarantees about systems with hostile processes there is no reason we cannot harden against this race. We do that by simply ignoring any ignore marks if the inode has open writers (aka i_writecount > 0). (We actually do not ignore ignore marks if the FAN_MARK_SURV_MODIFY flag is set) Reported-by: Vasily Novikov <vasily.novikov@kaspersky.com> Signed-off-by: Eric Paris <eparis@redhat.com>
2010-10-29 05:21:57 +08:00
/*
* If some other task has this inode open for write we should not add
* an ignored mark, unless that ignored mark is supposed to survive
* modification changes anyway.
*/
if ((flags & FAN_MARK_IGNORED_MASK) &&
!(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
(atomic_read(&inode->i_writecount) > 0))
return 0;
mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_inode_mark(group, inode);
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
if (!fsn_mark) {
fsn_mark = fanotify_add_new_mark(group, inode, NULL);
if (IS_ERR(fsn_mark)) {
mutex_unlock(&group->mark_mutex);
return PTR_ERR(fsn_mark);
}
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
if (added & ~inode->i_fsnotify_mask)
fsnotify_recalc_inode_mask(inode);
mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
return 0;
}
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
/* fanotify syscalls */
SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
{
struct fsnotify_group *group;
int f_flags, fd;
struct user_struct *user;
struct fanotify_event_info *oevent;
pr_debug("%s: flags=%d event_f_flags=%d\n",
__func__, flags, event_f_flags);
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (flags & ~FAN_ALL_INIT_FLAGS)
return -EINVAL;
fanotify: check file flags passed in fanotify_init Without this patch fanotify_init does not validate the value passed in event_f_flags. When a fanotify event is read from the fanotify file descriptor a new file descriptor is created where file.f_flags = event_f_flags. Internal and external open flags are stored together in field f_flags of struct file. Hence, an application might create file descriptors with internal flags like FMODE_EXEC, FMODE_NOCMTIME set. Jan Kara and Eric Paris both aggreed that this is a bug and the value of event_f_flags should be checked: https://lkml.org/lkml/2014/4/29/522 https://lkml.org/lkml/2014/4/29/539 This updated patch version considers the comments by Michael Kerrisk in https://lkml.org/lkml/2014/5/4/10 With the patch the value of event_f_flags is checked. When specifying an invalid value error EINVAL is returned. Internal flags are disallowed. File creation flags are disallowed: O_CREAT, O_DIRECTORY, O_EXCL, O_NOCTTY, O_NOFOLLOW, O_TRUNC, and O_TTY_INIT. Flags which do not make sense with fanotify are disallowed: __O_TMPFILE, O_PATH, FASYNC, and O_DIRECT. This leaves us with the following allowed values: O_RDONLY, O_WRONLY, O_RDWR are basic functionality. The are stored in the bits given by O_ACCMODE. O_APPEND is working as expected. The value might be useful in a logging application which appends the current status each time the log is opened. O_LARGEFILE is needed for files exceeding 4GB on 32bit systems. O_NONBLOCK may be useful when monitoring slow devices like tapes. O_NDELAY is equal to O_NONBLOCK except for platform parisc. To avoid code breaking on parisc either both flags should be allowed or none. The patch allows both. __O_SYNC and O_DSYNC may be used to avoid data loss on power disruption. O_NOATIME may be useful to reduce disk activity. O_CLOEXEC may be useful, if separate processes shall be used to scan files. Once this patch is accepted, the fanotify_init.2 manpage has to be updated. Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-05 07:05:44 +08:00
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;
}
user = get_current_user();
if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
free_uid(user);
return -EMFILE;
}
f_flags = O_RDWR | FMODE_NONOTIFY;
if (flags & FAN_CLOEXEC)
f_flags |= O_CLOEXEC;
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);
if (IS_ERR(group)) {
free_uid(user);
return PTR_ERR(group);
}
group->fanotify_data.user = user;
atomic_inc(&user->fanotify_listeners);
oevent = fanotify_alloc_event(NULL, FS_Q_OVERFLOW, NULL);
if (unlikely(!oevent)) {
fd = -ENOMEM;
goto out_destroy_group;
}
group->overflow_event = &oevent->fse;
if (force_o_largefile())
event_f_flags |= O_LARGEFILE;
group->fanotify_data.f_flags = event_f_flags;
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
#endif
switch (flags & FAN_ALL_CLASS_BITS) {
case FAN_CLASS_NOTIF:
group->priority = FS_PRIO_0;
break;
case FAN_CLASS_CONTENT:
group->priority = FS_PRIO_1;
break;
case FAN_CLASS_PRE_CONTENT:
group->priority = FS_PRIO_2;
break;
default:
fd = -EINVAL;
goto out_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_DEFAULT_MAX_EVENTS;
}
if (flags & FAN_UNLIMITED_MARKS) {
fd = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out_destroy_group;
group->fanotify_data.max_marks = UINT_MAX;
} else {
group->fanotify_data.max_marks = FANOTIFY_DEFAULT_MAX_MARKS;
}
fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
if (fd < 0)
goto out_destroy_group;
return fd;
out_destroy_group:
fsnotify_destroy_group(group);
return fd;
}
SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
__u64, mask, int, dfd,
const char __user *, pathname)
{
struct inode *inode = NULL;
struct vfsmount *mnt = NULL;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
struct fsnotify_group *group;
struct fd f;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
struct path path;
int ret;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
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 (mask & ((__u64)0xffffffff << 32))
return -EINVAL;
if (flags & ~FAN_ALL_MARK_FLAGS)
return -EINVAL;
switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
case FAN_MARK_ADD: /* fallthrough */
case FAN_MARK_REMOVE:
if (!mask)
return -EINVAL;
break;
case FAN_MARK_FLUSH:
if (flags & ~(FAN_MARK_MOUNT | FAN_MARK_FLUSH))
return -EINVAL;
break;
default:
return -EINVAL;
}
if (mask & FAN_ONDIR) {
flags |= FAN_MARK_ONDIR;
mask &= ~FAN_ONDIR;
}
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
if (mask & ~(FAN_ALL_EVENTS | FAN_ALL_PERM_EVENTS | FAN_EVENT_ON_CHILD))
#else
if (mask & ~(FAN_ALL_EVENTS | FAN_EVENT_ON_CHILD))
#endif
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
return -EINVAL;
f = fdget(fanotify_fd);
if (unlikely(!f.file))
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
return -EBADF;
/* verify that this is indeed an fanotify instance */
ret = -EINVAL;
if (unlikely(f.file->f_op != &fanotify_fops))
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
goto fput_and_out;
group = f.file->private_data;
/*
* group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not
* allowed to set permissions events.
*/
ret = -EINVAL;
if (mask & FAN_ALL_PERM_EVENTS &&
group->priority == FS_PRIO_0)
goto fput_and_out;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
if (flags & FAN_MARK_FLUSH) {
ret = 0;
if (flags & FAN_MARK_MOUNT)
fsnotify_clear_vfsmount_marks_by_group(group);
else
fsnotify_clear_inode_marks_by_group(group);
goto fput_and_out;
}
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
ret = fanotify_find_path(dfd, pathname, &path, flags);
if (ret)
goto fput_and_out;
/* inode held in place by reference to path; group by fget on fd */
if (!(flags & FAN_MARK_MOUNT))
inode = path.dentry->d_inode;
else
mnt = path.mnt;
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
/* create/update an inode mark */
switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
case FAN_MARK_ADD:
if (flags & FAN_MARK_MOUNT)
ret = fanotify_add_vfsmount_mark(group, mnt, mask, flags);
else
ret = fanotify_add_inode_mark(group, inode, mask, flags);
break;
case FAN_MARK_REMOVE:
if (flags & FAN_MARK_MOUNT)
ret = fanotify_remove_vfsmount_mark(group, mnt, mask, flags);
else
ret = fanotify_remove_inode_mark(group, inode, mask, flags);
break;
default:
ret = -EINVAL;
}
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
path_put(&path);
fput_and_out:
fdput(f);
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
return ret;
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE6(fanotify_mark,
int, fanotify_fd, unsigned int, flags,
__u32, mask0, __u32, mask1, int, dfd,
const char __user *, pathname)
{
return sys_fanotify_mark(fanotify_fd, flags,
#ifdef __BIG_ENDIAN
((__u64)mask0 << 32) | mask1,
#else
((__u64)mask1 << 32) | mask0,
#endif
dfd, pathname);
}
#endif
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
/*
* fanotify_user_setup - Our initialization function. Note that we cannot return
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
* error because we have compiled-in VFS hooks. So an (unlikely) failure here
* must result in panic().
*/
static int __init fanotify_user_setup(void)
{
fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC);
fsnotify: do not share events between notification groups Currently fsnotify framework creates one event structure for each notification event and links this event into all interested notification groups. This is done so that we save memory when several notification groups are interested in the event. However the need for event structure shared between inotify & fanotify bloats the event structure so the result is often higher memory consumption. Another problem is that fsnotify framework keeps path references with outstanding events so that fanotify can return open file descriptors with its events. This has the undesirable effect that filesystem cannot be unmounted while there are outstanding events - a regression for inotify compared to a situation before it was converted to fsnotify framework. For fanotify this problem is hard to avoid and users of fanotify should kind of expect this behavior when they ask for file descriptors from notified files. This patch changes fsnotify and its users to create separate event structure for each group. This allows for much simpler code (~400 lines removed by this patch) and also smaller event structures. For example on 64-bit system original struct fsnotify_event consumes 120 bytes, plus additional space for file name, additional 24 bytes for second and each subsequent group linking the event, and additional 32 bytes for each inotify group for private data. After the conversion inotify event consumes 48 bytes plus space for file name which is considerably less memory unless file names are long and there are several groups interested in the events (both of which are uncommon). Fanotify event fits in 56 bytes after the conversion (fanotify doesn't care about file names so its events don't have to have it allocated). A win unless there are four or more fanotify groups interested in the event. The conversion also solves the problem with unmount when only inotify is used as we don't have to grab path references for inotify events. [hughd@google.com: fanotify: fix corruption preventing startup] Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Eric Paris <eparis@parisplace.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:48:14 +08:00
fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
fanotify_perm_event_cachep = KMEM_CACHE(fanotify_perm_event_info,
SLAB_PANIC);
#endif
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
return 0;
}
fanotify: fanotify_mark syscall implementation NAME fanotify_mark - add, remove, or modify an fanotify mark on a filesystem object SYNOPSIS int fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int dfd, const char *pathname) DESCRIPTION fanotify_mark() is used to add remove or modify a mark on a filesystem object. Marks are used to indicate that the fanotify group is interested in events which occur on that object. At this point in time marks may only be added to files and directories. fanotify_fd must be a file descriptor returned by fanotify_init() The flags field must contain exactly one of the following: FAN_MARK_ADD - or the bits in mask and ignored mask into the mark FAN_MARK_REMOVE - bitwise remove the bits in mask and ignored mark from the mark The following values can be OR'd into the flags field: FAN_MARK_DONT_FOLLOW - same meaning as O_NOFOLLOW as described in open(2) FAN_MARK_ONLYDIR - same meaning as O_DIRECTORY as described in open(2) dfd may be any of the following: AT_FDCWD: the object will be lookup up based on pathname similar to open(2) file descriptor of a directory: if pathname is not NULL the object to modify will be lookup up similar to openat(2) file descriptor of the final object: if pathname is NULL the object to modify will be the object referenced by dfd The mask is the bitwise OR of the set of events of interest such as: FAN_ACCESS - object was accessed (read) FAN_MODIFY - object was modified (write) FAN_CLOSE_WRITE - object was writable and was closed FAN_CLOSE_NOWRITE - object was read only and was closed FAN_OPEN - object was opened FAN_EVENT_ON_CHILD - interested in objected that happen to children. Only relavent when the object is a directory FAN_Q_OVERFLOW - event queue overflowed (not implemented) RETURN VALUE On success, this system call returns 0. On error, -1 is returned, and errno is set to indicate the error. ERRORS EINVAL An invalid value was specified in flags. EINVAL An invalid value was specified in mask. EINVAL An invalid value was specified in ignored_mask. EINVAL fanotify_fd is not a file descriptor as returned by fanotify_init() EBADF fanotify_fd is not a valid file descriptor EBADF dfd is not a valid file descriptor and path is NULL. ENOTDIR dfd is not a directory and path is not NULL EACCESS no search permissions on some part of the path ENENT file not found ENOMEM Insufficient kernel memory is available. CONFORMING TO These system calls are Linux-specific. Signed-off-by: Eric Paris <eparis@redhat.com>
2009-12-18 10:24:26 +08:00
device_initcall(fanotify_user_setup);