12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331 |
- // SPDX-License-Identifier: GPL-2.0
- #include <linux/fanotify.h>
- #include <linux/fcntl.h>
- #include <linux/file.h>
- #include <linux/fs.h>
- #include <linux/anon_inodes.h>
- #include <linux/fsnotify_backend.h>
- #include <linux/init.h>
- #include <linux/mount.h>
- #include <linux/namei.h>
- #include <linux/poll.h>
- #include <linux/security.h>
- #include <linux/syscalls.h>
- #include <linux/slab.h>
- #include <linux/types.h>
- #include <linux/uaccess.h>
- #include <linux/compat.h>
- #include <linux/sched/signal.h>
- #include <linux/memcontrol.h>
- #include <linux/statfs.h>
- #include <linux/exportfs.h>
- #include <asm/ioctls.h>
- #include "../../mount.h"
- #include "../fdinfo.h"
- #include "fanotify.h"
- #define FANOTIFY_DEFAULT_MAX_EVENTS 16384
- #define FANOTIFY_DEFAULT_MAX_MARKS 8192
- #define FANOTIFY_DEFAULT_MAX_LISTENERS 128
- /*
- * All flags that may be specified in parameter event_f_flags of fanotify_init.
- *
- * Internal and external open flags are stored together in field f_flags of
- * struct file. Only external open flags shall be allowed in event_f_flags.
- * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
- * excluded.
- */
- #define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \
- O_ACCMODE | O_APPEND | O_NONBLOCK | \
- __O_SYNC | O_DSYNC | O_CLOEXEC | \
- O_LARGEFILE | O_NOATIME )
- extern const struct fsnotify_ops fanotify_fsnotify_ops;
- struct kmem_cache *fanotify_mark_cache __read_mostly;
- struct kmem_cache *fanotify_fid_event_cachep __read_mostly;
- struct kmem_cache *fanotify_path_event_cachep __read_mostly;
- struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
- #define FANOTIFY_EVENT_ALIGN 4
- #define FANOTIFY_INFO_HDR_LEN \
- (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
- static int fanotify_fid_info_len(int fh_len, int name_len)
- {
- int info_len = fh_len;
- if (name_len)
- info_len += name_len + 1;
- return roundup(FANOTIFY_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN);
- }
- static int fanotify_event_info_len(unsigned int fid_mode,
- struct fanotify_event *event)
- {
- struct fanotify_info *info = fanotify_event_info(event);
- int dir_fh_len = fanotify_event_dir_fh_len(event);
- int fh_len = fanotify_event_object_fh_len(event);
- int info_len = 0;
- int dot_len = 0;
- if (dir_fh_len) {
- info_len += fanotify_fid_info_len(dir_fh_len, info->name_len);
- } else if ((fid_mode & FAN_REPORT_NAME) && (event->mask & FAN_ONDIR)) {
- /*
- * With group flag FAN_REPORT_NAME, if name was not recorded in
- * event on a directory, we will report the name ".".
- */
- dot_len = 1;
- }
- if (fh_len)
- info_len += fanotify_fid_info_len(fh_len, dot_len);
- return info_len;
- }
- /*
- * Get an fanotify notification event if one exists and is small
- * enough to fit in "count". Return an error pointer if the count
- * is not large enough. When permission event is dequeued, its state is
- * updated accordingly.
- */
- static struct fanotify_event *get_one_event(struct fsnotify_group *group,
- size_t count)
- {
- size_t event_size = FAN_EVENT_METADATA_LEN;
- struct fanotify_event *event = NULL;
- unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
- pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
- spin_lock(&group->notification_lock);
- if (fsnotify_notify_queue_is_empty(group))
- goto out;
- if (fid_mode) {
- event_size += fanotify_event_info_len(fid_mode,
- FANOTIFY_E(fsnotify_peek_first_event(group)));
- }
- if (event_size > count) {
- event = ERR_PTR(-EINVAL);
- goto out;
- }
- event = FANOTIFY_E(fsnotify_remove_first_event(group));
- if (fanotify_is_perm_event(event->mask))
- FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
- out:
- spin_unlock(&group->notification_lock);
- return event;
- }
- static int create_fd(struct fsnotify_group *group, struct path *path,
- struct file **file)
- {
- int client_fd;
- struct file *new_file;
- client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
- if (client_fd < 0)
- return client_fd;
- /*
- * we need a new file handle for the userspace program so it can read even if it was
- * originally opened O_WRONLY.
- */
- new_file = dentry_open(path,
- group->fanotify_data.f_flags | FMODE_NONOTIFY,
- current_cred());
- if (IS_ERR(new_file)) {
- /*
- * we still send an event even if we can't open the file. this
- * can happen when say tasks are gone and we try to open their
- * /proc files or we try to open a WRONLY file like in sysfs
- * we just send the errno to userspace since there isn't much
- * else we can do.
- */
- put_unused_fd(client_fd);
- client_fd = PTR_ERR(new_file);
- } else {
- *file = new_file;
- }
- return client_fd;
- }
- /*
- * Finish processing of permission event by setting it to ANSWERED state and
- * drop group->notification_lock.
- */
- static void finish_permission_event(struct fsnotify_group *group,
- struct fanotify_perm_event *event,
- unsigned int response)
- __releases(&group->notification_lock)
- {
- bool destroy = false;
- assert_spin_locked(&group->notification_lock);
- event->response = response;
- if (event->state == FAN_EVENT_CANCELED)
- destroy = true;
- else
- event->state = FAN_EVENT_ANSWERED;
- spin_unlock(&group->notification_lock);
- if (destroy)
- fsnotify_destroy_event(group, &event->fae.fse);
- }
- static int process_access_response(struct fsnotify_group *group,
- struct fanotify_response *response_struct)
- {
- struct fanotify_perm_event *event;
- int fd = response_struct->fd;
- int response = response_struct->response;
- pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
- fd, response);
- /*
- * make sure the response is valid, if invalid we do nothing and either
- * userspace can send a valid response or we will clean it up after the
- * timeout
- */
- switch (response & ~FAN_AUDIT) {
- case FAN_ALLOW:
- case FAN_DENY:
- break;
- default:
- return -EINVAL;
- }
- if (fd < 0)
- return -EINVAL;
- if ((response & FAN_AUDIT) && !FAN_GROUP_FLAG(group, FAN_ENABLE_AUDIT))
- return -EINVAL;
- spin_lock(&group->notification_lock);
- list_for_each_entry(event, &group->fanotify_data.access_list,
- fae.fse.list) {
- if (event->fd != fd)
- continue;
- list_del_init(&event->fae.fse.list);
- finish_permission_event(group, event, response);
- wake_up(&group->fanotify_data.access_waitq);
- return 0;
- }
- spin_unlock(&group->notification_lock);
- return -ENOENT;
- }
- static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
- int info_type, const char *name, size_t name_len,
- char __user *buf, size_t count)
- {
- struct fanotify_event_info_fid info = { };
- struct file_handle handle = { };
- unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf;
- size_t fh_len = fh ? fh->len : 0;
- size_t info_len = fanotify_fid_info_len(fh_len, name_len);
- size_t len = info_len;
- pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
- __func__, fh_len, name_len, info_len, count);
- if (!fh_len)
- return 0;
- if (WARN_ON_ONCE(len < sizeof(info) || len > count))
- return -EFAULT;
- /*
- * Copy event info fid header followed by variable sized file handle
- * and optionally followed by variable sized filename.
- */
- switch (info_type) {
- case FAN_EVENT_INFO_TYPE_FID:
- case FAN_EVENT_INFO_TYPE_DFID:
- if (WARN_ON_ONCE(name_len))
- return -EFAULT;
- break;
- case FAN_EVENT_INFO_TYPE_DFID_NAME:
- if (WARN_ON_ONCE(!name || !name_len))
- return -EFAULT;
- break;
- default:
- return -EFAULT;
- }
- info.hdr.info_type = info_type;
- info.hdr.len = len;
- info.fsid = *fsid;
- if (copy_to_user(buf, &info, sizeof(info)))
- return -EFAULT;
- buf += sizeof(info);
- len -= sizeof(info);
- if (WARN_ON_ONCE(len < sizeof(handle)))
- return -EFAULT;
- handle.handle_type = fh->type;
- handle.handle_bytes = fh_len;
- if (copy_to_user(buf, &handle, sizeof(handle)))
- return -EFAULT;
- buf += sizeof(handle);
- len -= sizeof(handle);
- if (WARN_ON_ONCE(len < fh_len))
- return -EFAULT;
- /*
- * For an inline fh and inline file name, copy through stack to exclude
- * the copy from usercopy hardening protections.
- */
- fh_buf = fanotify_fh_buf(fh);
- if (fh_len <= FANOTIFY_INLINE_FH_LEN) {
- memcpy(bounce, fh_buf, fh_len);
- fh_buf = bounce;
- }
- if (copy_to_user(buf, fh_buf, fh_len))
- return -EFAULT;
- buf += fh_len;
- len -= fh_len;
- if (name_len) {
- /* Copy the filename with terminating null */
- name_len++;
- if (WARN_ON_ONCE(len < name_len))
- return -EFAULT;
- if (copy_to_user(buf, name, name_len))
- return -EFAULT;
- buf += name_len;
- len -= name_len;
- }
- /* Pad with 0's */
- WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN);
- if (len > 0 && clear_user(buf, len))
- return -EFAULT;
- return info_len;
- }
- static ssize_t copy_event_to_user(struct fsnotify_group *group,
- struct fanotify_event *event,
- char __user *buf, size_t count)
- {
- struct fanotify_event_metadata metadata;
- struct path *path = fanotify_event_path(event);
- struct fanotify_info *info = fanotify_event_info(event);
- unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
- struct file *f = NULL;
- int ret, fd = FAN_NOFD;
- int info_type = 0;
- pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- metadata.event_len = FAN_EVENT_METADATA_LEN +
- fanotify_event_info_len(fid_mode, event);
- metadata.metadata_len = FAN_EVENT_METADATA_LEN;
- metadata.vers = FANOTIFY_METADATA_VERSION;
- metadata.reserved = 0;
- metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
- metadata.pid = pid_vnr(event->pid);
- if (path && path->mnt && path->dentry) {
- fd = create_fd(group, path, &f);
- if (fd < 0)
- return fd;
- }
- metadata.fd = fd;
- ret = -EFAULT;
- /*
- * Sanity check copy size in case get_one_event() and
- * event_len sizes ever get out of sync.
- */
- if (WARN_ON_ONCE(metadata.event_len > count))
- goto out_close_fd;
- if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN))
- goto out_close_fd;
- buf += FAN_EVENT_METADATA_LEN;
- count -= FAN_EVENT_METADATA_LEN;
- if (fanotify_is_perm_event(event->mask))
- FANOTIFY_PERM(event)->fd = fd;
- /* Event info records order is: dir fid + name, child fid */
- if (fanotify_event_dir_fh_len(event)) {
- info_type = info->name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
- FAN_EVENT_INFO_TYPE_DFID;
- ret = copy_info_to_user(fanotify_event_fsid(event),
- fanotify_info_dir_fh(info),
- info_type, fanotify_info_name(info),
- info->name_len, buf, count);
- if (ret < 0)
- goto out_close_fd;
- buf += ret;
- count -= ret;
- }
- if (fanotify_event_object_fh_len(event)) {
- const char *dot = NULL;
- int dot_len = 0;
- if (fid_mode == FAN_REPORT_FID || info_type) {
- /*
- * With only group flag FAN_REPORT_FID only type FID is
- * reported. Second info record type is always FID.
- */
- info_type = FAN_EVENT_INFO_TYPE_FID;
- } else if ((fid_mode & FAN_REPORT_NAME) &&
- (event->mask & FAN_ONDIR)) {
- /*
- * With group flag FAN_REPORT_NAME, if name was not
- * recorded in an event on a directory, report the
- * name "." with info type DFID_NAME.
- */
- info_type = FAN_EVENT_INFO_TYPE_DFID_NAME;
- dot = ".";
- dot_len = 1;
- } else if ((event->mask & ALL_FSNOTIFY_DIRENT_EVENTS) ||
- (event->mask & FAN_ONDIR)) {
- /*
- * With group flag FAN_REPORT_DIR_FID, a single info
- * record has type DFID for directory entry modification
- * event and for event on a directory.
- */
- info_type = FAN_EVENT_INFO_TYPE_DFID;
- } else {
- /*
- * With group flags FAN_REPORT_DIR_FID|FAN_REPORT_FID,
- * a single info record has type FID for event on a
- * non-directory, when there is no directory to report.
- * For example, on FAN_DELETE_SELF event.
- */
- info_type = FAN_EVENT_INFO_TYPE_FID;
- }
- ret = copy_info_to_user(fanotify_event_fsid(event),
- fanotify_event_object_fh(event),
- info_type, dot, dot_len, buf, count);
- if (ret < 0)
- goto out_close_fd;
- buf += ret;
- count -= ret;
- }
- if (f)
- fd_install(fd, f);
- return metadata.event_len;
- out_close_fd:
- if (fd != FAN_NOFD) {
- put_unused_fd(fd);
- fput(f);
- }
- return ret;
- }
- /* intofiy userspace file descriptor functions */
- static __poll_t fanotify_poll(struct file *file, poll_table *wait)
- {
- struct fsnotify_group *group = file->private_data;
- __poll_t ret = 0;
- poll_wait(file, &group->notification_waitq, wait);
- spin_lock(&group->notification_lock);
- if (!fsnotify_notify_queue_is_empty(group))
- ret = EPOLLIN | EPOLLRDNORM;
- spin_unlock(&group->notification_lock);
- return ret;
- }
- static ssize_t fanotify_read(struct file *file, char __user *buf,
- size_t count, loff_t *pos)
- {
- struct fsnotify_group *group;
- struct fanotify_event *event;
- char __user *start;
- int ret;
- DEFINE_WAIT_FUNC(wait, woken_wake_function);
- start = buf;
- group = file->private_data;
- pr_debug("%s: group=%p\n", __func__, group);
- add_wait_queue(&group->notification_waitq, &wait);
- while (1) {
- /*
- * User can supply arbitrarily large buffer. Avoid softlockups
- * in case there are lots of available events.
- */
- cond_resched();
- event = get_one_event(group, count);
- if (IS_ERR(event)) {
- ret = PTR_ERR(event);
- break;
- }
- if (!event) {
- ret = -EAGAIN;
- if (file->f_flags & O_NONBLOCK)
- break;
- ret = -ERESTARTSYS;
- if (signal_pending(current))
- break;
- if (start != buf)
- break;
- wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
- continue;
- }
- ret = copy_event_to_user(group, event, buf, count);
- if (unlikely(ret == -EOPENSTALE)) {
- /*
- * We cannot report events with stale fd so drop it.
- * Setting ret to 0 will continue the event loop and
- * do the right thing if there are no more events to
- * read (i.e. return bytes read, -EAGAIN or wait).
- */
- ret = 0;
- }
- /*
- * Permission events get queued to wait for response. Other
- * events can be destroyed now.
- */
- if (!fanotify_is_perm_event(event->mask)) {
- fsnotify_destroy_event(group, &event->fse);
- } else {
- if (ret <= 0) {
- spin_lock(&group->notification_lock);
- finish_permission_event(group,
- FANOTIFY_PERM(event), FAN_DENY);
- wake_up(&group->fanotify_data.access_waitq);
- } else {
- spin_lock(&group->notification_lock);
- list_add_tail(&event->fse.list,
- &group->fanotify_data.access_list);
- spin_unlock(&group->notification_lock);
- }
- }
- if (ret < 0)
- break;
- buf += ret;
- count -= ret;
- }
- remove_wait_queue(&group->notification_waitq, &wait);
- if (start != buf && ret != -EFAULT)
- ret = buf - start;
- return ret;
- }
- static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t count, loff_t *pos)
- {
- struct fanotify_response response = { .fd = -1, .response = -1 };
- struct fsnotify_group *group;
- int ret;
- if (!IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
- return -EINVAL;
- group = file->private_data;
- if (count < sizeof(response))
- return -EINVAL;
- count = sizeof(response);
- pr_debug("%s: group=%p count=%zu\n", __func__, group, count);
- if (copy_from_user(&response, buf, count))
- return -EFAULT;
- ret = process_access_response(group, &response);
- if (ret < 0)
- count = ret;
- return count;
- }
- static int fanotify_release(struct inode *ignored, struct file *file)
- {
- struct fsnotify_group *group = file->private_data;
- /*
- * Stop new events from arriving in the notification queue. since
- * userspace cannot use fanotify fd anymore, no event can enter or
- * leave access_list by now either.
- */
- fsnotify_group_stop_queueing(group);
- /*
- * Process all permission events on access_list and notification queue
- * and simulate reply from userspace.
- */
- spin_lock(&group->notification_lock);
- while (!list_empty(&group->fanotify_data.access_list)) {
- struct fanotify_perm_event *event;
- event = list_first_entry(&group->fanotify_data.access_list,
- struct fanotify_perm_event, fae.fse.list);
- list_del_init(&event->fae.fse.list);
- finish_permission_event(group, event, FAN_ALLOW);
- spin_lock(&group->notification_lock);
- }
- /*
- * Destroy all non-permission events. For permission events just
- * dequeue them and set the response. They will be freed once the
- * response is consumed and fanotify_get_response() returns.
- */
- while (!fsnotify_notify_queue_is_empty(group)) {
- struct fanotify_event *event;
- event = FANOTIFY_E(fsnotify_remove_first_event(group));
- if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
- spin_unlock(&group->notification_lock);
- fsnotify_destroy_event(group, &event->fse);
- } else {
- finish_permission_event(group, FANOTIFY_PERM(event),
- FAN_ALLOW);
- }
- spin_lock(&group->notification_lock);
- }
- spin_unlock(&group->notification_lock);
- /* Response for all permission events it set, wakeup waiters */
- wake_up(&group->fanotify_data.access_waitq);
- /* matches the fanotify_init->fsnotify_alloc_group */
- fsnotify_destroy_group(group);
- return 0;
- }
- static long fanotify_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
- {
- struct fsnotify_group *group;
- struct fsnotify_event *fsn_event;
- void __user *p;
- int ret = -ENOTTY;
- size_t send_len = 0;
- group = file->private_data;
- p = (void __user *) arg;
- switch (cmd) {
- case FIONREAD:
- spin_lock(&group->notification_lock);
- list_for_each_entry(fsn_event, &group->notification_list, list)
- send_len += FAN_EVENT_METADATA_LEN;
- spin_unlock(&group->notification_lock);
- ret = put_user(send_len, (int __user *) p);
- break;
- }
- return ret;
- }
- static const struct file_operations fanotify_fops = {
- .show_fdinfo = fanotify_show_fdinfo,
- .poll = fanotify_poll,
- .read = fanotify_read,
- .write = fanotify_write,
- .fasync = NULL,
- .release = fanotify_release,
- .unlocked_ioctl = fanotify_ioctl,
- .compat_ioctl = compat_ptr_ioctl,
- .llseek = noop_llseek,
- };
- static int fanotify_find_path(int dfd, const char __user *filename,
- struct path *path, unsigned int flags, __u64 mask,
- unsigned int obj_type)
- {
- int ret;
- pr_debug("%s: dfd=%d filename=%p flags=%x\n", __func__,
- dfd, filename, flags);
- if (filename == NULL) {
- struct fd f = fdget(dfd);
- ret = -EBADF;
- if (!f.file)
- goto out;
- ret = -ENOTDIR;
- if ((flags & FAN_MARK_ONLYDIR) &&
- !(S_ISDIR(file_inode(f.file)->i_mode))) {
- fdput(f);
- goto out;
- }
- *path = f.file->f_path;
- path_get(path);
- fdput(f);
- } else {
- unsigned int lookup_flags = 0;
- if (!(flags & FAN_MARK_DONT_FOLLOW))
- lookup_flags |= LOOKUP_FOLLOW;
- if (flags & FAN_MARK_ONLYDIR)
- lookup_flags |= LOOKUP_DIRECTORY;
- ret = user_path_at(dfd, filename, lookup_flags, path);
- if (ret)
- goto out;
- }
- /* you can only watch an inode if you have read permissions on it */
- ret = inode_permission(path->dentry->d_inode, MAY_READ);
- if (ret) {
- path_put(path);
- goto out;
- }
- ret = security_path_notify(path, mask, obj_type);
- if (ret)
- path_put(path);
- out:
- return ret;
- }
- static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
- __u32 mask, unsigned int flags,
- __u32 umask, int *destroy)
- {
- __u32 oldmask = 0;
- /* umask bits cannot be removed by user */
- mask &= ~umask;
- spin_lock(&fsn_mark->lock);
- if (!(flags & FAN_MARK_IGNORED_MASK)) {
- oldmask = fsn_mark->mask;
- fsn_mark->mask &= ~mask;
- } else {
- fsn_mark->ignored_mask &= ~mask;
- }
- /*
- * We need to keep the mark around even if remaining mask cannot
- * result in any events (e.g. mask == FAN_ONDIR) to support incremenal
- * changes to the mask.
- * Destroy mark when only umask bits remain.
- */
- *destroy = !((fsn_mark->mask | fsn_mark->ignored_mask) & ~umask);
- spin_unlock(&fsn_mark->lock);
- return mask & oldmask;
- }
- static int fanotify_remove_mark(struct fsnotify_group *group,
- fsnotify_connp_t *connp, __u32 mask,
- unsigned int flags, __u32 umask)
- {
- struct fsnotify_mark *fsn_mark = NULL;
- __u32 removed;
- int destroy_mark;
- mutex_lock(&group->mark_mutex);
- fsn_mark = fsnotify_find_mark(connp, group);
- if (!fsn_mark) {
- mutex_unlock(&group->mark_mutex);
- return -ENOENT;
- }
- removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
- umask, &destroy_mark);
- if (removed & fsnotify_conn_mask(fsn_mark->connector))
- fsnotify_recalc_mask(fsn_mark->connector);
- if (destroy_mark)
- fsnotify_detach_mark(fsn_mark);
- mutex_unlock(&group->mark_mutex);
- if (destroy_mark)
- fsnotify_free_mark(fsn_mark);
- /* matches the fsnotify_find_mark() */
- fsnotify_put_mark(fsn_mark);
- return 0;
- }
- static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
- struct vfsmount *mnt, __u32 mask,
- unsigned int flags, __u32 umask)
- {
- return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
- mask, flags, umask);
- }
- static int fanotify_remove_sb_mark(struct fsnotify_group *group,
- struct super_block *sb, __u32 mask,
- unsigned int flags, __u32 umask)
- {
- return fanotify_remove_mark(group, &sb->s_fsnotify_marks, mask,
- flags, umask);
- }
- static int fanotify_remove_inode_mark(struct fsnotify_group *group,
- struct inode *inode, __u32 mask,
- unsigned int flags, __u32 umask)
- {
- return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask,
- flags, umask);
- }
- static __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)) {
- oldmask = fsn_mark->mask;
- fsn_mark->mask |= mask;
- } else {
- fsn_mark->ignored_mask |= mask;
- 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,
- fsnotify_connp_t *connp,
- unsigned int type,
- __kernel_fsid_t *fsid)
- {
- 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, group);
- ret = fsnotify_add_mark_locked(mark, connp, type, 0, fsid);
- if (ret) {
- fsnotify_put_mark(mark);
- return ERR_PTR(ret);
- }
- return mark;
- }
- static int fanotify_add_mark(struct fsnotify_group *group,
- fsnotify_connp_t *connp, unsigned int type,
- __u32 mask, unsigned int flags,
- __kernel_fsid_t *fsid)
- {
- struct fsnotify_mark *fsn_mark;
- __u32 added;
- mutex_lock(&group->mark_mutex);
- fsn_mark = fsnotify_find_mark(connp, group);
- if (!fsn_mark) {
- fsn_mark = fanotify_add_new_mark(group, connp, type, fsid);
- 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 & ~fsnotify_conn_mask(fsn_mark->connector))
- fsnotify_recalc_mask(fsn_mark->connector);
- mutex_unlock(&group->mark_mutex);
- fsnotify_put_mark(fsn_mark);
- return 0;
- }
- static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
- struct vfsmount *mnt, __u32 mask,
- unsigned int flags, __kernel_fsid_t *fsid)
- {
- return fanotify_add_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
- FSNOTIFY_OBJ_TYPE_VFSMOUNT, mask, flags, fsid);
- }
- static int fanotify_add_sb_mark(struct fsnotify_group *group,
- struct super_block *sb, __u32 mask,
- unsigned int flags, __kernel_fsid_t *fsid)
- {
- return fanotify_add_mark(group, &sb->s_fsnotify_marks,
- FSNOTIFY_OBJ_TYPE_SB, mask, flags, fsid);
- }
- static int fanotify_add_inode_mark(struct fsnotify_group *group,
- struct inode *inode, __u32 mask,
- unsigned int flags, __kernel_fsid_t *fsid)
- {
- pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
- /*
- * If some other task has this inode open for write we should not add
- * an 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) &&
- inode_is_open_for_write(inode))
- return 0;
- return fanotify_add_mark(group, &inode->i_fsnotify_marks,
- FSNOTIFY_OBJ_TYPE_INODE, mask, flags, fsid);
- }
- static struct fsnotify_event *fanotify_alloc_overflow_event(void)
- {
- struct fanotify_event *oevent;
- oevent = kmalloc(sizeof(*oevent), GFP_KERNEL_ACCOUNT);
- if (!oevent)
- return NULL;
- fanotify_init_event(oevent, 0, FS_Q_OVERFLOW);
- oevent->type = FANOTIFY_EVENT_TYPE_OVERFLOW;
- return &oevent->fse;
- }
- /* 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;
- unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
- unsigned int class = flags & FANOTIFY_CLASS_BITS;
- pr_debug("%s: flags=%x event_f_flags=%x\n",
- __func__, flags, event_f_flags);
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- #ifdef CONFIG_AUDITSYSCALL
- if (flags & ~(FANOTIFY_INIT_FLAGS | FAN_ENABLE_AUDIT))
- #else
- if (flags & ~FANOTIFY_INIT_FLAGS)
- #endif
- return -EINVAL;
- if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
- return -EINVAL;
- switch (event_f_flags & O_ACCMODE) {
- case O_RDONLY:
- case O_RDWR:
- case O_WRONLY:
- break;
- default:
- return -EINVAL;
- }
- if (fid_mode && class != FAN_CLASS_NOTIF)
- return -EINVAL;
- /*
- * Child name is reported with parent fid so requires dir fid.
- * We can report both child fid and dir fid with or without name.
- */
- if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID))
- return -EINVAL;
- 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;
- group->fanotify_data.flags = flags;
- atomic_inc(&user->fanotify_listeners);
- group->memcg = get_mem_cgroup_from_mm(current->mm);
- group->overflow_event = fanotify_alloc_overflow_event();
- if (unlikely(!group->overflow_event)) {
- fd = -ENOMEM;
- goto out_destroy_group;
- }
- if (force_o_largefile())
- event_f_flags |= O_LARGEFILE;
- group->fanotify_data.f_flags = event_f_flags;
- init_waitqueue_head(&group->fanotify_data.access_waitq);
- INIT_LIST_HEAD(&group->fanotify_data.access_list);
- switch (class) {
- case FAN_CLASS_NOTIF:
- group->priority = FS_PRIO_0;
- break;
- case FAN_CLASS_CONTENT:
- group->priority = FS_PRIO_1;
- break;
- case FAN_CLASS_PRE_CONTENT:
- group->priority = FS_PRIO_2;
- break;
- default:
- fd = -EINVAL;
- goto out_destroy_group;
- }
- if (flags & FAN_UNLIMITED_QUEUE) {
- fd = -EPERM;
- if (!capable(CAP_SYS_ADMIN))
- goto out_destroy_group;
- group->max_events = UINT_MAX;
- } else {
- group->max_events = FANOTIFY_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;
- }
- if (flags & FAN_ENABLE_AUDIT) {
- fd = -EPERM;
- if (!capable(CAP_AUDIT_WRITE))
- goto out_destroy_group;
- }
- fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
- if (fd < 0)
- goto out_destroy_group;
- return fd;
- out_destroy_group:
- fsnotify_destroy_group(group);
- return fd;
- }
- /* Check if filesystem can encode a unique fid */
- static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid)
- {
- __kernel_fsid_t root_fsid;
- int err;
- /*
- * Make sure path is not in filesystem with zero fsid (e.g. tmpfs).
- */
- err = vfs_get_fsid(path->dentry, fsid);
- if (err)
- return err;
- if (!fsid->val[0] && !fsid->val[1])
- return -ENODEV;
- /*
- * Make sure path is not inside a filesystem subvolume (e.g. btrfs)
- * which uses a different fsid than sb root.
- */
- err = vfs_get_fsid(path->dentry->d_sb->s_root, &root_fsid);
- if (err)
- return err;
- if (root_fsid.val[0] != fsid->val[0] ||
- root_fsid.val[1] != fsid->val[1])
- return -EXDEV;
- /*
- * We need to make sure that the file system supports at least
- * encoding a file handle so user can use name_to_handle_at() to
- * compare fid returned with event to the file handle of watched
- * objects. However, name_to_handle_at() requires that the
- * filesystem also supports decoding file handles.
- */
- if (!path->dentry->d_sb->s_export_op ||
- !path->dentry->d_sb->s_export_op->fh_to_dentry)
- return -EOPNOTSUPP;
- return 0;
- }
- static int fanotify_events_supported(struct path *path, __u64 mask)
- {
- /*
- * Some filesystems such as 'proc' acquire unusual locks when opening
- * files. For them fanotify permission events have high chances of
- * deadlocking the system - open done when reporting fanotify event
- * blocks on this "unusual" lock while another process holding the lock
- * waits for fanotify permission event to be answered. Just disallow
- * permission events for such filesystems.
- */
- if (mask & FANOTIFY_PERM_EVENTS &&
- path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM)
- return -EINVAL;
- return 0;
- }
- static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
- int dfd, const char __user *pathname)
- {
- struct inode *inode = NULL;
- struct vfsmount *mnt = NULL;
- struct fsnotify_group *group;
- struct fd f;
- struct path path;
- __kernel_fsid_t __fsid, *fsid = NULL;
- u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
- unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
- bool ignored = flags & FAN_MARK_IGNORED_MASK;
- unsigned int obj_type, fid_mode;
- u32 umask = 0;
- int ret;
- pr_debug("%s: fanotify_fd=%d flags=%x dfd=%d pathname=%p mask=%llx\n",
- __func__, fanotify_fd, flags, dfd, pathname, mask);
- /* we only use the lower 32 bits as of right now. */
- if (mask & ((__u64)0xffffffff << 32))
- return -EINVAL;
- if (flags & ~FANOTIFY_MARK_FLAGS)
- return -EINVAL;
- switch (mark_type) {
- case FAN_MARK_INODE:
- obj_type = FSNOTIFY_OBJ_TYPE_INODE;
- break;
- case FAN_MARK_MOUNT:
- obj_type = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
- break;
- case FAN_MARK_FILESYSTEM:
- obj_type = FSNOTIFY_OBJ_TYPE_SB;
- break;
- default:
- return -EINVAL;
- }
- switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
- case FAN_MARK_ADD:
- case FAN_MARK_REMOVE:
- if (!mask)
- return -EINVAL;
- break;
- case FAN_MARK_FLUSH:
- if (flags & ~(FANOTIFY_MARK_TYPE_BITS | FAN_MARK_FLUSH))
- return -EINVAL;
- break;
- default:
- return -EINVAL;
- }
- if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS))
- valid_mask |= FANOTIFY_PERM_EVENTS;
- if (mask & ~valid_mask)
- return -EINVAL;
- /* Event flags (ONDIR, ON_CHILD) are meaningless in ignored mask */
- if (ignored)
- mask &= ~FANOTIFY_EVENT_FLAGS;
- f = fdget(fanotify_fd);
- if (unlikely(!f.file))
- return -EBADF;
- /* verify that this is indeed an fanotify instance */
- ret = -EINVAL;
- if (unlikely(f.file->f_op != &fanotify_fops))
- goto fput_and_out;
- group = f.file->private_data;
- /*
- * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not
- * allowed to set permissions events.
- */
- ret = -EINVAL;
- if (mask & FANOTIFY_PERM_EVENTS &&
- group->priority == FS_PRIO_0)
- goto fput_and_out;
- /*
- * Events with data type inode do not carry enough information to report
- * event->fd, so we do not allow setting a mask for inode events unless
- * group supports reporting fid.
- * inode events are not supported on a mount mark, because they do not
- * carry enough information (i.e. path) to be filtered by mount point.
- */
- fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
- if (mask & FANOTIFY_INODE_EVENTS &&
- (!fid_mode || mark_type == FAN_MARK_MOUNT))
- goto fput_and_out;
- if (flags & FAN_MARK_FLUSH) {
- ret = 0;
- if (mark_type == FAN_MARK_MOUNT)
- fsnotify_clear_vfsmount_marks_by_group(group);
- else if (mark_type == FAN_MARK_FILESYSTEM)
- fsnotify_clear_sb_marks_by_group(group);
- else
- fsnotify_clear_inode_marks_by_group(group);
- goto fput_and_out;
- }
- ret = fanotify_find_path(dfd, pathname, &path, flags,
- (mask & ALL_FSNOTIFY_EVENTS), obj_type);
- if (ret)
- goto fput_and_out;
- if (flags & FAN_MARK_ADD) {
- ret = fanotify_events_supported(&path, mask);
- if (ret)
- goto path_put_and_out;
- }
- if (fid_mode) {
- ret = fanotify_test_fid(&path, &__fsid);
- if (ret)
- goto path_put_and_out;
- fsid = &__fsid;
- }
- /* inode held in place by reference to path; group by fget on fd */
- if (mark_type == FAN_MARK_INODE)
- inode = path.dentry->d_inode;
- else
- mnt = path.mnt;
- /* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
- if (mnt || !S_ISDIR(inode->i_mode)) {
- mask &= ~FAN_EVENT_ON_CHILD;
- umask = FAN_EVENT_ON_CHILD;
- /*
- * If group needs to report parent fid, register for getting
- * events with parent/name info for non-directory.
- */
- if ((fid_mode & FAN_REPORT_DIR_FID) &&
- (flags & FAN_MARK_ADD) && !ignored)
- mask |= FAN_EVENT_ON_CHILD;
- }
- /* create/update an inode mark */
- switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE)) {
- case FAN_MARK_ADD:
- if (mark_type == FAN_MARK_MOUNT)
- ret = fanotify_add_vfsmount_mark(group, mnt, mask,
- flags, fsid);
- else if (mark_type == FAN_MARK_FILESYSTEM)
- ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask,
- flags, fsid);
- else
- ret = fanotify_add_inode_mark(group, inode, mask,
- flags, fsid);
- break;
- case FAN_MARK_REMOVE:
- if (mark_type == FAN_MARK_MOUNT)
- ret = fanotify_remove_vfsmount_mark(group, mnt, mask,
- flags, umask);
- else if (mark_type == FAN_MARK_FILESYSTEM)
- ret = fanotify_remove_sb_mark(group, mnt->mnt_sb, mask,
- flags, umask);
- else
- ret = fanotify_remove_inode_mark(group, inode, mask,
- flags, umask);
- break;
- default:
- ret = -EINVAL;
- }
- path_put_and_out:
- path_put(&path);
- fput_and_out:
- fdput(f);
- return ret;
- }
- #ifndef CONFIG_ARCH_SPLIT_ARG64
- SYSCALL_DEFINE5(fanotify_mark, int, fanotify_fd, unsigned int, flags,
- __u64, mask, int, dfd,
- const char __user *, pathname)
- {
- return do_fanotify_mark(fanotify_fd, flags, mask, dfd, pathname);
- }
- #endif
- #if defined(CONFIG_ARCH_SPLIT_ARG64) || defined(CONFIG_COMPAT)
- SYSCALL32_DEFINE6(fanotify_mark,
- int, fanotify_fd, unsigned int, flags,
- SC_ARG64(mask), int, dfd,
- const char __user *, pathname)
- {
- return do_fanotify_mark(fanotify_fd, flags, SC_VAL64(__u64, mask),
- dfd, pathname);
- }
- #endif
- /*
- * fanotify_user_setup - Our initialization function. Note that we cannot return
- * error because we have compiled-in VFS hooks. So an (unlikely) failure here
- * must result in panic().
- */
- static int __init fanotify_user_setup(void)
- {
- BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 10);
- BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9);
- fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
- SLAB_PANIC|SLAB_ACCOUNT);
- fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
- SLAB_PANIC);
- fanotify_path_event_cachep = KMEM_CACHE(fanotify_path_event,
- SLAB_PANIC);
- if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
- fanotify_perm_event_cachep =
- KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
- }
- return 0;
- }
- device_initcall(fanotify_user_setup);
|