summaryrefslogtreecommitdiff
path: root/fs/notify
diff options
context:
space:
mode:
Diffstat (limited to 'fs/notify')
-rw-r--r--fs/notify/dnotify/dnotify.c20
-rw-r--r--fs/notify/fanotify/Kconfig1
-rw-r--r--fs/notify/fanotify/fanotify.c71
-rw-r--r--fs/notify/fanotify/fanotify.h42
-rw-r--r--fs/notify/fanotify/fanotify_user.c549
-rw-r--r--fs/notify/fdinfo.c29
-rw-r--r--fs/notify/fsnotify.c232
-rw-r--r--fs/notify/fsnotify.h50
-rw-r--r--fs/notify/group.c11
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c2
-rw-r--r--fs/notify/inotify/inotify_user.c50
-rw-r--r--fs/notify/mark.c228
12 files changed, 875 insertions, 410 deletions
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 3464fa7e8538..c4cdaf5fa7ed 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -16,12 +16,11 @@
#include <linux/security.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
-#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
static int dir_notify_enable __read_mostly = 1;
#ifdef CONFIG_SYSCTL
-static struct ctl_table dnotify_sysctls[] = {
+static const struct ctl_table dnotify_sysctls[] = {
{
.procname = "dir-notify-enable",
.data = &dir_notify_enable,
@@ -110,7 +109,7 @@ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask,
prev = &dn->dn_next;
continue;
}
- fown = &dn->dn_filp->f_owner;
+ fown = file_f_owner(dn->dn_filp);
send_sigio(fown, dn->dn_fd, POLL_MSG);
if (dn->dn_mask & FS_DN_MULTISHOT)
prev = &dn->dn_next;
@@ -162,7 +161,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
if (!S_ISDIR(inode->i_mode))
return;
- fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
+ fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group);
if (!fsn_mark)
return;
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
@@ -316,6 +315,10 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
goto out_err;
}
+ error = file_f_owner_allocate(filp);
+ if (error)
+ goto out_err;
+
/* set up the new_fsn_mark and new_dn_mark */
new_fsn_mark = &new_dn_mark->fsn_mark;
fsnotify_init_mark(new_fsn_mark, dnotify_group);
@@ -326,7 +329,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
fsnotify_group_lock(dnotify_group);
/* add the new_fsn_mark or find an old one. */
- fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
+ fsn_mark = fsnotify_find_inode_mark(inode, dnotify_group);
if (fsn_mark) {
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
@@ -343,9 +346,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
new_fsn_mark = NULL;
}
- rcu_read_lock();
- f = lookup_fdget_rcu(fd);
- rcu_read_unlock();
+ f = fget_raw(fd);
/* if (f != filp) means that we lost a race and another task/thread
* actually closed the fd we are still playing with before we grabbed
@@ -402,8 +403,7 @@ static int __init dnotify_init(void)
SLAB_PANIC|SLAB_ACCOUNT);
dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
- dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops,
- FSNOTIFY_GROUP_NOFS);
+ dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, 0);
if (IS_ERR(dnotify_group))
panic("unable to allocate fsnotify group for dnotify\n");
dnotify_sysctl_init();
diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig
index a511f9d8677b..0e36aaf379b7 100644
--- a/fs/notify/fanotify/Kconfig
+++ b/fs/notify/fanotify/Kconfig
@@ -15,7 +15,6 @@ config FANOTIFY
config FANOTIFY_ACCESS_PERMISSIONS
bool "fanotify permissions checking"
depends on FANOTIFY
- depends on SECURITY
default n
help
Say Y here is you want fanotify listeners to be able to make permissions
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 224bccaab4cc..3083643b864b 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
-#include <linux/fdtable.h>
#include <linux/fsnotify_backend.h>
#include <linux/init.h>
#include <linux/jiffies.h>
@@ -167,6 +166,8 @@ static bool fanotify_should_merge(struct fanotify_event *old,
case FANOTIFY_EVENT_TYPE_FS_ERROR:
return fanotify_error_event_equal(FANOTIFY_EE(old),
FANOTIFY_EE(new));
+ case FANOTIFY_EVENT_TYPE_MNT:
+ return false;
default:
WARN_ON_ONCE(1);
}
@@ -224,7 +225,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
struct fanotify_perm_event *event,
struct fsnotify_iter_info *iter_info)
{
- int ret;
+ int ret, errno;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
@@ -263,14 +264,23 @@ static int fanotify_get_response(struct fsnotify_group *group,
ret = 0;
break;
case FAN_DENY:
+ /* Check custom errno from pre-content events */
+ errno = fanotify_get_response_errno(event->response);
+ if (errno) {
+ ret = -errno;
+ break;
+ }
+ fallthrough;
default:
ret = -EPERM;
}
/* Check if the response should be audited */
- if (event->response & FAN_AUDIT)
- audit_fanotify(event->response & ~FAN_AUDIT,
- &event->audit_rule);
+ if (event->response & FAN_AUDIT) {
+ u32 response = event->response &
+ (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS);
+ audit_fanotify(response & ~FAN_AUDIT, &event->audit_rule);
+ }
pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
group, event, ret);
@@ -304,7 +314,10 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
__func__, iter_info->report_mask, event_mask, data, data_type);
- if (!fid_mode) {
+ if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) {
+ if (data_type != FSNOTIFY_EVENT_MNT)
+ return 0;
+ } else if (!fid_mode) {
/* Do we have path to open a file descriptor? */
if (!path)
return 0;
@@ -402,7 +415,7 @@ static int fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
{
int dwords, type = 0;
char *ext_buf = NULL;
- void *buf = fh->buf;
+ void *buf = fh + 1;
int err;
fh->type = FILEID_ROOT;
@@ -549,9 +562,27 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
return &pevent->fae;
}
-static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
+static struct fanotify_event *fanotify_alloc_mnt_event(u64 mnt_id, gfp_t gfp)
+{
+ struct fanotify_mnt_event *pevent;
+
+ pevent = kmem_cache_alloc(fanotify_mnt_event_cachep, gfp);
+ if (!pevent)
+ return NULL;
+
+ pevent->fae.type = FANOTIFY_EVENT_TYPE_MNT;
+ pevent->mnt_id = mnt_id;
+
+ return &pevent->fae;
+}
+
+static struct fanotify_event *fanotify_alloc_perm_event(const void *data,
+ int data_type,
gfp_t gfp)
{
+ const struct path *path = fsnotify_data_path(data, data_type);
+ const struct file_range *range =
+ fsnotify_data_file_range(data, data_type);
struct fanotify_perm_event *pevent;
pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
@@ -565,6 +596,9 @@ static struct fanotify_event *fanotify_alloc_perm_event(const struct path *path,
pevent->hdr.len = 0;
pevent->state = FAN_EVENT_INIT;
pevent->path = *path;
+ /* NULL ppos means no range info */
+ pevent->ppos = range ? &range->pos : NULL;
+ pevent->count = range ? range->count : 0;
path_get(path);
return &pevent->fae;
@@ -716,6 +750,7 @@ static struct fanotify_event *fanotify_alloc_event(
fid_mode);
struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
const struct path *path = fsnotify_data_path(data, data_type);
+ u64 mnt_id = fsnotify_data_mnt_id(data, data_type);
struct mem_cgroup *old_memcg;
struct dentry *moved = NULL;
struct inode *child = NULL;
@@ -802,7 +837,7 @@ static struct fanotify_event *fanotify_alloc_event(
old_memcg = set_active_memcg(group->memcg);
if (fanotify_is_perm_event(mask)) {
- event = fanotify_alloc_perm_event(path, gfp);
+ event = fanotify_alloc_perm_event(data, data_type, gfp);
} else if (fanotify_is_error_event(mask)) {
event = fanotify_alloc_error_event(group, fsid, data,
data_type, &hash);
@@ -811,8 +846,12 @@ static struct fanotify_event *fanotify_alloc_event(
moved, &hash, gfp);
} else if (fid_mode) {
event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
- } else {
+ } else if (path) {
event = fanotify_alloc_path_event(path, &hash, gfp);
+ } else if (mnt_id) {
+ event = fanotify_alloc_mnt_event(mnt_id, gfp);
+ } else {
+ WARN_ON_ONCE(1);
}
if (!event)
@@ -910,8 +949,9 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR);
BUILD_BUG_ON(FAN_RENAME != FS_RENAME);
+ BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS);
- BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21);
+ BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 24);
mask = fanotify_group_event_mask(group, iter_info, &match_mask,
mask, data, data_type, dir);
@@ -969,6 +1009,7 @@ finish:
static void fanotify_free_group_priv(struct fsnotify_group *group)
{
+ put_user_ns(group->user_ns);
kfree(group->fanotify_data.merge_hash);
if (group->fanotify_data.ucounts)
dec_ucount(group->fanotify_data.ucounts,
@@ -1012,6 +1053,11 @@ static void fanotify_free_error_event(struct fsnotify_group *group,
mempool_free(fee, &group->fanotify_data.error_events_pool);
}
+static void fanotify_free_mnt_event(struct fanotify_event *event)
+{
+ kmem_cache_free(fanotify_mnt_event_cachep, FANOTIFY_ME(event));
+}
+
static void fanotify_free_event(struct fsnotify_group *group,
struct fsnotify_event *fsn_event)
{
@@ -1038,6 +1084,9 @@ static void fanotify_free_event(struct fsnotify_group *group,
case FANOTIFY_EVENT_TYPE_FS_ERROR:
fanotify_free_error_event(group, event);
break;
+ case FANOTIFY_EVENT_TYPE_MNT:
+ fanotify_free_mnt_event(event);
+ break;
default:
WARN_ON_ONCE(1);
}
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index e5ab33cae6a7..b78308975082 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -9,6 +9,7 @@ extern struct kmem_cache *fanotify_mark_cache;
extern struct kmem_cache *fanotify_fid_event_cachep;
extern struct kmem_cache *fanotify_path_event_cachep;
extern struct kmem_cache *fanotify_perm_event_cachep;
+extern struct kmem_cache *fanotify_mnt_event_cachep;
/* Possible states of the permission event */
enum {
@@ -24,7 +25,7 @@ enum {
* stored in either the first or last 2 dwords.
*/
#define FANOTIFY_INLINE_FH_LEN (3 << 2)
-#define FANOTIFY_FH_HDR_LEN offsetof(struct fanotify_fh, buf)
+#define FANOTIFY_FH_HDR_LEN sizeof(struct fanotify_fh)
/* Fixed size struct for file handle */
struct fanotify_fh {
@@ -33,7 +34,6 @@ struct fanotify_fh {
#define FANOTIFY_FH_FLAG_EXT_BUF 1
u8 flags;
u8 pad;
- unsigned char buf[];
} __aligned(4);
/* Variable size struct for dir file handle + child file handle + name */
@@ -91,7 +91,7 @@ static inline char **fanotify_fh_ext_buf_ptr(struct fanotify_fh *fh)
BUILD_BUG_ON(FANOTIFY_FH_HDR_LEN % 4);
BUILD_BUG_ON(__alignof__(char *) - 4 + sizeof(char *) >
FANOTIFY_INLINE_FH_LEN);
- return (char **)ALIGN((unsigned long)(fh->buf), __alignof__(char *));
+ return (char **)ALIGN((unsigned long)(fh + 1), __alignof__(char *));
}
static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh)
@@ -101,7 +101,7 @@ static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh)
static inline void *fanotify_fh_buf(struct fanotify_fh *fh)
{
- return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh->buf;
+ return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh + 1;
}
static inline int fanotify_info_dir_fh_len(struct fanotify_info *info)
@@ -244,6 +244,7 @@ enum fanotify_event_type {
FANOTIFY_EVENT_TYPE_PATH_PERM,
FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
+ FANOTIFY_EVENT_TYPE_MNT,
__FANOTIFY_EVENT_TYPE_NUM
};
@@ -276,7 +277,7 @@ static inline void fanotify_init_event(struct fanotify_event *event,
#define FANOTIFY_INLINE_FH(name, size) \
struct { \
struct fanotify_fh name; \
- /* Space for object_fh.buf[] - access with fanotify_fh_buf() */ \
+ /* Space for filehandle - access with fanotify_fh_buf() */ \
unsigned char _inline_fh_buf[size]; \
}
@@ -409,12 +410,23 @@ struct fanotify_path_event {
struct path path;
};
+struct fanotify_mnt_event {
+ struct fanotify_event fae;
+ u64 mnt_id;
+};
+
static inline struct fanotify_path_event *
FANOTIFY_PE(struct fanotify_event *event)
{
return container_of(event, struct fanotify_path_event, fae);
}
+static inline struct fanotify_mnt_event *
+FANOTIFY_ME(struct fanotify_event *event)
+{
+ return container_of(event, struct fanotify_mnt_event, fae);
+}
+
/*
* Structure for permission fanotify events. It gets allocated and freed in
* fanotify_handle_event() since we wait there for user response. When the
@@ -425,6 +437,8 @@ FANOTIFY_PE(struct fanotify_event *event)
struct fanotify_perm_event {
struct fanotify_event fae;
struct path path;
+ const loff_t *ppos; /* optional file range info */
+ size_t count;
u32 response; /* userspace answer to the event */
unsigned short state; /* state of the event */
int fd; /* fd we passed to userspace for this event */
@@ -446,6 +460,14 @@ static inline bool fanotify_is_perm_event(u32 mask)
mask & FANOTIFY_PERM_EVENTS;
}
+static inline bool fanotify_event_has_access_range(struct fanotify_event *event)
+{
+ if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS))
+ return false;
+
+ return FANOTIFY_PERM(event)->ppos;
+}
+
static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
{
return container_of(fse, struct fanotify_event, fse);
@@ -456,6 +478,11 @@ static inline bool fanotify_is_error_event(u32 mask)
return mask & FAN_FS_ERROR;
}
+static inline bool fanotify_is_mnt_event(u32 mask)
+{
+ return mask & (FAN_MNT_ATTACH | FAN_MNT_DETACH);
+}
+
static inline const struct path *fanotify_event_path(struct fanotify_event *event)
{
if (event->type == FANOTIFY_EVENT_TYPE_PATH)
@@ -518,3 +545,8 @@ static inline unsigned int fanotify_mark_user_flags(struct fsnotify_mark *mark)
return mflags;
}
+
+static inline u32 fanotify_get_response_errno(int res)
+{
+ return (res >> FAN_ERRNO_SHIFT) & FAN_ERRNO_MASK;
+}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index fbdc63cc10d9..b192ee068a7a 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1,7 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/fanotify.h>
#include <linux/fcntl.h>
-#include <linux/fdtable.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/anon_inodes.h>
@@ -59,7 +58,7 @@ static int fanotify_max_queued_events __read_mostly;
static long ft_zero = 0;
static long ft_int_max = INT_MAX;
-static struct ctl_table fanotify_table[] = {
+static const struct ctl_table fanotify_table[] = {
{
.procname = "max_user_groups",
.data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS],
@@ -101,8 +100,7 @@ static void __init fanotify_sysctls_init(void)
*
* 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.
+ * Internal flags like FMODE_EXEC shall be excluded.
*/
#define FANOTIFY_INIT_ALL_EVENT_F_BITS ( \
O_ACCMODE | O_APPEND | O_NONBLOCK | \
@@ -115,14 +113,19 @@ struct kmem_cache *fanotify_mark_cache __ro_after_init;
struct kmem_cache *fanotify_fid_event_cachep __ro_after_init;
struct kmem_cache *fanotify_path_event_cachep __ro_after_init;
struct kmem_cache *fanotify_perm_event_cachep __ro_after_init;
+struct kmem_cache *fanotify_mnt_event_cachep __ro_after_init;
#define FANOTIFY_EVENT_ALIGN 4
#define FANOTIFY_FID_INFO_HDR_LEN \
(sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
-#define FANOTIFY_PIDFD_INFO_HDR_LEN \
+#define FANOTIFY_PIDFD_INFO_LEN \
sizeof(struct fanotify_event_info_pidfd)
#define FANOTIFY_ERROR_INFO_LEN \
(sizeof(struct fanotify_event_info_error))
+#define FANOTIFY_RANGE_INFO_LEN \
+ (sizeof(struct fanotify_event_info_range))
+#define FANOTIFY_MNT_INFO_LEN \
+ (sizeof(struct fanotify_event_info_mnt))
static int fanotify_fid_info_len(int fh_len, int name_len)
{
@@ -160,9 +163,6 @@ static size_t fanotify_event_len(unsigned int info_mode,
int fh_len;
int dot_len = 0;
- if (!info_mode)
- return event_len;
-
if (fanotify_is_error_event(event->mask))
event_len += FANOTIFY_ERROR_INFO_LEN;
@@ -177,13 +177,18 @@ static size_t fanotify_event_len(unsigned int info_mode,
dot_len = 1;
}
- if (info_mode & FAN_REPORT_PIDFD)
- event_len += FANOTIFY_PIDFD_INFO_HDR_LEN;
-
if (fanotify_event_has_object_fh(event)) {
fh_len = fanotify_event_object_fh_len(event);
event_len += fanotify_fid_info_len(fh_len, dot_len);
}
+ if (fanotify_is_mnt_event(event->mask))
+ event_len += FANOTIFY_MNT_INFO_LEN;
+
+ if (info_mode & FAN_REPORT_PIDFD)
+ event_len += FANOTIFY_PIDFD_INFO_LEN;
+
+ if (fanotify_event_has_access_range(event))
+ event_len += FANOTIFY_RANGE_INFO_LEN;
return event_len;
}
@@ -259,20 +264,12 @@ static int create_fd(struct fsnotify_group *group, const struct path *path,
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.
+ * We provide an fd for the userspace program, so it could access the
+ * file without generating fanotify events itself.
*/
- new_file = dentry_open(path,
- group->fanotify_data.f_flags | __FMODE_NONOTIFY,
- current_cred());
+ new_file = dentry_open_nonotify(path, group->fanotify_data.f_flags,
+ 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 {
@@ -335,11 +332,12 @@ static int process_access_response(struct fsnotify_group *group,
struct fanotify_perm_event *event;
int fd = response_struct->fd;
u32 response = response_struct->response;
+ int errno = fanotify_get_response_errno(response);
int ret = info_len;
struct fanotify_response_info_audit_rule friar;
- pr_debug("%s: group=%p fd=%d response=%u buf=%p size=%zu\n", __func__,
- group, fd, response, info, info_len);
+ pr_debug("%s: group=%p fd=%d response=%x errno=%d buf=%p size=%zu\n",
+ __func__, group, fd, response, errno, info, info_len);
/*
* 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
@@ -350,7 +348,31 @@ static int process_access_response(struct fsnotify_group *group,
switch (response & FANOTIFY_RESPONSE_ACCESS) {
case FAN_ALLOW:
+ if (errno)
+ return -EINVAL;
+ break;
case FAN_DENY:
+ /* Custom errno is supported only for pre-content groups */
+ if (errno && group->priority != FSNOTIFY_PRIO_PRE_CONTENT)
+ return -EINVAL;
+
+ /*
+ * Limit errno to values expected on open(2)/read(2)/write(2)
+ * of regular files.
+ */
+ switch (errno) {
+ case 0:
+ case EIO:
+ case EPERM:
+ case EBUSY:
+ case ETXTBSY:
+ case EAGAIN:
+ case ENOSPC:
+ case EDQUOT:
+ break;
+ default:
+ return -EINVAL;
+ }
break;
default:
return -EINVAL;
@@ -388,6 +410,25 @@ static int process_access_response(struct fsnotify_group *group,
return -ENOENT;
}
+static size_t copy_mnt_info_to_user(struct fanotify_event *event,
+ char __user *buf, int count)
+{
+ struct fanotify_event_info_mnt info = { };
+
+ info.hdr.info_type = FAN_EVENT_INFO_TYPE_MNT;
+ info.hdr.len = FANOTIFY_MNT_INFO_LEN;
+
+ if (WARN_ON(count < info.hdr.len))
+ return -EFAULT;
+
+ info.mnt_id = FANOTIFY_ME(event)->mnt_id;
+
+ if (copy_to_user(buf, &info, sizeof(info)))
+ return -EFAULT;
+
+ return info.hdr.len;
+}
+
static size_t copy_error_info_to_user(struct fanotify_event *event,
char __user *buf, int count)
{
@@ -514,7 +555,7 @@ static int copy_pidfd_info_to_user(int pidfd,
size_t count)
{
struct fanotify_event_info_pidfd info = { };
- size_t info_len = FANOTIFY_PIDFD_INFO_HDR_LEN;
+ size_t info_len = FANOTIFY_PIDFD_INFO_LEN;
if (WARN_ON_ONCE(info_len > count))
return -EFAULT;
@@ -529,6 +570,30 @@ static int copy_pidfd_info_to_user(int pidfd,
return info_len;
}
+static size_t copy_range_info_to_user(struct fanotify_event *event,
+ char __user *buf, int count)
+{
+ struct fanotify_perm_event *pevent = FANOTIFY_PERM(event);
+ struct fanotify_event_info_range info = { };
+ size_t info_len = FANOTIFY_RANGE_INFO_LEN;
+
+ if (WARN_ON_ONCE(info_len > count))
+ return -EFAULT;
+
+ if (WARN_ON_ONCE(!pevent->ppos))
+ return -EINVAL;
+
+ info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE;
+ info.hdr.len = info_len;
+ info.offset = *(pevent->ppos);
+ info.count = pevent->count;
+
+ if (copy_to_user(buf, &info, info_len))
+ return -EFAULT;
+
+ return info_len;
+}
+
static int copy_info_records_to_user(struct fanotify_event *event,
struct fanotify_info *info,
unsigned int info_mode, int pidfd,
@@ -650,6 +715,24 @@ static int copy_info_records_to_user(struct fanotify_event *event,
total_bytes += ret;
}
+ if (fanotify_event_has_access_range(event)) {
+ ret = copy_range_info_to_user(event, buf, count);
+ if (ret < 0)
+ return ret;
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
+ if (fanotify_is_mnt_event(event->mask)) {
+ ret = copy_mnt_info_to_user(event, buf, count);
+ if (ret < 0)
+ return ret;
+ buf += ret;
+ count -= ret;
+ total_bytes += ret;
+ }
+
return total_bytes;
}
@@ -663,7 +746,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES);
unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD;
struct file *f = NULL, *pidfd_file = NULL;
- int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD;
+ int ret, pidfd = -ESRCH, fd = -EBADF;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
@@ -691,10 +774,39 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
if (!FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV) &&
path && path->mnt && path->dentry) {
fd = create_fd(group, path, &f);
- if (fd < 0)
- return fd;
+ /*
+ * Opening an fd from dentry can fail for several reasons.
+ * For example, when tasks are gone and we try to open their
+ * /proc files or we try to open a WRONLY file like in sysfs
+ * or when trying to open a file that was deleted on the
+ * remote network server.
+ *
+ * For a group with FAN_REPORT_FD_ERROR, we will send the
+ * event with the error instead of the open fd, otherwise
+ * Userspace may not get the error at all.
+ * In any case, userspace will not know which file failed to
+ * open, so add a debug print for further investigation.
+ */
+ if (fd < 0) {
+ pr_debug("fanotify: create_fd(%pd2) failed err=%d\n",
+ path->dentry, fd);
+ if (!FAN_GROUP_FLAG(group, FAN_REPORT_FD_ERROR)) {
+ /*
+ * Historically, we've handled EOPENSTALE in a
+ * special way and silently dropped such
+ * events. Now we have to keep it to maintain
+ * backward compatibility...
+ */
+ if (fd == -EOPENSTALE)
+ fd = 0;
+ return fd;
+ }
+ }
}
- metadata.fd = fd;
+ if (FAN_GROUP_FLAG(group, FAN_REPORT_FD_ERROR))
+ metadata.fd = fd;
+ else
+ metadata.fd = fd >= 0 ? fd : FAN_NOFD;
if (pidfd_mode) {
/*
@@ -709,18 +821,16 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
* The PIDTYPE_TGID check for an event->pid is performed
* preemptively in an attempt to catch out cases where the event
* listener reads events after the event generating process has
- * already terminated. Report FAN_NOPIDFD to the event listener
- * in those cases, with all other pidfd creation errors being
- * reported as FAN_EPIDFD.
+ * already terminated. Depending on flag FAN_REPORT_FD_ERROR,
+ * report either -ESRCH or FAN_NOPIDFD to the event listener in
+ * those cases with all other pidfd creation errors reported as
+ * the error code itself or as FAN_EPIDFD.
*/
- if (metadata.pid == 0 ||
- !pid_has_task(event->pid, PIDTYPE_TGID)) {
- pidfd = FAN_NOPIDFD;
- } else {
+ if (metadata.pid && pid_has_task(event->pid, PIDTYPE_TGID))
pidfd = pidfd_prepare(event->pid, 0, &pidfd_file);
- if (pidfd < 0)
- pidfd = FAN_EPIDFD;
- }
+
+ if (!FAN_GROUP_FLAG(group, FAN_REPORT_FD_ERROR) && pidfd < 0)
+ pidfd = pidfd == -ESRCH ? FAN_NOPIDFD : FAN_EPIDFD;
}
ret = -EFAULT;
@@ -737,15 +847,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
buf += FAN_EVENT_METADATA_LEN;
count -= FAN_EVENT_METADATA_LEN;
- if (fanotify_is_perm_event(event->mask))
- FANOTIFY_PERM(event)->fd = fd;
-
- if (info_mode) {
- ret = copy_info_records_to_user(event, info, info_mode, pidfd,
- buf, count);
- if (ret < 0)
- goto out_close_fd;
- }
+ ret = copy_info_records_to_user(event, info, info_mode, pidfd,
+ buf, count);
+ if (ret < 0)
+ goto out_close_fd;
if (f)
fd_install(fd, f);
@@ -753,15 +858,18 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
if (pidfd_file)
fd_install(pidfd, pidfd_file);
+ if (fanotify_is_perm_event(event->mask))
+ FANOTIFY_PERM(event)->fd = fd;
+
return metadata.event_len;
out_close_fd:
- if (fd != FAN_NOFD) {
+ if (f) {
put_unused_fd(fd);
fput(f);
}
- if (pidfd >= 0) {
+ if (pidfd_file) {
put_unused_fd(pidfd);
fput(pidfd_file);
}
@@ -828,15 +936,6 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
}
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
@@ -845,7 +944,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
if (!fanotify_is_perm_event(event->mask)) {
fsnotify_destroy_event(group, &event->fse);
} else {
- if (ret <= 0) {
+ if (ret <= 0 || FANOTIFY_PERM(event)->fd < 0) {
spin_lock(&group->notification_lock);
finish_permission_event(group,
FANOTIFY_PERM(event), FAN_DENY, NULL);
@@ -1003,22 +1102,17 @@ static int fanotify_find_path(int dfd, const char __user *filename,
dfd, filename, flags);
if (filename == NULL) {
- struct fd f = fdget(dfd);
+ CLASS(fd, f)(dfd);
- ret = -EBADF;
- if (!f.file)
- goto out;
+ if (fd_empty(f))
+ return -EBADF;
- ret = -ENOTDIR;
if ((flags & FAN_MARK_ONLYDIR) &&
- !(S_ISDIR(file_inode(f.file)->i_mode))) {
- fdput(f);
- goto out;
- }
+ !(S_ISDIR(file_inode(fd_file(f))->i_mode)))
+ return -ENOTDIR;
- *path = f.file->f_path;
+ *path = fd_file(f)->f_path;
path_get(path);
- fdput(f);
} else {
unsigned int lookup_flags = 0;
@@ -1076,7 +1170,7 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
}
static int fanotify_remove_mark(struct fsnotify_group *group,
- fsnotify_connp_t *connp, __u32 mask,
+ void *obj, unsigned int obj_type, __u32 mask,
unsigned int flags, __u32 umask)
{
struct fsnotify_mark *fsn_mark = NULL;
@@ -1084,7 +1178,7 @@ static int fanotify_remove_mark(struct fsnotify_group *group,
int destroy_mark;
fsnotify_group_lock(group);
- fsn_mark = fsnotify_find_mark(connp, group);
+ fsn_mark = fsnotify_find_mark(obj, obj_type, group);
if (!fsn_mark) {
fsnotify_group_unlock(group);
return -ENOENT;
@@ -1105,30 +1199,6 @@ static int fanotify_remove_mark(struct fsnotify_group *group,
return 0;
}
-static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
- struct vfsmount *mnt, __u32 mask,
- unsigned int flags, __u32 umask)
-{
- return fanotify_remove_mark(group, &real_mount(mnt)->mnt_fsnotify_marks,
- mask, flags, umask);
-}
-
-static int fanotify_remove_sb_mark(struct fsnotify_group *group,
- struct super_block *sb, __u32 mask,
- unsigned int flags, __u32 umask)
-{
- return fanotify_remove_mark(group, &sb->s_fsnotify_marks, mask,
- flags, umask);
-}
-
-static int fanotify_remove_inode_mark(struct fsnotify_group *group,
- struct inode *inode, __u32 mask,
- unsigned int flags, __u32 umask)
-{
- return fanotify_remove_mark(group, &inode->i_fsnotify_marks, mask,
- flags, umask);
-}
-
static bool fanotify_mark_update_flags(struct fsnotify_mark *fsn_mark,
unsigned int fan_flags)
{
@@ -1249,7 +1319,7 @@ static int fanotify_set_mark_fsid(struct fsnotify_group *group,
}
static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
- fsnotify_connp_t *connp,
+ void *obj,
unsigned int obj_type,
unsigned int fan_flags,
struct fan_fsid *fsid)
@@ -1264,6 +1334,7 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
* A group with FAN_UNLIMITED_MARKS does not contribute to mark count
* in the limited groups account.
*/
+ BUILD_BUG_ON(!(FANOTIFY_ADMIN_INIT_FLAGS & FAN_UNLIMITED_MARKS));
if (!FAN_GROUP_FLAG(group, FAN_UNLIMITED_MARKS) &&
!inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_FANOTIFY_MARKS))
return ERR_PTR(-ENOSPC);
@@ -1288,7 +1359,7 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
fan_mark->fsid.val[0] = fan_mark->fsid.val[1] = 0;
}
- ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0);
+ ret = fsnotify_add_mark_locked(mark, obj, obj_type, 0);
if (ret)
goto out_put_mark;
@@ -1313,7 +1384,7 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group)
}
static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
- unsigned int fan_flags)
+ __u32 mask, unsigned int fan_flags)
{
/*
* Non evictable mark cannot be downgraded to evictable mark.
@@ -1340,11 +1411,16 @@ static int fanotify_may_update_existing_mark(struct fsnotify_mark *fsn_mark,
fsn_mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
return -EEXIST;
+ /* For now pre-content events are not generated for directories */
+ mask |= fsn_mark->mask;
+ if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR)
+ return -EEXIST;
+
return 0;
}
static int fanotify_add_mark(struct fsnotify_group *group,
- fsnotify_connp_t *connp, unsigned int obj_type,
+ void *obj, unsigned int obj_type,
__u32 mask, unsigned int fan_flags,
struct fan_fsid *fsid)
{
@@ -1353,9 +1429,9 @@ static int fanotify_add_mark(struct fsnotify_group *group,
int ret = 0;
fsnotify_group_lock(group);
- fsn_mark = fsnotify_find_mark(connp, group);
+ fsn_mark = fsnotify_find_mark(obj, obj_type, group);
if (!fsn_mark) {
- fsn_mark = fanotify_add_new_mark(group, connp, obj_type,
+ fsn_mark = fanotify_add_new_mark(group, obj, obj_type,
fan_flags, fsid);
if (IS_ERR(fsn_mark)) {
fsnotify_group_unlock(group);
@@ -1366,7 +1442,7 @@ static int fanotify_add_mark(struct fsnotify_group *group,
/*
* Check if requested mark flags conflict with an existing mark flags.
*/
- ret = fanotify_may_update_existing_mark(fsn_mark, fan_flags);
+ ret = fanotify_may_update_existing_mark(fsn_mark, mask, fan_flags);
if (ret)
goto out;
@@ -1392,42 +1468,6 @@ out:
return ret;
}
-static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
- struct vfsmount *mnt, __u32 mask,
- unsigned int flags, struct fan_fsid *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, struct fan_fsid *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, struct fan_fsid *fsid)
-{
- pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
-
- /*
- * If some other task has this inode open for write we should not add
- * an ignore mask, unless that ignore mask is supposed to survive
- * modification changes anyway.
- */
- if ((flags & FANOTIFY_MARK_IGNORE_BITS) &&
- !(flags & FAN_MARK_IGNORED_SURV_MODIFY) &&
- inode_is_open_for_write(inode))
- return 0;
-
- return fanotify_add_mark(group, &inode->i_fsnotify_marks,
- FSNOTIFY_OBJ_TYPE_INODE, mask, flags, fsid);
-}
-
static struct fsnotify_event *fanotify_alloc_overflow_event(void)
{
struct fanotify_event *oevent;
@@ -1459,11 +1499,13 @@ static struct hlist_head *fanotify_alloc_merge_hash(void)
/* fanotify syscalls */
SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
{
+ struct user_namespace *user_ns = current_user_ns();
struct fsnotify_group *group;
int f_flags, fd;
unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
unsigned int class = flags & FANOTIFY_CLASS_BITS;
unsigned int internal_flags = 0;
+ struct file *file;
pr_debug("%s: flags=%x event_f_flags=%x\n",
__func__, flags, event_f_flags);
@@ -1472,10 +1514,11 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
/*
* An unprivileged user can setup an fanotify group with
* limited functionality - an unprivileged group is limited to
- * notification events with file handles and it cannot use
- * unlimited queue/marks.
+ * notification events with file handles or mount ids and it
+ * cannot use unlimited queue/marks.
*/
- if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) || !fid_mode)
+ if ((flags & FANOTIFY_ADMIN_INIT_FLAGS) ||
+ !(flags & (FANOTIFY_FID_BITS | FAN_REPORT_MNT)))
return -EPERM;
/*
@@ -1501,6 +1544,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID))
return -EINVAL;
+ /* Don't allow mixing mnt events with inode events for now */
+ if (flags & FAN_REPORT_MNT) {
+ if (class != FAN_CLASS_NOTIF)
+ return -EINVAL;
+ if (flags & (FANOTIFY_FID_BITS | FAN_REPORT_FD_ERROR))
+ return -EINVAL;
+ }
+
if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
return -EINVAL;
@@ -1532,7 +1583,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
(!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID)))
return -EINVAL;
- f_flags = O_RDWR | __FMODE_NONOTIFY;
+ f_flags = O_RDWR;
if (flags & FAN_CLOEXEC)
f_flags |= O_CLOEXEC;
if (flags & FAN_NONBLOCK)
@@ -1540,14 +1591,13 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
/* fsnotify_alloc_group takes a ref. Dropped in fanotify_release */
group = fsnotify_alloc_group(&fanotify_fsnotify_ops,
- FSNOTIFY_GROUP_USER | FSNOTIFY_GROUP_NOFS);
+ FSNOTIFY_GROUP_USER);
if (IS_ERR(group)) {
return PTR_ERR(group);
}
/* Enforce groups limits per user in all containing user ns */
- group->fanotify_data.ucounts = inc_ucount(current_user_ns(),
- current_euid(),
+ group->fanotify_data.ucounts = inc_ucount(user_ns, current_euid(),
UCOUNT_FANOTIFY_GROUPS);
if (!group->fanotify_data.ucounts) {
fd = -EMFILE;
@@ -1556,6 +1606,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
group->fanotify_data.flags = flags | internal_flags;
group->memcg = get_mem_cgroup_from_mm(current->mm);
+ group->user_ns = get_user_ns(user_ns);
group->fanotify_data.merge_hash = fanotify_alloc_merge_hash();
if (!group->fanotify_data.merge_hash) {
@@ -1576,44 +1627,44 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
INIT_LIST_HEAD(&group->fanotify_data.access_list);
switch (class) {
case FAN_CLASS_NOTIF:
- group->priority = FS_PRIO_0;
+ group->priority = FSNOTIFY_PRIO_NORMAL;
break;
case FAN_CLASS_CONTENT:
- group->priority = FS_PRIO_1;
+ group->priority = FSNOTIFY_PRIO_CONTENT;
break;
case FAN_CLASS_PRE_CONTENT:
- group->priority = FS_PRIO_2;
+ group->priority = FSNOTIFY_PRIO_PRE_CONTENT;
break;
default:
fd = -EINVAL;
goto out_destroy_group;
}
+ BUILD_BUG_ON(!(FANOTIFY_ADMIN_INIT_FLAGS & FAN_UNLIMITED_QUEUE));
if (flags & FAN_UNLIMITED_QUEUE) {
- fd = -EPERM;
- if (!capable(CAP_SYS_ADMIN))
- goto out_destroy_group;
group->max_events = UINT_MAX;
} else {
group->max_events = fanotify_max_queued_events;
}
- if (flags & FAN_UNLIMITED_MARKS) {
- fd = -EPERM;
- if (!capable(CAP_SYS_ADMIN))
- goto out_destroy_group;
- }
-
if (flags & FAN_ENABLE_AUDIT) {
fd = -EPERM;
if (!capable(CAP_AUDIT_WRITE))
goto out_destroy_group;
}
- fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
+ fd = get_unused_fd_flags(f_flags);
if (fd < 0)
goto out_destroy_group;
+ file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group,
+ f_flags, FMODE_NONOTIFY);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ fd = PTR_ERR(file);
+ goto out_destroy_group;
+ }
+ fd_install(fd, file);
return fd;
out_destroy_group:
@@ -1693,12 +1744,24 @@ static int fanotify_events_supported(struct fsnotify_group *group,
unsigned int flags)
{
unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+ bool is_dir = d_is_dir(path->dentry);
/* Strict validation of events in non-dir inode mask with v5.17+ APIs */
bool strict_dir_events = FAN_GROUP_FLAG(group, FAN_REPORT_TARGET_FID) ||
(mask & FAN_RENAME) ||
(flags & FAN_MARK_IGNORE);
/*
+ * Filesystems need to opt-into pre-content evnets (a.k.a HSM)
+ * and they are only supported on regular files and directories.
+ */
+ if (mask & FANOTIFY_PRE_CONTENT_EVENTS) {
+ if (!(path->mnt->mnt_sb->s_iflags & SB_I_ALLOW_HSM))
+ return -EOPNOTSUPP;
+ if (!is_dir && !d_is_reg(path->dentry))
+ return -EINVAL;
+ }
+
+ /*
* 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
@@ -1730,7 +1793,7 @@ static int fanotify_events_supported(struct fsnotify_group *group,
* but because we always allowed it, error only when using new APIs.
*/
if (strict_dir_events && mark_type == FAN_MARK_INODE &&
- !d_is_dir(path->dentry) && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
+ !is_dir && (mask & FANOTIFY_DIRONLY_EVENT_BITS))
return -ENOTDIR;
return 0;
@@ -1740,16 +1803,17 @@ 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;
struct fan_fsid __fsid, *fsid = NULL;
+ struct user_namespace *user_ns = NULL;
+ struct mnt_namespace *mntns;
u32 valid_mask = FANOTIFY_EVENTS | FANOTIFY_EVENT_FLAGS;
unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS;
unsigned int obj_type, fid_mode;
+ void *obj = NULL;
u32 umask = 0;
int ret;
@@ -1773,6 +1837,9 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
case FAN_MARK_FILESYSTEM:
obj_type = FSNOTIFY_OBJ_TYPE_SB;
break;
+ case FAN_MARK_MNTNS:
+ obj_type = FSNOTIFY_OBJ_TYPE_MNTNS;
+ break;
default:
return -EINVAL;
}
@@ -1811,39 +1878,50 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
umask = FANOTIFY_EVENT_FLAGS;
}
- f = fdget(fanotify_fd);
- if (unlikely(!f.file))
+ CLASS(fd, f)(fanotify_fd);
+ if (fd_empty(f))
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;
+ if (unlikely(fd_file(f)->f_op != &fanotify_fops))
+ return -EINVAL;
+ group = fd_file(f)->private_data;
+
+ /* Only report mount events on mnt namespace */
+ if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) {
+ if (mask & ~FANOTIFY_MOUNT_EVENTS)
+ return -EINVAL;
+ if (mark_type != FAN_MARK_MNTNS)
+ return -EINVAL;
+ } else {
+ if (mask & FANOTIFY_MOUNT_EVENTS)
+ return -EINVAL;
+ if (mark_type == FAN_MARK_MNTNS)
+ return -EINVAL;
+ }
/*
- * An unprivileged user is not allowed to setup mount nor filesystem
- * marks. This also includes setting up such marks by a group that
- * was initialized by an unprivileged user.
+ * A user is allowed to setup sb/mount/mntns marks only if it is
+ * capable in the user ns where the group was created.
*/
- ret = -EPERM;
- if ((!capable(CAP_SYS_ADMIN) ||
- FAN_GROUP_FLAG(group, FANOTIFY_UNPRIV)) &&
+ if (!ns_capable(group->user_ns, CAP_SYS_ADMIN) &&
mark_type != FAN_MARK_INODE)
- goto fput_and_out;
+ return -EPERM;
/*
- * group->priority == FS_PRIO_0 == FAN_CLASS_NOTIF. These are not
- * allowed to set permissions events.
+ * Permission events are not allowed for FAN_CLASS_NOTIF.
+ * Pre-content permission events are not allowed for FAN_CLASS_CONTENT.
*/
- ret = -EINVAL;
if (mask & FANOTIFY_PERM_EVENTS &&
- group->priority == FS_PRIO_0)
- goto fput_and_out;
+ group->priority == FSNOTIFY_PRIO_NORMAL)
+ return -EINVAL;
+ else if (mask & FANOTIFY_PRE_CONTENT_EVENTS &&
+ group->priority == FSNOTIFY_PRIO_CONTENT)
+ return -EINVAL;
if (mask & FAN_FS_ERROR &&
mark_type != FAN_MARK_FILESYSTEM)
- goto fput_and_out;
+ return -EINVAL;
/*
* Evictable is only relevant for inode marks, because only inode object
@@ -1851,7 +1929,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
*/
if (flags & FAN_MARK_EVICTABLE &&
mark_type != FAN_MARK_INODE)
- goto fput_and_out;
+ return -EINVAL;
/*
* Events that do not carry enough information to report
@@ -1861,9 +1939,9 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
* point.
*/
fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
- if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
+ if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_MOUNT_EVENTS|FANOTIFY_EVENT_FLAGS) &&
(!fid_mode || mark_type == FAN_MARK_MOUNT))
- goto fput_and_out;
+ return -EINVAL;
/*
* FAN_RENAME uses special info type records to report the old and
@@ -1871,23 +1949,21 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
* useful and was not implemented.
*/
if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME))
- goto fput_and_out;
+ return -EINVAL;
+
+ /* Pre-content events are not currently generated for directories. */
+ if (mask & FANOTIFY_PRE_CONTENT_EVENTS && mask & FAN_ONDIR)
+ return -EINVAL;
if (mark_cmd == FAN_MARK_FLUSH) {
- ret = 0;
- if (mark_type == FAN_MARK_MOUNT)
- fsnotify_clear_vfsmount_marks_by_group(group);
- else if (mark_type == FAN_MARK_FILESYSTEM)
- fsnotify_clear_sb_marks_by_group(group);
- else
- fsnotify_clear_inode_marks_by_group(group);
- goto fput_and_out;
+ fsnotify_clear_marks_by_group(group, obj_type);
+ return 0;
}
ret = fanotify_find_path(dfd, pathname, &path, flags,
(mask & ALL_FSNOTIFY_EVENTS), obj_type);
if (ret)
- goto fput_and_out;
+ return ret;
if (mark_cmd == FAN_MARK_ADD) {
ret = fanotify_events_supported(group, &path, mask, flags);
@@ -1907,21 +1983,55 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
fsid = &__fsid;
}
- /* inode held in place by reference to path; group by fget on fd */
- if (mark_type == FAN_MARK_INODE)
+ /*
+ * In addition to being capable in the user ns where group was created,
+ * the user also needs to be capable in the user ns associated with
+ * the filesystem or in the user ns associated with the mntns
+ * (when marking mntns).
+ */
+ if (obj_type == FSNOTIFY_OBJ_TYPE_INODE) {
inode = path.dentry->d_inode;
- else
- mnt = path.mnt;
+ obj = inode;
+ } else if (obj_type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+ user_ns = path.mnt->mnt_sb->s_user_ns;
+ obj = path.mnt;
+ } else if (obj_type == FSNOTIFY_OBJ_TYPE_SB) {
+ user_ns = path.mnt->mnt_sb->s_user_ns;
+ obj = path.mnt->mnt_sb;
+ } else if (obj_type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+ mntns = mnt_ns_from_dentry(path.dentry);
+ user_ns = mntns->user_ns;
+ obj = mntns;
+ }
- ret = mnt ? -EINVAL : -EISDIR;
- /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */
- if (mark_cmd == FAN_MARK_ADD && ignore == FAN_MARK_IGNORE &&
- (mnt || S_ISDIR(inode->i_mode)) &&
- !(flags & FAN_MARK_IGNORED_SURV_MODIFY))
+ ret = -EPERM;
+ if (user_ns && !ns_capable(user_ns, CAP_SYS_ADMIN))
goto path_put_and_out;
+ ret = -EINVAL;
+ if (!obj)
+ goto path_put_and_out;
+
+ /*
+ * If some other task has this inode open for write we should not add
+ * an ignore mask, unless that ignore mask is supposed to survive
+ * modification changes anyway.
+ */
+ if (mark_cmd == FAN_MARK_ADD && (flags & FANOTIFY_MARK_IGNORE_BITS) &&
+ !(flags & FAN_MARK_IGNORED_SURV_MODIFY)) {
+ ret = !inode ? -EINVAL : -EISDIR;
+ /* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */
+ if (ignore == FAN_MARK_IGNORE &&
+ (!inode || S_ISDIR(inode->i_mode)))
+ goto path_put_and_out;
+
+ ret = 0;
+ if (inode && inode_is_open_for_write(inode))
+ goto path_put_and_out;
+ }
+
/* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
- if (mnt || !S_ISDIR(inode->i_mode)) {
+ if (!inode || !S_ISDIR(inode->i_mode)) {
mask &= ~FAN_EVENT_ON_CHILD;
umask = FAN_EVENT_ON_CHILD;
/*
@@ -1936,26 +2046,12 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
/* create/update an inode mark */
switch (mark_cmd) {
case FAN_MARK_ADD:
- if (mark_type == FAN_MARK_MOUNT)
- ret = fanotify_add_vfsmount_mark(group, mnt, mask,
- flags, fsid);
- else if (mark_type == FAN_MARK_FILESYSTEM)
- ret = fanotify_add_sb_mark(group, mnt->mnt_sb, mask,
- flags, fsid);
- else
- ret = fanotify_add_inode_mark(group, inode, mask,
- flags, fsid);
+ ret = fanotify_add_mark(group, obj, obj_type, 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);
+ ret = fanotify_remove_mark(group, obj, obj_type, mask, flags,
+ umask);
break;
default:
ret = -EINVAL;
@@ -1963,8 +2059,6 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
path_put_and_out:
path_put(&path);
-fput_and_out:
- fdput(f);
return ret;
}
@@ -2011,7 +2105,7 @@ static int __init fanotify_user_setup(void)
FANOTIFY_DEFAULT_MAX_USER_MARKS);
BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
- BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12);
+ BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 14);
BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
fanotify_mark_cache = KMEM_CACHE(fanotify_mark,
@@ -2024,6 +2118,7 @@ static int __init fanotify_user_setup(void)
fanotify_perm_event_cachep =
KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
}
+ fanotify_mnt_event_cachep = KMEM_CACHE(fanotify_mnt_event, SLAB_PANIC);
fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS;
init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index 5c430736ec12..1161eabf11ee 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -41,29 +41,23 @@ static void show_fdinfo(struct seq_file *m, struct file *f,
#if defined(CONFIG_EXPORTFS)
static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
{
- struct {
- struct file_handle handle;
- u8 pad[MAX_HANDLE_SZ];
- } f;
+ DEFINE_FLEX(struct file_handle, f, f_handle, handle_bytes, MAX_HANDLE_SZ);
int size, ret, i;
- f.handle.handle_bytes = sizeof(f.pad);
- size = f.handle.handle_bytes >> 2;
+ size = f->handle_bytes >> 2;
- ret = exportfs_encode_fid(inode, (struct fid *)f.handle.f_handle, &size);
- if ((ret == FILEID_INVALID) || (ret < 0)) {
- WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret);
+ ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size);
+ if ((ret == FILEID_INVALID) || (ret < 0))
return;
- }
- f.handle.handle_type = ret;
- f.handle.handle_bytes = size * sizeof(u32);
+ f->handle_type = ret;
+ f->handle_bytes = size * sizeof(u32);
seq_printf(m, "fhandle-bytes:%x fhandle-type:%x f_handle:",
- f.handle.handle_bytes, f.handle.handle_type);
+ f->handle_bytes, f->handle_type);
- for (i = 0; i < f.handle.handle_bytes; i++)
- seq_printf(m, "%02x", (int)f.handle.f_handle[i]);
+ for (i = 0; i < f->handle_bytes; i++)
+ seq_printf(m, "%02x", (int)f->f_handle[i]);
}
#else
static void show_mark_fhandle(struct seq_file *m, struct inode *inode)
@@ -127,6 +121,11 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n",
sb->s_dev, mflags, mark->mask, mark->ignore_mask);
+ } else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+ struct mnt_namespace *mnt_ns = fsnotify_conn_mntns(mark->connector);
+
+ seq_printf(m, "fanotify mnt_ns:%u mflags:%x mask:%x ignored_mask:%x\n",
+ mnt_ns->ns.inum, mflags, mark->mask, mark->ignore_mask);
}
}
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 2fc105a72a8f..e2b4f17a48bb 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -28,6 +28,11 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
fsnotify_clear_marks_by_mount(mnt);
}
+void __fsnotify_mntns_delete(struct mnt_namespace *mntns)
+{
+ fsnotify_clear_marks_by_mntns(mntns);
+}
+
/**
* fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
* @sb: superblock being unmounted.
@@ -89,11 +94,25 @@ static void fsnotify_unmount_inodes(struct super_block *sb)
void fsnotify_sb_delete(struct super_block *sb)
{
+ struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+
+ /* Were any marks ever added to any object on this sb? */
+ if (!sbinfo)
+ return;
+
fsnotify_unmount_inodes(sb);
fsnotify_clear_marks_by_sb(sb);
/* Wait for outstanding object references from connectors */
- wait_var_event(&sb->s_fsnotify_connectors,
- !atomic_long_read(&sb->s_fsnotify_connectors));
+ wait_var_event(fsnotify_sb_watched_objects(sb),
+ !atomic_long_read(fsnotify_sb_watched_objects(sb)));
+ WARN_ON(fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT));
+ WARN_ON(fsnotify_sb_has_priority_watchers(sb,
+ FSNOTIFY_PRIO_PRE_CONTENT));
+}
+
+void fsnotify_sb_free(struct super_block *sb)
+{
+ kfree(sb->s_fsnotify_info);
}
/*
@@ -103,17 +122,13 @@ void fsnotify_sb_delete(struct super_block *sb)
* parent cares. Thus when an event happens on a child it can quickly tell
* if there is a need to find a parent and send the event to the parent.
*/
-void __fsnotify_update_child_dentry_flags(struct inode *inode)
+void fsnotify_set_children_dentry_flags(struct inode *inode)
{
struct dentry *alias;
- int watched;
if (!S_ISDIR(inode->i_mode))
return;
- /* determine if the children should tell inode about their events */
- watched = fsnotify_inode_watches_children(inode);
-
spin_lock(&inode->i_lock);
/* run all of the dentries associated with this inode. Since this is a
* directory, there damn well better only be one item on this list */
@@ -129,10 +144,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
continue;
spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
- if (watched)
- child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
- else
- child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+ child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
spin_unlock(&child->d_lock);
}
spin_unlock(&alias->d_lock);
@@ -140,6 +152,24 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
spin_unlock(&inode->i_lock);
}
+/*
+ * Lazily clear false positive PARENT_WATCHED flag for child whose parent had
+ * stopped watching children.
+ */
+static void fsnotify_clear_child_dentry_flag(struct inode *pinode,
+ struct dentry *dentry)
+{
+ spin_lock(&dentry->d_lock);
+ /*
+ * d_lock is a sufficient barrier to prevent observing a non-watched
+ * parent state from before the fsnotify_set_children_dentry_flags()
+ * or fsnotify_update_flags() call that had set PARENT_WATCHED.
+ */
+ if (!fsnotify_inode_watches_children(pinode))
+ dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+ spin_unlock(&dentry->d_lock);
+}
+
/* Are inode/sb/mount interested in parent and name info with this event? */
static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
__u32 mask)
@@ -158,24 +188,44 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT);
/* Did either inode/sb/mount subscribe for events with parent/name? */
- marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask);
- marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask);
+ marks_mask |= fsnotify_parent_needed_mask(
+ READ_ONCE(inode->i_fsnotify_mask));
+ marks_mask |= fsnotify_parent_needed_mask(
+ READ_ONCE(inode->i_sb->s_fsnotify_mask));
marks_mask |= fsnotify_parent_needed_mask(mnt_mask);
/* Did they subscribe for this event with parent/name info? */
return mask & marks_mask;
}
-/* Are there any inode/mount/sb objects that are interested in this event? */
+/* Are there any inode/mount/sb objects that watch for these events? */
static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
__u32 mask)
{
- __u32 marks_mask = inode->i_fsnotify_mask | mnt_mask |
- inode->i_sb->s_fsnotify_mask;
+ __u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask |
+ READ_ONCE(inode->i_sb->s_fsnotify_mask);
return mask & marks_mask & ALL_FSNOTIFY_EVENTS;
}
+/* Report pre-content event with optional range info */
+int fsnotify_pre_content(const struct path *path, const loff_t *ppos,
+ size_t count)
+{
+ struct file_range range;
+
+ /* Report page aligned range only when pos is known */
+ if (!ppos)
+ return fsnotify_path(path, FS_PRE_ACCESS);
+
+ range.path = path;
+ range.pos = PAGE_ALIGN_DOWN(*ppos);
+ range.count = PAGE_ALIGN(*ppos + count) - range.pos;
+
+ return fsnotify_parent(path->dentry, FS_PRE_ACCESS, &range,
+ FSNOTIFY_EVENT_FILE_RANGE);
+}
+
/*
* Notify this dentry's parent about a child's events with child name info
* if parent is watching or if inode/sb/mount are interested in events with
@@ -188,7 +238,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
int data_type)
{
const struct path *path = fsnotify_data_path(data, data_type);
- __u32 mnt_mask = path ? real_mount(path->mnt)->mnt_fsnotify_mask : 0;
+ __u32 mnt_mask = path ?
+ READ_ONCE(real_mount(path->mnt)->mnt_fsnotify_mask) : 0;
struct inode *inode = d_inode(dentry);
struct dentry *parent;
bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED;
@@ -214,7 +265,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
p_inode = parent->d_inode;
p_mask = fsnotify_inode_watches_children(p_inode);
if (unlikely(parent_watched && !p_mask))
- __fsnotify_update_child_dentry_flags(p_inode);
+ fsnotify_clear_child_dentry_flag(p_inode, dentry);
/*
* Include parent/name in notification either if some notification
@@ -305,16 +356,19 @@ static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask,
if (!inode_mark)
return 0;
- if (mask & FS_EVENT_ON_CHILD) {
- /*
- * Some events can be sent on both parent dir and child marks
- * (e.g. FS_ATTRIB). If both parent dir and child are
- * watching, report the event once to parent dir with name (if
- * interested) and once to child without name (if interested).
- * The child watcher is expecting an event without a file name
- * and without the FS_EVENT_ON_CHILD flag.
- */
- mask &= ~FS_EVENT_ON_CHILD;
+ /*
+ * Some events can be sent on both parent dir and child marks (e.g.
+ * FS_ATTRIB). If both parent dir and child are watching, report the
+ * event once to parent dir with name (if interested) and once to child
+ * without name (if interested).
+ *
+ * In any case regardless whether the parent is watching or not, the
+ * child watcher is expecting an event without the FS_EVENT_ON_CHILD
+ * flag. The file name is expected if and only if this is a directory
+ * event.
+ */
+ mask &= ~FS_EVENT_ON_CHILD;
+ if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) {
dir = NULL;
name = NULL;
}
@@ -371,7 +425,7 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
file_name, cookie, iter_info);
}
-static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp)
+static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp)
{
struct fsnotify_mark_connector *conn;
struct hlist_node *node = NULL;
@@ -489,13 +543,15 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
{
const struct path *path = fsnotify_data_path(data, data_type);
struct super_block *sb = fsnotify_data_sb(data, data_type);
+ const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type);
+ struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL;
struct fsnotify_iter_info iter_info = {};
struct mount *mnt = NULL;
struct inode *inode2 = NULL;
struct dentry *moved;
int inode2_type;
int ret = 0;
- __u32 test_mask, marks_mask;
+ __u32 test_mask, marks_mask = 0;
if (path)
mnt = real_mount(path->mnt);
@@ -525,20 +581,23 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
* SRCU because we have no references to any objects and do not
* need SRCU to keep them "alive".
*/
- if (!sb->s_fsnotify_marks &&
+ if ((!sbinfo || !sbinfo->sb_marks) &&
(!mnt || !mnt->mnt_fsnotify_marks) &&
(!inode || !inode->i_fsnotify_marks) &&
- (!inode2 || !inode2->i_fsnotify_marks))
+ (!inode2 || !inode2->i_fsnotify_marks) &&
+ (!mnt_data || !mnt_data->ns->n_fsnotify_marks))
return 0;
- marks_mask = sb->s_fsnotify_mask;
+ if (sb)
+ marks_mask |= READ_ONCE(sb->s_fsnotify_mask);
if (mnt)
- marks_mask |= mnt->mnt_fsnotify_mask;
+ marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask);
if (inode)
- marks_mask |= inode->i_fsnotify_mask;
+ marks_mask |= READ_ONCE(inode->i_fsnotify_mask);
if (inode2)
- marks_mask |= inode2->i_fsnotify_mask;
-
+ marks_mask |= READ_ONCE(inode2->i_fsnotify_mask);
+ if (mnt_data)
+ marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask);
/*
* If this is a modify event we may need to clear some ignore masks.
@@ -552,8 +611,10 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
- iter_info.marks[FSNOTIFY_ITER_TYPE_SB] =
- fsnotify_first_mark(&sb->s_fsnotify_marks);
+ if (sbinfo) {
+ iter_info.marks[FSNOTIFY_ITER_TYPE_SB] =
+ fsnotify_first_mark(&sbinfo->sb_marks);
+ }
if (mnt) {
iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] =
fsnotify_first_mark(&mnt->mnt_fsnotify_marks);
@@ -566,6 +627,10 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
iter_info.marks[inode2_type] =
fsnotify_first_mark(&inode2->i_fsnotify_marks);
}
+ if (mnt_data) {
+ iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] =
+ fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks);
+ }
/*
* We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark
@@ -589,11 +654,98 @@ out:
}
EXPORT_SYMBOL_GPL(fsnotify);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+/*
+ * At open time we check fsnotify_sb_has_priority_watchers() and set the
+ * FMODE_NONOTIFY_ mode bits accordignly.
+ * Later, fsnotify permission hooks do not check if there are permission event
+ * watches, but that there were permission event watches at open time.
+ */
+void file_set_fsnotify_mode_from_watchers(struct file *file)
+{
+ struct dentry *dentry = file->f_path.dentry, *parent;
+ struct super_block *sb = dentry->d_sb;
+ __u32 mnt_mask, p_mask;
+
+ /* Is it a file opened by fanotify? */
+ if (FMODE_FSNOTIFY_NONE(file->f_mode))
+ return;
+
+ /*
+ * Permission events is a super set of pre-content events, so if there
+ * are no permission event watchers, there are also no pre-content event
+ * watchers and this is implied from the single FMODE_NONOTIFY_PERM bit.
+ */
+ if (likely(!fsnotify_sb_has_priority_watchers(sb,
+ FSNOTIFY_PRIO_CONTENT))) {
+ file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
+ return;
+ }
+
+ /*
+ * If there are permission event watchers but no pre-content event
+ * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that.
+ */
+ if ((!d_is_dir(dentry) && !d_is_reg(dentry)) ||
+ likely(!fsnotify_sb_has_priority_watchers(sb,
+ FSNOTIFY_PRIO_PRE_CONTENT))) {
+ file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
+ return;
+ }
+
+ /*
+ * OK, there are some pre-content watchers. Check if anybody is
+ * watching for pre-content events on *this* file.
+ */
+ mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
+ if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask,
+ FSNOTIFY_PRE_CONTENT_EVENTS))) {
+ /* Enable pre-content events */
+ file_set_fsnotify_mode(file, 0);
+ return;
+ }
+
+ /* Is parent watching for pre-content events on this file? */
+ if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
+ parent = dget_parent(dentry);
+ p_mask = fsnotify_inode_watches_children(d_inode(parent));
+ dput(parent);
+ if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) {
+ /* Enable pre-content events */
+ file_set_fsnotify_mode(file, 0);
+ return;
+ }
+ }
+ /* Nobody watching for pre-content events from this file */
+ file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
+}
+#endif
+
+void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+ struct fsnotify_mnt data = {
+ .ns = ns,
+ .mnt_id = real_mount(mnt)->mnt_id_unique,
+ };
+
+ if (WARN_ON_ONCE(!ns))
+ return;
+
+ /*
+ * This is an optimization as well as making sure fsnotify_init() has
+ * been called.
+ */
+ if (!ns->n_fsnotify_marks)
+ return;
+
+ fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0);
+}
+
static __init int fsnotify_init(void)
{
int ret;
- BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23);
+ BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
ret = init_srcu_struct(&fsnotify_mark_srcu);
if (ret)
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index fde74eb333cc..5950c7a67f41 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -9,39 +9,64 @@
#include "../mount.h"
+/*
+ * fsnotify_connp_t is what we embed in objects which connector can be attached
+ * to.
+ */
+typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
+
static inline struct inode *fsnotify_conn_inode(
struct fsnotify_mark_connector *conn)
{
- return container_of(conn->obj, struct inode, i_fsnotify_marks);
+ return conn->obj;
}
static inline struct mount *fsnotify_conn_mount(
struct fsnotify_mark_connector *conn)
{
- return container_of(conn->obj, struct mount, mnt_fsnotify_marks);
+ return real_mount(conn->obj);
}
static inline struct super_block *fsnotify_conn_sb(
struct fsnotify_mark_connector *conn)
{
- return container_of(conn->obj, struct super_block, s_fsnotify_marks);
+ return conn->obj;
}
-static inline struct super_block *fsnotify_connector_sb(
+static inline struct mnt_namespace *fsnotify_conn_mntns(
struct fsnotify_mark_connector *conn)
{
- switch (conn->type) {
+ return conn->obj;
+}
+
+static inline struct super_block *fsnotify_object_sb(void *obj,
+ enum fsnotify_obj_type obj_type)
+{
+ switch (obj_type) {
case FSNOTIFY_OBJ_TYPE_INODE:
- return fsnotify_conn_inode(conn)->i_sb;
+ return ((struct inode *)obj)->i_sb;
case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
- return fsnotify_conn_mount(conn)->mnt.mnt_sb;
+ return ((struct vfsmount *)obj)->mnt_sb;
case FSNOTIFY_OBJ_TYPE_SB:
- return fsnotify_conn_sb(conn);
+ return (struct super_block *)obj;
default:
return NULL;
}
}
+static inline struct super_block *fsnotify_connector_sb(
+ struct fsnotify_mark_connector *conn)
+{
+ return fsnotify_object_sb(conn->obj, conn->type);
+}
+
+static inline fsnotify_connp_t *fsnotify_sb_marks(struct super_block *sb)
+{
+ struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+
+ return sbinfo ? &sbinfo->sb_marks : NULL;
+}
+
/* destroy all events sitting in this groups notification queue */
extern void fsnotify_flush_notify(struct fsnotify_group *group);
@@ -67,14 +92,19 @@ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
/* run the list of all marks associated with sb and destroy them */
static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
{
- fsnotify_destroy_marks(&sb->s_fsnotify_marks);
+ fsnotify_destroy_marks(fsnotify_sb_marks(sb));
+}
+
+static inline void fsnotify_clear_marks_by_mntns(struct mnt_namespace *mntns)
+{
+ fsnotify_destroy_marks(&mntns->n_fsnotify_marks);
}
/*
* update the dentry->d_flags of all of inode's children to indicate if inode cares
* about events that happen to its children.
*/
-extern void __fsnotify_update_child_dentry_flags(struct inode *inode);
+extern void fsnotify_set_children_dentry_flags(struct inode *inode);
extern struct kmem_cache *fsnotify_mark_connector_cachep;
diff --git a/fs/notify/group.c b/fs/notify/group.c
index 1de6631a3925..18446b7b0d49 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -115,7 +115,6 @@ static struct fsnotify_group *__fsnotify_alloc_group(
const struct fsnotify_ops *ops,
int flags, gfp_t gfp)
{
- static struct lock_class_key nofs_marks_lock;
struct fsnotify_group *group;
group = kzalloc(sizeof(struct fsnotify_group), gfp);
@@ -136,16 +135,6 @@ static struct fsnotify_group *__fsnotify_alloc_group(
group->ops = ops;
group->flags = flags;
- /*
- * For most backends, eviction of inode with a mark is not expected,
- * because marks hold a refcount on the inode against eviction.
- *
- * Use a different lockdep class for groups that support evictable
- * inode marks, because with evictable marks, mark_mutex is NOT
- * fs-reclaim safe - the mutex is taken when evicting inodes.
- */
- if (flags & FSNOTIFY_GROUP_NOFS)
- lockdep_set_class(&group->mark_mutex, &nofs_marks_lock);
return group;
}
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 993375f0db67..cd7d11b0eb08 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -121,7 +121,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask,
event->sync_cookie = cookie;
event->name_len = len;
if (len)
- strcpy(event->name, name->name);
+ strscpy(event->name, name->name, event->name_len + 1);
ret = fsnotify_add_event(group, fsn_event, inotify_merge);
if (ret) {
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 85d8fdd55329..b372fb2c56bd 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __ro_after_init;
static long it_zero = 0;
static long it_int_max = INT_MAX;
-static struct ctl_table inotify_table[] = {
+static const struct ctl_table inotify_table[] = {
{
.procname = "max_user_instances",
.data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
@@ -544,7 +544,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
int create = (arg & IN_MASK_CREATE);
int ret;
- fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
+ fsn_mark = fsnotify_find_inode_mark(inode, group);
if (!fsn_mark)
return -ENOENT;
else if (create) {
@@ -569,7 +569,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
/* more bits in old than in new? */
int dropped = (old_mask & ~new_mask);
/* more bits in this fsn_mark than the inode's mask? */
- int do_inode = (new_mask & ~inode->i_fsnotify_mask);
+ int do_inode = (new_mask & ~READ_ONCE(inode->i_fsnotify_mask));
/* update the inode with this new fsn_mark */
if (dropped || do_inode)
@@ -732,7 +732,6 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
struct fsnotify_group *group;
struct inode *inode;
struct path path;
- struct fd f;
int ret;
unsigned flags = 0;
@@ -752,21 +751,17 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
if (unlikely(!(mask & ALL_INOTIFY_BITS)))
return -EINVAL;
- f = fdget(fd);
- if (unlikely(!f.file))
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
return -EBADF;
/* IN_MASK_ADD and IN_MASK_CREATE don't make sense together */
- if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE))) {
- ret = -EINVAL;
- goto fput_and_out;
- }
+ if (unlikely((mask & IN_MASK_ADD) && (mask & IN_MASK_CREATE)))
+ return -EINVAL;
/* verify that this is indeed an inotify instance */
- if (unlikely(f.file->f_op != &inotify_fops)) {
- ret = -EINVAL;
- goto fput_and_out;
- }
+ if (unlikely(fd_file(f)->f_op != &inotify_fops))
+ return -EINVAL;
if (!(mask & IN_DONT_FOLLOW))
flags |= LOOKUP_FOLLOW;
@@ -776,17 +771,15 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname,
ret = inotify_find_inode(pathname, &path, flags,
(mask & IN_ALL_EVENTS));
if (ret)
- goto fput_and_out;
+ return ret;
/* inode held in place by reference to path; group by fget on fd */
inode = path.dentry->d_inode;
- group = f.file->private_data;
+ group = fd_file(f)->private_data;
/* create/update an inode mark */
ret = inotify_update_watch(group, inode, mask);
path_put(&path);
-fput_and_out:
- fdput(f);
return ret;
}
@@ -794,33 +787,26 @@ SYSCALL_DEFINE2(inotify_rm_watch, int, fd, __s32, wd)
{
struct fsnotify_group *group;
struct inotify_inode_mark *i_mark;
- struct fd f;
- int ret = -EINVAL;
+ CLASS(fd, f)(fd);
- f = fdget(fd);
- if (unlikely(!f.file))
+ if (fd_empty(f))
return -EBADF;
/* verify that this is indeed an inotify instance */
- if (unlikely(f.file->f_op != &inotify_fops))
- goto out;
+ if (unlikely(fd_file(f)->f_op != &inotify_fops))
+ return -EINVAL;
- group = f.file->private_data;
+ group = fd_file(f)->private_data;
i_mark = inotify_idr_find(group, wd);
if (unlikely(!i_mark))
- goto out;
-
- ret = 0;
+ return -EINVAL;
fsnotify_destroy_mark(&i_mark->fsn_mark, group);
/* match ref taken by inotify_idr_find */
fsnotify_put_mark(&i_mark->fsn_mark);
-
-out:
- fdput(f);
- return ret;
+ return 0;
}
/*
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d6944ff86ffa..798340db69d7 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -97,6 +97,23 @@ void fsnotify_get_mark(struct fsnotify_mark *mark)
refcount_inc(&mark->refcnt);
}
+static fsnotify_connp_t *fsnotify_object_connp(void *obj,
+ enum fsnotify_obj_type obj_type)
+{
+ switch (obj_type) {
+ case FSNOTIFY_OBJ_TYPE_INODE:
+ return &((struct inode *)obj)->i_fsnotify_marks;
+ case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
+ return &real_mount(obj)->mnt_fsnotify_marks;
+ case FSNOTIFY_OBJ_TYPE_SB:
+ return fsnotify_sb_marks(obj);
+ case FSNOTIFY_OBJ_TYPE_MNTNS:
+ return &((struct mnt_namespace *)obj)->n_fsnotify_marks;
+ default:
+ return NULL;
+ }
+}
+
static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn)
{
if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
@@ -105,6 +122,8 @@ static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn)
return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask;
else if (conn->type == FSNOTIFY_OBJ_TYPE_SB)
return &fsnotify_conn_sb(conn)->s_fsnotify_mask;
+ else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS)
+ return &fsnotify_conn_mntns(conn)->n_fsnotify_mask;
return NULL;
}
@@ -113,13 +132,78 @@ __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn)
if (WARN_ON(!fsnotify_valid_obj_type(conn->type)))
return 0;
- return *fsnotify_conn_mask_p(conn);
+ return READ_ONCE(*fsnotify_conn_mask_p(conn));
+}
+
+static void fsnotify_get_sb_watched_objects(struct super_block *sb)
+{
+ atomic_long_inc(fsnotify_sb_watched_objects(sb));
+}
+
+static void fsnotify_put_sb_watched_objects(struct super_block *sb)
+{
+ atomic_long_t *watched_objects = fsnotify_sb_watched_objects(sb);
+
+ /* the superblock can go away after this decrement */
+ if (atomic_long_dec_and_test(watched_objects))
+ wake_up_var(watched_objects);
}
static void fsnotify_get_inode_ref(struct inode *inode)
{
ihold(inode);
- atomic_long_inc(&inode->i_sb->s_fsnotify_connectors);
+ fsnotify_get_sb_watched_objects(inode->i_sb);
+}
+
+static void fsnotify_put_inode_ref(struct inode *inode)
+{
+ /* read ->i_sb before the inode can go away */
+ struct super_block *sb = inode->i_sb;
+
+ iput(inode);
+ fsnotify_put_sb_watched_objects(sb);
+}
+
+/*
+ * Grab or drop watched objects reference depending on whether the connector
+ * is attached and has any marks attached.
+ */
+static void fsnotify_update_sb_watchers(struct super_block *sb,
+ struct fsnotify_mark_connector *conn)
+{
+ struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+ bool is_watched = conn->flags & FSNOTIFY_CONN_FLAG_IS_WATCHED;
+ struct fsnotify_mark *first_mark = NULL;
+ unsigned int highest_prio = 0;
+
+ if (conn->obj)
+ first_mark = hlist_entry_safe(conn->list.first,
+ struct fsnotify_mark, obj_list);
+ if (first_mark)
+ highest_prio = first_mark->group->priority;
+ if (WARN_ON(highest_prio >= __FSNOTIFY_PRIO_NUM))
+ highest_prio = 0;
+
+ /*
+ * If the highest priority of group watching this object is prio,
+ * then watched object has a reference on counters [0..prio].
+ * Update priority >= 1 watched objects counters.
+ */
+ for (unsigned int p = conn->prio + 1; p <= highest_prio; p++)
+ atomic_long_inc(&sbinfo->watched_objects[p]);
+ for (unsigned int p = conn->prio; p > highest_prio; p--)
+ atomic_long_dec(&sbinfo->watched_objects[p]);
+ conn->prio = highest_prio;
+
+ /* Update priority >= 0 (a.k.a total) watched objects counter */
+ BUILD_BUG_ON(FSNOTIFY_PRIO_NORMAL != 0);
+ if (first_mark && !is_watched) {
+ conn->flags |= FSNOTIFY_CONN_FLAG_IS_WATCHED;
+ fsnotify_get_sb_watched_objects(sb);
+ } else if (!first_mark && is_watched) {
+ conn->flags &= ~FSNOTIFY_CONN_FLAG_IS_WATCHED;
+ fsnotify_put_sb_watched_objects(sb);
+ }
}
/*
@@ -171,11 +255,33 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
!(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF))
want_iref = true;
}
- *fsnotify_conn_mask_p(conn) = new_mask;
+ /*
+ * We use WRITE_ONCE() to prevent silly compiler optimizations from
+ * confusing readers not holding conn->lock with partial updates.
+ */
+ WRITE_ONCE(*fsnotify_conn_mask_p(conn), new_mask);
return fsnotify_update_iref(conn, want_iref);
}
+static bool fsnotify_conn_watches_children(
+ struct fsnotify_mark_connector *conn)
+{
+ if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
+ return false;
+
+ return fsnotify_inode_watches_children(fsnotify_conn_inode(conn));
+}
+
+static void fsnotify_conn_set_children_dentry_flags(
+ struct fsnotify_mark_connector *conn)
+{
+ if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
+ return;
+
+ fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn));
+}
+
/*
* Calculate mask of events for a list of marks. The caller must make sure
* connector and connector->obj cannot disappear under us. Callers achieve
@@ -184,15 +290,23 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
*/
void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
{
+ bool update_children;
+
if (!conn)
return;
spin_lock(&conn->lock);
+ update_children = !fsnotify_conn_watches_children(conn);
__fsnotify_recalc_mask(conn);
+ update_children &= fsnotify_conn_watches_children(conn);
spin_unlock(&conn->lock);
- if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
- __fsnotify_update_child_dentry_flags(
- fsnotify_conn_inode(conn));
+ /*
+ * Set children's PARENT_WATCHED flags only if parent started watching.
+ * When parent stops watching, we clear false positive PARENT_WATCHED
+ * flags lazily in __fsnotify_parent().
+ */
+ if (update_children)
+ fsnotify_conn_set_children_dentry_flags(conn);
}
/* Free all connectors queued for freeing once SRCU period ends */
@@ -213,35 +327,12 @@ static void fsnotify_connector_destroy_workfn(struct work_struct *work)
}
}
-static void fsnotify_put_inode_ref(struct inode *inode)
-{
- struct super_block *sb = inode->i_sb;
-
- iput(inode);
- if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors))
- wake_up_var(&sb->s_fsnotify_connectors);
-}
-
-static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn)
-{
- struct super_block *sb = fsnotify_connector_sb(conn);
-
- if (sb)
- atomic_long_inc(&sb->s_fsnotify_connectors);
-}
-
-static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn)
-{
- struct super_block *sb = fsnotify_connector_sb(conn);
-
- if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors))
- wake_up_var(&sb->s_fsnotify_connectors);
-}
-
static void *fsnotify_detach_connector_from_object(
struct fsnotify_mark_connector *conn,
unsigned int *type)
{
+ fsnotify_connp_t *connp = fsnotify_object_connp(conn->obj, conn->type);
+ struct super_block *sb = fsnotify_connector_sb(conn);
struct inode *inode = NULL;
*type = conn->type;
@@ -259,12 +350,15 @@ static void *fsnotify_detach_connector_from_object(
fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0;
} else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) {
fsnotify_conn_sb(conn)->s_fsnotify_mask = 0;
+ } else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+ fsnotify_conn_mntns(conn)->n_fsnotify_mask = 0;
}
- fsnotify_put_sb_connectors(conn);
- rcu_assign_pointer(*(conn->obj), NULL);
+ rcu_assign_pointer(*connp, NULL);
conn->obj = NULL;
conn->type = FSNOTIFY_OBJ_TYPE_DETACHED;
+ if (sb)
+ fsnotify_update_sb_watchers(sb, conn);
return inode;
}
@@ -316,6 +410,11 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
objp = fsnotify_detach_connector_from_object(conn, &type);
free_conn = true;
} else {
+ struct super_block *sb = fsnotify_connector_sb(conn);
+
+ /* Update watched objects after detaching mark */
+ if (sb)
+ fsnotify_update_sb_watchers(sb, conn);
objp = __fsnotify_recalc_mask(conn);
type = conn->type;
}
@@ -536,8 +635,28 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
return -1;
}
+static int fsnotify_attach_info_to_sb(struct super_block *sb)
+{
+ struct fsnotify_sb_info *sbinfo;
+
+ /* sb info is freed on fsnotify_sb_delete() */
+ sbinfo = kzalloc(sizeof(*sbinfo), GFP_KERNEL);
+ if (!sbinfo)
+ return -ENOMEM;
+
+ /*
+ * cmpxchg() provides the barrier so that callers of fsnotify_sb_info()
+ * will observe an initialized structure
+ */
+ if (cmpxchg(&sb->s_fsnotify_info, NULL, sbinfo)) {
+ /* Someone else created sbinfo for us */
+ kfree(sbinfo);
+ }
+ return 0;
+}
+
static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
- unsigned int obj_type)
+ void *obj, unsigned int obj_type)
{
struct fsnotify_mark_connector *conn;
@@ -547,10 +666,9 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
spin_lock_init(&conn->lock);
INIT_HLIST_HEAD(&conn->list);
conn->flags = 0;
+ conn->prio = 0;
conn->type = obj_type;
- conn->obj = connp;
- conn->flags = 0;
- fsnotify_get_sb_connectors(conn);
+ conn->obj = obj;
/*
* cmpxchg() provides the barrier so that readers of *connp can see
@@ -558,10 +676,8 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp,
*/
if (cmpxchg(connp, NULL, conn)) {
/* Someone else created list structure for us */
- fsnotify_put_sb_connectors(conn);
kmem_cache_free(fsnotify_mark_connector_cachep, conn);
}
-
return 0;
}
@@ -598,24 +714,36 @@ out:
* to which group and for which inodes. These marks are ordered according to
* priority, highest number first, and then by the group's location in memory.
*/
-static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
- fsnotify_connp_t *connp,
+static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj,
unsigned int obj_type, int add_flags)
{
+ struct super_block *sb = fsnotify_object_sb(obj, obj_type);
struct fsnotify_mark *lmark, *last = NULL;
struct fsnotify_mark_connector *conn;
+ fsnotify_connp_t *connp;
int cmp;
int err = 0;
if (WARN_ON(!fsnotify_valid_obj_type(obj_type)))
return -EINVAL;
+ /*
+ * Attach the sb info before attaching a connector to any object on sb.
+ * The sb info will remain attached as long as sb lives.
+ */
+ if (sb && !fsnotify_sb_info(sb)) {
+ err = fsnotify_attach_info_to_sb(sb);
+ if (err)
+ return err;
+ }
+
+ connp = fsnotify_object_connp(obj, obj_type);
restart:
spin_lock(&mark->lock);
conn = fsnotify_grab_connector(connp);
if (!conn) {
spin_unlock(&mark->lock);
- err = fsnotify_attach_connector_to_object(connp, obj_type);
+ err = fsnotify_attach_connector_to_object(connp, obj, obj_type);
if (err)
return err;
goto restart;
@@ -649,6 +777,8 @@ restart:
/* mark should be the last entry. last is the current last entry */
hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
added:
+ if (sb)
+ fsnotify_update_sb_watchers(sb, conn);
/*
* Since connector is attached to object using cmpxchg() we are
* guaranteed that connector initialization is fully visible by anyone
@@ -667,7 +797,7 @@ out_err:
* event types should be delivered to which group.
*/
int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
- fsnotify_connp_t *connp, unsigned int obj_type,
+ void *obj, unsigned int obj_type,
int add_flags)
{
struct fsnotify_group *group = mark->group;
@@ -688,7 +818,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
fsnotify_get_mark(mark); /* for g_list */
spin_unlock(&mark->lock);
- ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags);
+ ret = fsnotify_add_mark_list(mark, obj, obj_type, add_flags);
if (ret)
goto err;
@@ -706,14 +836,14 @@ err:
return ret;
}
-int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp,
+int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj,
unsigned int obj_type, int add_flags)
{
int ret;
struct fsnotify_group *group = mark->group;
fsnotify_group_lock(group);
- ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags);
+ ret = fsnotify_add_mark_locked(mark, obj, obj_type, add_flags);
fsnotify_group_unlock(group);
return ret;
}
@@ -723,12 +853,16 @@ EXPORT_SYMBOL_GPL(fsnotify_add_mark);
* Given a list of marks, find the mark associated with given group. If found
* take a reference to that mark and return it, else return NULL.
*/
-struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp,
+struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type,
struct fsnotify_group *group)
{
+ fsnotify_connp_t *connp = fsnotify_object_connp(obj, obj_type);
struct fsnotify_mark_connector *conn;
struct fsnotify_mark *mark;
+ if (!connp)
+ return NULL;
+
conn = fsnotify_grab_connector(connp);
if (!conn)
return NULL;
generated by cgit (git 2.34.1) at 2025-07-23 14:09:02 +0000